Predictive Models in Health Based on Machine Learning

Journal: Advances in Medicine and Engineering Interdisciplinary Research DOI: 10.32629/ameir.v2i4.2813

Javier Mora Pineda

1. Department of Cardiac, Vascular and Thoracic Surgery, Clínica Las Condes 2. ECMO Unit, Clínica Las Condes 3. Clinical Data Science Unit, Clínica Las Condes

Abstract

Finding causality in medicine is of great interest in research, in order to generate interventions that treat or cure the disease. Most classical statistical models allow association to be inferred, and only a few designs are able to demonstrate cause and effect with an adequate methodology and solid evidence. Evidence-based medicine supports its findings in models that go from a hypothesis to search for data to prove or rule it out. This also applies to the development of predictive models to be reliable and to produce impact in clinical practice. The large amount of data stored in electronic health records and greater computational power mean that machine learning techniques can play a preponderant role in the development of new predictive analysis and recognition of unknown patterns with these modern computational models. These models, along with changing the view from data to information, are increasingly being incorporated into daily clinical practice, providing greater precision and speed for supporting decision making. The intent of this review is to provide theoretical bases and evidence of how these modern computational techniques of machine learning have allowed to achieve better results and they are being widely used. This article will review the most relevant aspects of health data science in Latin America.

Keywords

data sciences; machine learning; artificial intelligence; predictive models; clinical decision support systems; cardiac surgery; data

References

[1] Cerda J, Valdivia G. John Snow. La epidemia de cólera y el nacimiento de la epidemiología moderna. [John Snow, the cholera epidemic and the foundation of modern epidemiology]. Rev Chil Infectol. 2007;24(4):331-334. doi: 10.4067/S0716-10182007000400014
[2] Amrhein V, Greenland S, McShane B. Scientists rise up against statistical significance. Nature. 2019;567(7748):305-307. doi: 10.1038/ d41586-019-00857-9
[3] Alanazi HO, Abdullah AH, Qureshi KN. A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care. J Med Syst. 2017;41(4):69. doi: 10.1007/s10916-017-0715-6
[4] Mora J. Proyecciones de la ciencia de datos en la cirugía cardíaca. [Projections of data science in cardiac surgery]. Rev Med Clin Condes. 2022;33(3):294-306. doi: 10.1016/j.rmclc.2022.05.007
[5] Dunstan J, Maass A, Tobar F. Una Mirada a la Era de los Datos. Ed. Universitaria 2022.
[6] Mitchell TM. Machine Learning. McGraw-Hill. 1997.
[7] Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and Regression Trees. Routledge; 2017.
[8] Carreno A, Inza I, Lozano JA. Eventos raros, anomalıas y novedades vistas desde el paraguas de la clasificacion supervisada. IX Simposio de Teoría y Aplicaciones de la Minería de Datos. 2018:925-930. https://sci2s.ugr.es/caepia18/proceedings/docs/CAEPIA2018_paper_192.pdf
[9] de Hond AAH, Leeuwenberg AM, Hooft L, Kant IMJ, Nijman SWJ, van Os HJA, et al. Guidelines and quality criteria for artificial intelligence based prediction models in healthcare: a scoping review. NPJ Digit Med. 2022;5(1):2. doi: 10.1038/s41746-021-00549-7.
[10] Alanazi HO, Abdullah AH, Qureshi KN. A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care. J Med Syst. 2017;41(4):69. doi: 10.1007/s10916-017-0715-6
[11] LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD. Back propagation applied to handwritten zip code recognition. Neural Comput. 1989;1(4):541-551.
[12] LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series. In: Arbib, Michael A. (ed.). The handbook of brain theory and neural networks (Second ed.). The MIT press. 1995:276-278.
[13] Liu Q, Cui X, Abbod MF, Huang SJ, Han YY, Shieh JS. Brain death prediction based on ensembled artificial neural networks in neurosurgical intensive care unit. J Taiwan Inst Chem Eng. 2011;42(1):97-107. https://doi. org/10.1016/j.jtice.2010.05.00
[14] Rughani AI, Dumont TM, Lu Z, Bongard J, Horgan MA, Penar PL, Tranmer BI. Use of an artificial neural network to predict head injury outcome. J Neurosurg. 2010;113(3):585-90. doi: 10.3171/2009.11.JNS09857
[15] Güler , Gökçil Z, Gülbandilar E. Evaluating of traumatic brain injuries using artificial neural networks. Expert Syst. Appl. 2009;36(7):10424-10427. Doi: 10.1016/j.eswa.2009.01.036
[16] Low D, Kuralmani V, Ng SK, Lee KK, Ng I, Ang BT. Prediction of outcome utilizing both physiological and biochemical parameters in severe head injury. J Neurotrauma. 2009;26(8):1177-82. doi: 10.1089/ neu.2008.0841
[17] Nemesure MD, Heinz MV, Huang R, Jacobson NC. Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence. Sci Rep. 2021;11(1):1980. doi: 10.1038/s41598-021-81368-4
[18] Tejavibulya L, Rolison M, Gao S, Liang Q, Peterson H, Dadashkarimi J, et al. Predicting the future of neuroimaging predictive models in mental health. Mol Psychiatry. 2022. doi: 10.1038/s41380-022-01635-2
[19] Ma X, Wu J, Xue X. Identification of DNA-binding proteins using support vector machine with sequence information. Comput Math Methods Med. 2013;2013:524502. doi: 10.1155/2013/524502
[20] Baxter SL, Marks C, Kuo TT, Ohno-Machado L, Weinreb RN. Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records. Am J Ophthalmol. 2019;208:30-40. doi: 10.1016/j.ajo.2019.07.005
[21] Fan G, Deng Z, Ye Q, Wang B. Machine learning-based prediction models for patients no-show in online outpatient appointments. Data Sci Manage. 2021;2:45-52. doi: 10.1016/j.dsm.2021.06.002
[22] Ramírez H, Dunstan J, Montenegro H. Soluciones tecnológicas, basadas en técnicas matemáticas avanzadas de aprendizaje de máquinas. FONDEF IDeA I+D ID19I10271
[23] Modelo de IA a través de chatbot logra mejorar la agenda de citas médicas en Chile. Salud Digital, Fundacion Carlos Slim. https://saluddigital.com/es/noticias/modelo-de-ia-a-traves-dechatbot-logra-mejorar-la-agenda-de-citas-medicas-en-chile/
[24] Covacevich Stipicich T. Exploring representations of ICD codes for patient readmission prediction (Doctoral dissertation, Pontificia Universidad Catolica de Chile (Chile)). 2021. https://repositorio.uc.cl/xmlui/handle/11534/58535
[25] Fierro C, Pérez J, Mora J. Predicting unplanned read missions with highly unstructured data. 2020. Workshop paper at AI4AH, ICLR 2020. doi: 10.48550/arXiv.2003.11622
[26] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735-1780. doi: 10.1162/neco.1997.9.8.1735.
[27] Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1:18. doi: 10.1038/s41746-018-0029-1
[28] Zhao Y, Qiao Z, Xiao C, Glass L, Sun J. PyHealth: A Python Library for Health Predictive Models. arXiv:2101.04209 https://doi.org/10.48550/ arXiv.2101.04209
[29] Wells PS. Integrated strategies for the diagnosis of venous thromboembolism. J Thromb Haemost. 2007;5 Suppl 1:41-50. doi: 10.1111/j.1538-7836.2007.02493.x

Copyright © 2024 Javier Mora Pineda

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License