Predição de Sepse a partir de Dados do Atendimento Pré-Hospitalar
Abstract
Sepsis is a syndrome that affects millions of people each year, causing approximately 20% of deaths worldwide. Early recognition of sepsis symptoms makes possible to start the appropriate treatment in time to provide better outcomes. Thus, it is relevant to develop tools that enable early identification of sepsis in the prehospital environment, such as the qSofa heuristic score. This article presents the results of tests performed with machine learning models trained with data from the first attendence provided by SAMU. Even with a restricted data set, the models developed showed improvements in the order of 7.7% in accuracy and 17.7% in AUC in relation to the results of qSofa.
References
Barton, C., Chettipally, U., Zhou, Y., Jiang, Z., Lynn-Palevsky, A., Le, S., Calvert, J., and Das, R. (2019). Evaluation of a machine learning algorithm for up to 48-hour advance prediction of sepsis using six vital signs. Computers in biology and medicine, 109:79–84.
Brasil (2003). Portaria Nº 1.864, de 29 de setembro de 2003. Ministério da Saúde.
Buchman, T. G., Simpson, S. Q., Sciarretta, K. L., Finne, K. P., Sowers, N., Collier, M., Chavan, S., Oke, I., Pennini, M. E., Santhosh, A., Wax, M., Woodbury, R., Chu, S., Merkeley, T. G., Disbrow, G. L., Bright, R. A., MaCurdy, T. E., and Kelman, J. A. (2020). Sepsis Among Medicare Beneciaries: 3. The Methods, Models, and Forecasts of Sepsis, 2012-2018. Critical Care Medicine, 48:302–318.
CatBoost (2021). Catboost. https://catboost.ai/docs/concepts/about.html. Acesso em 19-04-2021.
Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM.
Elezkurtaj, S., Greuel, S., Ihlow, J., Michaelis, E. G., Bischoff, P., Kunze, C. A., Sinn, B. V., Gerhold, M., Hauptmann, K., Ingold-Heppner, B., Miller, F., Herbst, H., Corman, V. M., Martin, H., Radbruch, H., Heppner, F. L., and Horst, D. (2021). Causes of death and comorbidities in hospitalized patients with COVID-19. Scientic Reports, 11(4263).
Goh, K. H., Wang, L., Yeow, A. Y. K., Poh, H., Li, K., Yeow, J. J. L., and Tan, G. Y. H. (2021). Arti- cial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature communications, 12(1).
Jouffroy, R., Saade, A., Carpentier, A., Ellouze, S., Philippe, P., Idialisoa, R., Carli, P., and Vivien, B. (2019). Triage of Septic Patients Using qSOFA Criteria at the SAMU Regulation: A Retrospective Analysis. Prehospital Emergency Care, 22(1).
Koyama, S., Yamaguchi, Y., Gibo, K., Nakayama, I., and Ueda, S. (2019). Use of prehospital qSOFA in predicting in-hospital mortality in patients with suspected infection: A retrospective cohort study. PLoS One, 14(5).
Lane, D. J., Wunsch, H., Saskin, R., Cheskes, S., Lin, S., Morrison, L. J., and Scales, D. C. (2020). Screening strategies to identify sepsis in the prehospital setting: a validation study. Canadian Medical Association journal, 192(10):E230—-E239.
Li, H., Liu, L., Zhang, D., Xu, J., Dai, H., Tang, N., Su, X., and Cao, B. (2020). SARS-CoV-2 and viral sepsis: observations and hypotheses. The Lancet, 395:1517–1520.
Mao, Q., Jay, M., Hoffman, J. L., Calvert, J., Barton, C., Shimabukuro, D., Shieh, L., Chettipally, U., Fletcher, G., Kerem, Y., Zhou, Y., and Das, R. (2018). Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ open, 8(1).
Microsoft (2016). Lightgbm. https://www.microsoft.com/en-us/research/project/lightgbm. Acesso em 19-04-2021.
O’Dwyer, G., Konder, M. T., Reciputti, L. P., Macedo, C., and Lopes, M. G. M. (2017). O processo de implantação do Serviço de Atendimento Móvel de Urgência no Brasil: estratégias de ação e dimensões estruturais. Cadernos de Saúde Pública, 33(7).
Pucchio, A., Eisenhauer, E. A., and Moraes, F. Y. (2021). Medical students need articial intelligence and machine learning training. Nature Biotechnology, 39:388-389.
Raschka, S. and Mirjalili, V. (2017). Python Machine Learning. Packt Publishing, second edition.
Reyna, M. A., Josef, C. S., Jeter, R., Shashikumar, S. P. B., Westover, B., Nemati, S., Clifford, G. D. D., and Sharma, A. (2020). Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019. Critical Care Medicine, 48:210–217.
Rudd, K. E., Johnson, S. C., Agesa, K. M., Shackelford, K. A., Tsoi, D., Kievlan, D. R., Colombara, D. V., Ikuta, K. S., Kissoon, N., Finfer, S., Fleischmann-Struzek, C., Machado, F. R., Reinhart, K. K., Rowan, K., Seymour, C. W., Watson, R. S., West, T. E., Marinho, F., Hay, S. I., Lozano, R., Lopez, A. D., Angus, D. C., Murray, C. J. L., and Naghavi, M. (2020). Global, regional, and national sepsis incidence and mortality, 1990–2017: analysis for the Global Burden of Disease Study. The Lancet, 395:200–211.
Scikit-learn (2021). Scikit-learn. https://scikit-learn.org/. Acesso em 19-04-2021.
Shiraishi, D. and Marujo, E. (2020). Predição de sepse em unidade de terapia intensiva: uma abordagem de aprendizado de máquina. In Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 416–421, Porto Alegre, RS, Brasil. SBC.
Singer, M., Deutschman, C. S., Seymour, C. W., Shankar-Hari, M., Annane, D., Bauer, M., Bellomo, R., Bernard, G. R., Chiche, J.-D., Coopersmith, C. M., Hotchkiss, R. S., Levy, M. M., Marshall, J. C., Mar- tin, G. S., Opal, S. M., Rubenfeld, G. D., van der Poll, T., Vincent, J.-L., and Angus, D. C. (2016). The Third International Consensus Denitions for Sepsis and Septic Shock (Sepsis-3). JAMA, 315(8):801– 810.
World Health Organization (2020). Global report on the epidemiology and burden of sepsis: current evidence, identifying gaps and future directions. https://apps.who.int/iris/bitstream/handle/10665/334216/9789240010789-eng.pdf, Geneva.
Zafer, M. M., El-Mahallawy, H. A., and Ashour, H. M. (2021). Severe COVID-19 and Sepsis: Immune Pathogenesis and Laboratory Markers. Microorganisms, 9(1).
Brasil (2003). Portaria Nº 1.864, de 29 de setembro de 2003. Ministério da Saúde.
Buchman, T. G., Simpson, S. Q., Sciarretta, K. L., Finne, K. P., Sowers, N., Collier, M., Chavan, S., Oke, I., Pennini, M. E., Santhosh, A., Wax, M., Woodbury, R., Chu, S., Merkeley, T. G., Disbrow, G. L., Bright, R. A., MaCurdy, T. E., and Kelman, J. A. (2020). Sepsis Among Medicare Beneciaries: 3. The Methods, Models, and Forecasts of Sepsis, 2012-2018. Critical Care Medicine, 48:302–318.
CatBoost (2021). Catboost. https://catboost.ai/docs/concepts/about.html. Acesso em 19-04-2021.
Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM.
Elezkurtaj, S., Greuel, S., Ihlow, J., Michaelis, E. G., Bischoff, P., Kunze, C. A., Sinn, B. V., Gerhold, M., Hauptmann, K., Ingold-Heppner, B., Miller, F., Herbst, H., Corman, V. M., Martin, H., Radbruch, H., Heppner, F. L., and Horst, D. (2021). Causes of death and comorbidities in hospitalized patients with COVID-19. Scientic Reports, 11(4263).
Goh, K. H., Wang, L., Yeow, A. Y. K., Poh, H., Li, K., Yeow, J. J. L., and Tan, G. Y. H. (2021). Arti- cial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature communications, 12(1).
Jouffroy, R., Saade, A., Carpentier, A., Ellouze, S., Philippe, P., Idialisoa, R., Carli, P., and Vivien, B. (2019). Triage of Septic Patients Using qSOFA Criteria at the SAMU Regulation: A Retrospective Analysis. Prehospital Emergency Care, 22(1).
Koyama, S., Yamaguchi, Y., Gibo, K., Nakayama, I., and Ueda, S. (2019). Use of prehospital qSOFA in predicting in-hospital mortality in patients with suspected infection: A retrospective cohort study. PLoS One, 14(5).
Lane, D. J., Wunsch, H., Saskin, R., Cheskes, S., Lin, S., Morrison, L. J., and Scales, D. C. (2020). Screening strategies to identify sepsis in the prehospital setting: a validation study. Canadian Medical Association journal, 192(10):E230—-E239.
Li, H., Liu, L., Zhang, D., Xu, J., Dai, H., Tang, N., Su, X., and Cao, B. (2020). SARS-CoV-2 and viral sepsis: observations and hypotheses. The Lancet, 395:1517–1520.
Mao, Q., Jay, M., Hoffman, J. L., Calvert, J., Barton, C., Shimabukuro, D., Shieh, L., Chettipally, U., Fletcher, G., Kerem, Y., Zhou, Y., and Das, R. (2018). Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ open, 8(1).
Microsoft (2016). Lightgbm. https://www.microsoft.com/en-us/research/project/lightgbm. Acesso em 19-04-2021.
O’Dwyer, G., Konder, M. T., Reciputti, L. P., Macedo, C., and Lopes, M. G. M. (2017). O processo de implantação do Serviço de Atendimento Móvel de Urgência no Brasil: estratégias de ação e dimensões estruturais. Cadernos de Saúde Pública, 33(7).
Pucchio, A., Eisenhauer, E. A., and Moraes, F. Y. (2021). Medical students need articial intelligence and machine learning training. Nature Biotechnology, 39:388-389.
Raschka, S. and Mirjalili, V. (2017). Python Machine Learning. Packt Publishing, second edition.
Reyna, M. A., Josef, C. S., Jeter, R., Shashikumar, S. P. B., Westover, B., Nemati, S., Clifford, G. D. D., and Sharma, A. (2020). Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019. Critical Care Medicine, 48:210–217.
Rudd, K. E., Johnson, S. C., Agesa, K. M., Shackelford, K. A., Tsoi, D., Kievlan, D. R., Colombara, D. V., Ikuta, K. S., Kissoon, N., Finfer, S., Fleischmann-Struzek, C., Machado, F. R., Reinhart, K. K., Rowan, K., Seymour, C. W., Watson, R. S., West, T. E., Marinho, F., Hay, S. I., Lozano, R., Lopez, A. D., Angus, D. C., Murray, C. J. L., and Naghavi, M. (2020). Global, regional, and national sepsis incidence and mortality, 1990–2017: analysis for the Global Burden of Disease Study. The Lancet, 395:200–211.
Scikit-learn (2021). Scikit-learn. https://scikit-learn.org/. Acesso em 19-04-2021.
Shiraishi, D. and Marujo, E. (2020). Predição de sepse em unidade de terapia intensiva: uma abordagem de aprendizado de máquina. In Anais do XX Simpósio Brasileiro de Computação Aplicada à Saúde, pages 416–421, Porto Alegre, RS, Brasil. SBC.
Singer, M., Deutschman, C. S., Seymour, C. W., Shankar-Hari, M., Annane, D., Bauer, M., Bellomo, R., Bernard, G. R., Chiche, J.-D., Coopersmith, C. M., Hotchkiss, R. S., Levy, M. M., Marshall, J. C., Mar- tin, G. S., Opal, S. M., Rubenfeld, G. D., van der Poll, T., Vincent, J.-L., and Angus, D. C. (2016). The Third International Consensus Denitions for Sepsis and Septic Shock (Sepsis-3). JAMA, 315(8):801– 810.
World Health Organization (2020). Global report on the epidemiology and burden of sepsis: current evidence, identifying gaps and future directions. https://apps.who.int/iris/bitstream/handle/10665/334216/9789240010789-eng.pdf, Geneva.
Zafer, M. M., El-Mahallawy, H. A., and Ashour, H. M. (2021). Severe COVID-19 and Sepsis: Immune Pathogenesis and Laboratory Markers. Microorganisms, 9(1).
Published
2021-06-15
How to Cite
KAIESKI, Naira; LORA, Priscila Schmidt; COSTA, Cristiano André da.
Predição de Sepse a partir de Dados do Atendimento Pré-Hospitalar. In: BRAZILIAN SYMPOSIUM ON COMPUTING APPLIED TO HEALTH (SBCAS), 21. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 369-380.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2021.16080.
