AMIA ... Annual Symposium proceedings. AMIA Symposium最新文献

QuizTime is an innovative, asynchronous, spaced learning platform that provides just-in-time learning to increase knowledge and retention. QuizTime was created in 2015, and since then, its effectiveness has been tested and studied across multiple healthcare learning interventions. This paper describes the importance of spaced learning in knowledge acquisition and retention, and the motivation behind the creation of the innovative QuizTime platform. We demonstrate the usefulness of this platform, as shown by multiple case studies using QuizTime, to increase and engage medical students, residents, physicians and health care providers with new quizzes and interventions.

Low-yield repetitive laboratory diagnostics burden patients and inflate cost of care. In this study, we assess whether stability in repeated laboratory diagnostic measurements is predictable with uncertainty estimates using electronic health record data available before the diagnostic is ordered. We use probabilistic regression to predict a distribution of plausible values, allowing use-time customization for various definitions of "stability" given dynamic ranges and clinical scenarios. After converting distributions into "stability" scores, the models achieve a sensitivity of 29% for white blood cells, 60% for hemoglobin, 100% for platelets, 54% for potassium, 99% for albumin and 35% for creatinine for predicting stability at 90% precision, suggesting those fractions of repetitive tests could be reduced with low risk of missing important changes. The findings demonstrate the feasibility of using electronic health record data to identify low-yield repetitive tests and offer personalized guidance for better usage of testing while ensuring high quality care.

Medications such as buprenorphine-naloxone are among the most effective treatments for opioid use disorder, but limited retention in treatment limits long-term outcomes. In this study, we assess the feasibility of a machine learning model to predict retention vs. attrition in medication for opioid use disorder (MOUD) treatment using electronic medical record data including concepts extracted from clinical notes. A logistic regression classifier was trained on 374 MOUD treatments with 68% resulting in potential attrition. On a held-out test set of 157 events, the full model achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 (95% CI: 0.64-0.90) and AUROC of 0.74 (95% CI: 0.62-0.87) with a limited model using only structured EMR data. Risk prediction for opioid MOUD retention vs. attrition is feasible given electronic medical record data, even without necessarily incorporating concepts extracted from clinical notes.

For older patients, falls are the leading cause offatal and nonfatal injuries. Guidelines recommend that at-risk older adults are referred to appropriate fall-prevention exercise programs, but many do not receive support for fall-risk management in the primary care setting. Advances in health information technology may be able to address this gap. This article describes the development and usability testing of a clinical decision support (CDS) tool for fall prevention exercise. Using rapid qualitative analysis and human-centered design, our team developed and tested the usability of our CDS prototype with primary care team members. Across 31 Health-Information Technology Usability Evaluation Scale surveys, our CDS prototype received a median score of 5.0, mean (SD) of 4.5 (0.8), and a range of 4.1-4.9. This study highlights the features and usability offall prevention CDS for helping primary care providers deliver patient-centeredfall prevention care.

With increased application of natural language processing (NLP) in medicine, many NLP models are being developed for uncovering relevant clinical features from electronic health records. Temporal information plays a key role in understanding the context, significance, and interpretation of medical concepts extracted from clinical notes. This is particularly true in situations where the behavior, value, or status of a medical concept changes over time. In this paper, we introduce a systematic framework, NLP annotation-Relaxation-Generation (NRG). NRG compiles incidents of medical concept changes from status annotations and timestamps of multiple clinical notes. We demonstrate the effectiveness of the NRG pipeline by applying it to two medical concepts related to patients with inflammatory bowel disease: extra-intestinal manifestations and medications. We show that the NRG pipeline offers not only insights into medical concept changes over time, but can help convey longitudinal changes in clinical features at both individual and population level.

Knowledge of social determinants of health (SDOH), which refer to nonmedical factors influencing health outcomes, can help providers improve patient care. However, SDOH are often documented in unstructured notes, making them more inaccessible. Although previous works have attempted SDOH extraction from clinical notes, most efforts defined SDOH more narrowly and focused on the note's social history (SH) section, where social factors are traditionally documented. Here, we introduce a new SDOH dataset covering a broad range of SDOH content that is annotated over entire notes. We characterize what, where, and how SDOH information is documented in clinical text, present baseline systems using a token classification and generative approach, and investigate whether training only on the SH section can effectively extract SDOH from the entire note. The final dataset, consisting of 2,007 annotations covering 7 open-ended SDOH domains over 500 notes, will be publicly released to encourage further research in this area.

The HerediGene Population Study is a large research study focused on identifying new genetic biomarkers for disease prevention, diagnosis, prognosis, and development of new therapeutics. A substantial IT infrastructure evolved to reach enrollment targets and return results to participants. More than 170,000 participants have been enrolled in the study to date, with 5.87% of those whole genome sequenced and 0.46% of those genotyped harboring pathogenic variants. Among other purposes, this infrastructure supports: (1) identifying candidates from clinical criteria, (2) monitoring for qualifying clinical events (e.g., blood draw), (3) contacting candidates, (4) obtaining consent electronically, (5) initiating lab orders, (6) integrating consent and lab orders into clinical workflow, (7) de-identifying samples and clinical data, (8) shipping/transmitting samples and clinical data, (9) genotyping/sequencing samples, (10) and re-identifying and returning results for participants where applicable. This study may serve as a model for similar genomic research and precision public health initiatives.

Electronic health records (EHRs) contain a wealth of information that can be used to further precision health. One particular data element in EHRs that is not only under-utilized but oftentimes unaccounted for is missing data. However, missingness can provide valuable information about comorbidities and best practices for monitoring patients, which could save lives and reduce burden on the healthcare system. We characterize patterns of missing data in laboratory measurements collected at the University of Pennsylvania Hospital System from long-term COVID-19 patients and focus on the changes in these patterns between 2020 and 2021. We investigate how these patterns are associated with comorbidities such as acute respiratory distress syndrome (ARDS), and 90-day mortality in ARDS patients. This work displays how knowledge and experience can change the way clinicians and hospitals manage a novel disease. It can also provide insight into best practices when it comes to patient monitoring to improve outcomes.

Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generalize across healthcare organizations is challenging. This is due, in part, to the inherent siloed nature of these organizations and patient privacy requirements. To address this problem, we illustrate how split learning can enable collaborative training of deep learning models across disparate and privately maintained health datasets, while keeping the original records and model parameters private. We introduce a new privacy-preserving distributed learning framework that offers a higher level of privacy compared to conventional federated learning. We use several biomedical imaging and electronic health record (EHR) datasets to show that deep learning models trained via split learning can achieve highly similar performance to their centralized and federated counterparts while greatly improving computational efficiency and reducing privacy risks.