Interpretable machine learning for mortality modeling on patients with chronic diseases considering the COVID-19 pandemic in a region of Chile: A Shapley value based approach

References

• Acar HC, Can G, Karaali R, Börekçi Ş, Balkan İİ, Gemicioğlu B, Konukoğlu D, Erginöz E, Erdoğan MS, Tabak F. 2021. An easy-to-use nomogram for predicting in-hospital mortality risk in covid-19: a retrospective cohort study in a university hospital. BMC Infect Dis. 21(1):1–12.
   PubMed Web of Science ®Google Scholar
• Avati A, Jung K, Harman S, Downing L, Ng A, Shah NH. 2018. Improving palliative care with deep learning. BMC Med Inform Decis Mak. 18(4):55–64.
   PubMedGoogle Scholar
• Batiste-Alentorn XG, Novellas JA, Martínez CL, Calsina-Berna À. 2017. Manual de atención integral de personas con enfermedades crónicas avanzadas: aspectos clínicos. Elsevier Health Sciences.
   Google Scholar
• Breiman LJ, Charles F, Stone J, Olshen RA. 1994. Classification and regression trees. New York: Wadsworth.
   Google Scholar
• Calvache JA, Gil F, De Vries E. 2020. How many people need palliative care for cancer and non-cancer diseases in a middle-income country? Analysis of mortality data. Colombian J Anestesiol. 48(4):e201.
   Google Scholar
• Cao Y, Fang X, Ottosson J, Näslund E, Stenberg E. 2019. A comparative study of machine learning algorithms in predicting severe complications after bariatric surgery. J Clin Med. 8(5):668.
   PubMed Web of Science ®Google Scholar
• Cary Jr MP, Zhuang F, Draelos RL, Pan W, Amarasekara S, Douthit BJ, Kang Y, Colón-Emeric CS. 2021. Machine learning algorithms to predict mortality and allocate palliative care for older patients with hip fracture. J Am Med Dir Assoc. 22(2):291–296.
   PubMed Web of Science ®Google Scholar
• Chen S, Webb GI, Liu L, Ma X. 2020. A novel selective naïve Bayes algorithm. Knowl Based Syst. 192:105361.
   Web of Science ®Google Scholar
• Chen T, Guestrin C. 2016. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, Association for Computing Machinery, New York, NY, USA, p. 785–794.
   Google Scholar
• Chieregato M, Frangiamore F, Morassi M, Baresi C, Nici S, Bassetti C, Bnà C, Galelli M. 2022. A hybrid machine learning/deep learning covid-19 severity predictive model from ct images and clinical data. Sci Rep. 12(1):1–15.
   PubMed Web of Science ®Google Scholar
• Chow E, Harth T, Hruby G, Finkelstein J, Wu J, Danjoux C,. 2001. How accurate are physicians’ clinical predictions of survival and the available prognostic tools in estimating survival times in terminally iii cancer patients? A systematic review. Clin Oncol. 13(3):209–218.
   Web of Science ®Google Scholar
• de la Salud OP. 2017. Las dimensiones económicas de las enfermedades no transmisibles en américa latina y el caribe. https://iris.paho.org/bitstream/handle/10665.2/33994/9789275319055-spa.pdf?sequence=1&isAllowed=y
   Google Scholar
• Departamento de Estadíticas e Informaci’́on de Salud (DEIS) C. 2022. Defunciones por causa. https://deis.minsal.cl//#datosabiertos
   Google Scholar
• Desai RJ, Wang SV, Vaduganathan M, Evers T, Schneeweiss S. 2020. Comparison of machine learning methods with traditional models for use of administrative claims with electronic medical records to predict heart failure outcomes. JAMA Network Open 3(1):e1918962.
   PubMed Web of Science ®Google Scholar
• Effrosynidis D, Arampatzis A. 2021. An evaluation of feature selection methods for environmental data. Ecol Inform. 61:101224.
   Web of Science ®Google Scholar
• Fernández VP, Fernández RSM. 2004. Regresión logística multinomial. Cuadernos de la Sociedad Española de Ciencias Forestales 18:323–327.
   Google Scholar
• Han PK, Lee M, Reeve BB, Mariotto AB, Wang Z, Hays RD, Yabroff KR, Topor M, Feuer EJ. 2012. Development of a prognostic model for six-month mortality in older adults with declining health. J Pain Symptom Manage. 43(3):527–539.
   PubMed Web of Science ®Google Scholar
• Hariz WHM, Adnan M, Rashid A. 2012. Hybrid approaches using decision tree, naive bayes, means and Euclidean distances for childhood obesity prediction. Int J Softw Eng Appl. 6(3):99–106.
   Google Scholar
• Hart S. 1989. Shapley value. In: Eatwell J, Milgate M, Newman P, editors. Game theory. London: Springer. p. 210–216.
   Google Scholar
• Hastie T, Tibshirani R, Friedman J. 2001. The elements of statistical learning. Springer series in statistics. New York: Springer.
   Google Scholar
• Hidalgo Ruiz-Capillas S. 2014. Random forests para detección de fraude en medios de pago. Master’s thesis.
   Google Scholar
• Hsu J-F, Yang C, Lin C-Y, Chu S-M, Huang H-R, Chiang M-C, Wang H-C, Liao W-C, Fu R-H, Tsai M-H. 2021. Machine learning algorithms to predict mortality of neonates on mechanical intubation for respiratory failure. Biomedicines 9(10):1377.
   PubMed Web of Science ®Google Scholar
• INE. 2018. Anuario de estadísticas vitales. https://www.ine.cl/estadisticas/sociales/demografia-y-vitales/nacimientos-matrimonios-y-defunciones
   Google Scholar
• Keany E. 2020. Borutashap: A wrapper feature selection method which combines the boruta feature selection algorithm with Shapley values, Zenodo. [accessed 2021 October 25] https://zenodo.org/record/4247618.
   Google Scholar
• Kursa MB, Rudnicki WR. 2010. Feature selection with the boruta package. J Stat Softw 36(11):1–13. https://www.jstatsoft.org/index.php/jss/article/view/v036i11
   Web of Science ®Google Scholar
• Lang X, Wu D, Mao W. 2022. Comparison of supervised machine learning methods to predict ship propulsion power at sea. Ocean Eng. 245:110387. https://www.sciencedirect.com/science/article/pii/S0029801821016802
   Web of Science ®Google Scholar
• Lundberg SM, Lee SI. 2017. A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. Vol. 30.
   Google Scholar
• Lundberg SM, Erion GG, Lee S-I. 2018. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888
   Google Scholar
• McCullagh P, Nelder J. 1989. Generalized linear models ii. London: Chapman and Hall.
   Google Scholar
• Meléndez, A, Limón, E. 2018. Del “paliativo no oncológico” al “paciente crónico avanzado”. más allá de las palabras. el reto de los cuidados paliativos del siglo xxi, Monografía SECPAL sobre Cronicidad Avanzada. p. 13–15.
   Google Scholar
• Ministerio de Salud, C. 2021. Ley 21375 consagra los cuidados paliativos y los derechos de las personas que padecen enfermedades terminales o graves. http://bcn.cl/2s7z9
   Google Scholar
• Ministerio de Salud GdC. 2019. Matriz de cuidados a lo largo del curso de vida. https://www.minsal.cl/wp-content/uploads/2018/09/Matriz-de-cuidados-a-lo-largo-del-curso-de-vida-2019.pdf
   Google Scholar
• Mitchell TM. 1997. Machine learning. New York: McGraw-Hill.
   Google Scholar
• Pastrana T, Lima L, Centeno C, Wenk R, Eisenchlas J, Monti C, Rocafort J. 2012. Atlas de cuidados paliativos en latinoamérica.
   Google Scholar
• Pastrana T, Lima L, Sánchez-Cárdenas M, Steijn D, Garralda E, Pons-Izquierdo JJ, Centeno C. 2021. Atlas de cuidados paliativos de latinoamérica 2020.
   Google Scholar
• Ray S. 2019. A quick review of machine learning algorithms. In: 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), p. 35–39.
   Google Scholar
• Sánchez-Herrera B, Carrillo-González GM, Barrera-Ortiz L, Chaparro-Díaz L. 2013. Carga del cuidado de la enfermedad crónica no transmisible. Aquichan 13(2):247–260.
   Google Scholar
• Shin S, Austin PC, Ross HJ, Abdel-Qadir H, Freitas C, Tomlinson G, Chicco D, Mahendiran M, Lawler PR, Billia F, Gramolini A, Epelman S, Wang B, Lee DS. 2021. Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality. ESC Heart Failure 8(1):106–115. arXiv:10.1002/ehf2.13073.
   PubMed Web of Science ®Google Scholar
• Smith M, Alvarez F. 2021. Identifying mortality factors from machine learning using Shapley values–a case of covid19. Expert Syst Appl. 176:114832.
   PubMed Web of Science ®Google Scholar
• Sun H, Wang S. 2011. Measuring the component overlapping in the Gaussian mixture model. Data Min Knowl Discov 23:479–502.
   Web of Science ®Google Scholar
• Tax DM, Duin RP. 2004. Support vector data description. Mach. Learn 54:45–66.
   Web of Science ®Google Scholar
• Vargas J, Conde MB, Paccapelo MV, Zingaretti ML. 2012. Máquinas de soporte vectorial: metodología y aplicación en r, in: Décimo Congreso Latinoamericano de Sociedades de Estadística.
   Google Scholar
• Vuttipittayamongkol P, Elyan E, Petrovski A. 2021. On the class overlap problem in imbalanced data classification. Knowl Based Syst. 212:106631.
   Web of Science ®Google Scholar
• World Health Organization. 2020. World health statistics 2020 monitoring health for the sdgs sustainable development goals. https://apps.who.int/iris/bitstream/handle/10665/332070/9789240005105-eng.pdf
   Google Scholar
• World Health Organization. 2021a. Fact sheets. noncommunicable diseases. https://www.who.int/news-room/fact-sheets/detail/noncommunicable-diseases
   Google Scholar
• World Health Organization. 2021b. The global health observatory explore a world of health data. https://www.who.int/data/gho/data/themes/topics/topic-details/GHO/ncd-mortality
   Google Scholar