Wearable Sensors Improve Prediction of Post-Stroke Walking Function Following Inpatient Rehabilitation

Early Prediction of Poststroke Rehabilitation Outcomes Using Wearable Sensors

OBJECTIVE

Inpatient rehabilitation represents a critical setting for stroke treatment, providing intensive, targeted therapy and task-specific practice to minimize a patient's functional deficits and facilitate their reintegration into the community. However, impairment and recovery vary greatly after stroke, making it difficult to predict a patient's future outcomes or response to treatment. In this study, the authors examined the value of early-stage wearable sensor data to predict 3 functional outcomes (ambulation, independence, and risk of falling) at rehabilitation discharge.

METHODS

Fifty-five individuals undergoing inpatient stroke rehabilitation participated in this study. Supervised machine learning classifiers were retrospectively trained to predict discharge outcomes using data collected at hospital admission, including patient information, functional assessment scores, and inertial sensor data from the lower limbs during gait and/or balance tasks. Model performance was compared across different data combinations and was benchmarked against a traditional model trained without sensor data.

RESULTS

For patients who were ambulatory at admission, sensor data improved the predictions of ambulation and risk of falling (with weighted F1 scores increasing by 19.6% and 23.4%, respectively) and maintained similar performance for predictions of independence, compared to a benchmark model without sensor data. The best-performing sensor-based models predicted discharge ambulation (community vs household), independence (high vs low), and risk of falling (normal vs high) with accuracies of 84.4%, 68.8%, and 65.9%, respectively. Most misclassifications occurred with admission or discharge scores near the classification boundary. For patients who were nonambulatory at admission, sensor data recorded during simple balance tasks did not offer predictive value over the benchmark models.

CONCLUSION

These findings support the continued investigation of wearable sensors as an accessible, easy-to-use tool to predict the functional recovery after stroke.

IMPACT

Accurate, early prediction of poststroke rehabilitation outcomes from wearable sensors would improve our ability to deliver personalized, effective care and discharge planning in the inpatient setting and beyond.

Monitoring walking asymmetries and endpoint control in persons living with chronic stroke: Implications for remote diagnosis and telerehabilitation

Objective

The objective of this study was to assess the feasibility of monitoring and diagnosing compromised walking motion in the frontal plane, particularly in persons living with the chronic effects of stroke (PwCS). The study aimed to determine whether active control of walking in the frontal plane could be monitored and provide diagnostic insights into compensations made by PwCS during community living.

Methods

The study recruited PwCS with noticeable walking asymmetries and employed a monitoring method to assess frontal plane motion. Monitoring was conducted both within a single assessment and between assessments. The study aimed to uncover baseline data and diagnostic information about active control in chronic stroke survivors. Data were collected using sensors during 6 minutes of walking and compared between the paretic and non-paretic legs.

Results

The study demonstrated the feasibility of monitoring frontal plane motion and diagnosing disturbed endpoint control (p < 0.0125) in chronic stroke survivors when comparing the paretic leg to the non-paretic leg. A greater variability was observed in the paretic leg (p < 0.0125), and sensors were able to diagnose a stronger coupling of the body with its endpoint on the paretic side (p < 0.0125). Similar results were obtained when monitoring was conducted over a six-minute walking period, and no significant diagnostic differences were found between the two monitoring assessments. Monitoring did not reveal performance fatigue or debilitation over time.

Conclusions

This study's findings indicate that monitoring frontal plane motion is a feasible approach for diagnosing compromised walking motion. The results suggest that individuals with walking asymmetries, exhibit differences in endpoint control and variability between their paretic and non-paretic legs. These insights could contribute to more effective rehabilitation strategies and highlight the potential for monitoring compensations during various activities of daily living.

AI in Rehabilitation Medicine: Opportunities and Challenges

Artificial intelligence (AI) tools are increasingly able to learn from larger and more complex data, thus allowing clinicians and scientists to gain new insights from the information they collect about their patients every day. In rehabilitation medicine, AI can be used to find patterns in huge amounts of healthcare data. These patterns can then be leveraged at the individual level, to design personalized care strategies and interventions to optimize each patient's outcomes. However, building effective AI tools requires many careful considerations about how we collect and handle data, how we train the models, and how we interpret results. In this perspective, we discuss some of the current opportunities and challenges for AI in rehabilitation. We first review recent trends in AI for the screening, diagnosis, treatment, and continuous monitoring of disease or injury, with a special focus on the different types of healthcare data used for these applications. We then examine potential barriers to designing and integrating AI into the clinical workflow, and we propose an end-to-end framework to address these barriers and guide the development of effective AI for rehabilitation. Finally, we present ideas for future work to pave the way for AI implementation in real-world rehabilitation practices.

Perturbation-Based Balance Exercise Using a Wearable Device to Improve Reactive Postural Control

Reactive postural control is an important component of the balance function for fall prevention. Perturbation-based balance exercises improve reactive postural control; however, these exercises require large, complex instruments and expert medical guidance. This study investigates the effects of unexpected perturbation-based balance exercises using a wearable balance exercise device (WBED) on reactive postural control. Eighteen healthy adult males participated in this study. Participants were assigned to the WBED and Sham groups. In the intervention session, participants in the WBED group randomly underwent unexpected perturbation in the mediolateral direction, while the Sham group performed the same exercises without perturbation. Before and after the intervention session, all participants underwent evaluation of reactive balance function using air cylinders. Peak displacement (D), time at peak displacement (T), peak velocity (V), and root mean square (RMS) of center of pressure (COP) data were measured. For mediolateral and anteroposterior COP (COPML and COP[Formula: see text]), the main effects of group and time factors (pre/post) were investigated through the analysis of variance for split-plot factorial design. In the WBED group, the D-COPML and V-COPML of the post-test significantly decreased compared to those of the pre-test (p = 0.017 and p = 0.003, respectively). Furthermore, the D-COPAP and RMSAP of the post-test significantly decreased compared to those of the pre-test (p = 0.036 and p = 0.015, respectively). This study proved that the perturbation-based balance exercise using WBED immediately improved reactive postural control. Therefore, wearable exercise devices, such as WBED, may contribute to the prevention of falls and fall-related injuries.