Uma revisão sistemática da literatura sobre avaliação de Modelos de Aprendizado de Máquina em aplicações de saúde

Autores

DOI:

https://doi.org/10.33448/rsd-v12i6.42042

Palavras-chave:

Validação de modelos de AM; AM para a área da saúde; Monitoramento de modelos de AM.

Resumo

Os modelos de Aprendizado de Máquina (AM) têm sido aplicados para resolver problemas em diversos contextos, o que necessariamente envolve a avaliação adequada dos modelos para garantir seu desempenho. Uma vez implantados, os modelos de AM estão sujeitos a problemas de desempenho, como aqueles relacionados a mudanças nos dados (drift). Esse tipo de problema tem motivado esforços na análise e manutenção de modelos, bem como no aprendizado contínuo, que busca a capacidade de aprender continuamente a partir de um fluxo (contínuo) de dados. Portanto, é importante entender e desenvolver metodologias que possam ser utilizadas para avaliar modelos de AM, tornando seu uso em ambientes do mundo real viável. Entre as áreas atuais de aplicação de AM, uma que se destaca, em particular, é o Aprendizado de Máquina para a área da saúde, especialmente em conjunto com Software para Suporte à Decisão em Aplicações Médicas, apresentando desafios específicos para a avaliação e monitoramento de modelos, especialmente considerando que previsões ou classificações incorretas podem levar a situações que ameaçam a vida. Este artigo apresenta uma revisão sistemática da literatura cujo objetivo é identificar técnicas atuais para avaliar e manter modelos de AM aplicados a área da saúde em uso efetivo no mundo real.

Referências

Arowolo, M. O., Ogundokun, R. O., Misra, S., Kadri, A. F., & Aduragba, T. O. (2022). Machine Learning Approach Using KPCA-SVMs for Predicting COVID-19. In Garg, L., Chakraborty, C., Mahmoudi, S., Sohmen, V. S. (Eds.), Healthcare Informatics for Fighting COVID-19 and Future Epidemics (pp. 193–209). Springer International Publishing. https://doi.org/10.1007/978-3-030-72752-9_10

Bellocchio, F., Lonati, C., Ion Titapiccolo, J., Nadal, J., Meiselbach, H., Schmid, M., Baerthlein, B., Tschulena, U., Schneider, M., Schultheiss, U. T., Barbieri, C., Moore, C., Steppan, S., Eckardt, K.-U., Stuard, S., & Neri, L. (2021). Validation of a Novel Predictive Algorithm for Kidney Failure in Patients Suffering from Chronic Kidney Disease: The Prognostic Reasoning System for Chronic Kidney Disease (PROGRES-CKD). International Journal of Environmental Research and Public Health, 18 (23). https://doi.org/10.3390/ijerph182312649

Birkenbihl, C., Emon, M. A., Vrooman, H., Westwood, S., Lovestone, S., AddNeuroMed Consortium, Hofmann-Apitius, M., Fröhlich, H., & Alzheimer’s Disease Neuroimaging Initiative (2020). Differences in Cohort Study Data Affect External Validation of Artificial Intelligence Models for Predictive Diagnostics of Dementia - Lessons for Translation Into Clinical Practice. The EPMA Journal, 11 (3), 367–376. https://doi.org/10.1007/s13167-020-00216-z

Carolan, J. E., McGonigle, J., Dennis, A., Lorgelly, P., & Banerjee, A. (2022). Technology-Enabled, Evidence-Driven, and Patient-Centered: The Way Forward for Regulating Software as a Medical Device. JMIR Med Inform, 10 (1), e34038. https://doi.org/10.2196/34038

Collin, C. B., Gebhardt, T., Golebiewski, M., Karaderi, T., Hillemanns, M., Khan, F. M., Salehzadeh-Yazdi, A., Kirschner, M., Krobitsch, S., consortium, E.-S., & Kuepfer, L. (2022). Computational Models for Clinical Applications in Personalized Medicine-Guidelines and Recommendations for Data Integration and Model Validation. Journal of Personalized Medicine, 12 (2). https://doi.org/10.3390/jpm12020166

Duckworth, C., Chmiel, F. P., Burns, D. K., Zlatev, Z. D., White, N. M., Daniels, T. W. V., Kiuber, M., & Boniface, M. J. (2021). Emergency Department Admissions During COVID-19: Explainable Machine Learning to Characterise Data Drift and Detect Emergent Health Risks. MedRxiv. https://doi.org/10.1101/2021.05.27.21257713

Fries, J. A., Varma, P., Chen, V. S., Xiao, K., Tejeda, H., Saha, P., Dunnmon, J., Chubb, H., Maskatia, S., Fiterau, M., Delp, S., Ashley, E., Ré, C., & Priest, J. R. (2019). Weakly Supervised Classification of Aortic Valve Malformations Using Unlabeled Cardiac MRI Sequences. BioRxiv. https://doi.org/10.1101/339630

Ghassemi, M., Naumann, T., Schulam, P., Beam, A. L., Chen, I. Y., & Ranganath, R. (2020). A Review of Challenges and Opportunities in Machine Learning for Health. AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science Proceedings, 2020, 191–200.

https://doi.org/10.48550/arXiv.1806.00388

Gopal, M. (2019). Applied Machine Learning. McGraw-Hill Education.

Harris, S., Bonnici, T., Keen, T., Lilaonitkul, W., White, M. J., & Swanepoel, N. (2022). Clinical Deployment Environments: Five Pillars of Translational Machine Learning for Health. Frontiers in Digital Health, 4. https://doi.org/10.3389/fdgth.2022.939292

Van Helvoort, E. M., van Spil, W. E., Jansen, M. P., Welsing, P. M., Kloppenburg, M., Loef, M., Blanco, F. J., Haugen, I. K., Berenbaum, F., Bacardit, J., & others. (2020). Cohort Profile: The Applied Public-Private Research Enabling Osteoarthritis Clinical Headway (IMI-APPROACH) Study: A 2-Year, European, Cohort Study to Describe, Validate and Predict Phenotypes of Osteoarthritis Using Clinical, Imaging and Biochemical Markers. BMJ Open, 10 (7), e035101. https://doi.org/10.1136/bmjopen-2019-035101

Huda, A., Castaño, A., Niyogi, A., Schumacher, J., Stewart, M., Bruno, M., Hu, M., Ahmad, F., Deo, R., & Shah, S. (2021). A Machine Learning Model for Identifying Patients at Risk for Wild-type Transthyretin Amyloid Cardiomyopathy. Nature Communications, 12, 2725. https://doi.org/10.1038/s41467-021-22876-9

Iakovakis, D., Hadjidimitriou, S., Charisis, V., Bostantjopoulou, S., Katsarou, Z., Klingelhoefer, L., Reichmann, H., Dias, S. B., Diniz, J. A., Trivedi, D., Chaudhuri, K. R., & Hadjileontiadis, L. J. (2018). Motor Impairment Estimates via Touchscreen Typing Dynamics Toward Parkinson’s Disease Detection From Data Harvested In-the-Wild. Frontiers in ICT, 5. https://doi.org/10.3389/fict.2018.00028

Johri, P., Saxena, V. S., & Kumar, A. (2021). Rummage of Machine Learning Algorithms in Cancer Diagnosis. International Journal of E-Health and Medical Communications (IJEHMC), 12 (1), 1–15. http://doi.org/10.4018/IJEHMC.2021010101

Kamran, F., Tang, S., Otles, E., McEvoy, D. S., Saleh, S. N., Gong, J., Li, B. Y., Dutta, S., Liu, X., Medford, R. J., Valley, T. S., West, L. R., Singh, K., Blumberg, S., Donnelly, J. P., Shenoy, E. S., Ayanian, J. Z., Nallamothu, B. K., Sjoding, M. W., & Wiens, J. (2022). Early Identification of Patients Admitted to Hospital for COVID-19 at Risk of Clinical Deterioration: Model Development and Multisite External Validation Study. BMJ, 376. https://doi.org/10.1136/bmj-2021-068576

Kitchenham, B., & Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering version 2.3. Engineering, 45(4ve), 1051.

Lam, J., Shimizu, C., Tremoulet, A., Bainto, E., Roberts, S., Sivilay, N., Gardiner, M., Kanegaye, J., Hogan, A., Salazar, J., Mohandas, S., Szmuszkovicz, J., Mahanta, S., Dionne, A., Newburger, J., Ansusinha, E., Debiasi, R., Hao, S., Ling, B., & Sykes, M. (2022). A Machine-Learning Algorithm for Diagnosis of Multisystem Inflammatory Syndrome in Children and Kawasaki Disease in the USA: A Retrospective Model Development and Validation Study. The Lancet Digital Health, 4, e717–e726. https://doi.org/10.1016/S2589-7500(22)00149-2

Li, J., Liu, S., Hu, Y., Zhu, L., Mao, Y., & Liu, J. (2022). Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study. J Med Internet Res, 24 (8), e38082. https://doi.org/10.2196/38082

Lin, W., Gan, W., Feng, P., Zhong, L., Yao, Z., Chen, P., He, W., & Yu, N. (2022). Online Prediction Model for Primary Aldosteronism in Patients With Hypertension in Chinese Population: A Two-Center Retrospective Study. Frontiers in Endocrinology, 13. https://doi.org/10.3389/fendo.2022.882148

Luo, C., Zhu, Y., Zhu, Z., Li, R., Chen, G., & Wang, Z. (2022). A Machine Learning-Based Risk Stratification Tool for In-Hospital Mortality of Intensive Care Unit Patients With Heart Failure. Journal of Translational Medicine, 20 (1), 136. https://doi.org/10.1186/s12967-022-03340-8

Maleki, F., Muthukrishnan, N., Ovens, K., Reinhold, C., & Forghani, R. (2020). Machine Learning Algorithm Validation: From Essentials to Advanced Applications and Implications for Regulatory Certification and Deployment. Neuroimaging Clinics of North America, 30 (4), 433–445. https://doi.org/10.1016/j.nic.2020.08.004

Maleki, F., Muthukrishnan, N., Ovens, K., Md, C., & Forghani, R. (2020). Machine Learning Algorithm Validation. Neuroimaging Clinics of North America, 30, 433–445. https://doi.org/10.1016/j.nic.2020.08.004

Malki, Z., Atlam, E.-S., Ewis, A., Dagnew, G., Ghoneim, O. A., Mohamed, A. A., Abdel-Daim, M. M., & Gad, I. (2021). The COVID-19 Pandemic: Prediction Study Based on Machine Learning Models. Environmental Science and Pollution Research, 28, 40496–40506. https://doi.org/10.1007/s11356-021-13824-7

Mitchell, T. M., & others. (2007). Machine Learning (Vol. 1). McGraw-hill New York.

Qasim, H. M., Ata, O., Ansari, M. A., Alomary, M. N., Alghamdi, S., & Almehmadi, M. (2021). Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem. Medicina, 57 (11), 1217. https://doi.org/10.3390/medicina57111217

Rafiq, R., Modave, F., Guha, S., & Albert, M. (2020). Validation Methods to Promote Real-world Applicability of Machine Learning in Medicine. 2020 3rd International Conference on Digital Medicine and Image Processing, 13–19. https://doi.org/10.1145/3441369.3441372

Risman, A., Trelles, M., & Denning, D. W. (2021). Evaluation of Multiple Open-Source Deep Learning Models for Detecting and Grading COVID-19 on Chest Radiographs. Journal of Medical Imaging, 8 (6), 064502. https://doi.org/10.1117/1.JMI.8.6.064502

Rojas, J. C., Fahrenbach, J., Makhni, S., Cook, S. C., Williams, J. S., Umscheid, C. A., & Chin, M. H. (2022). Framework for Integrating Equity Into Machine Learning Models: A Case Study. Chest, 161 (6), 1621–1627. https://doi.org/10.1016/j.chest.2022.02.001

Sengupta, P. P., Shrestha, S., Berthon, B., Messas, E., Donal, E., Tison, G. H., Min, J. K., D’hooge, J., Voigt, J.-U., Dudley, J., Verjans, J. W., Shameer, K., Johnson, K., Lovstakken, L., Tabassian, M., Piccirilli, M., Pernot, M., Yanamala, N., Duchateau, N., & others. (2020). Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council. JACC: Cardiovascular Imaging, 13 (9), 2017–2035. https://doi.org/10.1016/j.jcmg.2020.07.015

Shickel, B., Siegel, S., Heesacker, M., Benton, S., & Rashidi, P. (2020). Automatic Detection and Classification of Cognitive Distortions in Mental Health Text. 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), 275–280. https://doi.org/10.1109/BIBE50027.2020.00052

Sun, H., Depraetere, K., Meesseman, L., Cabanillas Silva, P., Szymanowsky, R., Fliegenschmidt, J., Hulde, N., von Dossow, V., Vanbiervliet, M., De Baerdemaeker, J., Roccaro-Waldmeyer, D. M., Stieg, J., Domínguez Hidalgo, M., & Dahlweid, F.-M. (2022). Machine Learning–Based Prediction Models for Different Clinical Risks in Different Hospitals: Evaluation of Live Performance. J Med Internet Res, 24 (6), e34295. https://doi.org/10.2196/34295

The RADAR-CNS Consortium, Böttcher, S., Bruno, E., Manyakov, N. V., Epitashvili, N., Claes, K., Glasstetter, M., Thorpe, S., Lees, S., Dümpelmann, M., van Laerhoven, K., Richardson, M. P., & Schulze-Bonhage, A. (2021). Detecting Tonic-Clonic Seizures in Multimodal Biosignal Data From Wearables: Methodology Design and Validation. JMIR MHealth and UHealth, 9 (11). https://doi.org/10.2196/27674

Treveil, M., Omont, N., Stenac, C., Lefevre, K., Phan, D., Zentici, J., Lavoillotte, A., Miyazaki, M., & Heidmann, L. (2020). Introducing MLOps. O’Reilly Media.

Vieira, D. M., Fernandes, C., Lucena, C., & Lifschitz, S. (2021). Driftage: A Multi-Agent System Framework for Concept Drift Detection. GigaScience, 10 (6). https://doi.org/10.1093/gigascience/giab030

Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., & others. (2019). Do No Harm: A Roadmap for Responsible Machine Learning for Health Care. Nature Medicine, 25 (9), 1337–1340. https://doi.org/10.1038/s41591-019-0548-6

Wojtusiak., J. (2021). Reproducibility, Transparency and Evaluation of Machine Learning in Health Applications. Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies - HEALTHINF, 685–692. https://doi.org/10.5220/0010348306850692

Yang, C., Zou, Y., Liu, J., & Mulligan, K. (2014). Predictive Model Evaluation for PHM. International Journal of Prognostics and Health Management, 5. https://doi.org/10.36001/ijphm.2014.v5i2.2238

Downloads

Publicado

14/06/2023

Como Citar

SOUZA, C. M. P. de .; BARRETO, C. A. da S. .; MACEDO, L. V. de .; BRITO, B. A. O. de .; TARGINO, V. V. .; BETCEL, E. C. .; ALMEIDA, F. G. de .; RODRIGUES, A. A. G. .; MALAQUIAS, R. S. .; BARROCA FILHO, I. de M. . Uma revisão sistemática da literatura sobre avaliação de Modelos de Aprendizado de Máquina em aplicações de saúde. Research, Society and Development, [S. l.], v. 12, n. 6, p. e5412642042, 2023. DOI: 10.33448/rsd-v12i6.42042. Disponível em: https://rsdjournal.org/index.php/rsd/article/view/42042. Acesso em: 26 dez. 2024.

Edição

Seção

Artigos de Revisão