Accurate diagnosis of sepsis using a neural network: Pilot study using routine clinical variables. (October 2021)

• Record Type: Journal Article
• Authors: Arriaga-Pizano, Lourdes Andrea; Gonzalez-Olvera, Marcos Angel; Ferat-Osorio, Eduardo Antonio; Escobar, Jesica; Hernandez-Perez, Ana Luisa; Revilla-Monsalve, Cristina; Lopez-Macias, Constatino; León-Pedroza, José Israel; Cabrera-Rivera, Graciela Libier; Guadarrama-Aranda, Uriel; Leder, Ron; Gallardo-Hernandez, Ana Gabriela
• Is Part Of: Computer methods and programs in biomedicine. Volume 210(2021)
• Publication Date: 2021-10
• Subjects: Sepsis -- Diagnosis -- Markers -- Neural network; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106366
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Sepsis is a severe infection that increases the mortality, but its detection is difficult and there is no gold standard test. Early detection and treatment improve the patient outcome. We develop a neural network to diagnose if the patient has sepsis using routine laboratory test and vital signals that are frequently measured in ICU patients. The neural network could correctly diagnose all but one case, with a 91% sensitivity in the validation data set, and 100% specificity. The developed system can be a useful tool at any hospital to diagnose sepsis, because the required tests are inexpensive and widely available. Abstract: Background and objectives: Sepsis is a severe infection that increases mortality risk and is one if the main causes of death in intensive care units. Accurate detection is key to successful interventions, but diagnosis of sepsis is complicated because the initial signs and symptoms are not specific. Biomarkers that have been proposed have low specificity and sensitivity, are expensive, and not available in every hospital. In this study, we propose the use of artificial intelligence in the form of a neural network to diagnose sepsis using only common laboratory tests and vital signs that are routine and widely available. Methods: A retrospective, cross sectional cohort of 113 patients from an intensive care unit, each with 48 routinely evaluated vital signs and biochemical parameters was used to train, validate and test a neural network with 48 inputs, 10 neurons in a single hidden layer and one output. The sensitivity and specificity of the neural network as a point sampled diagnostic test was calculated. Results: All but one case were correctly diagnosed by the neural network, with 91% sensitivity and 100% specificity in the validation data set, and 100% sensitivity and specificity in the test data set. Conclusions: The designed neural network system can identify patients with sepsis, with minimal resources using standard laboratory tests widely available in most health care facilities. This should reduce the burden on the medical staff of a difficult diagnosis and should improve outcomes for patients with sepsis.