This review reports the user experience of symptom checkers, aiming to characterize users studied in the existing literature, identify the aspects of user experience of symptom checkers that have been studied, and offer design suggestions. Our literature search resulted in 31 publications. We found that (1) most symptom checker users are relatively young; (2) eight relevant aspects of user experience have been explored, including motivation, trust, acceptability, satisfaction, accuracy, usability, safety/security, and functionality; (3) future symptom checkers should improve their accuracy, safety, and usability. Although many facets of user experience have been explored, methodological challenges exist and some important aspects of user experience remain understudied. Further research should be conducted to explore users' needs and the context of use. More qualitative and mixed-method studies are needed to understand actual users' experiences in the future.
The emergence of COVID19 created incredible worldwide challenges but offers unique opportunities to understand the physiology of its risk factors and their interactions with complex disease conditions, such as metabolic syndrome. Epidemiological analysis powered by topological data analysis (TDA) is a novel approach to uncover these clinically relevant interactions. Here TDA utilized Explorys data to discover associations among severe COVID19 and metabolic syndrome, and it explored the probative value of drug prescriptions to capture the involvement of RAAS and hypertension with COVID19 as well as modification of risk factor impact by hyperlipidemia on severe COVID19.
The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care.
Background Therapeutic duplication, the presence of multiple agents prescribed for the same indication without clarification for when each should be used, can contribute to serious medical errors. Joint Commission standards require that orders contain clarifying information about when each order should be given. In our system, as needed (PRN) acetaminophen and ibuprofen orders are major contributors to therapeutic duplication.Objective The objective of this study is to design and evaluate effectiveness of clinical decision support (CDS) to reduce therapeutic duplication with acetaminophen and ibuprofen orders.Methods This study was done in a pediatric health system with three freestanding hospitals. We iteratively designed and implemented two CDS strategies aimed at reducing the therapeutic duplication with these agents: (1) interruptive alert prompting clinicians for clarifying PRN comments at order entry and (2) addition of discrete "first-line" and "second-line" PRN reasons to orders. Therapeutic duplications were measured by manual review of orders for 30-day periods before and after each intervention and 6 months later.Results Therapeutic duplications decreased from 1,485 in the 30 days prior to the first alert implementation to 818 in the 30 days after but rose back to 1,208 in the 30 days prior to the second intervention. After discrete reasons were added to the order, therapeutic duplication decreased to 336 in the immediate 30 days and 6 months later remained at 277. Alerts firing rates decreased from 76.0 per 1,000 PRN acetaminophen or ibuprofen orders to 42.9 after the second intervention.Conclusion Interruptive alerts may reduce therapeutic duplication but are associated with high rates of user frustration and alert fatigue. Leveraging discrete PRN reasons for "first line" and "second line" produced a greater reduction in therapeutic duplication as well as fewer interruptive alerts and less manual entry for providers.
Objective Understanding public discourse on emergency use of unproven therapeutics is essential to monitor safe use and combat misinformation. We developed a natural language processing-based pipeline to understand public perceptions of and stances on coronavirus disease 2019 (COVID-19)-related drugs on Twitter across time. Methods This retrospective study included 609 189 US-based tweets between January 29, 2020 and November 30, 2021 on 4 drugs that gained wide public attention during the COVID-19 pandemic: (1) Hydroxychloroquine and Ivermectin, drug therapies with anecdotal evidence; and (2) Molnupiravir and Remdesivir, FDA-approved treatment options for eligible patients. Time-trend analysis was used to understand the popularity and related events. Content and demographic analyses were conducted to explore potential rationales of people's stances on each drug. Results Time-trend analysis revealed that Hydroxychloroquine and Ivermectin received much more discussion than Molnupiravir and Remdesivir, particularly during COVID-19 surges. Hydroxychloroquine and Ivermectin were highly politicized, related to conspiracy theories, hearsay, celebrity effects, etc. The distribution of stance between the 2 major US political parties was significantly different (P < .001); Republicans were much more likely to support Hydroxychloroquine (+55%) and Ivermectin (+30%) than Democrats. People with healthcare backgrounds tended to oppose Hydroxychloroquine (+7%) more than the general population; in contrast, the general population was more likely to support Ivermectin (+14%). Conclusion Our study found that social media users with have different perceptions and stances on off-label versus FDA-authorized drug use across different stages of COVID-19, indicating that health systems, regulatory agencies, and policymakers should design tailored strategies to monitor and reduce misinformation for promoting safe drug use. Our analysis pipeline and stance detection models are made public at .https://github.com/ningkko/COVID-drug.
OBJECTIVE:The aim of this study was to explore the state of health information technology (HIT) usability evaluation in Africa. MATERIALS AND METHODS:We searched three electronic databases: PubMed, Embase, and Association for Computing Machinery. We categorized the stage of evaluations, the type of interactions assessed, and methods applied using Stead's System Development Life Cycle (SDLC) and Bennett and Shackel's usability models. RESULTS:Analysis of 73 of 1002 articles that met inclusion criteria reveals that HIT usability evaluations in Africa have increased in recent years and mainly focused on later SDLC stage (stages 4 and 5) evaluations in sub-Saharan Africa. Forty percent of the articles examined system-user-task-environment (type 4) interactions. Most articles used mixed methods to measure usability. Interviews and surveys were often used at each development stage, while other methods, such as quality-adjusted life year analysis, were only found at stage 5. Sixty percent of articles did not include a theoretical model or framework. DISCUSSION:The use of multistage evaluation and mixed methods approaches to obtain a comprehensive understanding HIT usability is critical to ensure that HIT meets user needs. CONCLUSIONS:Developing and enhancing usable HIT is critical to promoting equitable health service delivery and high-quality care in Africa. Early-stage evaluations (stages 1 and 2) and interactions (types 0 and 1) should receive special attention to ensure HIT usability prior to implementing HIT in the field.
Though electronic health record (EHR) systems are a rich repository of clinical information with large potential, the use of EHR-based phenotyping algorithms is often hindered by inaccurate diagnostic records, the presence of many irrelevant features, and the requirement for a human-labeled training set. In this paper, we describe a knowledge-driven online multimodal automated phenotyping (KOMAP) system that i) generates a list of informative features by an online narrative and codified feature search engine (ONCE) and ii) enables the training of a multimodal phenotyping algorithm based on summary data. Powered by composite knowledge from multiple EHR sources, online article corpora, and a large language model, features selected by ONCE show high concordance with the state-of-the-art AI models (GPT4 and ChatGPT) and encourage large-scale phenotyping by providing a smaller but highly relevant feature set. Validation of the KOMAP system across four healthcare centers suggests that it can generate efficient phenotyping algorithms with robust performance. Compared to other methods requiring patient-level inputs and gold-standard labels, the fully online KOMAP provides a significant opportunity to enable multi-center collaboration.
Our objective was to detect common barriers to post-acute care (B2PAC) among hospitalized older adults using natural language processing (NLP) of clinical notes from patients discharged home when a clinical decision support system recommended post-acute care. We annotated B2PAC sentences from discharge planning notes and developed an NLP classifier to identify the highest-value B2PAC class (negative patient preferences). Thirteen machine learning models were compared with Amazon's AutoGluon deep learning model. The study included 594 acute care notes from 100 patient encounters (1156 sentences contained 11 B2PAC) in a large academic health system. The most frequent and modifiable B2PAC class was negative patient preferences (18.3%). The best supervised model was Extreme Gradient Boosting (F1: 0.859), but the deep learning model performed better (F1: 0.916). Alerting clinicians of negative patient preferences early in the hospitalization can prompt interventions such as patient education to ensure patients receive the right level of care and avoid negative outcomes.
Objective:Early and accurate prediction of patients at risk of readmission is key to reducing costs and improving outcomes. LACE is a widely used score to predict 30-day readmissions. We examine whether adding social determinants of health (SDOH) to LACE can improve its predictive performance. Methods:This is a retrospective study that included all inpatient encounters in the state of Maryland in 2019. We constructed predictive models by fitting Logistic Regression (LR) on LACE and different sets of SDOH predictors. We used the area under the curve (AUC) to evaluate discrimination and SHapley Additive exPlanations values to assess feature importance. Results:Our study population included 316 558 patients of whom 35 431 (11.19%) patients were readmitted after 30 days. Readmitted patients had more challenges with individual-level SDOH and were more likely to reside in communities with poor SDOH conditions. Adding a combination of individual and community-level SDOH improved LACE performance from AUC = 0.698 (95% CI [0.695-0.7]; ref) to AUC = 0.708 (95% CI [0.705-0.71]; P < .001). The increase in AUC was highest in black patients (+1.6), patients aged 65 years or older (+1.4), and male patients (+1.4). Discussion:We demonstrated the value of SDOH in improving the LACE index. Further, the additional predictive value of SDOH on readmission risk varies by subpopulations. Vulnerable populations like black patients and the elderly are likely to benefit more from the inclusion of SDOH in readmission prediction. Conclusion:These findings provide potential SDOH factors that health systems and policymakers can target to reduce overall readmissions.
Background Recognition of the patient and family's diverse backgrounds and language preference is critical for communicating effectively. In our hospital's electronic health record, a patient or family's identified language for communication is documented in a discrete field known as “preferred language.” This field serves as an interdepartmental method to identify patients with a non-English preferred language, creating a bolded banner for non-English speakers easily identifiable by health care professionals. Despite the importance of documenting preferred language to facilitate equitable care, this field is often blank. Objectives Using the Institute for Healthcare Improvement's Model for Improvement, our team sought to increase preferred language documentation within the neonatal intensive care unit (NICU) from a baseline of 74% in September 2021 to above 90% within 6 months. Methods A multidisciplinary team was assembled to address preferred language documentation. Our team incorporated guidance regarding preferred language documentation into a novel clinical decision support (CDS) tool aimed at addressing various safety and quality measures within the NICU. Our primary outcome metric was documentation of family's preferred language. Process measures included overall compliance with the CDS tool. A secondary outcome was the assessment of preferred language documentation accuracy. Results The average rate of preferred language documentation increased from a baseline of 74 to 92% within 6 months and is currently sustained at 96%. Moreover, our follow-up assessments found that 100% of a random sample of contacted patients (n = 88) had their language preferences documented correctly. Overall compliance with the CDS tool remained at 85% throughout the project. Conclusion Using a quality improvement framework coupled with a CDS initiative, our team was able to successfully and accurately improve preferred language documentation in our NICU. Future projects include strategies for more equitable care for patients with non-English preferences such as improved interpreter usage and discharge instructions in their preferred language.
Smart portable devices- smartphones and smartwatches- are rapidly being adopted by the general population, which has brought forward an opportunity to use the large volumes of physiological, behavioral, and activity data continuously being collected by these devices in naturalistic settings to perform research, monitor health, and track disease. While these data can serve to revolutionize health monitoring in research and clinical care, minimal research has been conducted to understand what motivates people to use these devices and their interest and comfort in sharing the data. In this study, we aimed to characterize the ownership and usage of smart devices among patients from an expansive academic health system in the southeastern US and understand their willingness to share data collected by the smart devices. We conducted an electronic survey of participants from an online patient advisory group around smart device ownership, usage, and data sharing. Out of the 3021 members of the online patient advisory group, 1368 (45%) responded to the survey, with 871 female (64%), 826 and 390 White (60%) and Black (29%) participants, respectively, and a slight majority (52%) age 58 and older. Most of the respondents (98%) owned a smartphone and the majority (59%) owned a wearable. In this population, people who identify as female, Hispanic, and Generation Z (age 18–25), and those completing higher education and having full-time employment, were most likely to own a wearable device compared to their demographic counterparts. 50% of smart device owners were willing to share and 32% would consider sharing their smart device data for research purposes. The type of activity data they are willing to share varies by gender, age, education, and employment. Findings from this study can be used to design both equitable and cost-effective digital health studies, leveraging personally-owned smartphones and wearables in representative populations, ultimately enabling the development of equitable digital health technologies.
OBJECTIVE:To analyze how physician clinical note length and composition relate to electronic health record (EHR)-based measures of burden and efficiency that have been tied to burnout. DATA SOURCES AND STUDY SETTING:Secondary EHR use metadata capturing physician-level measures from 203,728 US-based ambulatory physicians using the Epic Systems EHR between September 2020 and May 2021. STUDY DESIGN:In this cross-sectional study, we analyzed physician clinical note length and note composition (e.g., content from manual or templated text). Our primary outcomes were three time-based measures of EHR burden (time writing EHR notes, time in the EHR after-hours, and EHR time on unscheduled days), and one measure of efficiency (percent of visits closed in the same day). We used multivariate regression to estimate the relationship between our outcomes and note length and composition. DATA EXTRACTION:Physician-week measures of EHR usage were extracted from Epic's Signal platform used for measuring provider EHR efficiency. We calculated physician-level averages for our measures of interest and assigned physicians to overall note length deciles and note composition deciles from six sources, including templated text, manual text, and copy/paste text. PRINCIPAL FINDINGS:Physicians in the top decile of note length demonstrated greater burden and lower efficiency than the median physician, spending 39% more time in the EHR after hours (p < 0.001) and closing 5.6 percentage points fewer visits on the same day (p < 0.001). Copy/paste demonstrated a similar dose/response relationship, with top-decile copy/paste users closing 6.8 percentage points fewer visits on the same day (p < 0.001) and spending more time in the EHR after hours and on days off (both p < 0.001). Templated text (e.g., Epic's SmartTools) demonstrated a non-linear relationship with burden and efficiency, with very low and very high levels of use associated with increased EHR burden and decreased efficiency. CONCLUSIONS:"Efficiency tools" like copy/paste and templated text meant to reduce documentation burden and increase provider efficiency may have limited efficacy.
