Predicting Incident Adenocarcinoma of the Esophagus or Gastric Cardia Using Machine Learning of Electronic Health Records.
Electronic Health Records
Esophageal Neoplasms
Gastroesophageal Reflux Disease
Mass Screening
Stomach Neoplasms
Journal
Gastroenterology
ISSN: 1528-0012
Titre abrégé: Gastroenterology
Pays: United States
ID NLM: 0374630
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
received:
13
03
2023
revised:
11
07
2023
accepted:
09
08
2023
medline:
27
11
2023
pubmed:
20
8
2023
entrez:
19
8
2023
Statut:
ppublish
Résumé
Tools that can automatically predict incident esophageal adenocarcinoma (EAC) and gastric cardia adenocarcinoma (GCA) using electronic health records to guide screening decisions are needed. The Veterans Health Administration (VHA) Corporate Data Warehouse was accessed to identify Veterans with 1 or more encounters between 2005 and 2018. Patients diagnosed with EAC (n = 8430) or GCA (n = 2965) were identified in the VHA Central Cancer Registry and compared with 10,256,887 controls. Predictors included demographic characteristics, prescriptions, laboratory results, and diagnoses between 1 and 5 years before the index date. The Kettles Esophageal and Cardia Adenocarcinoma predictioN (K-ECAN) tool was developed and internally validated using simple random sampling imputation and extreme gradient boosting, a machine learning method. Training was performed in 50% of the data, preliminary validation in 25% of the data, and final testing in 25% of the data. K-ECAN was well-calibrated and had better discrimination (area under the receiver operating characteristic curve [AuROC], 0.77) than previously validated models, such as the Nord-Trøndelag Health Study (AuROC, 0.68) and Kunzmann model (AuROC, 0.64), or published guidelines. Using only data from between 3 and 5 years before index diminished its accuracy slightly (AuROC, 0.75). Undersampling men to simulate a non-VHA population, AUCs of the Nord-Trøndelag Health Study and Kunzmann model improved, but K-ECAN was still the most accurate (AuROC, 0.85). Although gastroesophageal reflux disease was strongly associated with EAC, it contributed only a small proportion of gain in information for prediction. K-ECAN is a novel, internally validated tool predicting incident EAC and GCA using electronic health records data. Further work is needed to validate K-ECAN outside VHA and to assess how best to implement it within electronic health records.
Sections du résumé
BACKGROUND & AIMS
OBJECTIVE
Tools that can automatically predict incident esophageal adenocarcinoma (EAC) and gastric cardia adenocarcinoma (GCA) using electronic health records to guide screening decisions are needed.
METHODS
METHODS
The Veterans Health Administration (VHA) Corporate Data Warehouse was accessed to identify Veterans with 1 or more encounters between 2005 and 2018. Patients diagnosed with EAC (n = 8430) or GCA (n = 2965) were identified in the VHA Central Cancer Registry and compared with 10,256,887 controls. Predictors included demographic characteristics, prescriptions, laboratory results, and diagnoses between 1 and 5 years before the index date. The Kettles Esophageal and Cardia Adenocarcinoma predictioN (K-ECAN) tool was developed and internally validated using simple random sampling imputation and extreme gradient boosting, a machine learning method. Training was performed in 50% of the data, preliminary validation in 25% of the data, and final testing in 25% of the data.
RESULTS
RESULTS
K-ECAN was well-calibrated and had better discrimination (area under the receiver operating characteristic curve [AuROC], 0.77) than previously validated models, such as the Nord-Trøndelag Health Study (AuROC, 0.68) and Kunzmann model (AuROC, 0.64), or published guidelines. Using only data from between 3 and 5 years before index diminished its accuracy slightly (AuROC, 0.75). Undersampling men to simulate a non-VHA population, AUCs of the Nord-Trøndelag Health Study and Kunzmann model improved, but K-ECAN was still the most accurate (AuROC, 0.85). Although gastroesophageal reflux disease was strongly associated with EAC, it contributed only a small proportion of gain in information for prediction.
CONCLUSIONS
CONCLUSIONS
K-ECAN is a novel, internally validated tool predicting incident EAC and GCA using electronic health records data. Further work is needed to validate K-ECAN outside VHA and to assess how best to implement it within electronic health records.
Identifiants
pubmed: 37597631
pii: S0016-5085(23)04890-4
doi: 10.1053/j.gastro.2023.08.011
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1420-1429.e10Subventions
Organisme : NIDDK NIH HHS
ID : K23 DK129784
Pays : United States
Informations de copyright
Copyright © 2023 AGA Institute. All rights reserved.