Jana Thompson luxzia

## features.csv
Features,Genre,Delta Start,Delta End,Impacted Morbidities,Behavior of Majority Class(White),Disproportionately Affected Races if Any
V2BA02b1_delta_V3BA02b1,diastolic blood pressure,Visit 2,Visit 3,"Chronic Hyptertension, Preeclampsia",Mean,Native Hawaiian/Other Pacific Islander/American Indian/Alaskan Native
V2BA02a1_delta_V3BA02a1,systolic blood pressure,Visit 2,Visit 3,"Chronic Hypertension, Postpartum Depression, Preeclampsia",Mean,Native Hawaiian/Other Pacific Islander
V1LA02b_delta_V3LA02b,sleep behavior,Visit 1,Visit 3,"Chronic Hypertension, Postpartum Depression",Mean,Native Hawaiian/Other Pacific Islander/American Indian/Alaskan Native
V1A03_delta_V3LA03,sleep behavior,Visit 1,Visit 3,Postpartum Anxiety,Mean,Asian/American Indian/Alaskan Native/Native Hawaiian/Other Pacific Islander
V1LB09a_delta_V3LB09a,sleep behavior,Visit1,Visit 3,"Postpartum Depression, Postpartum Anxiety",Mean,Native Hawaiian/Other Pacific Islander
V1LB09b_delta_V3LB09b,sleep behavior,Visit 1,Visit 3,"Chronic Hypertension, Postp

## awardees.csv

          
            Team Lead
            Institution
            Innovation Award(Rank)
            Health Disaprities Award(Rank)

            
              Ainesh Pandey
              IBM Data Science and AI Elite Team
              (1) 50k
              (1) 10k

            
              Nicole Carlson
              Emory University
              (2) 50k
              (3) 10k

            
              Monica Keith
              University of Washington
              (3) 50k
              (5) 10k

            
              Britnee Johnston
              Johnston and Company LLC
              (4) 50k
              (4) 10k

            
              Ali Ebrahim
              Delfina Inc
              (5) 50k
              (2) 10k

            
              Yaping Li
              FengYa LLC
              (6) 50k

            
              Ansaf Salleb-Aouissi
              Columbia University
              (7) 50k

## feedback_to_topic.csv
Dominant_Topic,Topic_Perc_Contrib,Keywords,review
1.0,0.432,"card, credit, work, show, use, even, get, time, check, detail","Same issue repeats - credit card tab not working especially for Sapphiro Amex cards, I can not 'manage' Amex cards a..."
1.0,0.492,"card, credit, work, show, use, even, get, time, check, detail",1. The app could do with a serious makeover also ensuring that all the functionality still works. Like never have I ...
1.0,0.688,"card, credit, work, show, use, even, get, time, check, detail",Hello... all other banks like sbi RBL etc have provided the facility to directly pay their credit card bills via thei...
0.0,0.769,"update, go, pay, bill, statement, click, unable, add, bug, due",I like to set limits for all transmissions just because I do not get overboard with spends. Before the previous updat...
2.0,0.568,"update, crash, mobile, well, change, send, verify, team, great, connection","To whom ever it concern, I had downloaded app and I have been trying to login through registered mobile n

## financial_use_case.csv

          
            Extracted Examples
             Document

            
              revenue: 10 million dollars
              press_release_2009.txt

            
              income: 3.2 thousand dollars
              press_release_2009.txt

            
              income: $4 billion
              press_release_2010.txt

            
              revenue: $3 million
              press_release_2010.txt

            
              income: 5.6 million dollars
              press_release_2012.txt

## DiD_results.txt
did = lm(Revenue - treatment + time + did, data = df_ral)
summary(did)

Call:
lm(formula = Revenue - treatment + time + did, data = df_ral)

Residuals:
Min     1Q      Median    3Q      Max
-9497   -4226   -1632     1550    65547

## ratio_analysis.csv

          
            
            Y0/Y1
            Y0/Y2

            
              
              1.627787307
              0.619856303

            
              
              1.663622527
              0.644457547

            
              
              1.614379085
              0.498318763

            
              
              1.670454545
              0.587217044

            
              
              2.024390244
              0.387548638

            
              
              1.653352354
              0.513286094

            
              
              1.603829161
              0.575277338

            
              
              1.64453125
              0.478409091

            
              
              1.517467249
              0.440151995

## sample_data.csv

          
            Y0
            Y1
            Y2

            
              949
              583
              1531

            
              1093
              657
              1696

            
              741
              459
              1487

            
              882
              528
              1502

            
              498
              246
              1285

            
              1159
              701
              2258

            
              1089
              679
              1893

            
              842
              512
              1760

            
              695
              458
              1579

## matching_results.csv

          
            Ind
            Best Control
            RelativeDistance
            Correlation
            Length
            MatchingStartDate
            MatchingEndDate
            rank

            
              1
              2
              0.43157838
              0.2395164
              100
              2019-1-22
              2019-05-01
              1

            
              1
              3
              0.43865135
              0.07071406
              100
              2019-01-22
              2019-05-01
              2

            
              1
              4
              0.44037795
              -0.04402647
              100
              2019-01-22
              2019-05-01
              3

            
              2
              4
              0.02556079
              -0.23020672
              100
              2019-01-22
              2019-05-01
              1

            
              2
              3
              0.02756030
              0.0985743
              100
              2019-01-22
              2019-05-01
              2

            
              2
              1
              0.56442680
              0.2395164
              100
              2019-01-22
              2019-05-01
              3

            
              3
              4
              0.01978961
              -0.41761812
              100
              2019-01-22
              2019-05-01
              1

            
              3
              2
              0.02754722
              0.985743
              100
              2019-01-22
              2019-05-01
              2

            
              3
              1
              0.57340486
              0.07071406
              100
              2019-01-22
              2019-05-01
              3

## XAI_design_prototype.txt
The overall title for this prototype is "AI for Explainable Healthcare Adverse Event Risk Prediction"

On the top of the prototype is the (fictional) patient's information: His name is Steve Rogers, he is 78 years old, his race is Black, and his Charlson Comorbidity Index conditions are COPD, PVD, and Type 2 DM with a 2% 10-year survival

On the left hand side of the image are questions grouped together within the larger user questions.

At the top are "why" questions: 1. why is this patient predicted of this risk and 2. what are his risk factors?
Below the "why" questions are the "how to be that" questions: 1. what can be doen to reduce the patient's risk? and 2. what worked for other patients with similar profiles?
After the "how to be that" questions are the "performance" questions: 1. on what types of patient might it work worse? and 2. how well does it work?
After the "performance" questions, and at the bottom of the left hand side are the "data" questions: 1. is the training data similar to my patien

## XAI_techniques.csv
question,example XAI techniques,explanations description
how (global model-wide),ProfWeight or BRCG or GLRM,1. Describe general model logic as feature impact or rules or decision-tree 2. if a user is only interested in a high-level view describe what are the top features or rules considered.
why,LIME or SHAP or ProtoDash,1. describe what the key features of the inquired instance determine the model's prediction of it. 2. Show similar exampels with the same predicted outcome to justify the model's prediction
why not (a different prediction),CEM or ProtoDash (on alternative prediction),1. describe what changes are required for the instance to get the alternative prediction and or what features of the instance guarantee the current prediction. 2. show prototypical examples that had the alternate outcomes.
how to change to be that (a different prediction),CEM,higlight feature that if changed (by increasing or decreasing or making absent or making present) could alter the prediction
how to remain to be this (the
	Features,Genre,Delta Start,Delta End,Impacted Morbidities,Behavior of Majority Class(White),Disproportionately Affected Races if Any
	V2BA02b1_delta_V3BA02b1,diastolic blood pressure,Visit 2,Visit 3,"Chronic Hyptertension, Preeclampsia",Mean,Native Hawaiian/Other Pacific Islander/American Indian/Alaskan Native
	V2BA02a1_delta_V3BA02a1,systolic blood pressure,Visit 2,Visit 3,"Chronic Hypertension, Postpartum Depression, Preeclampsia",Mean,Native Hawaiian/Other Pacific Islander
	V1LA02b_delta_V3LA02b,sleep behavior,Visit 1,Visit 3,"Chronic Hypertension, Postpartum Depression",Mean,Native Hawaiian/Other Pacific Islander/American Indian/Alaskan Native
	V1A03_delta_V3LA03,sleep behavior,Visit 1,Visit 3,Postpartum Anxiety,Mean,Asian/American Indian/Alaskan Native/Native Hawaiian/Other Pacific Islander
	V1LB09a_delta_V3LB09a,sleep behavior,Visit1,Visit 3,"Postpartum Depression, Postpartum Anxiety",Mean,Native Hawaiian/Other Pacific Islander
	V1LB09b_delta_V3LB09b,sleep behavior,Visit 1,Visit 3,"Chronic Hypertension, Postp
Team Lead	Institution	Innovation Award(Rank)	Health Disaprities Award(Rank)
Ainesh Pandey	IBM Data Science and AI Elite Team	(1) 50k	(1) 10k
Nicole Carlson	Emory University	(2) 50k	(3) 10k
Monica Keith	University of Washington	(3) 50k	(5) 10k
Britnee Johnston	Johnston and Company LLC	(4) 50k	(4) 10k
Ali Ebrahim	Delfina Inc	(5) 50k	(2) 10k
Yaping Li	FengYa LLC	(6) 50k
Ansaf Salleb-Aouissi	Columbia University	(7) 50k
	Dominant_Topic,Topic_Perc_Contrib,Keywords,review
	1.0,0.432,"card, credit, work, show, use, even, get, time, check, detail","Same issue repeats - credit card tab not working especially for Sapphiro Amex cards, I can not 'manage' Amex cards a..."
	1.0,0.492,"card, credit, work, show, use, even, get, time, check, detail",1. The app could do with a serious makeover also ensuring that all the functionality still works. Like never have I ...
	1.0,0.688,"card, credit, work, show, use, even, get, time, check, detail",Hello... all other banks like sbi RBL etc have provided the facility to directly pay their credit card bills via thei...
	0.0,0.769,"update, go, pay, bill, statement, click, unable, add, bug, due",I like to set limits for all transmissions just because I do not get overboard with spends. Before the previous updat...
	2.0,0.568,"update, crash, mobile, well, change, send, verify, team, great, connection","To whom ever it concern, I had downloaded app and I have been trying to login through registered mobile n
	Extracted Examples	Document
	revenue: 10 million dollars	press_release_2009.txt
	income: 3.2 thousand dollars	press_release_2009.txt
	income: $4 billion	press_release_2010.txt
	revenue: $3 million	press_release_2010.txt
	income: 5.6 million dollars	press_release_2012.txt
	did = lm(Revenue - treatment + time + did, data = df_ral)
	summary(did)

	Call:
	lm(formula = Revenue - treatment + time + did, data = df_ral)

	Residuals:
	Min 1Q Median 3Q Max
	-9497 -4226 -1632 1550 65547
		Y0/Y1	Y0/Y2
		1.627787307	0.619856303
		1.663622527	0.644457547
		1.614379085	0.498318763
		1.670454545	0.587217044
		2.024390244	0.387548638
		1.653352354	0.513286094
		1.603829161	0.575277338
		1.64453125	0.478409091
		1.517467249	0.440151995
Y0	Y1	Y2
949	583	1531
1093	657	1696
741	459	1487
882	528	1502
498	246	1285
1159	701	2258
1089	679	1893
842	512	1760
695	458	1579
Ind	Best Control	RelativeDistance	Correlation	Length	MatchingStartDate	MatchingEndDate	rank
1	2	0.43157838	0.2395164	100	2019-1-22	2019-05-01	1
1	3	0.43865135	0.07071406	100	2019-01-22	2019-05-01	2
1	4	0.44037795	-0.04402647	100	2019-01-22	2019-05-01	3
2	4	0.02556079	-0.23020672	100	2019-01-22	2019-05-01	1
2	3	0.02756030	0.0985743	100	2019-01-22	2019-05-01	2
2	1	0.56442680	0.2395164	100	2019-01-22	2019-05-01	3
3	4	0.01978961	-0.41761812	100	2019-01-22	2019-05-01	1
3	2	0.02754722	0.985743	100	2019-01-22	2019-05-01	2
3	1	0.57340486	0.07071406	100	2019-01-22	2019-05-01	3
	The overall title for this prototype is "AI for Explainable Healthcare Adverse Event Risk Prediction"

	On the top of the prototype is the (fictional) patient's information: His name is Steve Rogers, he is 78 years old, his race is Black, and his Charlson Comorbidity Index conditions are COPD, PVD, and Type 2 DM with a 2% 10-year survival

	On the left hand side of the image are questions grouped together within the larger user questions.

	At the top are "why" questions: 1. why is this patient predicted of this risk and 2. what are his risk factors?
	Below the "why" questions are the "how to be that" questions: 1. what can be doen to reduce the patient's risk? and 2. what worked for other patients with similar profiles?
	After the "how to be that" questions are the "performance" questions: 1. on what types of patient might it work worse? and 2. how well does it work?
	After the "performance" questions, and at the bottom of the left hand side are the "data" questions: 1. is the training data similar to my patien
	question,example XAI techniques,explanations description
	how (global model-wide),ProfWeight or BRCG or GLRM,1. Describe general model logic as feature impact or rules or decision-tree 2. if a user is only interested in a high-level view describe what are the top features or rules considered.
	why,LIME or SHAP or ProtoDash,1. describe what the key features of the inquired instance determine the model's prediction of it. 2. Show similar exampels with the same predicted outcome to justify the model's prediction
	why not (a different prediction),CEM or ProtoDash (on alternative prediction),1. describe what changes are required for the instance to get the alternative prediction and or what features of the instance guarantee the current prediction. 2. show prototypical examples that had the alternate outcomes.
	how to change to be that (a different prediction),CEM,higlight feature that if changed (by increasing or decreasing or making absent or making present) could alter the prediction
	how to remain to be this (the