Literature DB >> 32798181

Can Machine Learning Methods Produce Accurate and Easy-to-Use Preoperative Prediction Models of One-Year Improvements in Pain and Functioning After Knee Arthroplasty?

Alex H S Harris1, Alfred C Kuo2, Thomas R Bowe3, Luisa Manfredi3, Narlina F Lalani4, Nicholas J Giori5.   

Abstract

BACKGROUND: Approximately 15%-20% of total knee arthroplasty (TKA) patients do not experience clinically meaningful improvements. We sought to compare the accuracy and parsimony of several machine learning strategies for developing predictive models of failing to experience minimal clinically important differences in patient-reported outcome measures (PROMs) 1 year after TKA.
METHODS: Patients (N = 587) in 3 large Veteran Health Administration facilities completed PROMs before and 1 year after TKA (92% follow-up). Preoperative PROMs and electronic health record data were used to develop and validate models to predict failing to experience at least a minimal clinically important difference in Knee Injury and Osteoarthritis Outcome Score (KOOS) Total, KOOS JR, and KOOS subscales (Pain, Symptoms, Activities of Daily Living, Quality of Life, and recreation). Several machine learning strategies were used for model development. Ten-fold cross-validation and bootstrapping were used to produce measures of overall accuracy (C-statistic, Brier Score). The sensitivity and specificity of various predicted probability cut-points were examined.
RESULTS: The most accurate models produced were for the Activities of Daily Living, Pain, Symptoms, and Quality of Life subscales of the KOOS (C-statistics 0.76, 0.72, 0.72, and 0.71, respectively). Strategies varied substantially in terms of the numbers of inputs required to achieve similar accuracy, with none being superior for all outcomes.
CONCLUSION: Models produced in this project provide estimates of patient-specific improvements in major outcomes 1 year after TKA. Integrating these models into clinical decision support, informed consent and shared decision making could improve patient selection, education, and satisfaction. LEVEL OF EVIDENCE: Level III, diagnostic study. Published by Elsevier Inc.

Entities:  

Keywords:  decision support; knee arthroplasty; patient-reported outcomes; prediction; shared decision making

Year:  2020        PMID: 32798181     DOI: 10.1016/j.arth.2020.07.026

Source DB:  PubMed          Journal:  J Arthroplasty        ISSN: 0883-5403            Impact factor:   4.757


  8 in total

Review 1.  Artificial intelligence in orthopedic surgery: evolution, current state and future directions.

Authors:  Andrew P Kurmis; Jamie R Ianunzio
Journal:  Arthroplasty       Date:  2022-03-02

2.  Machine Learning: the Future of Total Knee Replacement.

Authors:  H Gene Dossett
Journal:  Fed Pract       Date:  2022-02-14

3.  Predictive Models for Clinical Outcomes in Total Knee Arthroplasty: A Systematic Analysis.

Authors:  Cécile Batailler; Timothy Lording; Daniele De Massari; Sietske Witvoet-Braam; Stefano Bini; Sébastien Lustig
Journal:  Arthroplast Today       Date:  2021-04-24

Review 4.  Artificial intelligence in arthroplasty.

Authors:  Glen Purnomo; Seng-Jin Yeo; Ming Han Lincoln Liow
Journal:  Arthroplasty       Date:  2021-11-02

Review 5.  Artificial intelligence in diagnosis of knee osteoarthritis and prediction of arthroplasty outcomes: a review.

Authors:  Lok Sze Lee; Ping Keung Chan; Chunyi Wen; Wing Chiu Fung; Amy Cheung; Vincent Wai Kwan Chan; Man Hong Cheung; Henry Fu; Chun Hoi Yan; Kwong Yuen Chiu
Journal:  Arthroplasty       Date:  2022-03-05

Review 6.  Machine learning in knee arthroplasty: specific data are key-a systematic review.

Authors:  Florian Hinterwimmer; Igor Lazic; Christian Suren; Michael T Hirschmann; Florian Pohlig; Daniel Rueckert; Rainer Burgkart; Rüdiger von Eisenhart-Rothe
Journal:  Knee Surg Sports Traumatol Arthrosc       Date:  2022-01-10       Impact factor: 4.114

Review 7.  Artificial intelligence in knee arthroplasty: current concept of the available clinical applications.

Authors:  Cécile Batailler; Jobe Shatrov; Elliot Sappey-Marinier; Elvire Servien; Sébastien Parratte; Sébastien Lustig
Journal:  Arthroplasty       Date:  2022-05-02

8.  Can minimal clinically important differences in patient reported outcome measures be predicted by machine learning in patients with total knee or hip arthroplasty? A systematic review.

Authors:  Benedikt Langenberger; Andreas Thoma; Verena Vogt
Journal:  BMC Med Inform Decis Mak       Date:  2022-01-20       Impact factor: 2.796

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.