Predicting the Risk of Pulmonary Embolism in Patients with Tuberculosis Using Machine Learning Algorithms

Overview

Journal Eur J Med Res

Publisher Biomed Central

Specialty General Medicine

Date 2024 Dec 22

PMID 39710777

Authors

Haobo Kong

Yong Li

Ya Shen

Jingjing Pan

Min Liang

Zhi Geng

Yanbei Zhang

Affiliations

Soon will be listed here.

Abstract

Background: This study aimed to develop predictive models with robust generalization capabilities for assessing the risk of pulmonary embolism in patients with tuberculosis using machine learning algorithms.

Methods: Data were collected from two centers and categorized into development and validation cohorts. Using the development cohort, candidate variables were selected via the Recursive Feature Elimination (RFE) method. Five machine learning algorithms, logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and support vector machine (SVM), were utilized to construct the predictive models. Model performance was evaluated through nested cross-validation and area under the curve (AUC) metrics, supplemented by interpretations using Shapley Additive explanations (SHAP) and line charts of AUC values. Models were subjected to external validation using an independent validation group, facilitating the early identification and management of pulmonary embolism risks in tuberculosis patients.

Results: Data from 694 patients were used for model development, and 236 patients from the validation group met the enrollment criteria. The optimal subset of variables identified included D-dimer, smoking status, dyspnea, age, sex, diabetes, platelet count, cough, fibrinogen, hemoglobin, hemoptysis, hypertension, chronic obstructive pulmonary disease (COPD), and chest pain. The RF model outperformed others, achieving an AUC of 0.839 (95% CI 0.780-0.899) and maintaining the highest average performance in external fivefold cross-validation (AUC: 0.906 ± 0.041).

Conclusions: The RF model demonstrates high and consistent effectiveness in predicting pulmonary embolism risk in tuberculosis patients.

References

Sultan A, Elgharib M, Tavares T, Jessri M, Basile J . The use of artificial intelligence, machine learning and deep learning in oncologic histopathology. J Oral Pathol Med. 2020; 49(9):849-856. DOI: 10.1111/jop.13042. View

Han X, Li C, Zhang S, Hou X, Chen Z, Zhang J . Why thromboembolism occurs in some patients with thrombocytopenia and treatment strategies. Thromb Res. 2020; 196:500-509. DOI: 10.1016/j.thromres.2020.10.005. View

Zhang L, Huang T, Xu F, Li S, Zheng S, Lyu J . Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest). BMC Emerg Med. 2022; 22(1):26. PMC: 8832779. DOI: 10.1186/s12873-022-00582-z. View

Cohoon K, Ashrani A, Crusan D, Petterson T, Bailey K, Heit J . Is Infection an Independent Risk Factor for Venous Thromboembolism? A Population-Based, Case-Control Study. Am J Med. 2017; 131(3):307-316.e2. PMC: 5817009. DOI: 10.1016/j.amjmed.2017.09.015. View

van Belle A, Buller H, Huisman M, Huisman P, Kaasjager K, Kamphuisen P . Effectiveness of managing suspected pulmonary embolism using an algorithm combining clinical probability, D-dimer testing, and computed tomography. JAMA. 2006; 295(2):172-9. DOI: 10.1001/jama.295.2.172. View

Jimenez D, de Miguel-Diez J, Guijarro R, Trujillo-Santos J, Otero R, Barba R . Trends in the Management and Outcomes of Acute Pulmonary Embolism: Analysis From the RIETE Registry. J Am Coll Cardiol. 2016; 67(2):162-170. DOI: 10.1016/j.jacc.2015.10.060. View

Huang L, Yin C, Gu X, Tang X, Zhang X, Hu C . Severe pulmonary tuberculosis complicated with insidious pulmonary thromboembolism: a case report and literature review. J Thromb Thrombolysis. 2019; 49(4):644-650. PMC: 7182625. DOI: 10.1007/s11239-019-01967-x. View

Sun X, Yin Y, Yang Q, Huo T . Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives. Eur J Med Res. 2023; 28(1):242. PMC: 10360247. DOI: 10.1186/s40001-023-01065-y. View

Zhu Q, Liu J . A united model for diagnosing pulmonary tuberculosis with random forest and artificial neural network. Front Genet. 2023; 14:1094099. PMC: 10033863. DOI: 10.3389/fgene.2023.1094099. View

10.

Segar M, Hall J, Jhund P, Powell-Wiley T, Morris A, Kao D . Machine Learning-Based Models Incorporating Social Determinants of Health vs Traditional Models for Predicting In-Hospital Mortality in Patients With Heart Failure. JAMA Cardiol. 2022; 7(8):844-854. PMC: 9260645. DOI: 10.1001/jamacardio.2022.1900. View

11.

Heit J, Spencer F, White R . The epidemiology of venous thromboembolism. J Thromb Thrombolysis. 2016; 41(1):3-14. PMC: 4715842. DOI: 10.1007/s11239-015-1311-6. View

12.

Badrick T, Banfi G, Bietenbeck A, Cervinski M, Loh T, Sikaris K . Machine Learning for Clinical Chemists. Clin Chem. 2019; 65(11):1350-1356. DOI: 10.1373/clinchem.2019.307512. View

13.

Spagnolo P, Lee J, Sverzellati N, Rossi G, Cottin V . The Lung in Rheumatoid Arthritis: Focus on Interstitial Lung Disease. Arthritis Rheumatol. 2018; 70(10):1544-1554. DOI: 10.1002/art.40574. View

14.

van der Meijden P, Heemskerk J . Platelet biology and functions: new concepts and clinical perspectives. Nat Rev Cardiol. 2018; 16(3):166-179. DOI: 10.1038/s41569-018-0110-0. View

15.

Park H, Cha S, Lim J, Jeon K, Yoo S, Lee J . Clinical Characteristics of Coexisting Pulmonary Thromboembolism in Patients With Respiratory Tuberculosis. Am J Med Sci. 2017; 353(2):166-171. DOI: 10.1016/j.amjms.2016.11.025. View

16.

Kamath S, Blann A, Lip G . Platelet activation: assessment and quantification. Eur Heart J. 2001; 22(17):1561-71. DOI: 10.1053/euhj.2000.2515. View

17.

Handelman G, Kok H, Chandra R, Razavi A, Lee M, Asadi H . eDoctor: machine learning and the future of medicine. J Intern Med. 2018; 284(6):603-619. DOI: 10.1111/joim.12822. View

18.

Nan G, Fei H, Zhen W, Yun D . Risk factors associated with venous thromboembolism in tuberculosis: A case control study. Clin Respir J. 2022; 16(12):835-841. PMC: 9716713. DOI: 10.1111/crj.13555. View

19.

Wang Y, Qiu L, Yu D, Yu Y, Hu L, Gu Y . Effects and related mechanism of alpha-adrenergic receptor inhibitor phentolamine in a rabbit model of acute pulmonary embolism combined with shock. Eur J Med Res. 2022; 27(1):238. PMC: 9641939. DOI: 10.1186/s40001-022-00842-5. View

20.

Kearon C, de Wit K, Parpia S, Schulman S, Afilalo M, Hirsch A . Diagnosis of Pulmonary Embolism with d-Dimer Adjusted to Clinical Probability. N Engl J Med. 2019; 381(22):2125-2134. DOI: 10.1056/NEJMoa1909159. View