Predicting Functional Independence Measure Scores During Rehabilitation With Wearable Inertial Sensors

Abstract

Evaluating patient progress and making discharge decisions regarding inpatient medical rehabilitation rely upon standard clinical assessments administered by trained clinicians. Wearable inertial sensors can offer more objective measures of patient movement and progress. We undertook a study to investigate the contribution of wearable sensor data to predict discharge functional independence measure (FIM) scores for 20 patients at an inpatient rehabilitation facility. The FIM utilizes a 7-point ordinal scale to measure patient independence while performing several activities of daily living, such as walking, grooming, and bathing. Wearable inertial sensor data were collected from ecological ambulatory tasks at two time points mid-stay during inpatient rehabilitation. Machine learning algorithms were trained with sensor-derived features and clinical information obtained from medical records at admission to the inpatient facility. While models trained only with clinical features predicted discharge scores well, we were able to achieve an even higher level of prediction accuracy when also including the wearable sensor-derived features. Correlations as high as 0.97 for leave-one-out cross validation predicting discharge FIM motor scores are reported.

Measuring changes in gait and vehicle transfer ability during inpatient rehabilitation with wearable inertial sensors

“…Several studies have used IMUs for analyzing gait and other movements as an inexpensive and unobtrusive substitute for other technologies [3]–[5]. In addition, we have shown in previous work that longitudinal changes in IMU metrics are predictive of patient FIM scores at discharge from inpatient rehabilitation [6]. …”

A Machine-Learning Model for Automatic Detection of Movement Compensations in Stroke Patients

“…That is, while the person is practicing RTG movements, they need to know how well they performed the movement in order to improve their performance in future repetitions. The prevailing way to monitor motor recovery of the patient is carried out by direct human observation, using standard clinical ratings such as the Fugl-Meyer assessment (FMA), Functional Test for the Hemiplegic Upper Extremity (FTHUE), and the Brunnstrom stage [13,14]. However, whereas those clinical scales are efficient tools, they also have some drawbacks [13][14][15][16][17].…”

“…The prevailing way to monitor motor recovery of the patient is carried out by direct human observation, using standard clinical ratings such as the Fugl-Meyer assessment (FMA), Functional Test for the Hemiplegic Upper Extremity (FTHUE), and the Brunnstrom stage [13,14]. However, whereas those clinical scales are efficient tools, they also have some drawbacks [13][14][15][16][17]. The subjective judgement exercised by therapists using those tools may lack accurate quantifiable data [14], likely because it is difficult for the human eye to detect variations in a small-scale movement [17].…”

“…However, whereas those clinical scales are efficient tools, they also have some drawbacks [13][14][15][16][17]. The subjective judgement exercised by therapists using those tools may lack accurate quantifiable data [14], likely because it is difficult for the human eye to detect variations in a small-scale movement [17]. This makes it difficult to precisely evaluate gradual improvements in movement execution.…”

“…In order to help stroke patients to continue the rehabilitation training after they leave the hospital, there is a need for automated assessment [4]. Automated assessment holds several benefits in comparison to assessment by human observation only in clinics [14]. For example, it can offer a more detailed tracking of the time course of recovery by identifying variations in their movements pattern [14,17], it avoids the "test" situation, which is often not representative of everyday function [14,18], and also, it can make the assessment more objective by giving an automated score from a model instead of from a specific therapist [17].…”