Monitoring functional status using a wearable real-time locating technology

Evaluation of risk stratification program based on trajectories of functional capacity in patients with acute coronary syndrome: The REACP study

Background

As a validated assessment tool for functional disability (activities of daily living), the Barthel index (BI) assessed initially at admission has the potential to stratify patients with high-risk acute coronary syndrome (ACS). Dynamic trajectory evaluation of functional capacity in hospitals may provide more prognostic information. We aimed to establish a novel dynamic BI-based risk stratification program (DBRP) during hospitalization to predict outcomes among ACS patients.

Methods

A total of 2,837 ACS patients were included from the Retrospective Multicenter Study for Early Evaluation of Acute Chest Pain. The DBRP rating (low, medium, and high-risk categories) was calculated from dynamic BI at admission and discharge. The primary outcome was all-cause mortality, and the secondary outcome was cardiac mortality.

Results

Of all the included patients, 312 (11%) died during a median follow-up period of 18.0 months. Kaplan-Meier analysis revealed that the cumulative mortality was significantly higher in patients in the higher risk category according to the DBRP. Multivariable Cox regression analysis indicated that, compared to the low-risk category, the higher risk category in the DBRP was an independent strong predictor of all-cause mortality after adjusting for confounding factors (medium-risk category: hazard ratio [HR]: 1.756, 95% confidence interval [95% CI]: 1.214-2.540; P = 0.003; high-risk category: HR: 5.052, 95% CI: 3.744-6.817; P < 0.001), and the same result was found for cardiac mortality.

Conclusion

The DBRP was a useful risk stratification tool for the early dynamic assessment of patients with ACS.

Clinical trial registration

[http://www.chictr.org.cn], identifier [ChiCTR1900024657].

Developing Acute Event Risk Profiles for Older Adults with Dementia in Long-Term Care Using Motor Behavior Clusters Derived from Deep Learning

OBJECTIVES

This paper uses deep (machine) learning techniques to develop and test how motor behaviors, derived from location and movement sensor tracking data, may be associated with falls, delirium, and urinary tract infections (UTIs) in long-term care (LTC) residents.

DESIGN

Longitudinal observational study.

SETTING AND PARTICIPANTS

A total of 23 LTC residents (81,323 observations) with cognitive impairment or dementia in 2 northeast Department of Veterans Affairs LTC facilities.

METHODS

More than 18 months of continuous (24/7) monitoring of motor behavior and activity levels used objective radiofrequency identification sensor data to track and record movement data. Occurrence of acute events was recorded each week. Unsupervised deep learning models were used to classify motor behaviors into 5 clusters; supervised decision tree algorithms used these clusters to predict acute health events (falls, delirium, and UTIs) the week before the week of the event.

RESULTS

Motor behaviors were classified into 5 categories (Silhouette score = 0.67), and these were significantly different from each other. Motor behavior classifications were sensitive and specific to falls, delirium, and UTI predictions 1 week before the week of the event (sensitivity range = 0.88-0.91; specificity range = 0.71-0.88).

CONCLUSION AND IMPLICATIONS

Intraindividual changes in motor behaviors predict some of the most common and detrimental acute events in LTC populations. Study findings suggest real-time locating system sensor data and machine learning techniques may be used in clinical applications to effectively prevent falls and lead to the earlier recognition of risk for delirium and UTIs in this vulnerable population.