Incidence and Risk Factors of Lower Limb Deep Vein Thrombosis in Psychiatric Inpatients by Applying Machine Learning to Electronic Health Records: A Retrospective Cohort Study

Overview

Journal Clin Epidemiol

Publisher Dove Medical Press

Specialty Public Health

Date 2025 Mar 3

PMID 40027401

Authors

Liang Xu

Miao Da

Affiliations

Soon will be listed here.

Abstract

Background: Psychiatric inpatients face an increased risk of deep vein thrombosis (DVT) due to their psychiatric conditions and pharmacological treatments. However, research focusing on this population remains limited.

Methods: This study analyzed 17,434 psychiatric inpatients at Huzhou Third Municipal Hospital, incorporating data on demographics, psychiatric diagnoses, physical illnesses, laboratory results, and medication use. Predictive models for DVT were developed using logistic regression, random forest, support vector machine (SVM), and XGBoost (Extreme Gradient Boosting). Feature importance was assessed using the random forest model.

Results: The DVT incidence among psychiatric inpatients was 1.6%. Predictive model performance, measured by the area under the curve (AUC), showed logistic regression (0.900), random forest (0.885), SVM (0.890), and XGBoost (0.889) performed well. Logistic regression and random forest models exhibited optimal overall performance, while XGBoost excelled in recall. Significant predictors of DVT included elevated D-dimer levels, age, Alzheimer's disease, and Madopar use.

Conclusion: Psychiatric inpatients require vigilance for DVT risk, with factors like D-dimer levels and age serving as critical indicators. Machine learning models effectively predict DVT risk, enabling early detection and personalized prevention strategies in clinical practice.

References

Duffett L . Deep Venous Thrombosis. Ann Intern Med. 2022; 175(9):ITC129-ITC144. DOI: 10.7326/AITC202209200. View

. Global, regional, and national burden of 12 mental disorders in 204 countries and territories, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019. Lancet Psychiatry. 2022; 9(2):137-150. PMC: 8776563. DOI: 10.1016/S2215-0366(21)00395-3. View

Wang P, Wang Y, Yuan Z, Wang F, Wang H, Li Y . Venous thromboembolism risk assessment of surgical patients in Southwest China using real-world data: establishment and evaluation of an improved venous thromboembolism risk model. BMC Med Inform Decis Mak. 2022; 22(1):59. PMC: 8895056. DOI: 10.1186/s12911-022-01795-9. View

Wang K, Ikwuezunma I, Puvanesarajah V, Babu J, Margalit A, Raad M . Using Predictive Modeling and Supervised Machine Learning to Identify Patients at Risk for Venous Thromboembolism Following Posterior Lumbar Fusion. Global Spine J. 2021; 13(4):1097-1103. PMC: 10189318. DOI: 10.1177/21925682211019361. View

Lei H, Zhang M, Wu Z, Liu C, Li X, Zhou W . Development and Validation of a Risk Prediction Model for Venous Thromboembolism in Lung Cancer Patients Using Machine Learning. Front Cardiovasc Med. 2022; 9:845210. PMC: 8934875. DOI: 10.3389/fcvm.2022.845210. View

Yamane K, Kimura F, Unoda K, Hosokawa T, Hirose T, Tani H . Postural abnormality as a risk marker for leg deep venous thrombosis in Parkinson's disease. PLoS One. 2013; 8(7):e66984. PMC: 3699565. DOI: 10.1371/journal.pone.0066984. View

Wang X, Xi H, Geng X, Li Y, Zhao M, Li F . Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty. Clin Appl Thromb Hemost. 2023; 29:10760296221139263. PMC: 9830569. DOI: 10.1177/10760296221139263. View

Masters C, Bateman R, Blennow K, Rowe C, Sperling R, Cummings J . Alzheimer's disease. Nat Rev Dis Primers. 2016; 1:15056. DOI: 10.1038/nrdp.2015.56. View

Jin S, Qin D, Liang B, Zhang L, Wei X, Wang Y . Machine learning predicts cancer-associated deep vein thrombosis using clinically available variables. Int J Med Inform. 2022; 161:104733. DOI: 10.1016/j.ijmedinf.2022.104733. View

10.

Knudson J, Kortepeter C, Dubitsky G, Ahmad S, Chen M . Antipsychotic drugs and venous thromboembolism. Lancet. 2000; 356(9225):252-3. DOI: 10.1016/S0140-6736(05)74504-9. View

11.

Silveira P, Ip I, Goldhaber S, Piazza G, Benson C, Khorasani R . Performance of Wells Score for Deep Vein Thrombosis in the Inpatient Setting. JAMA Intern Med. 2015; 175(7):1112-7. DOI: 10.1001/jamainternmed.2015.1687. View

12.

Sarker I . Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021; 2(3):160. PMC: 7983091. DOI: 10.1007/s42979-021-00592-x. View

13.

Nudel J, Bishara A, de Geus S, Patil P, Srinivasan J, Hess D . Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: an analysis of the MBSAQIP database. Surg Endosc. 2020; 35(1):182-191. PMC: 9278895. DOI: 10.1007/s00464-020-07378-x. View

14.

Meng L, Wei T, Fan R, Su H, Liu J, Wang L . Development and validation of a machine learning model to predict venous thromboembolism among hospitalized cancer patients. Asia Pac J Oncol Nurs. 2022; 9(12):100128. PMC: 9583033. DOI: 10.1016/j.apjon.2022.100128. View

15.

Shohat N, Ludwick L, Sherman M, Fillingham Y, Parvizi J . Using machine learning to predict venous thromboembolism and major bleeding events following total joint arthroplasty. Sci Rep. 2023; 13(1):2197. PMC: 9905066. DOI: 10.1038/s41598-022-26032-1. View

16.

Zhang S, Chu W, Wang H, Liang Y, Fan Y, Liu H . Evaluation of stability of deep venous thrombosis of the lower extremities using Doppler ultrasound. J Int Med Res. 2020; 48(8):300060520942098. PMC: 7526051. DOI: 10.1177/0300060520942098. View

17.

Kafeza M, Shalhoub J, Salooja N, Bingham L, Spagou K, Davies A . A systematic review of clinical prediction scores for deep vein thrombosis. Phlebology. 2016; 32(8):516-531. DOI: 10.1177/0268355516678729. View

18.

Navarrete S, Solar C, Tapia R, Pereira J, Fuentes E, Palomo I . Pathophysiology of deep vein thrombosis. Clin Exp Med. 2022; 23(3):645-654. DOI: 10.1007/s10238-022-00829-w. View

19.

Wang Z, Yang Y, He X, Jiang X, Gao X, Liu P . Incidence and Clinical Features of Venous Thromboembolism in Inpatients with Mental Illness. Clin Appl Thromb Hemost. 2023; 29:10760296231160753. PMC: 9986904. DOI: 10.1177/10760296231160753. View

20.

Rajula H, Verlato G, Manchia M, Antonucci N, Fanos V . Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment. Medicina (Kaunas). 2020; 56(9). PMC: 7560135. DOI: 10.3390/medicina56090455. View