{"title":"机器学习模型在整个护理过程中识别患者的步态速度,生成通知供临床医生评估","authors":"","doi":"10.1016/j.gaitpost.2024.09.001","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><p>The advent of digital and mobile health innovations, especially use of wearables for passive data collection, allows remote monitoring and creates an abundance of data. For this information to be interpretable, machine learning (ML) processes are necessary.</p></div><div><h3>Research question</h3><p>Can a machine learning model successfully identify patients expected to have low gait speed in the early recovery period following joint replacement surgery?</p></div><div><h3>Methods</h3><p>A commercial database from a smartphone-based care management platform passively collecting mobility data pre- and post-lower limb arthroplasty was used. We sought to create a ML model to predict gait speed recovery curves and identify patients at risk of poor gait speed outcome, a measure associated with range of motion and patient-reported outcomes. Model performance including sensitivity, specificity, precision, and accuracy were determined. Receiver operator curve (ROC) analysis was used to compare true and false positive rates. To benchmark our model, we compared threshold-based notifications based on the patient’s current gait speed.</p></div><div><h3>Results</h3><p>The performance of the predictive model was significantly improved compared to baseline of threshold-based exceptions using current gait speed. The ML model currently provides 53 % precision, 88 % accuracy, 36 % sensitivity, and 95 % specificity on the held-out test set. The ROC analysis suggests good clinical performance (AUC=0.81).</p></div><div><h3>Significance</h3><p>Utilization of ML to predict gait recovery following total joint replacement is feasible and provides results with excellent specificity. This model will allow inclusion of additional data for retraining as patient populations evolve. Clinician feedback regarding notifications, including resulting actions and outcomes, can be used to further inform the model and improve clinical utility.</p></div>","PeriodicalId":12496,"journal":{"name":"Gait & posture","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0966636224006064/pdfft?md5=36506074ccb670f756cc695c6903d7f8&pid=1-s2.0-S0966636224006064-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Machine learning model identifies patient gait speed throughout the episode of care, generating notifications for clinician evaluation\",\"authors\":\"\",\"doi\":\"10.1016/j.gaitpost.2024.09.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Introduction</h3><p>The advent of digital and mobile health innovations, especially use of wearables for passive data collection, allows remote monitoring and creates an abundance of data. For this information to be interpretable, machine learning (ML) processes are necessary.</p></div><div><h3>Research question</h3><p>Can a machine learning model successfully identify patients expected to have low gait speed in the early recovery period following joint replacement surgery?</p></div><div><h3>Methods</h3><p>A commercial database from a smartphone-based care management platform passively collecting mobility data pre- and post-lower limb arthroplasty was used. We sought to create a ML model to predict gait speed recovery curves and identify patients at risk of poor gait speed outcome, a measure associated with range of motion and patient-reported outcomes. Model performance including sensitivity, specificity, precision, and accuracy were determined. Receiver operator curve (ROC) analysis was used to compare true and false positive rates. To benchmark our model, we compared threshold-based notifications based on the patient’s current gait speed.</p></div><div><h3>Results</h3><p>The performance of the predictive model was significantly improved compared to baseline of threshold-based exceptions using current gait speed. The ML model currently provides 53 % precision, 88 % accuracy, 36 % sensitivity, and 95 % specificity on the held-out test set. The ROC analysis suggests good clinical performance (AUC=0.81).</p></div><div><h3>Significance</h3><p>Utilization of ML to predict gait recovery following total joint replacement is feasible and provides results with excellent specificity. This model will allow inclusion of additional data for retraining as patient populations evolve. Clinician feedback regarding notifications, including resulting actions and outcomes, can be used to further inform the model and improve clinical utility.</p></div>\",\"PeriodicalId\":12496,\"journal\":{\"name\":\"Gait & posture\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0966636224006064/pdfft?md5=36506074ccb670f756cc695c6903d7f8&pid=1-s2.0-S0966636224006064-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Gait & posture\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0966636224006064\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gait & posture","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0966636224006064","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
Machine learning model identifies patient gait speed throughout the episode of care, generating notifications for clinician evaluation
Introduction
The advent of digital and mobile health innovations, especially use of wearables for passive data collection, allows remote monitoring and creates an abundance of data. For this information to be interpretable, machine learning (ML) processes are necessary.
Research question
Can a machine learning model successfully identify patients expected to have low gait speed in the early recovery period following joint replacement surgery?
Methods
A commercial database from a smartphone-based care management platform passively collecting mobility data pre- and post-lower limb arthroplasty was used. We sought to create a ML model to predict gait speed recovery curves and identify patients at risk of poor gait speed outcome, a measure associated with range of motion and patient-reported outcomes. Model performance including sensitivity, specificity, precision, and accuracy were determined. Receiver operator curve (ROC) analysis was used to compare true and false positive rates. To benchmark our model, we compared threshold-based notifications based on the patient’s current gait speed.
Results
The performance of the predictive model was significantly improved compared to baseline of threshold-based exceptions using current gait speed. The ML model currently provides 53 % precision, 88 % accuracy, 36 % sensitivity, and 95 % specificity on the held-out test set. The ROC analysis suggests good clinical performance (AUC=0.81).
Significance
Utilization of ML to predict gait recovery following total joint replacement is feasible and provides results with excellent specificity. This model will allow inclusion of additional data for retraining as patient populations evolve. Clinician feedback regarding notifications, including resulting actions and outcomes, can be used to further inform the model and improve clinical utility.
期刊介绍:
Gait & Posture is a vehicle for the publication of up-to-date basic and clinical research on all aspects of locomotion and balance.
The topics covered include: Techniques for the measurement of gait and posture, and the standardization of results presentation; Studies of normal and pathological gait; Treatment of gait and postural abnormalities; Biomechanical and theoretical approaches to gait and posture; Mathematical models of joint and muscle mechanics; Neurological and musculoskeletal function in gait and posture; The evolution of upright posture and bipedal locomotion; Adaptations of carrying loads, walking on uneven surfaces, climbing stairs etc; spinal biomechanics only if they are directly related to gait and/or posture and are of general interest to our readers; The effect of aging and development on gait and posture; Psychological and cultural aspects of gait; Patient education.