Feasibility of Fall-Risk Detection in Older Adults: Real-World Use of Sensor Data With Machine Learning.

IF 1.1 4区医学 Q4 GERIATRICS & GERONTOLOGY

Journal of gerontological nursing Pub Date : 2024-10-01 DOI:10.3928/00989134-20240912-03

Matthew Farmer, Kimberly R Powell

{"title":"Feasibility of Fall-Risk Detection in Older Adults: Real-World Use of Sensor Data With Machine Learning.","authors":"Matthew Farmer, Kimberly R Powell","doi":"10.3928/00989134-20240912-03","DOIUrl":null,"url":null,"abstract":"Purpose: To use machine learning techniques with sensor data to predict fall risk in older adults aging in place.Method: We tested the feasibility of using anomaly detection on a dataset comprising 315 days of continuous unobtrusive sensor data obtained from a single participant to predict fall risk within a 10-day window. Predictions were validated with performance metrics, including accuracy, F1 score, and receiver operating characteristic-area under curve (ROC-AUC), using actual falls documented in the electronic health record.Results: The model resulted with accuracy = 0.96 (95% confidence interval [CI] [0.94, 0.99]), F1 = 0.78 (95% CI [0.73, 0.83]), and ROC-AUC = 0.89 (95% CI [0.85, 0.93]).Conclusion: The application of anomaly detection on sensor data may provide a timely and valid indication of fall risk in older adults within a 10-day window. Further research and validation are warranted to confirm these findings and expand the scope of application in the domain of older adult care and health care support. [Journal of Gerontological Nursing, 50(10), 7-10.].","PeriodicalId":15848,"journal":{"name":"Journal of gerontological nursing","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of gerontological nursing","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3928/00989134-20240912-03","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: To use machine learning techniques with sensor data to predict fall risk in older adults aging in place.

Method: We tested the feasibility of using anomaly detection on a dataset comprising 315 days of continuous unobtrusive sensor data obtained from a single participant to predict fall risk within a 10-day window. Predictions were validated with performance metrics, including accuracy, F1 score, and receiver operating characteristic-area under curve (ROC-AUC), using actual falls documented in the electronic health record.

Results: The model resulted with accuracy = 0.96 (95% confidence interval [CI] [0.94, 0.99]), F1 = 0.78 (95% CI [0.73, 0.83]), and ROC-AUC = 0.89 (95% CI [0.85, 0.93]).

Conclusion: The application of anomaly detection on sensor data may provide a timely and valid indication of fall risk in older adults within a 10-day window. Further research and validation are warranted to confirm these findings and expand the scope of application in the domain of older adult care and health care support. [Journal of Gerontological Nursing, 50(10), 7-10.].

查看原文本刊更多论文

老年人跌倒风险检测的可行性：传感器数据与机器学习的实际应用。

目的：利用机器学习技术和传感器数据预测居家养老老年人的跌倒风险：我们测试了在一个数据集上使用异常检测的可行性，该数据集包括从单个参与者处获取的 315 天连续非侵入式传感器数据，用于预测 10 天窗口期内的跌倒风险。利用电子健康记录中记录的实际跌倒情况，对预测结果进行了性能指标验证，包括准确率、F1 分数和接收器工作特征曲线下面积 (ROC-AUC)：结果：该模型的准确率为 0.96（95% 置信区间 [CI] [0.94，0.99]），F1 = 0.78（95% CI [0.73，0.83]），ROC-AUC = 0.89（95% CI [0.85，0.93]）：对传感器数据进行异常检测可在 10 天内及时有效地提示老年人的跌倒风险。为了证实这些发现并扩大其在老年人护理和医疗保健支持领域的应用范围，有必要开展进一步的研究和验证。[老年护理杂志》，50（10），7-10]。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of gerontological nursing 医学-护理

CiteScore

2.00

自引率

7.70%

发文量

审稿时长

6-12 weeks

期刊介绍： The Journal of Gerontological Nursing is a monthly, peer-reviewed journal publishing clinically relevant original articles on the practice of gerontological nursing across the continuum of care in a variety of health care settings, for more than 40 years.