Showing papers in "Journal of the American Medical Informatics Association in 2020"

TL;DR: The role that telehealth has played in transforming healthcare delivery during the 3 phases of the U.S. COVID-19 pandemic is described and how people, process, and technology work together to support a successful telehealth transformation is examined.

TL;DR: The COVID-19 pandemic has driven rapid expansion of telemedicine use for urgent care and nonurgent care visits beyond baseline periods, and this reflects an important change in teleomedicine that other institutions facing the COVID the pandemic should anticipate.

TL;DR: In early 2020, talks of preparation for coronavirus disease 2019 (COVID-19) were furiously circulating around the healthcare system nationwide, and having seen what was occurring in China, and later in Italy, the need for an immediate adaptation of the clinical care delivery system was clear.

TL;DR: The design and implementation of EHR-based rapid screening processes, laboratory testing, clinical decision support, reporting tools, and patient-facing technology related to COVID-19 are outlined.

TL;DR: Deep learning has not yet fully penetrated clinical NLP and is growing rapidly, but growing acceptance of deep learning as a baseline for NLP research, and of DL-based NLP in the medical community is shown.

TL;DR: A governance model is proposed that aims to not only address the ethical and regulatory issues that arise out of the application of AI in health care, but also stimulate further discussion about governance ofAI in health health care.

TL;DR: Specific examples of telehealth efforts that have been implemented in a large rural healthcare system in response to the COVID-19 pandemic are provided and how the massive shift to telehealth and reliance on virtual connections in these times of social isolation may impact rural health disparities is described.

TL;DR: Remote patient monitoring appears to be an effective approach for managing CO VID-19 symptoms at home while minimizing COVID-19 exposure and in-person healthcare utilization.

TL;DR: This challenge shows that clinical concept extraction and relation classification systems have a high performance for many concept types, but significant improvement is still required for ADEs and Reasons.

TL;DR: It is found that XAI evaluation in medicine has not been adequately and formally practiced, andple opportunities exist to advance XAI research in medicine.

TL;DR: An introductory tutorial on calibration measurements and calibration models for predictive models using existing R packages and custom implemented code in R on real and simulated data to help informaticians and software engineers understand the role that calibration plays in the evaluation of a clinical predictive model.

TL;DR: MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies is presented.

TL;DR: Patient self-triage tools integrated into electronic health record systems have the potential to greatly improve triage efficiency and prevent unnecessary visits during the COVID-19 pandemic.

TL;DR: As organizations increasingly rely on objective, vendor-defined EHR measures to design and evaluate interventions to reduce burnout, the findings point to the measures that should be targeted.

TL;DR: TREC-COVID differs from traditional IR shared task evaluations with special considerations for the expected users, IR modality considerations, topic development, participant requirements, assessment process, relevance criteria, evaluation metrics, iteration process, projected timeline, and the implications of data use as a post-task test collection.

TL;DR: The spectrum of COVID-19 symptoms identified from Twitter may complement those identified in clinical settings, and create a symptom lexicon for future research.

TL;DR: Demographic factors, including race/ethnicity and age, were significantly predictive of telehealth use, and patients 65+ had significantly higher odds of using either ER or office visits versus telehealth.

TL;DR: The available evidence shows that apps pose clinical risks to consumers and involvement of consumers, regulators, and healthcare professionals in development and testing can improve quality.

TL;DR: The literature provides early and rapidly growing evidence that integrating individual- level SDoH into EHRs can assist in risk assessment and predicting healthcare utilization and health outcomes, which further motivates efforts to collect and standardize patient-level S doH information.

TL;DR: A pathway for efficiently increasing capacity of remote pediatric enrollment for telehealth while fulfilling privacy, security, and convenience concerns is described from the experience of a large academic medical center.

TL;DR: A digital chatbot-based workflow is designed and implemented that has reduced wait times for employees entering hospitals during shift changes, allowed for physical distancing at hospital entrances, prevented higher-risk individuals from coming to work, and provided healthcare leaders with robust, real-time data for make staffing decisions.

TL;DR: Electronic PPE is defined as an approach using telemedicine tools to perform electronic medical screening exams while satisfying the Emergency Medical Treatment and Labor Act, which has the potential to conserve PPE and protect providers while maintaining safe standards for medical screenings exams in the emergency department for low-risk patients in whom COVID-19 is suspected.

TL;DR: There is an urgent need to address latent biases before the widespread implementation of AI algorithms in clinical practice, and several ways of managing them are proposed.

TL;DR: Deep learning approaches for extracting medications and their attributes such as ADEs, and demonstrated its superior performance compared with traditional machine learning algorithms, indicating its uses in broader NER and RC tasks in the medical domain.

TL;DR: The efficiency of transformer-based models for clinical concept extraction is demonstrated and an open-source package with pretrained clinical models to facilitate concept extraction and other downstream natural language processing (NLP) tasks in the medical domain is developed.

TL;DR: Physician understanding, explainability, and trust in ML risk calculators are related and physicians preferred ML outputs accompanied by model-agnostic explanations but the explainability method did not alter intended physician behavior.

TL;DR: The literature describing clinical reasoning ontology (CRO)–based clinical decision support systems (CDSSs) is described and the medical knowledge and reasoning concepts and their properties within these ontologies are identified to guide future research.

TL;DR: Proposed changes to privacy regulations such as the Health Insurance Portability and Accountability Act are discussed designed to let health information seamlessly and frictionlessly flow among the health entities that need to collaborate on treatment of patients and, also, allow it to flow to researchers trying to limit its impacts.

TL;DR: The COVID-19 Watcher can provide the public with real-time updates of outbreaks in their area and aggregates data from multiple resources that track CO VID-19 and visualizes them through an interactive, online dashboard.

TL;DR: Analysis showed that by using latent Drug-Drug interactions, the proposed relation extraction system was able to significantly improve the performance of non–Drug-Drug pairs in EHRs.