Development and validation of a simple machine learning tool to predict mortality in leptospirosis.

Autor: Galdino GS; Medical Sciences Postgraduate Program, Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, Fortaleza, Ceará, 60165-070, Brazil. studartgabriela@gmail.com.br.; Hospital Universitário Walter Cantídio, Federal University of Ceará, Fortaleza, Ceará, Brazil. studartgabriela@gmail.com.br., de Sandes-Freitas TV; Medical Sciences Postgraduate Program, Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, Fortaleza, Ceará, 60165-070, Brazil.; Hospital Universitário Walter Cantídio, Federal University of Ceará, Fortaleza, Ceará, Brazil.; Hospital Geral de Fortaleza, Fortaleza, Ceara, Brazil., de Andrade LGM; Botucatu Medical School, Universidade Estadual Paulista, Botucatu, São Paulo, Brazil., Adamian CMC; Hospital Universitário Walter Cantídio, Federal University of Ceará, Fortaleza, Ceará, Brazil., Meneses GC; Medical Sciences Postgraduate Program, Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, Fortaleza, Ceará, 60165-070, Brazil., da Silva Junior GB; Medical Sciences Postgraduate Program, Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, Fortaleza, Ceará, 60165-070, Brazil.; Hospital Universitário Walter Cantídio, Federal University of Ceará, Fortaleza, Ceará, Brazil.; School of Medicine, Medical Sciences and Public Health Postgraduate Programs, University of Fortaleza, Fortaleza, Ceará, Brazil., de Francesco Daher E; Medical Sciences Postgraduate Program, Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, Fortaleza, Ceará, 60165-070, Brazil.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2023 Mar 18; Vol. 13 (1), pp. 4506. Date of Electronic Publication: 2023 Mar 18.
DOI: 10.1038/s41598-023-31707-4
Abstrakt: Predicting risk factors for death in leptospirosis is challenging, and identifying high-risk patients is crucial as it might expedite the start of life-saving supportive care. Admission data of 295 leptospirosis patients were enrolled, and a machine-learning approach was used to fit models in a derivation cohort. The comparison of accuracy metrics was performed with two previous models-SPIRO score and quick SOFA score. A Lasso regression analysis was the selected model, demonstrating the best accuracy to predict mortality in leptospirosis [area under the curve (AUC-ROC) = 0.776]. A score-based prediction was carried out with the coefficients of this model and named LeptoScore. Then, to simplify the predictive tool, a new score was built by attributing points to the predictors with importance values higher than 1. The simplified score, named QuickLepto, has five variables (age > 40 years; lethargy; pulmonary symptom; mean arterial pressure < 80 mmHg and hematocrit < 30%) and good predictive accuracy (AUC-ROC = 0.788). LeptoScore and QuickLepto had better accuracy to predict mortality in patients with leptospirosis when compared to SPIRO score (AUC-ROC = 0.500) and quick SOFA score (AUC-ROC = 0.782). The main result is a new scoring system, the QuickLepto, that is a simple and useful tool to predict death in leptospirosis patients at hospital admission.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje