bewest

Glucose Sonification

demo

code

Sonification is the use of non-speech audio to convey information or perceptualize data.[1] Auditory perception has advantages in temporal, spatial, amplitude, and frequency resolution that open possibilities as an alternative or complement to visualization techniques.

bewest

sample

bewest

Community and MDR

The FDA enforces science and data driven standards to promote and protect public health and safety. One of the ways they perform their job is by providing oversight of all products available to the public. One way they acheive "oversight" is through "post market surveillance," in other words monitoring how devices perform, with a special focus on potential or actual harms or injuries. In other words, FDA is deeply committed to the idea that "vendors" who create a device should know and report performance, safety and effectiveness data even when a vendor ceases to make or sell a device.

https://www.fda.gov/downloads/medicaldevices/deviceregulationandguidance/guidancedocuments/ucm359566.pdf

bewest

Get one day data out of Nightscout

Here's how to get one day of data out of Nightscout. The trick is in realizing that the field used to define the date is different between different data types, and that different data types are stored in different places. In addition, the API itself has interesting behaviors, for example to switch between tsv, csv, and json outputs, to perform regex based searches, and in some cases bugs to work around.

Mechanics of the search syntax. The API endpoints support a query string syntax used to compose queries.

bewest

/*
  openhumans upload API

TOKEN=example_token
URL=http://www.openhumans.org/api/project/upload/?access_token=$TOKEN
METADATA='{"tags": ["survey", "diet", "csv"], "description": "Diet survey questions and responses", "md5": "156da7fc980988c51682374436849943"}'

http --verbose --form POST $URL \

bewest

2016-08-24T22:22:01-07:00,1472102521000,171,SingleUp,openaps://cgm
2016-08-24T22:17:01-07:00,1472102221000,159,FortyFiveUp,openaps://cgm
2016-08-24T22:12:01-07:00,1472101921000,147,FortyFiveUp,openaps://cgm
2016-08-24T22:07:02-07:00,1472101622000,145,FortyFiveUp,openaps://cgm
2016-08-24T22:02:01-07:00,1472101321000,140,FortyFiveUp,openaps://cgm
2016-08-24T21:57:01-07:00,1472101021000,131,FortyFiveUp,openaps://cgm
2016-08-24T21:52:01-07:00,1472100721000,124,Flat,openaps://cgm
2016-08-24T21:47:01-07:00,1472100421000,119,Flat,openaps://cgm
2016-08-24T21:42:01-07:00,1472100121000,118,Flat,openaps://cgm
2016-08-24T21:37:01-07:00,1472099821000,116,Flat,openaps://cgm

bewest

{
  "units": "mg/dL",
  "timeFormat": 12,
  "nightMode": false,
  "editMode": true,
  "showRawbg": "always",
  "customTitle": "Nightscout",
  "theme": "default",
  "alarmUrgentHigh": false,
  "alarmUrgentHighMins": [

bewest

rewind history, extracting data and observations for openai

 2315  ./mk-time-series monitor/glucose.json | tee mega-log-glucose.json
 2316  head mega-log-glucose.json 
 2327  cat mega-log-glucose.json | json -a hash
 2328  cat mega-log-glucose.json | json -a hash | wc -l

bewest

[
  {
    "type": "alias",
    "name": "rm-warmup",
    "rm-warmup": {
      "command": "! bash -c \"rm -f model.json monitor/clock.json > /dev/null\""
    }
  },
  {
    "type": "alias",

bewest

import gym
from gym import spaces
from gym.utils import seeding
import numpy as np
from openapscontrib.predict import predict


class DiabetesEnv(gym.Env):
  metadata = {