AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2018
Social Responsibility Practices of EHR Vendors: An Analysis of Disclosures in Annual Corporate Reports and Websites.
Socially desirable outcomes within healthcare IT depend not only on the ethical behavior of individuals, but also on the actions and policies of large corporations. It is therefore important to have public accountability mechanisms that can be applied to corporations. ⋯ The SASB standards and methodology were used to assess disclosures in the annual shareholder reports and websites of the top EHR vendors. The results showed a very low rate of meaningful disclosure.
-
AMIA Annu Symp Proc · Jan 2018
A Computable Phenotype for Acute Respiratory Distress Syndrome Using Natural Language Processing and Machine Learning.
Acute Respiratory Distress Syndrome (ARDS) is a syndrome of respiratory failure that may be identified using text from radiology reports. The objective of this study was to determine whether natural language processing (NLP) with machine learning performs better than a traditional keyword model for ARDS identification. Linguistic pre-processing of reports was performed and text features were inputs to machine learning classifiers tuned using 10-fold cross-validation on 80% of the sample size and tested in the remaining 20%. ⋯ The traditional model had an accuracy of 67.3% (95% CI: 58.3-76.3) with a positive predictive value (PPV) of 41.7% (95% CI: 27.7-55.6). The best NLP model had an accuracy of 83.0% (95% CI: 75.9-90.2) with a PPV of 71.4% (95% CI: 52.1-90.8). A computable phenotype for ARDS with NLP may identify more cases than the traditional model.
-
AMIA Annu Symp Proc · Jan 2017
Quantifying the Impact of Trainee Providers on Outpatient Clinic Workflow using Secondary EHR Data.
Providers today face productivity challenges including increased patient loads, increased clerical burdens from new government regulations and workflow impacts of electronic health records (EHR). Given these factors, methods to study and improve clinical workflow continue to grow in importance. ⋯ The purpose of this study is to demonstrate that secondary EHR data can be used to quantify that impact, with potentially important results for clinic efficiency and provider reimbursement models. Key findings from this study are that (1) Secondary EHR data can be used to reflect in clinic trainee activity, (2) presence of trainees, particularly in high-volume clinic sessions, is associated with longer session lengths, and (3) The timing of trainee appointments within clinic sessions impacts the session length.
-
AMIA Annu Symp Proc · Jan 2017
Big data in healthcare - the promises, challenges and opportunities from a research perspective: A case study with a model database.
Recent advances in data collection during routine health care in the form of Electronic Health Records (EHR), medical device data (e.g., infusion pump informatics, physiological monitoring data, and insurance claims data, among others, as well as biological and experimental data, have created tremendous opportunities for biological discoveries for clinical application. However, even with all the advancement in technologies and their promises for discoveries, very few research findings have been translated to clinical knowledge, or more importantly, to clinical practice. In this paper, we identify and present the initial work addressing the relevant challenges in three broad categories: data, accessibility, and translation. These issues are discussed in the context of a widely used detailed database from an intensive care unit, Medical Information Mart for Intensive Care (MIMIC III) database.
-
AMIA Annu Symp Proc · Jan 2017
Comparative StudyClinical Named Entity Recognition Using Deep Learning Models.
Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. ⋯ The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER.