Machine Learning for Predicting Venous Thromboembolism After Joint Arthroplasty: Systematic Review of Clinical Applicability and Model Performance

Junwei Ma; Huifeng Tang; Yunshan Zhang; Xuemei Yi; Tangsheng Zhong; Xinyun Li; Gang Wang

doi:10.2196/79886

journal article Feb 12, 2026

Machine Learning for Predicting Venous Thromboembolism After Joint Arthroplasty: Systematic Review of Clinical Applicability and Model Performance

Junwei Ma

JMIR Medical Informatics Vol. 14 pp. e79886-e79886 · JMIR Publications Inc.

View at Publisher Save 10.2196/79886

Abstract

Abstract

Background
There is increasing research on machine learning in predicting venous thromboembolism after joint arthroplasty, but the quality and clinical applicability of these models remain uncertain.

Objective
This systematic review aims to evaluate the predictive performance and methodological quality of machine learning models for venous thromboembolism risk after joint replacement surgery.

Methods
Web of Science, Embase, Scopus, CNKI, Wanfang, Vipro, and PubMed were searched until December 15, 2024. The risk of bias and applicability were evaluated using the PROBAST (Prediction Model Risk of Bias Assessment Tool) checklist. A qualitative comprehensive analysis was conducted to extract and describe the data related to the model’s characteristics and performance.

Results
This review encompassed 34 prediction models from 9 studies. The most frequently used machine learning models were extreme gradient boosting and logistic regression. The results showed that all studies had significant heterogeneity and high risk of bias. Although some models reported nearly flawless area under the curve (>0.9), they lacked external validation and may have overfitted. The models tested on large external datasets demonstrated more conservative performance.

Conclusions
The predictive performance of machine learning models varied greatly. Although the reported area under the curve values indicated that some models have good discriminative ability, this performance varied greatly and was inconsistent among the included studies. These models have a high risk of bias, and it is necessary to take this into account when they are used in clinical practice. Future studies should adopt a prospective study design, ensure appropriate data handling, and use external validation to improve model robustness and applicability.

Topics

No keywords indexed for this article. Browse by subject →

References

45

[1]

Rates of Total Joint Replacement in the United States: Future Projections to 2020–2040 Using the National Inpatient Sample

Jasvinder Singh, Shaohua Yu, Lang Chen et al.

The Journal of Rheumatology 10.3899/jrheum.170990

[2]

Yau "Swelling assessment after total knee arthroplasty" J Orthop Surg (Hong Kong) 10.1177/10225536221127668

[3]

Ding "Machine learning-based screening of risk factors and prediction of deep vein thrombosis and pulmonary embolism after hip arthroplasty" Clin Appl Thromb Hemost 10.1177/10760296231186145

[4]

Simon "Venous thromboembolism in total hip and total knee arthroplasty" JAMA Netw Open 10.1001/jamanetworkopen.2023.45883

[5]

Lee "The incidence of pulmonary embolism and deep vein thrombosis after knee arthroplasty in Asians remains low: a meta-analysis" Clin Orthop Relat Res 10.1007/s11999-012-2758-9

[6]

Malcolm "Pulmonary complications after hip and knee arthroplasty in the United States, 2004-2014" Anesth Analg 10.1213/ane.0000000000004265

[7]

Lewis "Venous thromboembolism prophylaxis strategies for people undergoing elective total knee replacement: a systematic review and network meta-analysis" Lancet Haematol 10.1016/s2352-3026(19)30155-3

[8]

Meng "Incidence and risk factor for preoperative deep vein thrombosis (DVT) in isolated calcaneal fracture, a prospective cohort study" Foot Ankle Surg 10.1016/j.fas.2020.06.007

[9]

Runner "Utilization patterns, efficacy, and complications of venous thromboembolism prophylaxis strategies in revision hip and knee arthroplasty as reported by American Board of Orthopaedic Surgery Part II candidates" J Arthroplasty 10.1016/j.arth.2021.01.072

[10]

Chong "Development and implementation of venous thromboembolism stewardship across a hospital network" Int J Med Inform 10.1016/j.ijmedinf.2021.104575

[11]

Agarwal "Trends of venous thromboembolism after total hip arthroplasty in the United States: analysis from 2011 to 2019" J Am Acad Orthop Surg 10.5435/jaaos-d-22-00708

[12]

Wei "Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures" Sci Rep 10.1038/s41598-024-57711-w

[13]

Use of Machine Learning Models to Predict Death After Acute Myocardial Infarction

Rohan Khera, Julian Haimovich, Nathan C. Hurley et al.

JAMA Cardiology 10.1001/jamacardio.2021.0122

[14]

Ryan "A machine learning approach to predict deep venous thrombosis among hospitalized patients" Clin Appl Thromb Hemost 10.1177/1076029621991185

[15]

Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: an analysis based on data from 207 centers

Chengfu Guan, Fuxin Ma, Sijie Chang et al.

Critical Care 10.1186/s13054-023-04683-4

[16]

Hou "The use of machine learning techniques to predict deep vein thrombosis in rehabilitation inpatients" Clin Appl Thromb Hemost 10.1177/10760296231179438

[17]

Arina "Prediction of complications and prognostication in perioperative medicine: a systematic review and PROBAST assessment of machine learning tools" Anesthesiology 10.1097/aln.0000000000004764

[18]

Salameh "Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist" BMJ 10.1136/bmj.m2632

[19]

Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies: The CHARMS Checklist

Karel G. M. Moons, Joris A. H. de Groot, Walter Bouwmeester et al.

PLoS Medicine 10.1371/journal.pmed.1001744

[20]

Xu Chin J Hosp Stat

[21]

Chen "Construction of prediction model of deep vein thrombosis risk after total knee arthroplasty based on XGBoost algorithm" Comput Math Methods Med 10.1155/2022/3452348

[22]

Harris "Can machine learning methods produce accurate and easy‑to‑use prediction models of 30‑day complications and mortality after knee or hip arthroplasty?" Clin Orthop Relat Res 10.1097/corr.0000000000000601

[23]

Rasouli Dezfouli "A machine learning framework for assessing the risk of venous thromboembolism in patients undergoing hip or knee replacement" J Healthc Inform Res 10.1007/s41666-022-00121-2

[24]

Shohat "Using machine learning to predict venous thromboembolism and major bleeding events following total joint arthroplasty" Sci Rep 10.1038/s41598-022-26032-1

[25]

Wang "Artificial intelligence‑based prediction of lower extremity deep vein thrombosis risk after knee/hip arthroplasty" Clin Appl Thromb Hemost 10.1177/10760296221139263

[26]

Sweerts "Development of prediction models for complications after primary total hip and knee arthroplasty: a single-centre retrospective cohort study in the Netherlands" BMJ Open 10.1136/bmjopen-2022-062065

[27]

Nemeth "Development and validation of a clinical prediction model for 90-day venous thromboembolism risk following total hip and total knee arthroplasty: a multinational study" J Thromb Haemost 10.1016/j.jtha.2023.09.033

[28]

Chen TQ Guestrin C . XGBoost: a scalable tree boosting system. Presented at: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD); Aug 13-17, 2016; San Francisco, CA. [doi: 10.1145/2939672.2939785] 10.1145/2939672.2939785

[29]

Liang "Global incidence of diarrheal diseases—an update using an interpretable predictive model based on XGBoost and SHAP: a systematic analysis" Nutrients 10.3390/nu16183217

[30]

XGBoost-Based Framework for Smoking-Induced Noncommunicable Disease Prediction

Khishigsuren Davagdorj, Van Huy Pham, Nipon Theera-Umpon et al.

International Journal of Environmental Research an... 10.3390/ijerph17186513

[31]

Tolles "Logistic regression: relating patient characteristics to outcomes" JAMA 10.1001/jama.2016.7653

[32]

Moore "XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction: a UK Biobank cohort study" Clin Med Insights Cardiol 10.1177/11795468221133611

[33]

An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests.

Carolin Strobl, James Malley, Gerhard Tutz

Psychological Methods 10.1037/a0016973

[34]

Raskob "Thrombosis: a major contributor to global disease burden" Semin Thromb Hemost 10.1055/s-0034-1390325

[35]

Chen "Interpretable machine learning for fall prediction among older adults in China" Am J Prev Med 10.1016/j.amepre.2023.04.006

[36]

Caprini "Thrombosis risk assessment as a guide to quality patient care" Dis Mon 10.1016/j.disamonth.2005.02.003

[37]

Ghadri "A novel clinical score (InterTAK Diagnostic Score) to differentiate takotsubo syndrome from acute coronary syndrome: results from the International Takotsubo Registry" Eur J Heart Fail 10.1002/ejhf.683

[38]

Zaka "Machine learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis" Eur Heart J Digit Health 10.1093/ehjdh/ztae074

[39]

Looi "External validation of a clinical score to differentiate takotsubo syndrome from non‑ST‑elevation myocardial infarction in women" Heart Lung Circ 10.1016/j.hlc.2023.04.002

[40]

Riley "External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges" BMJ 10.1136/bmj.i3140

[41]

Zobeiri "Post-cardiac arrest outcome prediction using machine learning: a systematic review and meta-analysis" Int J Med Inform 10.1016/j.ijmedinf.2024.105659

[42]

Mao "Risk prediction models for falls in hospitalized older patients: a systematic review and meta-analysis" BMC Geriatr 10.1186/s12877-025-05688-0

[43]

Alhabibi "Platelet-derived growth factor-beta as a new marker of deep venous thrombosis" J Res Med Sci 10.4103/jrms.jrms_965_18

[44]

Wang "Procoagulant factor levels and risk of venous thrombosis in the elderly" J Thromb Haemost 10.1111/jth.15127

[45]

Anghele "Predicting deep venous thrombosis using artificial intelligence: a clinical data approach" Bioengineering (Basel) 10.3390/bioengineering11111067

Metrics

1

Citations

45

References

Details

Published: Feb 12, 2026
Vol/Issue: 14
Pages: e79886-e79886

Authors

Cite This Article

Junwei Ma, Huifeng Tang, Yunshan Zhang, et al. (2026). Machine Learning for Predicting Venous Thromboembolism After Joint Arthroplasty: Systematic Review of Clinical Applicability and Model Performance. JMIR Medical Informatics, 14, e79886-e79886. https://doi.org/10.2196/79886

Machine Learning for Predicting Venous Thromboembolism After Joint Arthroplasty: Systematic Review of Clinical Applicability and Model Performance

You May Also Like