Using artificial neural networks for pattern recognition of post-surgical infections
DOI:
https://doi.org/10.34119/bjhrv6n1-260Keywords:
surgical site infections, infection prevention, post-operative care, biomedical engineering, statisticsAbstract
The objective is to use Artificial Intelligence (AI) for identifying which surgical patients have a likelihood ratio of developing an infection. We included in the study all the patients who underwent surgeries with wound class considered clean at a regional public hospital in Brazil. The first step was a retrospective analysis of risk factors and a correlation test for identifying which clinical variables are best related to post-discharge infections. Then, we developed an Artificial Neural Network (ANN) for pattern recognition to detect incidence of infections. The ANN can make accurate predictions in 77.3% of the cases in which an infection will occur, and the AUROC of the model is 0.9050. Thus, it is possible to take actions before the patients develop it, improving the quality of life and mental health as well as avoid increasing costs.
References
ABBAS, M.; PITTET, D. Surgical site infection prevention: a global priority. Journal of Hospital Infection, v. 93, n. 4, p. 319-322, 2016.
ANVISA - Agência Nacional de Vigilância Sanitária. Critérios diagnósticos de infecção relacionada à assistência à saúde: segurança do paciente e qualidade em serviços de saúde. Disponívelem:<https://www20.anvisa.gov.br/segurancadopaciente/index.php/publicacoes/item/criterios-diagnosticos-das-infeccoes-relacionadas-a-assistencia-a-saude>. Acesso em: 12 jan.23.
ARINGHIERI, R.; TÀNFANI, E.; TESTI, A. Operations research for health care delivery. Computers & Operations Research, v.40, n. 9, p. 2165-2250, 2013.
BADIA, J, M. et al. Impact of surgical site infection on healthcare costs and patient outcomes: a systematic review in six European countries. Journal of Hospital Infection, v. 96, n. 1, p. 1-15, 2017.
CORSO, L,L, et al. Optimization of a cemented femoral prosthesis considering bone remodeling. Journal of Biomechanical Engineering, v. 138, n. 1, p. 011002, 2016.
DE LISSOVOY, G, et al. Surgical site infection: incidence and impact on hospital utilization and treatment costs. American journal of infection control, v. 37, n. 5, p. 387-397, 2009.
DEPERLİĞLU, Ö. Classification of segmented heart sounds with Artificial Neural Networks. International Journal of Applied Mathematics Electronics and Computers, v. 6, n. 4, p. 39-44, 2018.
ESTEVA, A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, v. 542, n. 7639, p. 115-118, 2017.
GRAUPE, D. Principles of artificial neural networks. World Scientific, 2013.
HAYKIN, S.; NETWORK, N. A comprehensive foundation. Neural networks, v. 2, n. 2004, p. 41, 2004.
KUNHIMANGALAM, R.; OVALLATH, S.; JOSEPH, P, K. Artificial Neural Networks in the identification of peripheral nerve disorders. Journal of Mechanics in Medicine and Biology, v.12, n. 4, p.1-14, 2012.
LUGER, G,F. Artificial intelligence: structures and strategies for complex problem solving. 6. ed. Boston: Pearson Education, 2009.
MATTOS, V, L,D, de.; KONRATH, A,C.; AZAMBUJA, A,M,V. Introdução à Estatística com aplicações em Ciências Exatas. Rio de Janeiro: LTC, v. 1, 2017.
MULDER, T. et al. A diagnostic algorithm for the surveillance of deep surgical site infections after colorectal surgery. Infection Control & Hospital Epidemiology, v. 40, n. 5, p. 574-578, 2019.
PEREIRA, C, F, C, et al. Patient safety: vulnerabilities associated with the management of extra-hospital transfer in the framework of SUS. Brazilian Journal of Health Review, v. 5, n. 4, p. 17156-17170, 2022.
PERENCEVICH, E, N, et al. Health and economic impact of surgical site infections diagnosed after hospital discharge. Emerging infectious diseases, v. 9, n. 2, p. 196, 2003.
RESINO, S, et al. An artificial neural network improves the non-invasive diagnosis of significant fibrosis in hiv/hcv coinfected patients. Journal of Infection, v. 62, n. 1, p. 77-86, 2011.
ROFFMAN, D, et al. Predicting non-melanoma skin cancer via a multi-parameterized artificial neural network. Scientific reports, v. 8, n. 1, p. 1-7, 2018.
RON, L.; BETSY, F. Estatística Aplicada. 4 ed. São Paulo: Pearson Prentice Hall, 2010.
SILVA FILHO, W, S; DE OLIVEIRA, R, M, Sousa. The importance of artificial intelligence in radiology: a systematic literature review Importance of artificial intelligence in radiology: a systematic literature. Brazilian Journal of Health Review , v. 5, no. 4, p. 12638-12649, 2022.
SUN, G, et al. An infectious disease/fever screening radar system which stratifies higher-risk patients within ten seconds using a neural network and the fuzzy grouping method. Journal of Infection, v. 70, n. 3, p. 230-236, 2015.
TROUGHTON, R. et al. Mapping national surveillance of surgical site infections in England: needs and priorities. Journal of Hospital Infection, v. 100, n. 4, p. 378-385, 2018.
TUNC, S.; ALAGOZ, O.; BURNSIDE, E. Opportunities for operations research in medical decision making. IEEE Intelligent Systems, v. 29, n. 3, p. 59, maio/jun.2014.
WHO - World Health Organization. Implementation manual surgical safety checklist: safe surgery saves lives. Disponível em: http://www.who.int/patientsafety/safesurgery/ss_checklist/en/ Acesso em: 12.jan.2023.
WICHARD J, D.; CAMMANN, H, STEPHAN C.; TOLXDORFL, T. Classification Models for Early Detection of Prostate Cancer. Journal of Biomedicine and Biotechnology, v.8, p.1-7, 2008.
XIE, BO-QIA, et al. Ventilation/perfusion scintigraphy in children with post-infectious bronchiolitis obliterans: a pilot study. PLoS One, v. 9, n. 5, p. e98381, 2014.
