In secondary analysis of electronic health records, a crucial task consists in correctly identifying the patient cohort under investigation. In many cases, the most valuable and relevant information for an accurate classification of medical conditions exist only in clinical narratives. Therefore, it is necessary to use natural language processing (NLP) techniques to extract and evaluate these narratives. The most commonly used approach to this problem relies on extracting a number of clinician-defined medical concepts from text and using machine learning techniques to identify whether a particular patient has a certain condition. However, recent advances in deep learning and NLP enable models to learn a rich representation of (medical) language. Convolutional neural networks (CNN) for text classification can augment the existing techniques by leveraging the representation of language to learn which phrases in a text are relevant for a given medical condition. In this work, we compare concept extraction based methods with CNNs and other commonly used models in NLP in ten phenotyping tasks using 1,610 discharge summaries from the MIMIC-III database. We show that CNNs outperform concept extraction based methods in almost all of the tasks, with an improvement in F1-score of up to 26 and up to 7 percentage points in area under the ROC curve (AUC). We additionally assess the interpretability of both approaches by presenting and evaluating methods that calculate and extract the most salient phrases for a prediction. The results indicate that CNNs are a valid alternative to existing approaches in patient phenotyping and cohort identification, and should be further investigated. Moreover, the deep learning approach presented in this paper can be used to assist clinicians during chart review or support the extraction of billing codes from text by identifying and highlighting relevant phrases for various medical conditions.
Introduction Transgender individuals are underserved within the health care system but might increasingly seek urologic care as insurers expand coverage for medical and surgical gender transition. Aim To evaluate urology residents' exposure to transgender patient care and their perceived importance of transgender surgical education. Methods Urology residents from a representative sample of U.S. training programs were asked to complete a cross-sectional survey from January through March 2016. Main Outcome Measures Respondents were queried regarding demographics, transgender curricular exposure (didactic vs clinical), and perceived importance of training opportunities in transgender patient care. Results In total, 289 urology residents completed the survey (72% response rate). Fifty-four percent of residents reported exposure to transgender patient care, with more residents from Western (74%) and North Central (72%) sections reporting exposure (P ≤ .01). Exposure occurred more frequently through direct patient interaction rather than through didactic education (psychiatric, 23% vs 7%, P < .001; medical, 17% vs 6%, P < .001; surgical, 33% vs 11%, P < .001). Female residents placed greater importance on gender-confirming surgical training than did their male colleagues (91% vs 70%, P < .001). Compared with Western section residents (88%), those from South Central (60%, P = .002), Southeastern (63%, P = .002), and Mid-Atlantic (63%, P = .003) sections less frequently viewed transgender-related surgical training as important. Most residents (77%) stated transgender-related surgical training should be offered in fellowships. Conclusion Urology resident exposure to transgender patient care is regionally dependent. Perceived importance of gender-confirming surgical training varies by sex and geography. A gap exists between the direct transgender patient care urology residencies provide and the didactic transgender education they receive.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.