Dataset Information

Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities.

ABSTRACT: The success of many population studies is determined by proper matching of cases to controls. Some of the confounding and bias that afflict electronic health record (EHR)-based observational studies may be reduced by creating effective methods for finding adequate controls. We implemented a method to match case and control populations to compensate for sparse and unequal data collection practices common in EHR data. We did this by matching the healthcare utilization of patients after observing that more complete data was collected on high healthcare utilization patients vs. low healthcare utilization patients. In our results, we show that many of the anomalous differences in population comparisons are mitigated using this matching method compared to other traditional age and gender-based matching. As an example, the comparison of the disease associations of ulcerative colitis and Crohn's disease show differences that are not present when the controls are chosen in a random or even a matched age/gender/race algorithm. In conclusion, the use of healthcare utilization-based matching algorithms to find adequate controls greatly enhanced the accuracy of results in EHR studies. Full source code and documentation of the control matching methods is available at https://community.i2b2.org/wiki/display/conmat/.

SUBMITTER: Castro VM

PROVIDER: S-EPMC4261034 | biostudies-literature | 2014 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities.

Castro Victor M VM Apperson W Kay WK Gainer Vivian S VS Ananthakrishnan Ashwin N AN Goodson Alyssa P AP Wang Taowei D TD Herrick Christopher D CD Murphy Shawn N SN

Journal of biomedical informatics 20140906

The success of many population studies is determined by proper matching of cases to controls. Some of the confounding and bias that afflict electronic health record (EHR)-based observational studies may be reduced by creating effective methods for finding adequate controls. We implemented a method to match case and control populations to compensate for sparse and unequal data collection practices common in EHR data. We did this by matching the healthcare utilization of patients after observing t ...[more]

PMID: 25196084

Similar Datasets

Project description:BACKGROUND:Standards-based clinical data normalization has become a key component of effective data integration and accurate phenotyping for secondary use of electronic healthcare records (EHR) data. HL7 Fast Healthcare Interoperability Resources (FHIR) is an emerging clinical data standard for exchanging electronic healthcare data and has been used in modeling and integrating both structured and unstructured EHR data for a variety of clinical research applications. The overall objective of this study is to develop and evaluate a FHIR-based EHR phenotyping framework for identification of patients with obesity and its multiple comorbidities from semi-structured discharge summaries leveraging a FHIR-based clinical data normalization pipeline (known as NLP2FHIR). METHODS:We implemented a multi-class and multi-label classification system based on the i2b2 Obesity Challenge task to evaluate the FHIR-based EHR phenotyping framework. Two core parts of the framework are: (a) the conversion of discharge summaries into corresponding FHIR resources - Composition, Condition, MedicationStatement, Procedure and FamilyMemberHistory using the NLP2FHIR pipeline, and (b) the implementation of four machine learning algorithms (logistic regression, support vector machine, decision tree, and random forest) to train classifiers to predict disease state of obesity and 15 comorbidities using features extracted from standard FHIR resources and terminology expansions. We used the macro- and micro-averaged precision (P), recall (R), and F1 score (F1) measures to evaluate the classifier performance. We validated the framework using a second obesity dataset extracted from the MIMIC-III database. RESULTS:Using the NLP2FHIR pipeline, 1237 clinical discharge summaries from the 2008 i2b2 obesity challenge dataset were represented as the instances of the FHIR Composition resource consisting of 5677 records with 16 unique section types. After the NLP processing and FHIR modeling, a set of 244,438 FHIR clinical resource instances were generated. As the results of the four machine learning classifiers, the random forest algorithm performed the best with F1-micro(0.9466)/F1-macro(0.7887) and F1-micro(0.9536)/F1-macro(0.6524) for intuitive classification (reflecting medical professionals' judgments) and textual classification (reflecting the judgments based on explicitly reported information of diseases), respectively. The MIMIC-III obesity dataset was successfully integrated for prediction with minimal configuration of the NLP2FHIR pipeline and machine learning models. CONCLUSIONS:The study demonstrated that the FHIR-based EHR phenotyping approach could effectively identify the state of obesity and multiple comorbidities using semi-structured discharge summaries. Our FHIR-based phenotyping approach is a first concrete step towards improving the data aspect of phenotyping portability across EHR systems and enhancing interpretability of the machine learning-based phenotyping algorithms.

Dataset Information

Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities.

Publications

Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets