Multidimensional machine learning models predicting outcomes after trauma.

Humans Prospective Studies Pneumonia, Ventilator-Associated / diagnosis Machine Learning Logistic Models Acute Kidney Injury / diagnosis Retrospective Studies

Journal

Surgery
ISSN: 1532-7361
Titre abrégé: Surgery
Pays: United States
ID NLM: 0417347

Informations de publication

Date de publication:
12 2022
Historique:
received: 17 05 2022
revised: 01 08 2022
accepted: 04 08 2022
pubmed: 19 9 2022
medline: 24 11 2022
entrez: 18 9 2022
Statut: ppublish

Résumé

An emerging body of literature supports the role of individualized prognostic tools to guide the management of patients after trauma. The aim of this study was to develop advanced modeling tools from multidimensional data sources, including immunological analytes and clinical and administrative data, to predict outcomes in trauma patients. This was a prospective study of trauma patients at Level 1 centers from 2015 to 2019. Clinical, flow cytometry, and serum cytokine data were collected within 48 hours of admission. Sparse logistic regression models were developed, jointly selecting predictors and estimating the risk of ventilator-associated pneumonia, acute kidney injury, complicated disposition (death, rehabilitation, or nursing facility), and return to the operating room. Model parameters (regularization controlling model sparsity) and performance estimation were obtained via nested leave-one-out cross-validation. A total of 179 patients were included. The incidences of ventilator-associated pneumonia, acute kidney injury, complicated disposition, and return to the operating room were 17.7%, 28.8%, 22.5%, and 12.3%, respectively. Regarding extensive resource use, 30.7% of patients had prolonged intensive care unit stay, 73.2% had prolonged length of stay, and 23.5% had need for prolonged ventilatory support. The models were developed and cross-validated for ventilator-associated pneumonia, acute kidney injury, complicated dispositions, and return to the operating room, yielding predictive areas under the curve from 0.70 to 0.91. Each model derived its optimal predictive value by combining clinical, administrative, and immunological analyte data. Clinical, immunological, and administrative data can be combined to predict post-traumatic outcomes and resource use. Multidimensional machine learning modeling can identify trauma patients with complicated clinical trajectories and high resource needs.

Sections du résumé

BACKGROUND
An emerging body of literature supports the role of individualized prognostic tools to guide the management of patients after trauma. The aim of this study was to develop advanced modeling tools from multidimensional data sources, including immunological analytes and clinical and administrative data, to predict outcomes in trauma patients.
METHODS
This was a prospective study of trauma patients at Level 1 centers from 2015 to 2019. Clinical, flow cytometry, and serum cytokine data were collected within 48 hours of admission. Sparse logistic regression models were developed, jointly selecting predictors and estimating the risk of ventilator-associated pneumonia, acute kidney injury, complicated disposition (death, rehabilitation, or nursing facility), and return to the operating room. Model parameters (regularization controlling model sparsity) and performance estimation were obtained via nested leave-one-out cross-validation.
RESULTS
A total of 179 patients were included. The incidences of ventilator-associated pneumonia, acute kidney injury, complicated disposition, and return to the operating room were 17.7%, 28.8%, 22.5%, and 12.3%, respectively. Regarding extensive resource use, 30.7% of patients had prolonged intensive care unit stay, 73.2% had prolonged length of stay, and 23.5% had need for prolonged ventilatory support. The models were developed and cross-validated for ventilator-associated pneumonia, acute kidney injury, complicated dispositions, and return to the operating room, yielding predictive areas under the curve from 0.70 to 0.91. Each model derived its optimal predictive value by combining clinical, administrative, and immunological analyte data.
CONCLUSION
Clinical, immunological, and administrative data can be combined to predict post-traumatic outcomes and resource use. Multidimensional machine learning modeling can identify trauma patients with complicated clinical trajectories and high resource needs.

Identifiants

DOI: 10.1016/j.surg.2022.08.007 PMID: 36116976
pubmed: 36116976
pii: S0039-6060(22)00595-5
doi: 10.1016/j.surg.2022.08.007
pii:
doi:

Types de publication

Journal Article Research Support, U.S. Gov't, Non-P.H.S.

Langues

eng

Sous-ensembles de citation

IM

Pagination

1851-1859

Informations de copyright

Copyright © 2022 Elsevier Inc. All rights reserved.

Auteurs

Dimitrios Moris (D)

Medical Center, Duke University Durham, NC. Electronic address: dimitrios.moris@duke.edu.

Ricardo Henao (R)

School of Medicine, Duke University Durham, NC.

Hannah Hensman (H)

DecisionQ, Arlington, VA; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.

Linda Stempora (L)

Medical Center, Duke University Durham, NC; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.

Scott Chasse (S)

Medical Center, Duke University Durham, NC; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.

Seth Schobel (S)

Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD; Henry M. Jackson Foundation for the Advancement of Military Medicine, Inc, Bethesda, MD.

Christopher J Dente (CJ)

Department of Surgery, Emory University, Atlanta, GA.

Allan D Kirk (AD)

Medical Center, Duke University Durham, NC; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.

Eric Elster (E)

Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD; Walter Reed National Military Medical Center, Bethesda, MD.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female

Evaluation of Low-Value Services Across Major Medicare Advantage Insurers and Traditional Medicare.

Ciara Duggan, Adam L Beckman, Ishani Ganguli et al.
1.00
Humans United States Aged Cross-Sectional Studies Medicare Part C

Effectiveness of Virtual Yoga for Chronic Low Back Pain: A Randomized Clinical Trial.

Hallie Tankha, Devyn Gaskins, Amanda Shallcross et al.
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH

questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › Multidimensional machine learning models...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Caractéristiques des études épidémiologiques › Études épidémiologiques › Études de cohortes › Études prospectives › Multidimensional machine learning models...
questionsmedicales.fr › États, signes et symptômes pathologiques › Processus pathologiques › Caractéristiques de la maladie › Maladie iatrogène › Infection croisée › Pneumonie associée aux soins › Pneumopathie infectieuse sous ventilation assistée › Multidimensional machine learning models...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Apprentissage machine › Multidimensional machine learning models...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Statistiques comme sujet › Analyse de régression › Modèles logistiques › Multidimensional machine learning models...
questionsmedicales.fr › Maladies urogénitales › Maladies urologiques › Maladies du rein › Insuffisance rénale › Atteinte rénale aigüe › Multidimensional machine learning models...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Caractéristiques des études épidémiologiques › Études épidémiologiques › Études de cohortes › Études rétrospectives › Multidimensional machine learning models...