Predicting Deep Venous Thrombosis Using Artificial Intelligence: A Clinical Data Approach
Abstract
:1. Introduction
2. Materials and Methods
2.1. Related Work
2.2. Proposed Methodology
2.2.1. Data Collection
2.2.2. Preprocessing
2.2.3. Experimental Setup
2.3. System Architecture
2.3.1. Evaluation Metrics
- TP (True Positives): The number of positive instances correctly predicted by the model;
- FP (False Positives): The number of negative instances incorrectly predicted as positive by the model;
- TN (True Negatives): The number of negative instances correctly predicted by the model;
- FN (False Negatives): The number of positive instances incorrectly predicted as negative by the model.
- TPR = is the true positive rate;
- FPR = is the false positive rate.
2.3.2. Software
3. Results
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Conflicts of Interest
References
- Anderson, F.A.; Spencer, F.A. Risk factors for venous thromboembolism. Circulation 2003, 107 (Suppl. S1), I-9–I-16. [Google Scholar] [CrossRef] [PubMed]
- Heit, J.A.; Melton, L.J., III; Lohse, C.M.; Petterson, T.M.; Silverstein, M.D.; Mohr, D.N.; O’fallon, W.M. Incidence of venous thromboembolism in hospitalized patients vs. community residents. Mayo Clin. Proc. 2001, 76, 1102–1110. [Google Scholar] [CrossRef] [PubMed]
- Cushman, M. Epidemiology of venous thromboembolism. Semin. Hematol. 2004, 44, 42–49. [Google Scholar]
- Kearon, C.; Aki, E.K.; Comerota, A.J.; Prandoni, P.; Bounameaux, H.; Goldhaber, S.Z.; Nelson, M.E.; Wells, P.S.; Gould, M.K.; Dentali, F.; et al. Antithrombotic therapy for VTE disease. Chest 2012, 141 (Suppl. S2), e419S–e494S. [Google Scholar] [CrossRef] [PubMed]
- Wells, P.S.; Anderson, D.R.; Rodger, M.; Forgie, M.; Kearon, C.; Dreyer, J.; Kovacs, G.; Mitchell, M.; Lewandowski, B.; Kovacs, M.J. Evaluation of D-dimer in the diagnosis of suspected deep-vein thrombosis. N. Engl. J. Med. 2003, 349, 1227–1235. [Google Scholar] [CrossRef] [PubMed]
- Bauersachs, R.; Berkowitz, S.A.; Brenner, S. Diagnosis and treatment of deep-vein thrombosis. Dtsch. Ärzteblatt Int. 2010, 107, 698. [Google Scholar]
- Di Nisio, M.; Ageno, W.; Büller, H.R. Diagnosis and treatment of venous thrombosis and pulmonary embolism. J. Thromb. Haemost. 2016, 14, 190–194. [Google Scholar]
- Di Minno, M.N.D.; Ambrosino, P.; Ambrosini, F.; Tremoli, E.; Di Minno, G.; Dentali, F. Deep vein thrombosis and its complications. Semin. Thromb. Hemost. 2015, 41, 76–81. [Google Scholar]
- Beam, A.L.; Kohane, I.S. Big data and machine learning in health care. JAMA 2018, 319, 1317–1318. [Google Scholar] [CrossRef] [PubMed]
- Rajkomar, A.; Dean, J.; Kohane, I. Machine learning in medicine. N. Engl. J. Med. 2019, 380, 1347–1358. [Google Scholar] [CrossRef] [PubMed]
- Ahmad, M.A.; Eckert, C.; Teredesai, A. Interpretable machine learning in healthcare. Nat. Mach. Intell. 2020, 2, 563–571. [Google Scholar]
- Ryan, L.; Mataraso, S.; Siefkas, A.; Pellegrini, E.; Barnes, G.; Green-Saxena, A.; Hoffman, J.; Calvert, J.; Das, R. A Machine Learning Approach to Predict Deep Venous Thrombosis Among Hospitalized Patients. Clin. Appl. Thromb. Hemost. Off. J. Int. Acad. Clin. Appl. Thromb. Hemost. 2021, 27, 1076029621991185. [Google Scholar] [CrossRef] [PubMed]
- Contreras-Luján; Enrique, E.; García-Guerrero, E.E.; López-Bonilla, O.R.; Tlelo-Cuautle, E.; López-Mancilla, D.; Inzunza-González, E. Evaluation of Machine Learning Algorithms for Early Diagnosis of Deep Venous Thrombosis. Math. Comput. Appl. 2022, 27, 24. [Google Scholar] [CrossRef]
- Guan, C.; Ma, F.; Chang, S.; Zhang, J. Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: An analysis based on data from 207 centers. Crit. Care 2023, 27, 406. [Google Scholar] [CrossRef] [PubMed]
- Wei, C.; Wang, J.; Yu, P.; Li, A.; Xiong, Z.; Yuan, Z.; Yu, L.; Luo, J. Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures. Sci. Rep. 2024, 14, 6901. [Google Scholar] [CrossRef] [PubMed]
- Hou, T.; Qiao, W.; Song, S.; Guan, Y.; Zhu, C.; Yang, Q.; Gu, Q.; Sun, L.; Liu, S. The Use of Machine Learning Techniques to Predict Deep Vein Thrombosis in Rehabilitation Inpatients. Clin. Appl. Thromb. Hemost. 2023, 2023, 29. [Google Scholar] [CrossRef] [PubMed]
- Namjoo-Moghadam, A.; Abedi, V.; Avula, V.; Ashjazadeh, N.; Hooshmandi, E.; Abedinpour, N.; Rahimian, Z.; Borhani-Haghighi, A.; Zand, R. Machine learning-based Cerebral Venous Thrombosis diagnosis with clinical data. J. Stroke Cerebrovasc. Dis. 2024, 33, 107848. [Google Scholar] [CrossRef] [PubMed]
- Moscu, C.A.; Marina, V.; Anghele, M.; Anghele, A.D.; Dragomir, L. Did Personality Type Influence Burn Out Syndrome Manifestations During Covid-19 Pandemic? Int. J. Gen. Med. 2022, 15, 5487–5498. [Google Scholar] [CrossRef] [PubMed]
- Anghele, M.; Marina, V.; Moscu, C.A.; Dragomir, L.; Anghele, A.D.; Lescai, A.M. Emotional Distress in a Patients Following Polytrauma. J. Multidiscip. Healthc. 2023, 16, 1161–1170. [Google Scholar] [CrossRef] [PubMed]
- Dragomir, L.; Marina, V.; Moscu, C.A.; Anghele, M. The Patient Hides the Truth, but the Computer Tomography Examination Restores It! Diagnostics 2022, 12, 876. [Google Scholar] [CrossRef] [PubMed]
Model | Accuracy | Precision | Recall | F1-Score | Specificity | AUC-ROC |
---|---|---|---|---|---|---|
Logistic Regression | 0.97 | 0.95 | 0.99 | 0.98 | 0.94 | 0.95 |
Random Forest | 0.95 | 0.94 | 0.97 | 0.95 | 0.92 | 0.99 |
LightGBM | 0.96 | 0.94 | 0.98 | 0.96 | 0.92 | 0.97 |
Gradient Boosting | 0.93 | 0.91 | 0.97 | 0.94 | 0.88 | 0.98 |
k-Nearest Neighbors | 0.95 | 0.92 | 0.98 | 0.95 | 0.90 | 0.99 |
XGBoost | 0.96 | 0.95 | 0.97 | 0.96 | 0.94 | 0.97 |
CatBoost | 0.93 | 0.91 | 0.97 | 0.94 | 0.88 | 0.96 |
Artificial Neural Network | 0.96 | 0.94 | 0.98 | 0.96 | 0.92 | 0.98 |
Authors (Year) | Dataset Collection (Samples) | Applied Models | Performance (Proposed Model) |
---|---|---|---|
Ryan L. et al. (2021) [12] | Academic Medical Center USA (2011–2017) | XGBoost (proposed) | Recall: 99.90% Specificity: 80.00% AUC: 0.85 |
Contreras-Luján E.E. et al. (2022) [13] | Unspecified Public Hospital (59 patients) | Decision Trees, K-Nearest Neighbors (proposed), Support Vector Machine, Random Forest, Multilayer Perceptron Neural Network, Extra Trees | Accuracy: 90.40% Specificity: 80.66% Recall: 79.78% AUC: 0.868 |
Guan C., et al. (2023) [14] | eICU Collaborative Research Database (109,000 patients) | Random Forest (proposed), eXtreme Gradient Boosting (XGBoost), Support Vector Machines | Accuracy: 99.58% Precision: 90.95% Recall: 77.91% F1-Score: 0.8393 AUC: 0.9378 |
Wei C. et al. (2024) [15] | Second Affiliated Hospital of Nanchang University (4424 patients) | Extreme Gradient Boosting (proposed), Logistic Regression, Random Forest, Multilayer Perceptron, Support Vector Machine | Accuracy: 93.10% Recall: 95.60% Specificity: 91.10% F1-Score: 0.942 AUC: 0.979 |
Hou T. et al. (2023) [16] | Affiliated Hospital of Nantong University (801 patients) | Support Vector Machine, Logistic Regression, Decision Tree, Random Forest, Artificial Neural Networks (proposed) | Accuracy: 95.00% Recall: 92.00% Specificity: 93.00% F1-Score: 0.92 AUC: 0.97 |
Namjoo-Moghadam A. et al. (2024) [17] | Iran Cerebral Venous Thrombosis Registry (889 patients) | Generalized Linear Model, Random Forest, Support Vector Machine (proposed), Extreme Gradient Boosting | Accuracy: 86.00% Recall: 73.00% Specificity: 88.00% F1-Score: 0.8 AUC: 0.91 |
Our (2024) | Galati Hospital (299 patients) | Logistic Regression (proposed), Random Forest, LightGBM, Gradient Boosting, K-Nearest Neighbors, XGBoost, CatBoost, Artificial Neural Network | Accuracy: 97.37% Precision: 95.38% Recall: 99.99% Specificity: 94.23% F1-Score: 0.9764 AUC: 0.9516 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Anghele, A.-D.; Marina, V.; Dragomir, L.; Moscu, C.A.; Anghele, M.; Anghel, C. Predicting Deep Venous Thrombosis Using Artificial Intelligence: A Clinical Data Approach. Bioengineering 2024, 11, 1067. https://doi.org/10.3390/bioengineering11111067
Anghele A-D, Marina V, Dragomir L, Moscu CA, Anghele M, Anghel C. Predicting Deep Venous Thrombosis Using Artificial Intelligence: A Clinical Data Approach. Bioengineering. 2024; 11(11):1067. https://doi.org/10.3390/bioengineering11111067
Chicago/Turabian StyleAnghele, Aurelian-Dumitrache, Virginia Marina, Liliana Dragomir, Cosmina Alina Moscu, Mihaela Anghele, and Catalin Anghel. 2024. "Predicting Deep Venous Thrombosis Using Artificial Intelligence: A Clinical Data Approach" Bioengineering 11, no. 11: 1067. https://doi.org/10.3390/bioengineering11111067