AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
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 2018
Systematic Literature Review of Prescription Drug Monitoring Programs.
Prescription opioid abuse has become a serious national problem. To respond to the opioid epidemic, states have implemented prescription drug monitoring programs (PDMPs) to monitor and reduce opioid abuse. We conducted a systematic literature review to better understand the PDMP impact on reducing opioid abuse, improving prescriber practices, and how EHR integration has impacted PDMP usability. Lessons learned can help guide federal and state-based efforts to better respond to the opioid crisis.
-
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.
-
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
A Cross-Sectional Study of Prominent US Mobile Health Applications: Evaluating the Current Landscape.
Mobile health (mHealth) could offer unprecedented opportunity to provide medical support closer to the users. We have selected some relevant criteria to describe 100 apps from Google Play store and Apple's App Store's top suggestions in medical category. These characteristics were compared based on the paid or free nature of the apps, the target users: consumers or healthcare professionals, and the platform: Android or iOS. ⋯ Our study shows that even in top rated mHealth apps, a high proportion lacks some basic criteria regarding the quality of the apps including the presence of a privacy policy, describing content sources, participation of the target users in the app development, etc. Paid apps did not ensure better quality compared to free apps. The current mHealth market is not mature enough to be used widely and recommended by healthcare professionals.