Skip to content

Instantly share code, notes, and snippets.

@elon-gs

elon-gs/Tororo Data Analysis.ipynb

Created March 12, 2019 22:17
Show Gist options
  • Save elon-gs/1e9f07ca1432be567b9021966718780b to your computer and use it in GitHub Desktop.
Save elon-gs/1e9f07ca1432be567b9021966718780b to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Tororo Data Analysis.ipynb
{
"cells": [
{
"metadata": {},
"cell_type": "markdown",
"source": "#### Global Strategies and UCSF Preterm Birth Initiative\n# NoviGuide Study, Tororo District Hospital, 2017–2018"
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Table of Contents\n* [Read CSV data](#read-CSV)\n* [Count number of assessments, by type](#count)\n* [Calculate duration stats](#duration-stats)\n* [Analyze assessment distribution across day parts](#dayparts)\n* [Users ordered by usage](#usage)\n* [Assessment distribution across dayparts, top users only](#top-dayparts)\n* [Epidemiology](#epidemiology)\n * [Initial assessment](#initial-epi)\n * [Transfer assessment](#transfer-epi)\n * [Histogram of transfer babies’ DOL](#transfer-hist)\n * [Basic rounding assessment](#rounding-epi)\n* [Inventory](#inventory)\n * [Can’t test glucose](#cant-glucose)\n * [Respiratory treatment available (birth, transfer)](#resp-treatment)\n * [No IV Fluids](#no-iv-fluids)\n* [Synchronizations](#syncs)\n* [Learn More](#learnmore)"
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Read CSV data <a class=\"anchor\" id=\"read-csv\"></a>\n\nThis notebook presents key statistics and insights from a study of NoviGuide use in the neonatal clinic of Tororo District Hospital between early 2017 and early 2018. We begin by reading in CSV data extracted from Global Strategies’ Firebase database “NoviGuide Uganda.” This data has already been filtered to include only valid assessments — real (not practice) assessments performed by nurses (not Global Strategies staff) during the time period of the study."
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "import pandas as pd\nbirth_df = pd.read_csv('birth.csv')\ntransfer_df = pd.read_csv('transfer.csv')\nrounding_df = pd.read_csv('rounding.csv')\ndischarge_df = pd.read_csv('discharge.csv')\nabdominal_df = pd.read_csv('abdominal.csv')\nseizure_df = pd.read_csv('seizure.csv')\n\nassessments = ['BIRTH', 'TRANSFER', 'ROUNDING', 'DISCHARGE', 'ABDOMINAL_EM', 'SEIZURE_EM']",
"execution_count": 54,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Count number of assessments, by type <a class=\"anchor\" id=\"count\"></a>\n\nNoviGuide includes 6 different types of neonatal assessment.<br/><br/>\nTwo types, abdominal emergency (ABDOMINAL_EM) and seizure emergency (SEIZURE_EM), help nurses assess and treat a baby who appears to be experiencing a health emergency.<br/><br/>The remaining four assessments are routine:\n- the birth or initial assessment (BIRTH), for babies in their first day of life,\n- the transfer assessment (TRANSFER), for babies under 28 days of age who have just been admitted to a clinic,\n- the rounding assessment (ROUNDING), for monitoring babies who have already been admitted and assessed, and\n- the discharge assessment (DISCHARGE), to help assess a baby’s readiness to leave the facility.\n\nThe COMPLETE column of each DataFrame indicates whether the entire assessment was completed (True or False)."
},
{
"metadata": {
"scrolled": true,
"trusted": true
},
"cell_type": "code",
"source": "completehash = {\n 'BIRTH': birth_df['COMPLETE'].value_counts(),\n 'TRANSFER': transfer_df['COMPLETE'].value_counts(),\n 'ROUNDING': rounding_df['COMPLETE'].value_counts(),\n 'DISCHARGE': discharge_df['COMPLETE'].value_counts(),\n 'ABDOMINAL_EM': abdominal_df['COMPLETE'].value_counts(),\n 'SEIZURE_EM': seizure_df['COMPLETE'].value_counts()\n}\ncompletecounts = pd.DataFrame(completehash, columns=assessments)\ncompletecounts.loc['Total',:] = completecounts.sum(axis=0)\ncompletecounts.loc[:,'TOTAL'] = completecounts.sum(axis=1)\ncompletecounts.insert(0, \"\", [\"Complete assessments\", \"Incomplete assessments\", \"Total assessments\"])\ncompletecounts",
"execution_count": 55,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th></th>\n <th>BIRTH</th>\n <th>TRANSFER</th>\n <th>ROUNDING</th>\n <th>DISCHARGE</th>\n <th>ABDOMINAL_EM</th>\n <th>SEIZURE_EM</th>\n <th>TOTAL</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>True</th>\n <td>Complete assessments</td>\n <td>931.0</td>\n <td>286.0</td>\n <td>79.0</td>\n <td>92.0</td>\n <td>3.0</td>\n <td>21.0</td>\n <td>1412.0</td>\n </tr>\n <tr>\n <th>False</th>\n <td>Incomplete assessments</td>\n <td>161.0</td>\n <td>81.0</td>\n <td>32.0</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>15.0</td>\n <td>293.0</td>\n </tr>\n <tr>\n <th>Total</th>\n <td>Total assessments</td>\n <td>1092.0</td>\n <td>367.0</td>\n <td>111.0</td>\n <td>94.0</td>\n <td>5.0</td>\n <td>36.0</td>\n <td>1705.0</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " BIRTH TRANSFER ROUNDING DISCHARGE \\\nTrue Complete assessments 931.0 286.0 79.0 92.0 \nFalse Incomplete assessments 161.0 81.0 32.0 2.0 \nTotal Total assessments 1092.0 367.0 111.0 94.0 \n\n ABDOMINAL_EM SEIZURE_EM TOTAL \nTrue 3.0 21.0 1412.0 \nFalse 2.0 15.0 293.0 \nTotal 5.0 36.0 1705.0 "
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Calculate duration stats <a class=\"anchor\" id=\"duration-stats\"></a>\nThe DURATION column for each assessment indicates the time from initiation of the assessment to either a) completion or b) abandonment. Here we calculate various facts about assessment duration for both ALL and COMPLETE assessments, broken down by type."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "def durationArray(df):\n return [df['DURATION'].mean(), df.loc[df['COMPLETE'] == True, 'DURATION'].mean(),\n df['DURATION'].median(), df.loc[df['COMPLETE'] == True, 'DURATION'].median(),\n df['DURATION'].max(), df['DURATION'].sum(), df['DURATION'].sum() / 60]\ndurationhash = {\n 'BIRTH': durationArray(birth_df),\n 'TRANSFER': durationArray(transfer_df),\n 'ROUNDING': durationArray(rounding_df),\n 'DISCHARGE': durationArray(discharge_df),\n 'ABDOMINAL_EM': durationArray(abdominal_df),\n 'SEIZURE_EM': durationArray(seizure_df)\n}\ndurationsums = pd.DataFrame(durationhash, columns=assessments, index=['ALL Mean Mins',\n 'COMPLETE Mean Mins',\n 'ALL Median Mins',\n 'COMPLETE Median Mins',\n 'Max Mins', 'Total Mins', 'Total Hours'])\ndurationsums.loc[5:,'TOTAL'] = durationsums.sum(axis=1)\ndurationsums.round(1)",
"execution_count": 56,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>BIRTH</th>\n <th>TRANSFER</th>\n <th>ROUNDING</th>\n <th>DISCHARGE</th>\n <th>ABDOMINAL_EM</th>\n <th>SEIZURE_EM</th>\n <th>TOTAL</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>ALL Mean Mins</th>\n <td>4.6</td>\n <td>9.6</td>\n <td>8.8</td>\n <td>1.2</td>\n <td>1.3</td>\n <td>1.6</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>COMPLETE Mean Mins</th>\n <td>4.8</td>\n <td>10.4</td>\n <td>10.2</td>\n <td>1.2</td>\n <td>1.7</td>\n <td>2.3</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>ALL Median Mins</th>\n <td>2.0</td>\n <td>6.0</td>\n <td>6.0</td>\n <td>0.5</td>\n <td>1.0</td>\n <td>0.5</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>COMPLETE Median Mins</th>\n <td>2.0</td>\n <td>7.0</td>\n <td>7.0</td>\n <td>0.5</td>\n <td>2.0</td>\n <td>1.0</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>Max Mins</th>\n <td>54.0</td>\n <td>59.0</td>\n <td>53.0</td>\n <td>22.0</td>\n <td>2.0</td>\n <td>17.0</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>Total Mins</th>\n <td>4969.5</td>\n <td>3538.5</td>\n <td>978.5</td>\n <td>111.5</td>\n <td>6.5</td>\n <td>56.0</td>\n <td>9660.5</td>\n </tr>\n <tr>\n <th>Total Hours</th>\n <td>82.8</td>\n <td>59.0</td>\n <td>16.3</td>\n <td>1.9</td>\n <td>0.1</td>\n <td>0.9</td>\n <td>161.0</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " BIRTH TRANSFER ROUNDING DISCHARGE ABDOMINAL_EM \\\nALL Mean Mins 4.6 9.6 8.8 1.2 1.3 \nCOMPLETE Mean Mins 4.8 10.4 10.2 1.2 1.7 \nALL Median Mins 2.0 6.0 6.0 0.5 1.0 \nCOMPLETE Median Mins 2.0 7.0 7.0 0.5 2.0 \nMax Mins 54.0 59.0 53.0 22.0 2.0 \nTotal Mins 4969.5 3538.5 978.5 111.5 6.5 \nTotal Hours 82.8 59.0 16.3 1.9 0.1 \n\n SEIZURE_EM TOTAL \nALL Mean Mins 1.6 NaN \nCOMPLETE Mean Mins 2.3 NaN \nALL Median Mins 0.5 NaN \nCOMPLETE Median Mins 1.0 NaN \nMax Mins 17.0 NaN \nTotal Mins 56.0 9660.5 \nTotal Hours 0.9 161.0 "
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Analyze assessment distribution across day parts <a class=\"anchor\" id=\"dayparts\"></a>\nStaffing changes over the course of a day, so here we calculate the frequency of assessments during different day parts (morning/early afternoon, evening, and night)."
},
{
"metadata": {
"scrolled": false,
"trusted": true
},
"cell_type": "code",
"source": "def dayPartForTime(time):\n hour = int(time[:2])\n if hour >= 23 or hour < 7: return 'night (23.00-6.59)'\n if hour >= 7 and hour < 15: return 'day (7.00-14.59)'\n return 'evening (15.00-22.59)'\n return hour\ndef dayPartValues(df):\n return df['START_TIME'].apply(dayPartForTime).value_counts()\n\ndayparthash = {\n 'BIRTH': dayPartValues(birth_df),\n 'TRANSFER': dayPartValues(transfer_df),\n 'ROUNDING': dayPartValues(rounding_df),\n 'DISCHARGE': dayPartValues(discharge_df),\n 'ABDOMINAL_EM': dayPartValues(abdominal_df),\n 'SEIZURE_EM': dayPartValues(seizure_df)\n}\ndaypart_df = pd.DataFrame(dayparthash, columns=assessments)\ndaypart_df.loc[:,'TOTAL BY ALL USERS'] = daypart_df.sum(axis=1)\ndaypart_df.loc['Total',:] = daypart_df.sum(axis=0)\ndaypart_df.fillna(0)\ntotal = daypart_df.loc[:,'TOTAL BY ALL USERS'].iloc[[len(daypart_df.index) - 1]]\ndaypart_df.loc[:,'%'] = daypart_df['TOTAL BY ALL USERS'].apply(lambda x: (x / total) * 100).round(1)\ndaypart_df",
"execution_count": 57,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>BIRTH</th>\n <th>TRANSFER</th>\n <th>ROUNDING</th>\n <th>DISCHARGE</th>\n <th>ABDOMINAL_EM</th>\n <th>SEIZURE_EM</th>\n <th>TOTAL BY ALL USERS</th>\n <th>%</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>day (7.00-14.59)</th>\n <td>529.0</td>\n <td>176.0</td>\n <td>64.0</td>\n <td>54.0</td>\n <td>4.0</td>\n <td>12.0</td>\n <td>839.0</td>\n <td>49.2</td>\n </tr>\n <tr>\n <th>evening (15.00-22.59)</th>\n <td>451.0</td>\n <td>151.0</td>\n <td>44.0</td>\n <td>33.0</td>\n <td>1.0</td>\n <td>20.0</td>\n <td>700.0</td>\n <td>41.1</td>\n </tr>\n <tr>\n <th>night (23.00-6.59)</th>\n <td>112.0</td>\n <td>40.0</td>\n <td>3.0</td>\n <td>7.0</td>\n <td>NaN</td>\n <td>4.0</td>\n <td>166.0</td>\n <td>9.7</td>\n </tr>\n <tr>\n <th>Total</th>\n <td>1092.0</td>\n <td>367.0</td>\n <td>111.0</td>\n <td>94.0</td>\n <td>5.0</td>\n <td>36.0</td>\n <td>1705.0</td>\n <td>100.0</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " BIRTH TRANSFER ROUNDING DISCHARGE ABDOMINAL_EM \\\nday (7.00-14.59) 529.0 176.0 64.0 54.0 4.0 \nevening (15.00-22.59) 451.0 151.0 44.0 33.0 1.0 \nnight (23.00-6.59) 112.0 40.0 3.0 7.0 NaN \nTotal 1092.0 367.0 111.0 94.0 5.0 \n\n SEIZURE_EM TOTAL BY ALL USERS % \nday (7.00-14.59) 12.0 839.0 49.2 \nevening (15.00-22.59) 20.0 700.0 41.1 \nnight (23.00-6.59) 4.0 166.0 9.7 \nTotal 36.0 1705.0 100.0 "
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Users ordered by usage <a class=\"anchor\" id=\"usage\"></a>\nWe calculate the number of assessments completed by each user by getting value counts for the USER column and summing them across all assessment types."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "def userInstances(df):\n return df['USER'].value_counts().fillna(0)\nuser_df = userInstances(birth_df)\nuser_df.add(userInstances(transfer_df), fill_value=0)\nuser_df.add(userInstances(rounding_df), fill_value=0)\nuser_df.add(userInstances(discharge_df), fill_value=0)\nuser_df.add(userInstances(abdominal_df), fill_value=0)\nuser_df.add(userInstances(seizure_df), fill_value=0)\nuser_df",
"execution_count": 58,
"outputs": [
{
"data": {
"text/plain": "NG05 233\nNG11 220\nNG09 158\nNG08 69\nNG01 64\nNG04 60\nNG02 48\nNG12 46\nNG17 44\nNG03 44\nNG19 27\nNG06 26\nNG10 24\nNG16 8\nNG07 8\nNG15 7\nNG18 3\nNG14 2\nNG13 1\nName: USER, dtype: int64"
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Assessment distribution across dayparts, top users only <a class=\"anchor\" id=\"top-dayparts\"></a>\nWe can check to see if top users tended to do assessments at different times of day vs. the overall distribution."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "top_users = user_df.nlargest(3)\ntop_user_ids = top_users.index.tolist()\ndef topUserRows(df):\n return df[df['USER'].isin(top_user_ids)]\ndef dayPartValues(df):\n return df['START_TIME'].apply(dayPartForTime).value_counts()\ntopDayparthash = {\n 'BIRTH': dayPartValues(topUserRows(birth_df)),\n 'TRANSFER': dayPartValues(topUserRows(transfer_df)),\n 'ROUNDING': dayPartValues(topUserRows(rounding_df)),\n 'DISCHARGE': dayPartValues(topUserRows(discharge_df)),\n 'ABDOMINAL_EM': dayPartValues(topUserRows(abdominal_df)),\n 'SEIZURE_EM': dayPartValues(topUserRows(seizure_df))\n}\ntopDaypart_df = pd.DataFrame(topDayparthash, columns=assessments)\ntopDaypart_df.fillna(0)\ntopDaypart_df.loc['Total',:] = topDaypart_df.sum(axis=0)\ntopDaypart_df.loc[:,'TOTAL BY TOP USERS'] = topDaypart_df.sum(axis=1)\ntotal = topDaypart_df.loc[:,'TOTAL BY TOP USERS'].iloc[[len(topDaypart_df.index) - 1]]\ntopDaypart_df.loc[:,'%'] = topDaypart_df['TOTAL BY TOP USERS'].apply(lambda x: (x / total) * 100).round(1)\ntopDaypart_df",
"execution_count": 59,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>BIRTH</th>\n <th>TRANSFER</th>\n <th>ROUNDING</th>\n <th>DISCHARGE</th>\n <th>ABDOMINAL_EM</th>\n <th>SEIZURE_EM</th>\n <th>TOTAL BY TOP USERS</th>\n <th>%</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>day (7.00-14.59)</th>\n <td>306.0</td>\n <td>38.0</td>\n <td>20.0</td>\n <td>9.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>375.0</td>\n <td>49.9</td>\n </tr>\n <tr>\n <th>evening (15.00-22.59)</th>\n <td>227.0</td>\n <td>27.0</td>\n <td>14.0</td>\n <td>11.0</td>\n <td>NaN</td>\n <td>5.0</td>\n <td>284.0</td>\n <td>37.8</td>\n </tr>\n <tr>\n <th>night (23.00-6.59)</th>\n <td>78.0</td>\n <td>10.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>3.0</td>\n <td>93.0</td>\n <td>12.4</td>\n </tr>\n <tr>\n <th>Total</th>\n <td>611.0</td>\n <td>75.0</td>\n <td>34.0</td>\n <td>22.0</td>\n <td>0.0</td>\n <td>10.0</td>\n <td>752.0</td>\n <td>100.0</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " BIRTH TRANSFER ROUNDING DISCHARGE ABDOMINAL_EM \\\nday (7.00-14.59) 306.0 38.0 20.0 9.0 NaN \nevening (15.00-22.59) 227.0 27.0 14.0 11.0 NaN \nnight (23.00-6.59) 78.0 10.0 NaN 2.0 NaN \nTotal 611.0 75.0 34.0 22.0 0.0 \n\n SEIZURE_EM TOTAL BY TOP USERS % \nday (7.00-14.59) 2.0 375.0 49.9 \nevening (15.00-22.59) 5.0 284.0 37.8 \nnight (23.00-6.59) 3.0 93.0 12.4 \nTotal 10.0 752.0 100.0 "
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Epidemiology <a class=\"anchor\" id=\"epidemiology\"></a>\nIn this section we study some epidemiological patterns."
},
{
"metadata": {},
"cell_type": "markdown",
"source": "#### First add some convenience columns"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "def addBooleansToDf(df):\n df['UNDERWEIGHT'] = (df['WEIGHT'] < 2.5)\n df['PREMATURE'] = (df['GESTATION'] == 'Preterm')\n df['HIV_EXPOSED'] = (df['HIV_EXPOSURE_STATUS'] == 'exposed')\n df['HIV_UNKNOWN'] = (df['HIV_EXPOSURE_STATUS'] == 'unknown')\n df['ANY_ABX'] = (df['ABX_COUNT'] > 0)\n return df\naddBooleansToDf(birth_df)\naddBooleansToDf(transfer_df)",
"execution_count": 60,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>CLINIC</th>\n <th>GUID</th>\n <th>APP_VERSION</th>\n <th>TYPE</th>\n <th>COMPLETE</th>\n <th>USER</th>\n <th>TIMESTAMP</th>\n <th>DURATION</th>\n <th>START_DATE</th>\n <th>START_TIME</th>\n <th>...</th>\n <th>HEART_RATE</th>\n <th>RESP_THERAPIES_AVAILABLE</th>\n <th>CANT_GIVE_FLUIDS</th>\n <th>IV_FLUIDS_ML_KG_DAY</th>\n <th>JAUNDICE</th>\n <th>UNDERWEIGHT</th>\n <th>PREMATURE</th>\n <th>HIV_EXPOSED</th>\n <th>HIV_UNKNOWN</th>\n <th>ANY_ABX</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>Tororo District Hospital</td>\n <td>20170202065148181</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Thu Feb 02 2017 09:51:48 GMT+0300 (EAT)</td>\n <td>19.0</td>\n <td>2017-02-02</td>\n <td>09:51</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>1</th>\n <td>Tororo District Hospital</td>\n <td>20170202071840923</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Wed Feb 01 2017 23:18:40 GMT-0800 (PST)</td>\n <td>5.0</td>\n <td>2017-02-01</td>\n <td>23:18</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>2</th>\n <td>Tororo District Hospital</td>\n <td>20170202122629911</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Thu Feb 02 2017 15:26:29 GMT+0300 (EAT)</td>\n <td>3.0</td>\n <td>2017-02-02</td>\n <td>15:26</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>3</th>\n <td>Tororo District Hospital</td>\n <td>20170203015346248</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG03</td>\n <td>Fri Feb 03 2017 04:53:46 GMT+0300 (EAT)</td>\n <td>59.0</td>\n <td>2017-02-03</td>\n <td>04:53</td>\n <td>...</td>\n <td>&lt; 75 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>4</th>\n <td>Tororo District Hospital</td>\n <td>20170203063332353</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Fri Feb 03 2017 09:33:32 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-03</td>\n <td>09:33</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>5</th>\n <td>Tororo District Hospital</td>\n <td>20170203084308567</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG11</td>\n <td>Fri Feb 03 2017 11:43:08 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-03</td>\n <td>11:43</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>6</th>\n <td>Tororo District Hospital</td>\n <td>20170203151800239</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG04</td>\n <td>Fri Feb 03 2017 18:18:00 GMT+0300 (EAT)</td>\n <td>20.0</td>\n <td>2017-02-03</td>\n <td>18:18</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>7</th>\n <td>Tororo District Hospital</td>\n <td>20170204164332676</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG04</td>\n <td>Sat Feb 04 2017 19:43:32 GMT+0300 (EAT)</td>\n <td>15.0</td>\n <td>2017-02-04</td>\n <td>19:43</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>8</th>\n <td>Tororo District Hospital</td>\n <td>20170205090032721</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG06</td>\n <td>Sun Feb 05 2017 12:00:32 GMT+0300 (EAT)</td>\n <td>7.0</td>\n <td>2017-02-05</td>\n <td>12:00</td>\n <td>...</td>\n <td>75-100 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>9</th>\n <td>Tororo District Hospital</td>\n <td>20170205091206975</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG06</td>\n <td>Sun Feb 05 2017 12:12:06 GMT+0300 (EAT)</td>\n <td>29.0</td>\n <td>2017-02-05</td>\n <td>12:12</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>10</th>\n <td>Tororo District Hospital</td>\n <td>20170205144513992</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG06</td>\n <td>Sun Feb 05 2017 17:45:13 GMT+0300 (EAT)</td>\n <td>27.0</td>\n <td>2017-02-05</td>\n <td>17:45</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>11</th>\n <td>Tororo District Hospital</td>\n <td>20170206105529167</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Mon Feb 06 2017 13:55:29 GMT+0300 (EAT)</td>\n <td>20.0</td>\n <td>2017-02-06</td>\n <td>13:55</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>12</th>\n <td>Tororo District Hospital</td>\n <td>20170206115726460</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Mon Feb 06 2017 14:57:26 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-06</td>\n <td>14:57</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>13</th>\n <td>Tororo District Hospital</td>\n <td>20170206160332687</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Mon Feb 06 2017 19:03:32 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2017-02-06</td>\n <td>19:03</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>60 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>14</th>\n <td>Tororo District Hospital</td>\n <td>2017020712142845</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG12</td>\n <td>Tue Feb 07 2017 15:14:28 GMT+0300 (EAT)</td>\n <td>11.0</td>\n <td>2017-02-07</td>\n <td>15:14</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>15</th>\n <td>Tororo District Hospital</td>\n <td>2017020712291966</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG12</td>\n <td>Tue Feb 07 2017 15:29:19 GMT+0300 (EAT)</td>\n <td>14.0</td>\n <td>2017-02-07</td>\n <td>15:29</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>16</th>\n <td>Tororo District Hospital</td>\n <td>20170207124506120</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG12</td>\n <td>Tue Feb 07 2017 15:45:06 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-07</td>\n <td>15:45</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>17</th>\n <td>Tororo District Hospital</td>\n <td>20170207124900413</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG12</td>\n <td>Tue Feb 07 2017 15:49:00 GMT+0300 (EAT)</td>\n <td>3.0</td>\n <td>2017-02-07</td>\n <td>15:49</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>18</th>\n <td>Tororo District Hospital</td>\n <td>2017020713183682</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Tue Feb 07 2017 16:18:36 GMT+0300 (EAT)</td>\n <td>20.0</td>\n <td>2017-02-07</td>\n <td>16:18</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>19</th>\n <td>Tororo District Hospital</td>\n <td>20170208075554922</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Wed Feb 08 2017 10:55:54 GMT+0300 (EAT)</td>\n <td>7.0</td>\n <td>2017-02-08</td>\n <td>10:55</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>20</th>\n <td>Tororo District Hospital</td>\n <td>20170208105521814</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Wed Feb 08 2017 13:55:21 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2017-02-08</td>\n <td>13:55</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>21</th>\n <td>Tororo District Hospital</td>\n <td>20170208120436864</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG02</td>\n <td>Wed Feb 08 2017 15:04:36 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-08</td>\n <td>15:04</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>True</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>22</th>\n <td>Tororo District Hospital</td>\n <td>2017020909065171</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Thu Feb 09 2017 12:06:51 GMT+0300 (EAT)</td>\n <td>11.0</td>\n <td>2017-02-09</td>\n <td>12:06</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>23</th>\n <td>Tororo District Hospital</td>\n <td>20170209160048135</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Thu Feb 09 2017 19:00:48 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2017-02-09</td>\n <td>19:00</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>24</th>\n <td>Tororo District Hospital</td>\n <td>20170210064719899</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG11</td>\n <td>Fri Feb 10 2017 09:47:19 GMT+0300 (EAT)</td>\n <td>4.0</td>\n <td>2017-02-10</td>\n <td>09:47</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>25</th>\n <td>Tororo District Hospital</td>\n <td>20170213092716344</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG02</td>\n <td>Mon Feb 13 2017 12:27:16 GMT+0300 (EAT)</td>\n <td>40.0</td>\n <td>2017-02-13</td>\n <td>12:27</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>26</th>\n <td>Tororo District Hospital</td>\n <td>20170213101108751</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG02</td>\n <td>Mon Feb 13 2017 13:11:08 GMT+0300 (EAT)</td>\n <td>8.0</td>\n <td>2017-02-13</td>\n <td>13:11</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>60 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>27</th>\n <td>Tororo District Hospital</td>\n <td>20170213150349351</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG03</td>\n <td>Mon Feb 13 2017 18:03:49 GMT+0300 (EAT)</td>\n <td>16.0</td>\n <td>2017-02-13</td>\n <td>18:03</td>\n <td>...</td>\n <td>NaN</td>\n <td>Regular Nasal Cannula</td>\n <td>True</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>28</th>\n <td>Tororo District Hospital</td>\n <td>20170213152539654</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG03</td>\n <td>Mon Feb 13 2017 18:25:39 GMT+0300 (EAT)</td>\n <td>14.0</td>\n <td>2017-02-13</td>\n <td>18:25</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>NaN</td>\n <td>True</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>29</th>\n <td>Tororo District Hospital</td>\n <td>20170213163244524</td>\n <td>1.6</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG01</td>\n <td>Mon Feb 13 2017 19:32:44 GMT+0300 (EAT)</td>\n <td>18.0</td>\n <td>2017-02-13</td>\n <td>19:32</td>\n <td>...</td>\n <td>75-100 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>337</th>\n <td>Tororo District Hospital</td>\n <td>2018012611420272</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG12</td>\n <td>Fri Jan 26 2018 14:42:02 GMT+0300 (EAT)</td>\n <td>5.0</td>\n <td>2018-01-26</td>\n <td>14:42</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>338</th>\n <td>Tororo District Hospital</td>\n <td>2018012611483382</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Fri Jan 26 2018 14:48:33 GMT+0300 (EAT)</td>\n <td>8.0</td>\n <td>2018-01-26</td>\n <td>14:48</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>339</th>\n <td>Tororo District Hospital</td>\n <td>20180129090328755</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG19</td>\n <td>Mon Jan 29 2018 12:03:28 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-01-29</td>\n <td>12:03</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>340</th>\n <td>Tororo District Hospital</td>\n <td>20180129131952670</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG19</td>\n <td>Mon Jan 29 2018 16:19:52 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-01-29</td>\n <td>16:19</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>341</th>\n <td>Tororo District Hospital</td>\n <td>20180130104458156</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Tue Jan 30 2018 13:44:58 GMT+0300 (EAT)</td>\n <td>37.0</td>\n <td>2018-01-30</td>\n <td>13:44</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>342</th>\n <td>Tororo District Hospital</td>\n <td>20180130112421686</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Tue Jan 30 2018 14:24:21 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-01-30</td>\n <td>14:24</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>343</th>\n <td>Tororo District Hospital</td>\n <td>20180201122251789</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG08</td>\n <td>Thu Feb 01 2018 15:22:51 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-02-01</td>\n <td>15:22</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>344</th>\n <td>Tororo District Hospital</td>\n <td>20180203164311624</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG14</td>\n <td>Sat Feb 03 2018 19:43:11 GMT+0300 (EAT)</td>\n <td>22.0</td>\n <td>2018-02-03</td>\n <td>19:43</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>345</th>\n <td>Tororo District Hospital</td>\n <td>20180206141556254</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Tue Feb 06 2018 17:15:56 GMT+0300 (EAT)</td>\n <td>1.0</td>\n <td>2018-02-06</td>\n <td>17:15</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>346</th>\n <td>Tororo District Hospital</td>\n <td>2018020707455473</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG04</td>\n <td>Wed Feb 07 2018 10:45:54 GMT+0300 (EAT)</td>\n <td>7.0</td>\n <td>2018-02-07</td>\n <td>10:45</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>347</th>\n <td>Tororo District Hospital</td>\n <td>2018020910042127</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG01</td>\n <td>Fri Feb 09 2018 13:04:21 GMT+0300 (EAT)</td>\n <td>0.5</td>\n <td>2018-02-09</td>\n <td>13:04</td>\n <td>...</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>348</th>\n <td>Tororo District Hospital</td>\n <td>20180209100550496</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG01</td>\n <td>Fri Feb 09 2018 13:05:50 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-02-09</td>\n <td>13:05</td>\n <td>...</td>\n <td>75-100 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>349</th>\n <td>Tororo District Hospital</td>\n <td>2018020916571018</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG08</td>\n <td>Fri Feb 09 2018 19:57:10 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-02-09</td>\n <td>19:57</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>350</th>\n <td>Tororo District Hospital</td>\n <td>20180212044215274</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Mon Feb 12 2018 07:42:15 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-02-12</td>\n <td>07:42</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>351</th>\n <td>Tororo District Hospital</td>\n <td>20180212044502310</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Mon Feb 12 2018 07:45:02 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-02-12</td>\n <td>07:45</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>352</th>\n <td>Tororo District Hospital</td>\n <td>20180212193759363</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG15</td>\n <td>Mon Feb 12 2018 22:37:59 GMT+0300 (EAT)</td>\n <td>3.0</td>\n <td>2018-02-12</td>\n <td>22:37</td>\n <td>...</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>353</th>\n <td>Tororo District Hospital</td>\n <td>20180216171159285</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG19</td>\n <td>Fri Feb 16 2018 20:11:59 GMT+0300 (EAT)</td>\n <td>10.0</td>\n <td>2018-02-16</td>\n <td>20:11</td>\n <td>...</td>\n <td>&gt; 160 beats per minute</td>\n <td>Regular Nasal Cannula</td>\n <td>True</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>354</th>\n <td>Tororo District Hospital</td>\n <td>20180217050930915</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG17</td>\n <td>Sat Feb 17 2018 08:09:30 GMT+0300 (EAT)</td>\n <td>0.5</td>\n <td>2018-02-17</td>\n <td>08:09</td>\n <td>...</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>355</th>\n <td>Tororo District Hospital</td>\n <td>20180221071025561</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Wed Feb 21 2018 10:10:25 GMT+0300 (EAT)</td>\n <td>17.0</td>\n <td>2018-02-21</td>\n <td>10:10</td>\n <td>...</td>\n <td>75-100 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n <td>True</td>\n </tr>\n <tr>\n <th>356</th>\n <td>Tororo District Hospital</td>\n <td>20180222074342511</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Thu Feb 22 2018 10:43:42 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-02-22</td>\n <td>10:43</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>357</th>\n <td>Tororo District Hospital</td>\n <td>20180222075137626</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Thu Feb 22 2018 10:51:37 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-02-22</td>\n <td>10:51</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>358</th>\n <td>Tororo District Hospital</td>\n <td>20180222094404476</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Thu Feb 22 2018 12:44:04 GMT+0300 (EAT)</td>\n <td>8.0</td>\n <td>2018-02-22</td>\n <td>12:44</td>\n <td>...</td>\n <td>NaN</td>\n <td>Regular Nasal Cannula</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>359</th>\n <td>Tororo District Hospital</td>\n <td>20180222103554103</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG05</td>\n <td>Thu Feb 22 2018 13:35:54 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-02-22</td>\n <td>13:35</td>\n <td>...</td>\n <td>NaN</td>\n <td>Regular Nasal Cannula</td>\n <td>False</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>360</th>\n <td>Tororo District Hospital</td>\n <td>20180226152526459</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG12</td>\n <td>Mon Feb 26 2018 18:25:26 GMT+0300 (EAT)</td>\n <td>21.0</td>\n <td>2018-02-26</td>\n <td>18:25</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>True</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>361</th>\n <td>Tororo District Hospital</td>\n <td>20180301195521556</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG08</td>\n <td>Thu Mar 01 2018 22:55:21 GMT+0300 (EAT)</td>\n <td>20.0</td>\n <td>2018-03-01</td>\n <td>22:55</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n <tr>\n <th>362</th>\n <td>Tororo District Hospital</td>\n <td>20180301201557506</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG08</td>\n <td>Thu Mar 01 2018 23:15:57 GMT+0300 (EAT)</td>\n <td>1.0</td>\n <td>2018-03-01</td>\n <td>23:15</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>363</th>\n <td>Tororo District Hospital</td>\n <td>20180301201917955</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG08</td>\n <td>Thu Mar 01 2018 23:19:17 GMT+0300 (EAT)</td>\n <td>1.0</td>\n <td>2018-03-01</td>\n <td>23:19</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>80 ml/kg/day</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>364</th>\n <td>Tororo District Hospital</td>\n <td>20180302094825503</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Fri Mar 02 2018 12:48:25 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-03-02</td>\n <td>12:48</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>365</th>\n <td>Tororo District Hospital</td>\n <td>20180302105443169</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>True</td>\n <td>NG11</td>\n <td>Fri Mar 02 2018 13:54:43 GMT+0300 (EAT)</td>\n <td>6.0</td>\n <td>2018-03-02</td>\n <td>13:54</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>True</td>\n </tr>\n <tr>\n <th>366</th>\n <td>Tororo District Hospital</td>\n <td>20180305061411544</td>\n <td>1.7</td>\n <td>transfer</td>\n <td>False</td>\n <td>NG05</td>\n <td>Mon Mar 05 2018 09:14:11 GMT+0300 (EAT)</td>\n <td>2.0</td>\n <td>2018-03-05</td>\n <td>09:14</td>\n <td>...</td>\n <td>101-160 beats per minute</td>\n <td>Mechanical ventilation, CPAP, Regular Nasal Ca...</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n <td>False</td>\n </tr>\n </tbody>\n</table>\n<p>367 rows × 39 columns</p>\n</div>",
"text/plain": " CLINIC GUID APP_VERSION TYPE \\\n0 Tororo District Hospital 20170202065148181 1.6 transfer \n1 Tororo District Hospital 20170202071840923 1.6 transfer \n2 Tororo District Hospital 20170202122629911 1.6 transfer \n3 Tororo District Hospital 20170203015346248 1.6 transfer \n4 Tororo District Hospital 20170203063332353 1.6 transfer \n5 Tororo District Hospital 20170203084308567 1.6 transfer \n6 Tororo District Hospital 20170203151800239 1.6 transfer \n7 Tororo District Hospital 20170204164332676 1.6 transfer \n8 Tororo District Hospital 20170205090032721 1.6 transfer \n9 Tororo District Hospital 20170205091206975 1.6 transfer \n10 Tororo District Hospital 20170205144513992 1.6 transfer \n11 Tororo District Hospital 20170206105529167 1.6 transfer \n12 Tororo District Hospital 20170206115726460 1.6 transfer \n13 Tororo District Hospital 20170206160332687 1.6 transfer \n14 Tororo District Hospital 2017020712142845 1.6 transfer \n15 Tororo District Hospital 2017020712291966 1.6 transfer \n16 Tororo District Hospital 20170207124506120 1.6 transfer \n17 Tororo District Hospital 20170207124900413 1.6 transfer \n18 Tororo District Hospital 2017020713183682 1.6 transfer \n19 Tororo District Hospital 20170208075554922 1.6 transfer \n20 Tororo District Hospital 20170208105521814 1.6 transfer \n21 Tororo District Hospital 20170208120436864 1.6 transfer \n22 Tororo District Hospital 2017020909065171 1.6 transfer \n23 Tororo District Hospital 20170209160048135 1.6 transfer \n24 Tororo District Hospital 20170210064719899 1.6 transfer \n25 Tororo District Hospital 20170213092716344 1.6 transfer \n26 Tororo District Hospital 20170213101108751 1.6 transfer \n27 Tororo District Hospital 20170213150349351 1.6 transfer \n28 Tororo District Hospital 20170213152539654 1.6 transfer \n29 Tororo District Hospital 20170213163244524 1.6 transfer \n.. ... ... ... ... \n337 Tororo District Hospital 2018012611420272 1.7 transfer \n338 Tororo District Hospital 2018012611483382 1.7 transfer \n339 Tororo District Hospital 20180129090328755 1.7 transfer \n340 Tororo District Hospital 20180129131952670 1.7 transfer \n341 Tororo District Hospital 20180130104458156 1.7 transfer \n342 Tororo District Hospital 20180130112421686 1.7 transfer \n343 Tororo District Hospital 20180201122251789 1.7 transfer \n344 Tororo District Hospital 20180203164311624 1.7 transfer \n345 Tororo District Hospital 20180206141556254 1.7 transfer \n346 Tororo District Hospital 2018020707455473 1.7 transfer \n347 Tororo District Hospital 2018020910042127 1.7 transfer \n348 Tororo District Hospital 20180209100550496 1.7 transfer \n349 Tororo District Hospital 2018020916571018 1.7 transfer \n350 Tororo District Hospital 20180212044215274 1.7 transfer \n351 Tororo District Hospital 20180212044502310 1.7 transfer \n352 Tororo District Hospital 20180212193759363 1.7 transfer \n353 Tororo District Hospital 20180216171159285 1.7 transfer \n354 Tororo District Hospital 20180217050930915 1.7 transfer \n355 Tororo District Hospital 20180221071025561 1.7 transfer \n356 Tororo District Hospital 20180222074342511 1.7 transfer \n357 Tororo District Hospital 20180222075137626 1.7 transfer \n358 Tororo District Hospital 20180222094404476 1.7 transfer \n359 Tororo District Hospital 20180222103554103 1.7 transfer \n360 Tororo District Hospital 20180226152526459 1.7 transfer \n361 Tororo District Hospital 20180301195521556 1.7 transfer \n362 Tororo District Hospital 20180301201557506 1.7 transfer \n363 Tororo District Hospital 20180301201917955 1.7 transfer \n364 Tororo District Hospital 20180302094825503 1.7 transfer \n365 Tororo District Hospital 20180302105443169 1.7 transfer \n366 Tororo District Hospital 20180305061411544 1.7 transfer \n\n COMPLETE USER TIMESTAMP DURATION \\\n0 True NG11 Thu Feb 02 2017 09:51:48 GMT+0300 (EAT) 19.0 \n1 True NG02 Wed Feb 01 2017 23:18:40 GMT-0800 (PST) 5.0 \n2 True NG11 Thu Feb 02 2017 15:26:29 GMT+0300 (EAT) 3.0 \n3 True NG03 Fri Feb 03 2017 04:53:46 GMT+0300 (EAT) 59.0 \n4 True NG11 Fri Feb 03 2017 09:33:32 GMT+0300 (EAT) 2.0 \n5 False NG11 Fri Feb 03 2017 11:43:08 GMT+0300 (EAT) 2.0 \n6 True NG04 Fri Feb 03 2017 18:18:00 GMT+0300 (EAT) 20.0 \n7 True NG04 Sat Feb 04 2017 19:43:32 GMT+0300 (EAT) 15.0 \n8 False NG06 Sun Feb 05 2017 12:00:32 GMT+0300 (EAT) 7.0 \n9 True NG06 Sun Feb 05 2017 12:12:06 GMT+0300 (EAT) 29.0 \n10 True NG06 Sun Feb 05 2017 17:45:13 GMT+0300 (EAT) 27.0 \n11 True NG02 Mon Feb 06 2017 13:55:29 GMT+0300 (EAT) 20.0 \n12 True NG02 Mon Feb 06 2017 14:57:26 GMT+0300 (EAT) 2.0 \n13 True NG02 Mon Feb 06 2017 19:03:32 GMT+0300 (EAT) 6.0 \n14 False NG12 Tue Feb 07 2017 15:14:28 GMT+0300 (EAT) 11.0 \n15 False NG12 Tue Feb 07 2017 15:29:19 GMT+0300 (EAT) 14.0 \n16 False NG12 Tue Feb 07 2017 15:45:06 GMT+0300 (EAT) 2.0 \n17 False NG12 Tue Feb 07 2017 15:49:00 GMT+0300 (EAT) 3.0 \n18 True NG12 Tue Feb 07 2017 16:18:36 GMT+0300 (EAT) 20.0 \n19 True NG02 Wed Feb 08 2017 10:55:54 GMT+0300 (EAT) 7.0 \n20 True NG02 Wed Feb 08 2017 13:55:21 GMT+0300 (EAT) 6.0 \n21 False NG02 Wed Feb 08 2017 15:04:36 GMT+0300 (EAT) 2.0 \n22 True NG02 Thu Feb 09 2017 12:06:51 GMT+0300 (EAT) 11.0 \n23 True NG02 Thu Feb 09 2017 19:00:48 GMT+0300 (EAT) 2.0 \n24 False NG11 Fri Feb 10 2017 09:47:19 GMT+0300 (EAT) 4.0 \n25 False NG02 Mon Feb 13 2017 12:27:16 GMT+0300 (EAT) 40.0 \n26 True NG02 Mon Feb 13 2017 13:11:08 GMT+0300 (EAT) 8.0 \n27 True NG03 Mon Feb 13 2017 18:03:49 GMT+0300 (EAT) 16.0 \n28 True NG03 Mon Feb 13 2017 18:25:39 GMT+0300 (EAT) 14.0 \n29 True NG01 Mon Feb 13 2017 19:32:44 GMT+0300 (EAT) 18.0 \n.. ... ... ... ... \n337 False NG12 Fri Jan 26 2018 14:42:02 GMT+0300 (EAT) 5.0 \n338 True NG12 Fri Jan 26 2018 14:48:33 GMT+0300 (EAT) 8.0 \n339 True NG19 Mon Jan 29 2018 12:03:28 GMT+0300 (EAT) 6.0 \n340 True NG19 Mon Jan 29 2018 16:19:52 GMT+0300 (EAT) 6.0 \n341 True NG12 Tue Jan 30 2018 13:44:58 GMT+0300 (EAT) 37.0 \n342 True NG12 Tue Jan 30 2018 14:24:21 GMT+0300 (EAT) 6.0 \n343 True NG08 Thu Feb 01 2018 15:22:51 GMT+0300 (EAT) 2.0 \n344 True NG14 Sat Feb 03 2018 19:43:11 GMT+0300 (EAT) 22.0 \n345 True NG11 Tue Feb 06 2018 17:15:56 GMT+0300 (EAT) 1.0 \n346 True NG04 Wed Feb 07 2018 10:45:54 GMT+0300 (EAT) 7.0 \n347 False NG01 Fri Feb 09 2018 13:04:21 GMT+0300 (EAT) 0.5 \n348 True NG01 Fri Feb 09 2018 13:05:50 GMT+0300 (EAT) 2.0 \n349 True NG08 Fri Feb 09 2018 19:57:10 GMT+0300 (EAT) 6.0 \n350 True NG11 Mon Feb 12 2018 07:42:15 GMT+0300 (EAT) 2.0 \n351 True NG11 Mon Feb 12 2018 07:45:02 GMT+0300 (EAT) 2.0 \n352 False NG15 Mon Feb 12 2018 22:37:59 GMT+0300 (EAT) 3.0 \n353 True NG19 Fri Feb 16 2018 20:11:59 GMT+0300 (EAT) 10.0 \n354 False NG17 Sat Feb 17 2018 08:09:30 GMT+0300 (EAT) 0.5 \n355 True NG12 Wed Feb 21 2018 10:10:25 GMT+0300 (EAT) 17.0 \n356 True NG11 Thu Feb 22 2018 10:43:42 GMT+0300 (EAT) 6.0 \n357 True NG11 Thu Feb 22 2018 10:51:37 GMT+0300 (EAT) 6.0 \n358 True NG11 Thu Feb 22 2018 12:44:04 GMT+0300 (EAT) 8.0 \n359 True NG05 Thu Feb 22 2018 13:35:54 GMT+0300 (EAT) 2.0 \n360 True NG12 Mon Feb 26 2018 18:25:26 GMT+0300 (EAT) 21.0 \n361 False NG08 Thu Mar 01 2018 22:55:21 GMT+0300 (EAT) 20.0 \n362 True NG08 Thu Mar 01 2018 23:15:57 GMT+0300 (EAT) 1.0 \n363 True NG08 Thu Mar 01 2018 23:19:17 GMT+0300 (EAT) 1.0 \n364 True NG11 Fri Mar 02 2018 12:48:25 GMT+0300 (EAT) 2.0 \n365 True NG11 Fri Mar 02 2018 13:54:43 GMT+0300 (EAT) 6.0 \n366 False NG05 Mon Mar 05 2018 09:14:11 GMT+0300 (EAT) 2.0 \n\n START_DATE START_TIME ... HEART_RATE \\\n0 2017-02-02 09:51 ... 101-160 beats per minute \n1 2017-02-01 23:18 ... 101-160 beats per minute \n2 2017-02-02 15:26 ... 101-160 beats per minute \n3 2017-02-03 04:53 ... < 75 beats per minute \n4 2017-02-03 09:33 ... 101-160 beats per minute \n5 2017-02-03 11:43 ... 101-160 beats per minute \n6 2017-02-03 18:18 ... 101-160 beats per minute \n7 2017-02-04 19:43 ... 101-160 beats per minute \n8 2017-02-05 12:00 ... 75-100 beats per minute \n9 2017-02-05 12:12 ... 101-160 beats per minute \n10 2017-02-05 17:45 ... 101-160 beats per minute \n11 2017-02-06 13:55 ... 101-160 beats per minute \n12 2017-02-06 14:57 ... 101-160 beats per minute \n13 2017-02-06 19:03 ... 101-160 beats per minute \n14 2017-02-07 15:14 ... 101-160 beats per minute \n15 2017-02-07 15:29 ... 101-160 beats per minute \n16 2017-02-07 15:45 ... 101-160 beats per minute \n17 2017-02-07 15:49 ... 101-160 beats per minute \n18 2017-02-07 16:18 ... 101-160 beats per minute \n19 2017-02-08 10:55 ... > 160 beats per minute \n20 2017-02-08 13:55 ... 101-160 beats per minute \n21 2017-02-08 15:04 ... 101-160 beats per minute \n22 2017-02-09 12:06 ... 101-160 beats per minute \n23 2017-02-09 19:00 ... 101-160 beats per minute \n24 2017-02-10 09:47 ... 101-160 beats per minute \n25 2017-02-13 12:27 ... 101-160 beats per minute \n26 2017-02-13 13:11 ... 101-160 beats per minute \n27 2017-02-13 18:03 ... NaN \n28 2017-02-13 18:25 ... > 160 beats per minute \n29 2017-02-13 19:32 ... 75-100 beats per minute \n.. ... ... ... ... \n337 2018-01-26 14:42 ... > 160 beats per minute \n338 2018-01-26 14:48 ... > 160 beats per minute \n339 2018-01-29 12:03 ... 101-160 beats per minute \n340 2018-01-29 16:19 ... 101-160 beats per minute \n341 2018-01-30 13:44 ... > 160 beats per minute \n342 2018-01-30 14:24 ... > 160 beats per minute \n343 2018-02-01 15:22 ... > 160 beats per minute \n344 2018-02-03 19:43 ... 101-160 beats per minute \n345 2018-02-06 17:15 ... 101-160 beats per minute \n346 2018-02-07 10:45 ... 101-160 beats per minute \n347 2018-02-09 13:04 ... NaN \n348 2018-02-09 13:05 ... 75-100 beats per minute \n349 2018-02-09 19:57 ... 101-160 beats per minute \n350 2018-02-12 07:42 ... 101-160 beats per minute \n351 2018-02-12 07:45 ... 101-160 beats per minute \n352 2018-02-12 22:37 ... NaN \n353 2018-02-16 20:11 ... > 160 beats per minute \n354 2018-02-17 08:09 ... NaN \n355 2018-02-21 10:10 ... 75-100 beats per minute \n356 2018-02-22 10:43 ... 101-160 beats per minute \n357 2018-02-22 10:51 ... 101-160 beats per minute \n358 2018-02-22 12:44 ... NaN \n359 2018-02-22 13:35 ... NaN \n360 2018-02-26 18:25 ... 101-160 beats per minute \n361 2018-03-01 22:55 ... 101-160 beats per minute \n362 2018-03-01 23:15 ... 101-160 beats per minute \n363 2018-03-01 23:19 ... 101-160 beats per minute \n364 2018-03-02 12:48 ... 101-160 beats per minute \n365 2018-03-02 13:54 ... 101-160 beats per minute \n366 2018-03-05 09:14 ... 101-160 beats per minute \n\n RESP_THERAPIES_AVAILABLE CANT_GIVE_FLUIDS \\\n0 NaN NaN \n1 NaN NaN \n2 NaN NaN \n3 Regular Nasal Cannula False \n4 NaN NaN \n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n10 NaN NaN \n11 NaN NaN \n12 NaN NaN \n13 NaN False \n14 NaN NaN \n15 NaN NaN \n16 NaN NaN \n17 NaN NaN \n18 NaN NaN \n19 Regular Nasal Cannula NaN \n20 NaN NaN \n21 NaN NaN \n22 NaN NaN \n23 NaN NaN \n24 Regular Nasal Cannula NaN \n25 NaN NaN \n26 NaN False \n27 Regular Nasal Cannula True \n28 NaN True \n29 NaN False \n.. ... ... \n337 Regular Nasal Cannula NaN \n338 Regular Nasal Cannula NaN \n339 NaN NaN \n340 NaN NaN \n341 NaN NaN \n342 Regular Nasal Cannula NaN \n343 Regular Nasal Cannula False \n344 NaN NaN \n345 NaN False \n346 NaN False \n347 NaN NaN \n348 NaN NaN \n349 NaN False \n350 NaN False \n351 NaN False \n352 NaN NaN \n353 Regular Nasal Cannula True \n354 NaN NaN \n355 NaN NaN \n356 NaN False \n357 NaN False \n358 Regular Nasal Cannula False \n359 Regular Nasal Cannula False \n360 NaN NaN \n361 NaN NaN \n362 NaN NaN \n363 NaN NaN \n364 NaN NaN \n365 NaN NaN \n366 Mechanical ventilation, CPAP, Regular Nasal Ca... NaN \n\n IV_FLUIDS_ML_KG_DAY JAUNDICE UNDERWEIGHT PREMATURE HIV_EXPOSED \\\n0 NaN False False False False \n1 NaN False False False False \n2 NaN False False False False \n3 80 ml/kg/day False False False False \n4 NaN False False False False \n5 NaN NaN False False False \n6 NaN False True False False \n7 NaN False False False False \n8 NaN NaN False False False \n9 NaN False False False False \n10 NaN False False False False \n11 NaN False False False False \n12 NaN False False False False \n13 60 ml/kg/day False False False False \n14 NaN NaN False False False \n15 NaN NaN False False False \n16 NaN NaN False False False \n17 NaN NaN False False False \n18 NaN False False False False \n19 NaN False False False False \n20 NaN False False False False \n21 NaN NaN True True False \n22 NaN False False False False \n23 NaN False False False True \n24 NaN NaN False False False \n25 NaN NaN False False False \n26 60 ml/kg/day False False False False \n27 NaN False True True False \n28 NaN False True True False \n29 80 ml/kg/day False False False False \n.. ... ... ... ... ... \n337 NaN NaN False False False \n338 NaN False False False False \n339 NaN False False False False \n340 NaN False False False False \n341 NaN True False False False \n342 NaN True False False False \n343 80 ml/kg/day False True False False \n344 NaN False True False False \n345 80 ml/kg/day False False False False \n346 80 ml/kg/day False False False False \n347 NaN NaN True False False \n348 NaN False True False True \n349 80 ml/kg/day False True False False \n350 80 ml/kg/day True False False False \n351 80 ml/kg/day False False False False \n352 NaN NaN False False False \n353 NaN False False False False \n354 NaN NaN True False False \n355 NaN False True False False \n356 80 ml/kg/day False False False False \n357 80 ml/kg/day False False False False \n358 80 ml/kg/day False False True False \n359 80 ml/kg/day False False True False \n360 NaN False True False False \n361 NaN NaN False False False \n362 80 ml/kg/day False False False False \n363 80 ml/kg/day False False False False \n364 NaN False False False False \n365 NaN False False False False \n366 NaN NaN False False False \n\n HIV_UNKNOWN ANY_ABX \n0 False True \n1 False True \n2 False True \n3 False False \n4 False True \n5 False False \n6 False False \n7 False True \n8 False False \n9 False False \n10 False False \n11 False False \n12 False False \n13 False True \n14 False False \n15 False False \n16 False False \n17 False False \n18 False False \n19 False True \n20 False True \n21 False False \n22 False False \n23 False False \n24 False False \n25 False False \n26 False True \n27 False False \n28 False True \n29 False False \n.. ... ... \n337 False False \n338 False True \n339 False True \n340 False True \n341 False False \n342 False True \n343 False True \n344 False False \n345 False True \n346 False True \n347 False False \n348 False False \n349 False True \n350 False True \n351 False True \n352 False False \n353 False True \n354 False False \n355 True True \n356 False False \n357 False True \n358 False True \n359 False True \n360 False True \n361 False False \n362 False True \n363 False True \n364 False True \n365 False True \n366 False False \n\n[367 rows x 39 columns]"
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "#### Now calculate raw and normalized counts on initial and transfer"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "def valsForCol(col, normalize):\n if (normalize == True):\n return (col.value_counts(normalize = True) * 100).round(1)\n return col.value_counts()\ndef epi_df(df, normalize):\n epihash = {\n 'SICK_APPEARING': valsForCol(df['SICK'], normalize),\n 'DIFF_BREATHING': valsForCol(df['DIFFICULTY_BREATHING'], normalize),\n 'UNDER_2_5_KG': valsForCol(df['UNDERWEIGHT'], normalize),\n 'PREMATURE': valsForCol(df['PREMATURE'], normalize),\n 'ABNORMAL_VITALS': valsForCol(df['HAS_ABNORMAL_VITAL'], normalize),\n 'ABX_CALCULATED': valsForCol(df['ANY_ABX'], normalize),\n 'HIV_EXPOSED': valsForCol(df['HIV_EXPOSED'], normalize),\n 'HIV_UNKNOWN': valsForCol(df['HIV_UNKNOWN'], normalize)\n }\n epidf = pd.DataFrame(epihash, columns=epihash.keys())\n if (normalize == True):\n epidf.rename(columns=lambda x: x + '_%', inplace=True)\n \n return epidf",
"execution_count": 61,
"outputs": []
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Initial assessment epidemiology <a class=\"anchor\" id=\"initial-epi\"></a>"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "epi_df(birth_df, False)",
"execution_count": 62,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>SICK_APPEARING</th>\n <th>DIFF_BREATHING</th>\n <th>UNDER_2_5_KG</th>\n <th>PREMATURE</th>\n <th>ABNORMAL_VITALS</th>\n <th>ABX_CALCULATED</th>\n <th>HIV_EXPOSED</th>\n <th>HIV_UNKNOWN</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>False</th>\n <td>773</td>\n <td>821</td>\n <td>879</td>\n <td>959</td>\n <td>677</td>\n <td>652</td>\n <td>1037</td>\n <td>1071</td>\n </tr>\n <tr>\n <th>True</th>\n <td>319</td>\n <td>271</td>\n <td>213</td>\n <td>133</td>\n <td>415</td>\n <td>440</td>\n <td>55</td>\n <td>21</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " SICK_APPEARING DIFF_BREATHING UNDER_2_5_KG PREMATURE \\\nFalse 773 821 879 959 \nTrue 319 271 213 133 \n\n ABNORMAL_VITALS ABX_CALCULATED HIV_EXPOSED HIV_UNKNOWN \nFalse 677 652 1037 1071 \nTrue 415 440 55 21 "
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "#### The same data, normalized"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "epi_df(birth_df, True)",
"execution_count": 63,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>SICK_APPEARING_%</th>\n <th>DIFF_BREATHING_%</th>\n <th>UNDER_2_5_KG_%</th>\n <th>PREMATURE_%</th>\n <th>ABNORMAL_VITALS_%</th>\n <th>ABX_CALCULATED_%</th>\n <th>HIV_EXPOSED_%</th>\n <th>HIV_UNKNOWN_%</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>False</th>\n <td>70.8</td>\n <td>75.2</td>\n <td>80.5</td>\n <td>87.8</td>\n <td>62.0</td>\n <td>59.7</td>\n <td>95.0</td>\n <td>98.1</td>\n </tr>\n <tr>\n <th>True</th>\n <td>29.2</td>\n <td>24.8</td>\n <td>19.5</td>\n <td>12.2</td>\n <td>38.0</td>\n <td>40.3</td>\n <td>5.0</td>\n <td>1.9</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " SICK_APPEARING_% DIFF_BREATHING_% UNDER_2_5_KG_% PREMATURE_% \\\nFalse 70.8 75.2 80.5 87.8 \nTrue 29.2 24.8 19.5 12.2 \n\n ABNORMAL_VITALS_% ABX_CALCULATED_% HIV_EXPOSED_% HIV_UNKNOWN_% \nFalse 62.0 59.7 95.0 98.1 \nTrue 38.0 40.3 5.0 1.9 "
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Transfer assessment epidemiology <a class=\"anchor\" id=\"transfer-epi\"></a>"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "epi_df(transfer_df, False)",
"execution_count": 64,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>SICK_APPEARING</th>\n <th>DIFF_BREATHING</th>\n <th>UNDER_2_5_KG</th>\n <th>PREMATURE</th>\n <th>ABNORMAL_VITALS</th>\n <th>ABX_CALCULATED</th>\n <th>HIV_EXPOSED</th>\n <th>HIV_UNKNOWN</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>False</th>\n <td>83</td>\n <td>266</td>\n <td>256</td>\n <td>308</td>\n <td>172</td>\n <td>147</td>\n <td>355</td>\n <td>360</td>\n </tr>\n <tr>\n <th>True</th>\n <td>284</td>\n <td>101</td>\n <td>111</td>\n <td>59</td>\n <td>195</td>\n <td>220</td>\n <td>12</td>\n <td>7</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " SICK_APPEARING DIFF_BREATHING UNDER_2_5_KG PREMATURE \\\nFalse 83 266 256 308 \nTrue 284 101 111 59 \n\n ABNORMAL_VITALS ABX_CALCULATED HIV_EXPOSED HIV_UNKNOWN \nFalse 172 147 355 360 \nTrue 195 220 12 7 "
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "#### The same data, normalized"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "epi_df(transfer_df, True)",
"execution_count": 65,
"outputs": [
{
"data": {
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>SICK_APPEARING_%</th>\n <th>DIFF_BREATHING_%</th>\n <th>UNDER_2_5_KG_%</th>\n <th>PREMATURE_%</th>\n <th>ABNORMAL_VITALS_%</th>\n <th>ABX_CALCULATED_%</th>\n <th>HIV_EXPOSED_%</th>\n <th>HIV_UNKNOWN_%</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>False</th>\n <td>22.6</td>\n <td>72.5</td>\n <td>69.8</td>\n <td>83.9</td>\n <td>46.9</td>\n <td>40.1</td>\n <td>96.7</td>\n <td>98.1</td>\n </tr>\n <tr>\n <th>True</th>\n <td>77.4</td>\n <td>27.5</td>\n <td>30.2</td>\n <td>16.1</td>\n <td>53.1</td>\n <td>59.9</td>\n <td>3.3</td>\n <td>1.9</td>\n </tr>\n </tbody>\n</table>\n</div>",
"text/plain": " SICK_APPEARING_% DIFF_BREATHING_% UNDER_2_5_KG_% PREMATURE_% \\\nFalse 22.6 72.5 69.8 83.9 \nTrue 77.4 27.5 30.2 16.1 \n\n ABNORMAL_VITALS_% ABX_CALCULATED_% HIV_EXPOSED_% HIV_UNKNOWN_% \nFalse 46.9 40.1 96.7 98.1 \nTrue 53.1 59.9 3.3 1.9 "
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Histogram of transfer babies’ DOL <a class=\"anchor\" id=\"transfer-hist\"></a>\nBabies born elsewhere who were brought to the Tororo clinic for care ranged from DOL 0 to DOL 27."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "transfer_df['DOL'].hist(bins=27)",
"execution_count": 66,
"outputs": [
{
"data": {
"text/plain": "<matplotlib.axes._subplots.AxesSubplot at 0x114bdd710>"
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": "<Figure size 432x288 with 1 Axes>"
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Basic rounding assessment epidemiology <a class=\"anchor\" id=\"rounding-epi\"></a>"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": " rounding_df['TELL_US'].value_counts()",
"execution_count": 67,
"outputs": [
{
"data": {
"text/plain": "Term baby needing treatment 86\nPre-term 20\nHealthy, term baby 5\nName: TELL_US, dtype: int64"
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Inventory <a class=\"anchor\" id=\"inventory\"></a>"
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Can’t test glucose <a class=\"anchor\" id=\"cant-glucose\"></a>\nThe CANT_TEST_GLUCOSE column contains True if the user indicated that they could not test glucose and False if they did successfully test glucose. If it is blank, the user was not asked to test glucose in the course of the assessment."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "birth_df['CANT_TEST_GLUCOSE'].value_counts() + transfer_df['CANT_TEST_GLUCOSE'].value_counts() + seizure_df['CANT_TEST_GLUCOSE'].value_counts().append(pd.Series({ False: 0 }))",
"execution_count": 68,
"outputs": [
{
"data": {
"text/plain": "True 437\nFalse 380\ndtype: int64"
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### Respiratory treatment available (birth, transfer) <a class=\"anchor\" id=\"resp-treatment\"></a>\nIn some assessment flows, nurses were asked what respiratory therapies were available to them. This query surfaces the frequency of each response."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "birth_resp_vc = birth_df['RESP_THERAPIES_AVAILABLE'].value_counts().fillna(0)\nbirth_resp_vc.add(transfer_df['RESP_THERAPIES_AVAILABLE'].value_counts(), fill_value=0)",
"execution_count": 69,
"outputs": [
{
"data": {
"text/plain": "CPAP, Mechanical ventilation 1.0\nHigh Flow Nasal Cannula 4.0\nMechanical ventilation 5.0\nMechanical ventilation, CPAP, Regular Nasal Cannula 1.0\nRegular Nasal Cannula 288.0\nnone of the above 6.0\nName: RESP_THERAPIES_AVAILABLE, dtype: float64"
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "### No IV fluids <a class=\"anchor\" id=\"no-iv-fluids\"></a>\nNurses are sometimes asked if they wish to give IV fluids to a baby. In these cases, they can also indicate that they are unable to give these fluids — indicated by True in the CANT_GIVE_FLUIDS column."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "birth_df['CANT_GIVE_FLUIDS'].value_counts() + transfer_df['CANT_GIVE_FLUIDS'].value_counts()",
"execution_count": 70,
"outputs": [
{
"data": {
"text/plain": "False 312\nTrue 20\nName: CANT_GIVE_FLUIDS, dtype: int64"
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Synchronizations <a class=\"anchor\" id=\"syncs\"></a>\nThis data set contains a record of each time data stored on tablets offline was synchronized to the central database."
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "from dateutil.parser import parse\nfrom datetime import datetime\nbursts_df = pd.read_csv('bursts.csv')\n\nlen(bursts_df['Datetime'])",
"execution_count": 71,
"outputs": [
{
"data": {
"text/plain": "181"
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "## Learn More <a class=\"anchor\" id=\"learnmore\"></a>\nLearn More was accessed only 3 times (once by NG05 and twice by NG09)"
},
{
"metadata": {
"trusted": true
},
"cell_type": "code",
"source": "",
"execution_count": null,
"outputs": []
}
],
"metadata": {
"kernelspec": {
"name": "python3",
"display_name": "Python 3",
"language": "python"
},
"language_info": {
"name": "python",
"version": "3.7.1",
"mimetype": "text/x-python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python",
"file_extension": ".py"
},
"gist_id": "1e9f07ca1432be567b9021966718780b"
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment