Journal Information
Vol. 48. Issue 10.
Pages 584-593 (October 2024)
Share
Share
Download PDF
More article options
Vol. 48. Issue 10.
Pages 584-593 (October 2024)
Original article
Sepsis mortality prediction with Machine Learning Tecniques
Predicción de la mortalidad por sepsis con técnicas de aprendizaje automático
Javier Carrillo Pérez-Tomea, Tesifón Parrón-Carreñoa, Ana Belen Castaño-Fernándezb, Bruno José Nievas-Sorianoa, Gracia Castro-Lunaa,
Corresponding author
graciacl@ual.es

Corresponding author.
a Department of Nursing: Physiotherapy and Medicine, University of Almeria, 04120 Almeria, Spain
b Department of Applied Mathematics, University of Almería, 04120 Almeria, Spain
Article information
Abstract
Full Text
Bibliography
Download PDF
Statistics
Figures (4)
Show moreShow less
Tables (2)
Table 1. Descriptive statistics of quantitative variables according to exitus.
Table 2. Descriptive Statistics MIMIC III database.
Show moreShow less
Abstract
Objective

To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU).

Design

Cross-sectional descriptive study.

Setting

The Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database.

Patients

180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database.

Main variables of interest

Age, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels.

Results

A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%.

Conclusions

According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.

Keywords:
Sepsis
MIMIC III
Machine learning
Sepsis mortality
Resumen
Objetivo

Desarrollar un modelo de clasificación basado en técnicas de machine-learning de muerte por sepsis para pacientes ingresados en la Unidad de Cuidados Intensivos (UCI).

Diseño

Estudio descriptivo transversal.

Ämbito

Unidades de Cuidados Intensivos (UCI) de tres hospitales de Murcia (España) y pacientes con sepsis-3 de la base de datos de acceso abierto MIMIC III.

Pacientes

180 pacientes diagnosticados de sepsis en las UCI de tres hospitales y un total de 4559 pacientes con la base de datos MIMIC III.

Variables de interés principales

Se evaluaron la edad, el peso, la frecuencia cardiaca, la frecuencia respiratoria, la temperatura, los niveles de lactato, la saturación parcial de oxígeno, la presión arterial sistólica y diastólica, el pH, los niveles de orina y los niveles de potasio.

Resultados

Se calcularon un modelo de clasificación de bosque aleatorio con la base de datos local y la base de datos MIMIC III. La sensibilidad del modelo de nuestra base de datos teniendo en cuenta todas las variables catalogadas como importantes por el random forest fue del 95,45%%, la especificidad del 100% y la exactitud del 96,77% y un AUC del 95%. En el caso del modelo sobre la base de datos MIMIC III la sensibilidad fue del 97,55%, la especificidad del 100% y la exactitud del 98,28% con un AUC del 97,3%.

Conclusiones

Según la clasificación de bosque aleatorio en ambas bases de datos, los niveles de lactato, la diuresis y las variables relacionadas con el equilibrio ácido-base fueron las variables más importantes para determinar las muertes por sepsis en la UCI. Los niveles medios de potasio fueron más críticos en la base de datos MIMIC III que en las locales.

Palabras clave:
Sepsis
MIMIC III
Aprendizaje automático
Mortalidad por sepsis

Article

These are the options to access the full texts of the publication Medicina Intensiva (English Edition)
Member
If you are a member of the Sociedad Española de Medicina Intensiva, Crítica y Unidades Coronarias::
Go to the members area of the website of the SEMICYUC (www.semicyuc.org )and click the link to the magazine.
Subscriber
Subscriber

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe
Subscribe to

Medicina Intensiva (English Edition)

Purchase
Purchase article

Purchasing article the PDF version will be downloaded

Price 19.34 €

Purchase now
Contact
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
Email
Idiomas
Medicina Intensiva (English Edition)
es en

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?