Predicting patient-reported outcome of activities of daily living in stroke rehabilitation: a machine learning study

Table 2 Mutual information gains for the predictors sorted in descending order for each target variable

MAL-AOU		MAL-QOM		NEADL		SIS-ADL
Predictor	Gain	Predictor	Gain	Predictor	Gain	Predictor	Gain
Time since stroke	0.14	SIS-Total	0.12	SIS-Total	0.07	FMA-UE	0.10
WMFT-Quality	0.13	WMFT-Quality	0.06	SIS-ADL	0.06	SIS-ADL	0.09
SIS-Total	0.10	MAL-QOM	0.06	NEADL	0.05	MAL-AOU	0.05
FMA-UE	0.06	FMA-UE	0.03	MAL-AOU	0.03	CAHAI	0.05
MAL-QOM	0.06	MAL-AOU	0.03	BBT	0.02	Diagnosis	0.06
CAHAI	0.04	FIM	0.03	NIHSS	0.02	SIS-Total	0.02
FIM	0.03	Side of hemiplegia	0.02	FIM	0.01	Time since stroke	0.01
WMFT-Time	0.03	NEADL	0.02	Other predictors	0	NIHSS	0.01
MAL-AOU	0.01	Sex	0.01			Other predictors	0
Other predictors	0	Years of education	0.01
		Other predictors	0

ADL Activities of Daily Living, AOU Amount of Use, BBT Box and Block Test, CAHAI Chedoke Arm and Hand Activity Inventory, FMA-UE Upper Extremity subscale of the Fugl-Meyer Assessment, MAL Motor Activity Log, NEADL Nottingham Extended Activities of Daily Living, NIHSS National Institutes of Health Stroke Scale, QOM Quality of Movement, SIS Stroke Impact Scale, WMFT Wolf Motor Function Test