TY - JOUR
T1 - Accurate diagnosis of sepsis using a neural network
T2 - Pilot study using routine clinical variables
AU - Arriaga-Pizano, Lourdes Andrea
AU - Gonzalez-Olvera, Marcos Angel
AU - Ferat-Osorio, Eduardo Antonio
AU - Escobar, Jesica
AU - Hernandez-Perez, Ana Luisa
AU - Revilla-Monsalve, Cristina
AU - Lopez-Macias, Constatino
AU - León-Pedroza, José Israel
AU - Cabrera-Rivera, Graciela Libier
AU - Guadarrama-Aranda, Uriel
AU - Leder, Ron
AU - Gallardo-Hernandez, Ana Gabriela
N1 - Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/10
Y1 - 2021/10
N2 - 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.
AB - 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.
KW - Diagnosis
KW - Markers
KW - Neural network
KW - Sepsis
UR - http://www.scopus.com/inward/record.url?scp=85114357525&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2021.106366
DO - 10.1016/j.cmpb.2021.106366
M3 - Artículo
C2 - 34500141
AN - SCOPUS:85114357525
SN - 0169-2607
VL - 210
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
M1 - 106366
ER -