Web-based Real-Time Case Finding for the Population Health Management of Patients With Diabetes Mellitus: A Prospective Validation of the Natural Language Processing–Based Algorithm With Statewide Electronic Medical Records

Abstract

BackgroundDiabetes case finding based on structured medical records does not fully identify diabetic patients whose medical histories related to diabetes are available in the form of free text. Manual chart reviews have been used but involve high labor costs and long latency.ObjectiveThis study developed and tested a Web-based diabetes case finding algorithm using both structured and unstructured electronic medical records (EMRs).MethodsThis study was based on the health information exchange (HIE) EMR database that covers almost all health facilities in the state of Maine, United States. Using narrative clinical notes, a Web-based natural language processing (NLP) case finding algorithm was retrospectively (July 1, 2012, to June 30, 2013) developed with a random subset of HIE-associated facilities, which was then blind tested with the remaining facilities. The NLP-based algorithm was subsequently integrated into the HIE database and validated prospectively (July 1, 2013, to June 30, 2014).ResultsOf the 935,891 patients in the prospective cohort, 64,168 diabetes cases were identified using diagnosis codes alone. Our NLP-based case finding algorithm prospectively found an additional 5756 uncodified cases (5756/64,168, 8.97% increase) with a positive predictive value of .90. Of the 21,720 diabetic patients identified by both methods, 6616 patients (6616/21,720, 30.46%) were identified by the NLP-based algorithm before a diabetes diagnosis was noted in the structured EMR (mean time difference = 48 days).ConclusionsThe online NLP algorithm was effective in identifying uncodified diabetes cases in real time, leading to a significant improvement in diabetes case finding. The successful integration of the NLP-based case finding algorithm into the Maine HIE database indicates a strong potential for application of this novel method to achieve a more complete ascertainment of diagnoses of diabetes mellitus.

Evaluation of provider documentation patterns as a tool to deliver ongoing patient‐centred diabetes education and support

“…Compared with prior studies of clinic notes of people with DM that employed NLP techniques, our study adopted manual coding for the clinic notes and conducted regular group reviews. We believe this strategy allowed for the accuracy of coding to be unaffected by complicated sentences, incomplete sentences, acronyms and abbreviations used by healthcare providers (Figure ).…”

“…There have been limited studies analysing the clinic notes of people with DM . These studies focused on applying natural language processing (NLP) for information extraction, such as identifying people with type 2 DM with a specific phenotype, estimating the occurrence of hypoglycaemia and extracting the lab test results .…”

“…These studies focused on applying natural language processing (NLP) for information extraction, such as identifying people with type 2 DM with a specific phenotype, estimating the occurrence of hypoglycaemia and extracting the lab test results . However, limitations exist when NLP techniques were used in these studies, such as disagreement with manual classification, decreasing accuracy with semantically complex sentences, having difficulty distinguishing acronyms and abbreviations with different meanings and demonstrating successes in specific research settings . Considering the lack of NLP applications for information discovery in diabetes education using EHR physician note sections, we opted to manually code clinic notes in this study as a feasibility study.…”

Defining and characterizing the critical transition state prior to the type 2 diabetes disease

“…Changes in clinical status is then based on the detection of perturbations in the frequencies and measures of specific clinical events and laboratory test results involved in several key disease-related or other specific clinical pathways [16–22]. Thus, EMR analytics can reveal crucial information that is closely related to the disease progression or outcomes of targeted therapeutics.…”

Augmenting Qualitative Text Analysis with Natural Language Processing: Methodological Study (Preprint)

“…NLP is an area of research and application that explores how computers can be used to understand and manipulate natural language text or speech to accomplish useful tasks [3]. It allows for substantially larger text databases than typical qualitative analysis methods and has been applied to data from electronic health records [4,5], PubMed [6], social media data [7], and text messages [8]. However, research examining the methodological merits of NLP techniques is necessary to further consider NLP as a feasible and high quality approach.…”