Cargando…

ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction

BACKGROUND: Precise models are necessary to estimate mortality risk following traumatic injury to inform clinical decision making or quantify hospital performance. The Trauma and Injury Severity Score (TRISS) has been the historical gold standard in survival prediction but its limitations are well-c...

Descripción completa

Detalles Bibliográficos
Autores principales: Tran, Zachary, Verma, Arjun, Wurdeman, Taylor, Burruss, Sigrid, Mukherjee, Kaushik, Benharash, Peyman
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9612528/
https://www.ncbi.nlm.nih.gov/pubmed/36301826
http://dx.doi.org/10.1371/journal.pone.0276624
_version_ 1784819791990620160
author Tran, Zachary
Verma, Arjun
Wurdeman, Taylor
Burruss, Sigrid
Mukherjee, Kaushik
Benharash, Peyman
author_facet Tran, Zachary
Verma, Arjun
Wurdeman, Taylor
Burruss, Sigrid
Mukherjee, Kaushik
Benharash, Peyman
author_sort Tran, Zachary
collection PubMed
description BACKGROUND: Precise models are necessary to estimate mortality risk following traumatic injury to inform clinical decision making or quantify hospital performance. The Trauma and Injury Severity Score (TRISS) has been the historical gold standard in survival prediction but its limitations are well-characterized. The present study used International Classification of Diseases 10(th) Revision (ICD-10) injury codes with machine learning approaches to develop models whose performance was compared to that of TRISS. METHODS: The 2015–2017 National Trauma Data Bank was used to identify patients following trauma-related admission. Injury codes from ICD-10 were grouped by clinical relevance into 1,495 variables. The TRISS score, which comprises the Injury Severity Score, age, mechanism (blunt vs penetrating) as well as highest 24-hour values for systolic blood pressure (SBP), respiratory rate (RR) and Glasgow Coma Scale (GCS) was calculated for each patient. A base eXtreme gradient boosting model (XGBoost), a machine learning technique, was developed using injury variables as well as age, SBP, RR, mechanism and GCS. Prediction of in-hospital survival and other in-hospital complications were compared between both models using receiver operating characteristic (ROC) and reliability plots. A complete XGBoost model, containing injury variables, vitals, demographic information and comorbidities, was additionally developed. RESULTS: Of 1,380,740 patients, 1,338,417 (96.9%) survived to discharge. Compared to survivors, those who died were older and had a greater prevalence of penetrating injuries (18.0% vs 9.44%). The base XGBoost model demonstrated a greater receiver-operating characteristic (ROC) than TRISS (0.950 vs 0.907) which persisted across sub-populations and secondary endpoints. Furthermore, it exhibited high calibration across all risk levels (R(2) = 0.998 vs 0.816). The complete XGBoost model had an exceptional ROC of 0.960. CONCLUSIONS: We report improved performance of machine learning models over TRISS. Our model may improve stratification of injury severity in clinical and quality improvement settings.
format Online
Article
Text
id pubmed-9612528
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-96125282022-10-28 ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction Tran, Zachary Verma, Arjun Wurdeman, Taylor Burruss, Sigrid Mukherjee, Kaushik Benharash, Peyman PLoS One Research Article BACKGROUND: Precise models are necessary to estimate mortality risk following traumatic injury to inform clinical decision making or quantify hospital performance. The Trauma and Injury Severity Score (TRISS) has been the historical gold standard in survival prediction but its limitations are well-characterized. The present study used International Classification of Diseases 10(th) Revision (ICD-10) injury codes with machine learning approaches to develop models whose performance was compared to that of TRISS. METHODS: The 2015–2017 National Trauma Data Bank was used to identify patients following trauma-related admission. Injury codes from ICD-10 were grouped by clinical relevance into 1,495 variables. The TRISS score, which comprises the Injury Severity Score, age, mechanism (blunt vs penetrating) as well as highest 24-hour values for systolic blood pressure (SBP), respiratory rate (RR) and Glasgow Coma Scale (GCS) was calculated for each patient. A base eXtreme gradient boosting model (XGBoost), a machine learning technique, was developed using injury variables as well as age, SBP, RR, mechanism and GCS. Prediction of in-hospital survival and other in-hospital complications were compared between both models using receiver operating characteristic (ROC) and reliability plots. A complete XGBoost model, containing injury variables, vitals, demographic information and comorbidities, was additionally developed. RESULTS: Of 1,380,740 patients, 1,338,417 (96.9%) survived to discharge. Compared to survivors, those who died were older and had a greater prevalence of penetrating injuries (18.0% vs 9.44%). The base XGBoost model demonstrated a greater receiver-operating characteristic (ROC) than TRISS (0.950 vs 0.907) which persisted across sub-populations and secondary endpoints. Furthermore, it exhibited high calibration across all risk levels (R(2) = 0.998 vs 0.816). The complete XGBoost model had an exceptional ROC of 0.960. CONCLUSIONS: We report improved performance of machine learning models over TRISS. Our model may improve stratification of injury severity in clinical and quality improvement settings. Public Library of Science 2022-10-27 /pmc/articles/PMC9612528/ /pubmed/36301826 http://dx.doi.org/10.1371/journal.pone.0276624 Text en © 2022 Tran et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Tran, Zachary
Verma, Arjun
Wurdeman, Taylor
Burruss, Sigrid
Mukherjee, Kaushik
Benharash, Peyman
ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title_full ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title_fullStr ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title_full_unstemmed ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title_short ICD-10 based machine learning models outperform the Trauma and Injury Severity Score (TRISS) in survival prediction
title_sort icd-10 based machine learning models outperform the trauma and injury severity score (triss) in survival prediction
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9612528/
https://www.ncbi.nlm.nih.gov/pubmed/36301826
http://dx.doi.org/10.1371/journal.pone.0276624
work_keys_str_mv AT tranzachary icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction
AT vermaarjun icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction
AT wurdemantaylor icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction
AT burrusssigrid icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction
AT mukherjeekaushik icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction
AT benharashpeyman icd10basedmachinelearningmodelsoutperformthetraumaandinjuryseverityscoretrissinsurvivalprediction