Artificial inteligence techniques for sepsis recognition in hospital environments: integrative review
DOI:
https://doi.org/10.5585/rgss.v9i1.13932Keywords:
Sepsis, Artificial Intelligence, Predictive Model, Machine learning.Abstract
Sepsis is a generalized inflammation with high morbidity and mortality, whose recognition and early treatment are essential factors for a better patient´s quality of life; if not identified and treated promptly, could lead to death. This integrative review article aims to identify the techniques based on artificial intelligence adopted, their respective accuracy, sensitivity and specificity for early identification in cases of sepsis in a hospital environment. The research, adapted from the PRISMA method, was performed in five databases indexed from the following descriptors: sepsis, septic, forecasting, predict, prediction, detection, predicting, diagnosis, assessment, machine learning, artificial intelligence, data mining and deep learning. A total of 333 articles were identified, 21 with reference to the early recognition of sepsis by 16 techniques. The results showed that the neural networks performed better, varying the accuracy between 76% and 93%, the decision trees between 69.0% and 91.5% and the statistical methods between 56% and 89%. It is concluded that the most influential factor in the early identification of the diagnosis is the variety and quality of the data. The challenge in relation to pre-processing is also evident, since the data are generally from heterogeneous sources, collected with different criteria, methods and objectives.
Downloads
References
Altman, D. G., Moher, D., Liberati, A., & Tetzlaff, J. (Julho de 2009). Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLOS Medicine.
Ashal, G. E., Baratloo, A., Hosseini, M., & Negida, A. (2015). Simple Definition and Calculation of Accuracy, Sensitivity and Specificity.
Beale, R., Reinhart, K., Brunkhorst, F. M., Dobb, G., Levy, M., Martin , G., . . . Williams, M. D. (2009). Promoting Global Research Excellence in Severe Sepsis (PROGRESS): Lessons from an International Sepsis Registry. Infection 37, pp. 222-32.
Calvert, J. S., Price, D. A., Chettipaly, U. K., Barton, C. W., Feldman, M. D., Hoffman, J. L., & Jay, M. (2016). A computational approach to early sepsis detection.
Faisal, M., Scally, A., Richardson, D., Beatson, K., Howes, R., Speed, K., & Mohammed, A. M. (Abril de 2018). Development and External Validation of an Automated Computer-Aided Risk Score for Predicting Sepsis in Emergency Medical Admissions Using the Patient’s First Electronically Recorded Vital Signs and Blood Test Results. Society of Critical Care Medicine and Wolters Kluwer Health.
Ghalwash, M., Radosavljevic, V., & Obradovic, Z. (2013). Early Diagnosis and Its Benefits in Sepsis Blood Purification Treatment. IEEE International Conference on Healthcare Informatics.
Ghosh, S., Li, J., Cao, L., & Ramamohanarao, K. (2016). Septic shock prediction for ICU patients via coupled HMM walking on sequential contrast patterns.
Guillén, J., Liu, J., Furr, M., Wang, T., Strong, S., Moore, C. C., . . . Barnes , L. E. (2015). Predictive Models for Severe Sepsis in Adult ICU Patients. IEEE Systems and Information Engineering Design Symposium.
Gultepe, E., Green, J. P., Nguyen, H., Adams, J., Albertson, T., & Tagkopoulos, I. (2013). From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system.
Gultepe, E., Nguyen, H., Albertson, T., & Tagkopoulos, I. (2012). A Bayesian network for early diagnosis of sepsis patients: a basis for a clinical decision support system.
Hall, M. J., Willians, S. N., & A. G. (2011). Inpatient Care for Septicemia or Sepsis: A Challenge for Patients and Hospitals.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015). A targeted real-time early warning score (TREWScore) for septic shock. Science Translational Medicine.
Horng, S., Sontag, D. A., Halpern, Y., Jernite, Y., Shapiro, N., & Nathanson, L. (2017). Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning. Garvan Institute of Medical Research.
Jiang, Y., Tan, P., Song, H., Wan, B., Hosseini, M., & Sha, L. (2016). A Self-Adaptively Evolutionary Screening Approach for Sepsis Patient. IEEE.
Kam, H. J., & Kim, H. Y. (2017). Learning representations for the early detection of sepsis with deep neural networks. Computers in Biology and Medicine, pp. 248–255.
Kaukonen, K. M., Bailey, M., Pilcher, D., Cooper, D., & Bellomo, R. (2015). Systemic Inflammatory Response Syndrome Criteria in Defining Severe Sepsis. The New England Journal of Medicine, 10-17.
Kosh, G., & Landis, R. J. (Março de 1977). The measurement of observer agreement for categorical data. pp. 159-174.
Kumar, A., Roberts, D., Wood, K. E., Light, B., Parrillo, J. E., Sharma, S., . . . Cheang, M. (2006). Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock. Critical care medicine.
Lamping , F., Jack, T., Rubsamen, N., Sasse, M., Beerbaum, P., Mikolajczyk, R. T., . . . Karch, A. (2018). Development and validation of a diagnostic model for early differentiation of sepsis and non-infectious SIRS in critically ill children - a data-driven approach using machine learning. BMC Pediatrics.
Mao, Q., jay , M., Hoffman, J. L., Calvert, J., Barton, C., Shimabukuro, D., . . . Das, R. (2017). Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department,general ward and ICU. bmjopen.
Mitchell, S., Schinkel, K., Song, Y., Wang, Y., Ainsworth, J., Halbert, T., . . . Barnes, L. (2016). Optimization of Sepsis Risk Assessment for Ward Patients. IEEE Systems and Information Engineering Design Conference.
Nemati, S., Holder, A., Razmi, F., Stanley, M., Clifford, G. D., & Buchman, T. G. (2017). An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU. Critical Care Medicine.
Parente, J. D., Lee, D., Lin, J., Chase, G. J., & Shaw, G. M. (2010). A Fast and Accurate Diagnostic Test for Severe Sepsis Using Kernel Classifiers.
Parikh, R., Mathai, A., Parikh, S., Sekhar, C., & Thomas, R. (Janeiro de 2008). Understanding and using sensitivity, specificity and predictive values. pp. 45-50.
Purushotham, S., Meng, C., Che, Z., & Lui, Y. (2018). Benchmarking deep learning models on large healthcare datasets. Journal of Biomedical Informatics, pp. 112–134.
Rothman, M., Levy, M., Dellinger, P. R., Jones, S. L., Robert, F. L., Voelker, K. G., . . . Beals, J. (2017). Sepsis as 2 problems: Identifying sepsis at admission and predicting onset in the hospital using an electronic medical record–based acuity score. Journal of Critical Care 38, pp. 237–244.
Schuh, C. J. (2007). Sepsis and Septic Shock Analysis using Neural Networks. IEEE.
Seymour, W. C., Liu, X. V., Iwashyna, J. T., Brunkhorst, M. F., Rea, D. T., Sherag, a., . . . Angus, C. D. (2016). Assessment of Clinical Criteria for Sepsis For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). American Medical Association, 13.
Shashikumar, P. S., Li, Q., Clifford, G. D., & Nemati, S. (2017). Multiscale network representation of physiological time series for early prediction of sepsis. Institute of Physics and Engineering in Medicine - Physiol. Meas. 38, pp. 2235–2248.
Simundic, A. (Janeiro de 2009). Measures of Diagnostic Accuracy: Basic Definitions. The Journal of the International Federation of Clinical Chemistry and Laboratory Medicine.
Taylor, A. R., Pare, J. R., Venkatesh, A. K., Mowafi, H., Melnick, E. R., Fleischman, W., & Hall, K. M. (2015). Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data–Driven, Machine Learning Approach. Society for Academic Emergency Medicine.
Viana, R. A., Machado, F. R., & Souza, J. L. (2017). SEPSE: UM PROBLEMA DE SAÚDE PÚBLICA. A atuação e colaboração da Enfermagem na rápida identificação e tratamento da doença. São Paulo.
Wang, X., Wang, Z., Weng, J., Wen, C., Chen, H., & Wang, X. (2018). A New Effective Machine Learning Framework for Sepsis Diagnosis. IEEE.
Wyk, F. V., Khojandi, A., & Kamaleswaran, R. (Novembro de 2017). How much data should we collect A case study in sepsis detection using deep learning. IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT).
Zhang, Y., Lin, C., Chi, M., Ivy, C., & Huddleston, M. ,. (2017). LSTM for Septic Shock: Adding Unreliable Labels to Reliable Predictions. IEEE International Conference on Big Data (BIGDATA).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Revista de Gestão em Sistemas de Saúde
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho simultaneamente licenciado sob a Creative Commons Atribuição - Não comercial - Compartilhar igual 4.0 Internacional que permite o compartilhamento do trabalho com reconhecimento da autoria e publicação inicial nesta revista.
Autores têm autorização para assumir contratos adicionais separadamente, para distribuição não-exclusiva da versão do trabalho publicada nesta revista (ex.: publicar em repositório institucional ou como capítulo de livro), com reconhecimento de autoria e publicação inicial nesta revista.
Autores têm permissão e são estimulados a publicar e distribuir seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) a qualquer ponto antes ou durante o processo editorial, já que isso pode gerar alterações produtivas, bem como aumentar o impacto e a citação do trabalho publicado (Veja O Efeito do Acesso Livre) em http://opcit.eprints.org/oacitation-biblio.html
