• Supervised machine learning-ba...

Treffer: Supervised machine learning-based bias risk of prognostic models for total knee or hip arthroplasty patients: A systematic review.

Title:
Supervised machine learning-based bias risk of prognostic models for total knee or hip arthroplasty patients: A systematic review.
Authors:
Zhang H; Department of Orthopedics, Banan Hospital Affiliated to Chongqing Medical University, Chongqing, China., Jiang L; Department of Orthopedics, Banan Hospital Affiliated to Chongqing Medical University, Chongqing, China., Zheng J; Leshan City Vocational and Technical College Nursing Department, Leshan, China., Li C; Department of Orthopedics, Banan Hospital Affiliated to Chongqing Medical University, Chongqing, China.
Source:
Medicine [Medicine (Baltimore)] 2025 Oct 17; Vol. 104 (42), pp. e45230.
Publication Type:
Journal Article; Systematic Review
Language:
English
Journal Info:
Publisher: Lippincott Williams & Wilkins Country of Publication: United States NLM ID: 2985248R Publication Model: Print Cited Medium: Internet ISSN: 1536-5964 (Electronic) Linking ISSN: 00257974 NLM ISO Abbreviation: Medicine (Baltimore) Subsets: MEDLINE
Imprint Name(s):
Original Publication: Hagerstown, Md : Lippincott Williams & Wilkins
MeSH Terms:
Predictive Learning Models*/standards , Arthroplasty, Replacement, Knee*/statistics & numerical data , Arthroplasty, Replacement, Hip*/statistics & numerical data , Supervised Machine Learning*/standards, Humans ; Prognosis ; Prediction Algorithms ; Risk Assessment/methods ; Risk Assessment/standards ; Software Validation ; Bias
References:
J Clin Anesth. 2023 Sep;88:111147. (PMID: 37201387)
J Arthroplasty. 2021 May;36(5):1655-1662.e1. (PMID: 33478891)
Diabetes Res Clin Pract. 2024 Mar;209:111574. (PMID: 38346592)
J Knee Surg. 2023 May;36(6):637-643. (PMID: 35016246)
PLoS Med. 2013;10(2):e1001381. (PMID: 23393430)
Neural Netw. 2021 Nov;143:209-217. (PMID: 34157645)
IEEE Trans Neural Netw Learn Syst. 2018 Jun;29(6):2568-2580. (PMID: 28534794)
J Orthop Res. 2022 Feb;40(2):475-483. (PMID: 33734466)
JAMA Otolaryngol Head Neck Surg. 2022 Feb 1;148(2):180-186. (PMID: 34882175)
Front Oncol. 2024 Jan 24;13:1231508. (PMID: 38328435)
Biom J. 2024 Mar;66(2):e2300060. (PMID: 38351217)
J Orthop. 2021 Nov 25;28:91-95. (PMID: 34898926)
Ann Intern Med. 2019 Jan 1;170(1):51-58. (PMID: 30596875)
J Arthroplasty. 2024 May;39(5):1173-1177.e6. (PMID: 38007205)
Front Surg. 2021 Mar 11;8:606038. (PMID: 33777997)
J Am Acad Orthop Surg. 2023 Oct 1;31(19):e845-e858. (PMID: 37733328)
Arthroplast Today. 2021 Dec 08;13:13-23. (PMID: 34917716)
Arch Orthop Trauma Surg. 2023 Jun;143(6):3279-3289. (PMID: 35933638)
Lancet. 2019 Apr 20;393(10181):1577-1579. (PMID: 31007185)
Gastrointest Endosc. 2022 Apr;95(4):747-756.e2. (PMID: 34695422)
BMJ. 2021 Mar 29;372:n71. (PMID: 33782057)
Arthroplast Today. 2023 Jul 13;22:101166. (PMID: 37521739)
Knee. 2023 Oct;44:253-261. (PMID: 37703604)
J Glob Health. 2018 Dec;8(2):020303. (PMID: 30405904)
Zhongguo Xiu Fu Chong Jian Wai Ke Za Zhi. 2023 Dec 15;37(12):1562-1568. (PMID: 38130202)
Int J Gen Med. 2022 Apr 21;15:4339-4356. (PMID: 35480995)
Nurs Outlook. 2021 May-Jun;69(3):435-446. (PMID: 33386145)
Comput Biol Med. 2024 Mar;171:108093. (PMID: 38354499)
J Clin Med. 2024 Jan 21;13(2):. (PMID: 38276109)
Acta Orthop. 2021 Aug;92(4):385-393. (PMID: 33870837)
Nat Biotechnol. 2018 Aug 6;36(8):673-674. (PMID: 30080822)
PLoS One. 2023 Sep 8;18(9):e0274276. (PMID: 37682909)
Support Care Cancer. 2024 Feb 22;32(3):182. (PMID: 38386101)
Anesth Analg. 2019 Jul;129(1):43-50. (PMID: 30234533)
Geriatr Orthop Surg Rehabil. 2023 May 25;14:21514593231179316. (PMID: 37255949)
J Clin Endocrinol Metab. 2024 Jul 12;109(8):2029-2038. (PMID: 38330228)
Arch Orthop Trauma Surg. 2023 Sep;143(9):5985-5992. (PMID: 36905425)
Curr Rev Musculoskelet Med. 2020 Feb;13(1):69-76. (PMID: 31983042)
Arthritis Care Res (Hoboken). 2021 Oct;73(10):1518-1527. (PMID: 33749148)
Arthroplasty. 2021 Sep 2;3(1):33. (PMID: 35236492)
Clin Appl Thromb Hemost. 2023 Jan-Dec;29:10760296221139263. (PMID: 36596268)
PLoS Med. 2014 Oct 14;11(10):e1001744. (PMID: 25314315)
J Orthop. 2020 Mar 28;22:95-99. (PMID: 32300270)
Int J Surg. 2021 Dec;96:106183. (PMID: 34863965)
Eur J Prev Cardiol. 2024 Apr 18;31(6):744-753. (PMID: 38323650)
Reg Anesth Pain Med. 2021 Sep;46(9):779-783. (PMID: 34266992)
J Bone Joint Surg Am. 2022 Feb 2;104(3):265-270. (PMID: 34898530)
Bioengineering (Basel). 2024 Feb 15;11(2):. (PMID: 38391672)
Bone Joint J. 2021 Aug;103-B(8):1358-1366. (PMID: 34334050)
J Arthroplasty. 2023 Oct;38(10):1973-1981. (PMID: 36764409)
Clin Appl Thromb Hemost. 2023 Jan-Dec;29:10760296231186145. (PMID: 37394825)
PLoS One. 2022 Mar 22;17(3):e0263897. (PMID: 35316270)
Spine J. 2023 Mar;23(3):457-466. (PMID: 36892060)
JMIR Med Inform. 2015 Jan 21;3(1):e6. (PMID: 25608565)
J Healthc Inform Res. 2022 Oct 25;6(4):423-441. (PMID: 36744082)
Comput Math Methods Med. 2022 Jan 25;2022:3452348. (PMID: 35116072)
IEEE Trans Pattern Anal Mach Intell. 2024 Jul;46(7):4830-4842. (PMID: 38300782)
J Arthroplasty. 2019 Nov;34(11):2624-2631. (PMID: 31262622)
Neurocrit Care. 2024 Aug;41(1):285-296. (PMID: 38212559)
Arch Orthop Trauma Surg. 2023 Mar;143(3):1643-1650. (PMID: 35195782)
J Clin Epidemiol. 2003 Sep;56(9):826-32. (PMID: 14505766)
Arch Orthop Trauma Surg. 2023 Dec;143(12):7185-7193. (PMID: 37592158)
IEEE Trans Neural Netw Learn Syst. 2019 Jul;30(7):2212-2221. (PMID: 30507515)
BMC Musculoskelet Disord. 2015 Oct 05;16:279. (PMID: 26438322)
Contributed Indexing:
Keywords: arthroplasty; prognostic model; risk bias; supervised machine learning; systematic review
Entry Date(s):
Date Created: 20251105 Date Completed: 20251124 Latest Revision: 20251124
Update Code:
20251124
PubMed Central ID:
PMC12537099
DOI:
10.1097/MD.0000000000045230
PMID:
41189192
Database:
MEDLINE

Weitere Informationen

Background: As various machine learning (ML) algorithms have become more popular in orthopedic surgery, the research quality of these models requires further evaluation, and the methodological quality of the models still needs to be clarified. This study aimed to comprehensively analyze and evaluate the potential bias and applicability of existing studies of supervised ML-driven prognostic risk prediction models focusing on total knee arthroplasty/total hip arthroplasty individuals.
Methods: The China National Knowledge Infrastructure, Wanfang, PubMed, Web of Science, Cochrane Library, and Embase databases were searched from inception to January 20, 2024. The following data were extracted from the selected studies: author, year, joints, sample size, data source, study design, ML methods, ML performance, and primary outcome. The PROBAST checklist was applied to evaluate the risk of bias and applicability in prediction model studies. The protocol is registered in the PROSPERO database (CRD42024501747).
Results: A total of 2909 indexed records were obtained and 32 studies were included, 30 of which had models for internal validation only, 1 study for development and validation, and 1 study for external validation only. The PROBAST evaluation results showed that 1 externally validated model and 29/31 (93%) development models were rated as having a high risk of bias. There was a high risk of bias in the participant and analysis domains.
Conclusion: Almost all supervised ML models have the potential for a high bias risk. Factors contributing to a high bias risk include inadequate sample size, missing data during recruitment, model overfitting, and limited external validation. Adhering to strict standards and implementing comprehensive improvements when constructing prognosis models using supervised ML is crucial.
(Copyright © 2025 the Author(s). Published by Wolters Kluwer Health, Inc.)

The authors have no conflicts of interest to disclose.