A Machine Learning Approach to Classify Exercise Limitation Severity Using Cardiopulmonary Exercise Testing - Development and Validation
Main Article Content
Abstract
Background: There is no agreement on the best strategy for interpreting/ analyzing cardiopulmonary exercise test (CPET) results.
Aims: This study aims to evaluate the feasibility of using computer-aided algorithms to evaluate CPET data to identify the exercise limitation/ intolerance level.
Methods: This study used 206 retrospective CPET files from the Pulmonary Institute and the Cardiology Rehabilitation Center at the Sheba Medical Center and 50 from the exercise physiology laboratory at the Washington-Hill College, both in Israel. Eighty patients with confirmed primary cardiovascular-related exercise limitation, seventy-six with ventilatory-related exercise limitation, and fifty healthy (none or very mild exercise restraints) subjects comprised the pool of examined CPET data. Support Vector Machine (SVM) Learning was performed on 150 (50 in each group) of the 206 CPETs, while model validation was performed on the remaining 56 CPET files. By applying the K-means clustering method, distribution analysis was used to compare the SVM interpretive module's performance to that of senior cardiologists, pulmonologists, and expert exercise physiologists.
Results: Overall, the proposed interpretive model has a predictive power of between 78% and 100%, as shown by its ability to correctly classify the degree of exercise limitation.
Conclusions: The proposed machine-learning CPET interpretive module was highly sensitive and specific in identifying patients with mild, moderate, or severe cardiovascular- or ventilatory-related exercise limitations/ intolerance. Comparable modules may be applied to additional (kinds of exercise limitations) and larger populations, making this tool powerful and clinically applicable.
Article Details
The Medical Research Archives grants authors the right to publish and reproduce the unrevised contribution in whole or in part at any time and in any form for any scholarly non-commercial purpose with the condition that all publications of the contribution include a full citation to the journal as published by the Medical Research Archives.
References
2. Stickland MK, Neder A, Guenette JA, et al. Using Cardiopulmonary Exercise Testing to Understand Dyspnea and Exercise Intolerance in Respiratory Disease. CHEST. 2022; 161(6): 1505-1516.
3. Guazzi M, Bandera F, Ozemek C, Systrom D, Arena R. Cardiopulmonary Exercise Testing: What Is its Value? J Am Coll Cardiol. 2017; 70(13):1618-1636. doi: 10.1016/j.jacc. 2017.08.012.
4. Balady GJ, Arena R, Sietsema K, et al. Clinician’s Guide to Cardiopulmonary Exercise Testing in Adults: a scientific statement from the American Heart Association: A scientific statement from the American Heart Association. Circulation. 2010; 122(2): 191-225. oi:10.1161/CIR.0b013 e3181e52e69
5. Inbar O, Inbar O, Reuveny R, Segel MJ, Greenspan H, Scheinowitz M. A machine learning approach to the interpretation of cardiopulmonary exercise tests: Development and validation. Pulm Med. 2021; 2021: 5516248. doi:10.1155/2021/5516248.
6. Akay MF, Zayid EIM, Aktürk E, George JD. Artificial neural network-based model for predicting VO2max from a submaximal exercise test. Expert Syst Appl. 2011; 38(3):2007-2010. doi: 10.1016/j.eswa.2010. 07.135.
7. Sakr S, Elshawi R, Ahmed A, et al. Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project. PLoS One. 2018; 13(4): e0195344. doi: 10.1371/journal. pone.0195344.
8. Portella JJ, Andonian BJ, Brown DE, et al. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise Testing. IEEE J Biomed Health Inform. 2022;26(8):4228-4237. doi:10.1109/JBHI.2022.3163402.
9. Inbar O, Katz U, Dubnov RG, Epstein Y. "Guidelines for Cardiopulmonary Exercise Tests (CPET) Results". Medicine (Harefuah), 157 (9); 1-7, 2018. (Hebrew).
10. Wasserman K, Hansen JE, Sue DY, Stringer WW, Whipp BJ. Principles of exercise testing and interpretation: including pathophysiology and clinical applications. Medicine and Science in Sports and Exercise. 2005;37(7).
11. American Thoracic Society, American College of Chest Physicians. ATS/ACCP Statement on cardiopulmonary exercise testing. Am J Respir Crit Care Med. 2003; 167(2):211-277. doi:10.1164/rccm.167.2.211.
12. Inbar O, Oren A, Scheinowitz M, Rotstein A, Dlin R, Casaburi R. Normal cardiopulmonary responses during incremental exercise in 20- to 70-year-old men. Med Sci Sports Exer. 1994; 26(5):538-546. doi:10.1249/00005768-199405000-00003.
13. Hsu CW, Chang CC, Lin CJ. ACM transactions on intelligent systems and technology, IEEE Transactions on Neural Networks and Learning Systems. Published online 2003:1396-1400.
14. Chacey M, Goodman LF, Kynyk JA, Russell C, Magalang U, Asif MJ. Analysis of interpretation practices of cardiopulmonary exercise tests: a quality initiative. American Journal of Respiratory and Critical Care Medicine. 2012;185.
15. Yan K, Zhang D. Feature selection and analysis on correlated gas sensor data with recursive feature elimination. Sens Actuators B Chem. 2015; 212:353-363. doi: 10.1016/ j.snb.2015.02.025.
16. Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology. 2011;2(3).
17. Vapnik VN. An overview of statistical learning theory. IEEE Trans Neural Netw. 1999; 10(5):988-999. doi:10.1109/72.788640.
18. Vapnik VN. The Nature of Statistical Learning Theory. 840 Springer-Verlag New York. Vol 840. Springer-Verlag New York." Inc; 1995.
19. Awad M, Khan L, Bastani F, Yen IL. An effective support vector machines (SVMs) performance using hierarchical clustering. In: 16th IEEE International Conference on Tools with Artificial Intelligence. IEEE Comput. Soc; 2005.
20. Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory; 1992:144-152.
21. Hartigan JA, Wong MA. Algorithm AS 136: A K-means clustering algorithm. J R Stat Soc Ser C Appl Stat. 1979; 28(1):100. doi: 10.2307/2346830.
22. Macqueen J. Some methods for classification and analysis of multivariate observations. Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. 1967; 1:281-297.
23. Inbar O, Yamin C, Bar-On I, Nice S, David D. Transluminal Coronary Angioplasty (PTCA) on cardiopulmonary responses during exercise. J Sports Med Phys Fitness. 2008; 48(2):235-245.
24. Klainman E, Fink G, Lebzelter J, Zafrir N. Assessment of functional results after percutaneous transluminal coronary angioplasty by cardiopulmonary exercise test. Cardiology. 1998; 89(4):257-262. doi:10.1159 /000006797
25. Schmid A, Schilter D, Fengels I, et al. Design and validation of an interpretative strategy for cardiopulmonary exercise tests. Respirology. 2007; 12(6):916-923. doi:10. 1111/j.1440-1843.2007.01197. x.
26. Ashley E, Myers J, Froelicher V. Exercise testing scores as an example of better decisions through science. Med Sci Sports Exer. 2002; 34(8):1391-1398. doi:10.1097/ 00005768-200208000-00023.
27. Swets JA, Dawes RM, Monahan J. Better decisions through science. Sci Am. 2000; 283(4):82-87. doi:10.1038/scientificamerican 1000-82.
28. Zile MR, Brutsaert DL. New concepts in diastolic dysfunction and diastolic heart failure: Part I: diagnosis, prognosis, and measurements of diastolic function: Diagnosis, prognosis, and measurements of diastolic function. Circulation. 2002; 105(11):1387-1393. doi:10.1161/hc1102. 105289.
29. Brown DE, Sharma S, Jablonski JA, Weltman A. Neural network methods for diagnosing patient conditions from cardiopulmonary exercise testing data. BioData Min. 2022; 15(1). doi:10.1186/s13040 -022-00299-6.
30. Cauwenberghs N, Sente J, Van Criekinge H, et al. Integrative interpretation of cardiopulmonary exercise tests for cardiovascular outcome prediction: A machine learning approach. Diagnostics (Basel). 2023; 13(12). doi:10.3390/diagnostics 13122051.
31. Solin P, Bergin P, Richardson M, Kaye DM, Walters EH, Naughton MT. Influence of pulmonary capillary wedge pressure on central apnea in heart failure. Circulation. 1999; 99(12):1574-1579. doi: 10.1161/01.cir. 99.12.1574.
32. Writing Committee, EACPR, M. Guazzi, et al. Clinical recommendations for cardiopulmonary exercise testing data assessment in specific patient populations," European Heart Journal, vol. 33, no. 23, pp. 2917–2927, 2012.
33. Weisman IM, Zeballos RJ. Clinical exercise testing. Clin Chest Med. 2001; 22(4):679-701. doi:10.1016/s0272-5231(05) 70060-5.
34. Portella JJ, Andonian BJ, Brown DE, Mansur J, Wales D, West VL, Kraus WE, Hammond WE. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise testing. IEEE J. Biomed. Health Inform. 2022, 26, 4228–4237.
35. Zignoli A. Machine learning models for the automatic detection of exercise thresholds in cardiopulmonary exercising tests: From regression to generation to explanation. Sensors (Basel). 2023; 23(2):826. doi:10.3390/s23020826.
36.Ismail Fawaz H, Forestier G, Weber J. Idoumghar Muller PA. Deep learning for time series classification: A review. Data Min. Knowl. Discov. 2019, 33, 917–963.
37. Längkvist M, Karlsson, Loutfi A. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters. 2014; 42 (1): 11-24.