Prediction of Physical Frailty in Orthogeriatric Patients Using Sensor Insole–Based Gait Analysis and Machine Learning Algorithms: Cross-sectional Study

Abstract

Background Assessment of the physical frailty of older patients is of great importance in many medical disciplines to be able to implement individualized therapies. For physical tests, time is usually used as the only objective measure. To record other objective factors, modern wearables offer great potential for generating valid data and integrating the data into medical decision-making. Objective The aim of this study was to compare the predictive value of insole data, which were collected during the Timed-Up-and-Go (TUG) test, to the benchmark standard questionnaire for sarcopenia (SARC-F: strength, assistance with walking, rising from a chair, climbing stairs, and falls) and physical assessment (TUG test) for evaluating physical frailty, defined by the Short Physical Performance Battery (SPPB), using machine learning algorithms. Methods This cross-sectional study included patients aged >60 years with independent ambulation and no mental or neurological impairment. A comprehensive set of parameters associated with physical frailty were assessed, including body composition, questionnaires (European Quality of Life 5-dimension [EQ 5D 5L], SARC-F), and physical performance tests (SPPB, TUG), along with digital sensor insole gait parameters collected during the TUG test. Physical frailty was defined as an SPPB score≤8. Advanced statistics, including random forest (RF) feature selection and machine learning algorithms (K-nearest neighbor [KNN] and RF) were used to compare the diagnostic value of these parameters to identify patients with physical frailty. Results Classified by the SPPB, 23 of the 57 eligible patients were defined as having physical frailty. Several gait parameters were significantly different between the two groups (with and without physical frailty). The area under the receiver operating characteristic curve (AUROC) of the TUG test was superior to that of the SARC-F (0.862 vs 0.639). The recursive feature elimination algorithm identified 9 parameters, 8 of which were digital insole gait parameters. Both the KNN and RF algorithms trained with these parameters resulted in excellent results (AUROC of 0.801 and 0.919, respectively). Conclusions A gait analysis based on machine learning algorithms using sensor soles is superior to the SARC-F and the TUG test to identify physical frailty in orthogeriatric patients.

Digital health technology combining wearable gait sensors and machine learning improve the accuracy in prediction of frailty

“…Our final model, which was processed using a random forest machine learning method, achieved an impressive area under the curve (AUC) score of 0.926, indicating a high level of accuracy compared with previous estimates, ranging from 0.58 up to 0.92 (15)(16)(17)(18)(19)(20)(21)(22)(23). In contrast to other traditional predictive formulas, such as Furthermore, we also calculated the accuracy of each model when processing different complements of patient characteristics, in addition to overall model performance.…”

“…It also highlights the importance of gait-related measures for frailty prediction. Previous studies have used various artificial intelligence (AI) models to analyze frailty and predict frailty risk in older adults using different types of data, including clinical records (15-18, 24, 46), physical function data (47,48), and wearable sensor data (21,22,49). Additionally, the clinical implications of our method were summarized as follows:…”

“…For example, questions within the CGA frequently require advanced knowledge and thus might not accurately reflect the mental status of subjects. Concurrently, with the evolution of computer science and artificial intelligence, many researchers would like to predict frailty using ML approaches (Table 1) (15)(16)(17)(18)(19)(20)(21)(22)(23). Previous studies in this regard have commonly utilized easyto-access epidemiological datasets or electronic health records to construct ML algorithms (24); the nature of these databases mean that these algorithms are potentially limited to the use of a single dimension.…”

Wearable Sensor Systems for Fall Risk Assessment: A Review

“…Kraus et al ( 67 ) used the Moticon Science3 insole to investigate physical frailty. Along with pressure sensors, this insole system consists of a 6-axis inertial measurement unit at the midfoot.…”

“…By recognizing characteristic PPD and gait patterns while walking and standing, further insight into an individual's fall risk can be obtained. The parameters typically analyzed for fall risk assessment or fall detection in existing insole systems (57)(58)(59)(60)(61)(62)(63)(64)(65)(66)(67) are shown in Figure 4.…”