Skip to main content
main-content

01.12.2018 | Research article | Ausgabe 1/2018 Open Access

BMC Medical Informatics and Decision Making 1/2018

Combining information from a clinical data warehouse and a pharmaceutical database to generate a framework to detect comorbidities in electronic health records

Zeitschrift:
BMC Medical Informatics and Decision Making > Ausgabe 1/2018
Autoren:
Emmanuelle Sylvestre, Guillaume Bouzillé, Emmanuel Chazard, Cécil His-Mahier, Christine Riou, Marc Cuggia
Wichtige Hinweise

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1186/​s12911-018-0586-x) contains supplementary material, which is available to authorized users.

Abstract

Background

Medical coding is used for a variety of activities, from observational studies to hospital billing. However, comorbidities tend to be under-reported by medical coders. The aim of this study was to develop an algorithm to detect comorbidities in electronic health records (EHR) by using a clinical data warehouse (CDW) and a knowledge database.

Methods

We enriched the Theriaque pharmaceutical database with the French national Comorbidities List to identify drugs associated with at least one major comorbid condition and diagnoses associated with a drug indication. Then, we compared the drug indications in the Theriaque database with the ICD-10 billing codes in EHR to detect potentially missing comorbidities based on drug prescriptions. Finally, we improved comorbidity detection by matching drug prescriptions and laboratory test results. We tested the obtained algorithm by using two retrospective datasets extracted from the Rennes University Hospital (RUH) CDW. The first dataset included all adult patients hospitalized in the ear, nose, throat (ENT) surgical ward between October and December 2014 (ENT dataset). The second included all adult patients hospitalized at RUH between January and February 2015 (general dataset). We reviewed medical records to find written evidence of the suggested comorbidities in current or past stays.

Results

Among the 22,132 Common Units of Dispensation (CUD) codes present in the Theriaque database, 19,970 drugs (90.2%) were associated with one or several ICD-10 diagnoses, based on their indication, and 11,162 (50.4%) with at least one of the 4878 comorbidities from the comorbidity list. Among the 122 patients of the ENT dataset, 75.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 44.6% of the cases. Among the 4312 patients of the general dataset, 68.4% had at least one drug prescription without corresponding ICD-10 code. The comorbidity diagnoses suggested by the algorithm were confirmed in 20.3% of reviewed cases.

Conclusions

This simple algorithm based on combining accessible and immediately reusable data from knowledge databases, drug prescriptions and laboratory test results can detect comorbidities.
Zusatzmaterial
Additional file 1: List of excluded drugs with broad or imprecise indications according to their Anatomical Therapeutic Chemical (ATC) class. This table lists all drugs that were not included in the first step of the algorithm, with their ATC code and label. (DOCX 12 kb)
12911_2018_586_MOESM1_ESM.docx
Additional file 2: Algorithm Evaluation: Inter-observer agreement process. This file explains in detail inter-observer agreement process: the data used, all the different steps, the formalization, the process in case of disagreement between the experts. (DOCX 19 kb)
12911_2018_586_MOESM2_ESM.docx
Additional file 3: Characteristics of all ICD-10 codes suggested by the Theriaque database. This table describes the aggregated characteristics of all ICD-10 codes suggested by the algorithm for each dataset. The codes are separated between “Match” codes (codes added after expert review) and “Non-match” codes (codes that could not been added after expert review). (DOCX 15 kb)
12911_2018_586_MOESM3_ESM.docx
Additional file 4: Characteristics of the ICD-10 codes added after expert review. This table describes the aggregated characteristics of the ICD-10 codes added to each dataset after the manual review by the two experts. It also count the number of ICD-10 codes that were part of the CMA list. (DOCX 13 kb)
12911_2018_586_MOESM4_ESM.docx
Additional file 5: List of the ICD-10 codes added after expert review. This table lists all ICD-10 codes that were added after expert review, the number of stays were they were added, and specify if these codes are part of the CMA list. (DOCX 17 kb)
12911_2018_586_MOESM5_ESM.docx
Additional file 6: Ethics committee approval. This file (in French) is the official ethics committee approval for the study. (DOC 85 kb)
12911_2018_586_MOESM6_ESM.doc
Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 1/2018

BMC Medical Informatics and Decision Making 1/2018 Zur Ausgabe