Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Desarrollo de una escala predictiva en pacientes con shock séptico refractario mediante un modelo híbrido de aprendizaje automático y regresiónScale to predict risk for refractory septic shock based on a hybrid approach using machine learning and regression modeling

Other Titles
Scale to predict risk for refractory septic shock based on a hybrid approach using machine learning and regression modeling
Authors
Heo, SejinJeong, DaunChoi, MinyoungKim, InkyuKim, MinhaLee, Ye RimKo, Byuk SungRyoo, Seung MokHan, EunahChang, HyunglanYune, Chang JuneLee, Hui JaiSuh, Gil JoonChoi, Sung-HyukChung, Sung PhilLim, Tae HoKim, Won YoungKim, KyuseokHwang, Sung YeonPark, Jong EunLee, Gun TakShin, Tae Gun
Issue Date
Feb-2025
Publisher
Saned
Keywords
Aprendizaje automático; Machine learning; Predictivo; Risk; Septic shock; Shock séptico; Vasopresores; Vasopressors
Citation
Emergencias, v.37, no.1, pp 15 - 22
Pages
8
Indexed
SCIE
SCOPUS
Journal Title
Emergencias
Volume
37
Number
1
Start Page
15
End Page
22
URI
https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/212169
DOI
10.55633/s3me/108.2024
ISSN
1137-6821
2386-5857
Abstract
Objetivos. Desarrollar una escala predictiva en pacientes con shock séptico (SS) refractario basada en parámetros clínicos disponibles en la valoración inicial. Métodos. Estudio multicéntrico y retrospectivo que analizó pacientes de la base MIMIC-IV (Marketplace for Medical Information in Intensive Care) para la derivación y validación interna de la escala. Se realizó una validación externa con pacientes con SS diagnosticados en el servicio de urgencias (cohorte SU) y con pacientes diagnosticados en la unidad de cuidados intensivos (cohorte UCI). La escala de SS refractario (ESSR) se desarrolló con AutoScore. El rendimiento se analizó mediante el área bajo la curva (ABC) de la curva operativa del receptor (ROC). El resultado primario fue el desarrollo de SS refractario en las 24 horas siguientes al ingreso en la UCI o de la llegada al SU, definido como la necesidad de una dosis equivalente de noradrenalina superior a 0,5 µg/kg/min. Resultados. Se analizaron 29.618 pacientes de la base MIMIC-IV, 3.113 de la cohorte SU y 1.015 de la cohorte UCI. La ESSR incluyó seis variables: lactato, presión arterial sistólica, frecuencia cardiaca, temperatura, pH arterial y cifra de leucocitos. El ABC ROC fue de 0,873 (IC 95%: 0,846-0,900) en la validación interna; 0,705 (IC 95% 0,678-0,733) en la cohorte SU a su llegada y 0,781 (IC 95%: 0,757-0,805) en el momento de la hipoperfusión o hipotensión; y 0,822 (IC 95%: 0,787-0,857) en la cohorte UCI. La calibración fue aceptable en todas las cohortes. Conclusiones. La ESSR tuvo una precisión diagnóstica adecuada en múltiples cohortes de validación de pacientes incluidos en el SU y en la UCI.
Objective. To develop a scale to predict refractory septic shock (SS) based on clinical variables recorded during initial evaluations of patients. Methods. Multicenter retrospective study of data for patients with suspected infection registered in the Marketplace for Medical Information in Intensive Care (MIMIC-IV). These data were used for the development and internal validation of the refractory SS scale (RSSS). For external validation, we used retrospective data for 2 cohorts: 1) patients diagnosed with SS in an emergency department (ED cohort) whose data were registered in a Korean SS registry, and 2) patients diagnosed with SS in 6 hospital intensive care units (ICU cohort). A machine-learning automatic clinical scoring system (AutoScore) was used in the development phase. The performance of the RSSS in the validation cohorts was assessed with the area under the receiver operating characteristic curve (AUROC) for each. The primary outcome was the development of refractory SS within 24 hours of ICU admission. Refractory SS was defined by the need for a norepinephrine-equivalent dose greater than 0.5 µg/kg/min. Results. We collected data for 29 618 patients from the MIMIC-IV registry, 3113 patients for the ED cohort, and 1015 for the ICU cohort. The RSSS had 6 predictors: serum lactate level, systolic blood pressure, heart rate, temperature, arterial pH, and leukocyte count. The scale’s AUROCs were as follows: 0.873 (95% CI, 0.846-0.900) in the internal validation, 0.705 (95% CI, 0.678-0.733) in the ED cohort on arrival, 0.781 (95% CI, 0.757-0.805) in the ED cohort at the moment of diagnosing hypoperfusion or hypotension, and 0.822 (95% CI, 0.787-0.857) in the ICU cohort. Calibration was acceptable in all the cohorts. Conclusion. The RSSS had adequate diagnostic accuracy in multiple cohorts of patients diagnosed in the ED and ICU.
Files in This Item
Go to Link
Appears in
Collections
서울 의과대학 > 서울 응급의학교실 > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Ko, Byuk Sung photo

Ko, Byuk Sung
서울 의과대학 (DEPARTMENT OF EMERGENCY MEDICINE)
Read more

Altmetrics

Total Views & Downloads

BROWSE