Advanced Care Planning Content Encoding with Natural Language Processing.

While advanced care planning (ACP) is an essential practice for ensuring patient-centered care, its adoption remains poor and the completeness of its documentation variable. Natural language processing (NLP) approaches hold promise for supporting ACP, including its use for decision support to improve ACP gaps at the point of care. ACP themes were annotated on palliative care notes across four annotators (Fleiss kappa = 0.753) and supervised models trained (Huggingface models bert-base-uncased and Bio_ClinicalBERT) using 5-fold cross validation (F1=0.8, precision=0.75, recall=0.86, any theme). When applied across the full note corpus of 12,711 notes, we observed variability in documentation of ACP information. Our findings demonstrate the promise of NLP approaches for informatics-based approaches for ACP and patient-centered care.

A Symptom-Based Natural Language Processing Surveillance Pipeline for Post-COVID-19 Patients.

Post-acute sequelae of SARS CoV-2 (PASC) are a group of conditions in which patients previously infected with COVID-19 experience symptoms weeks/months post-infection. PASC has substantial societal burden, including increased healthcare costs and disabilities. This study presents a natural language processing (NLP) based pipeline for identification of PASC symptoms and demonstrates its ability to estimate the proportion of suspected PASC cases. A manual case review to obtain this estimate indicated our sample incidence of PASC (13%) was representative of the estimated population proportion (95% CI: 19±6.22%). However, the high number of cases classified as indeterminate demonstrates the challenges in classifying PASC even among experienced clinicians. Lastly, this study developed a dashboard to display views of aggregated PASC symptoms and measured its utility using the System Usability Scale. Overall comments related to the dashboard's potential were positive. This pipeline is crucial for monitoring post-COVID-19 patients with potential for use in clinical settings.

Development and Usability Evaluation of an Opioid Management App.

We describe the development and usability evaluation of a novel patient engagement tool (OPY) in its early stage from perspectives of both experts and end-users. The tool is aimed at engaging patients in positive behaviors surrounding the use, weaning, and disposal of opioid medications in the post-surgical setting. The messaging and design of the application were created through a behavioral economics lens. Expert-based heuristic analysis and user testing were conducted and demonstrated that while patients found the tool to be easy to use and subjectively somewhat useful, additional work to enhance the user interface and features is needed in close partnership with developers and stakeholders.

Crowdsourcing Electronic Health Record Improvements at Scale across an Integrated Health Care Delivery System.

BACKGROUND AND OBJECTIVE: Despite widespread adoption of electronic health records (EHRs), these systems have significant room for improved efficiency and efficacy. While the idea of crowdsourcing EHR improvement ideas has been reported, little is known about how this might work across an integrated health care delivery system in practice. METHODS: Our program solicited EHR improvement submissions during two timeframes across 10 hospitals and 60 clinics in an upper-Midwest integrated health care delivery system. Submissions were primarily collected via an EHR help feature. RESULTS: A total of 262 and 294 submissions were received in 2019 and 2022, with a majority initiated from physicians (73.5 and 46.9%, 2019 and 2022) specializing in family medicine (52.0 and 59.3%). In 2022, the program reached a larger variety of personnel than 2019, with 53.0% of submissions from advanced practice providers, nurses, administrative staff, and other roles (p < 0.0001). Many ideas (36.4 and 50.0% in 2019 and 2022) reflected a lack of user understanding of EHR features and were addressed through training/education. Significant (27.1 and 25.9%) or simple (24.0 and 14.7%) EHR optimizations were required to address most remaining suggestions, with a number part of planned EHR improvement projects already (16.3 and 17.6%). CONCLUSION: Our experience using a crowdsourcing approach for EHR improvement ideas provided clinicians and staff the opportunity to address frustrations with the EHR and offered concrete feedback and solutions. While previous studies have suggested EHR technology improvements as paramount, we observed large numbers of users having a misunderstanding of EHR features, highlighting the need for improved EHR user competency and training.

Health Information Technology Use among Chronic Disease Patients: An Analysis of the United States Health Information National Trends Survey.

BACKGROUND: Chronic disease is the leading cause of mortality in the United States. Health information technology (HIT) tools show promise for improving disease management. OBJECTIVES: This study aims to understand the following: (1) how self-perceptions of health compare between those with and without disease; (2) how HIT usage varies between chronic disease profiles (diabetes, hypertension, cardiovascular disease, pulmonary disease, depression, cancer, and comorbidities); (3) how HIT trends have changed in the past 6 years; and (4) the likelihood that a given chronic disease patient uses specific HIT tools. METHODS: The Health Information National Trends Survey (HINTS) inclusive of 2014 to 2020 served as the primary data source with statistical analysis completed using Stata. Bivariate analyses and two-tailed t-tests were conducted to compare self-perceived health and HIT usage to chronic disease. Logistic regression models were created to examine the odds of a specific patient using various forms of HIT, controlling for demographics and comorbidities. RESULTS: Logistic regression models controlling for sociodemographic factors and comorbidities showed that pulmonary disease, depression, and cancer patients had an increased likelihood of using HIT tools, for example, depression patients had an 81.1% increased likelihood of looking up health information (p < 0.0001). In contrast, diabetic, high blood pressure, and cardiovascular disease patients appeared to use HIT tools at similar rates to patients without chronic disease. Overall HIT usage has increased during the timeframe examined. CONCLUSION: This study demonstrates that certain chronic disease cohorts appear to have greater HIT usage than others. Further analysis should be done to understand what factors influence patients to utilize HIT which may provide additional insights into improving design and user experience for other populations with the goal of improving management of disease. Such analyses could also establish a new baseline to account for differences in HIT usage as a direct consequence of the novel coronavirus disease 2019 (COVID-19) pandemic.

Intersection of Health Informatics Tools and Community Engagement in Health-Related Research to Reduce Health Inequities: Scoping Review.

BACKGROUND: The exponential growth of health information technology has the potential to facilitate community engagement in research. However, little is known about the use of health information technology in community-engaged research, such as which types of health information technology are used, which populations are engaged, and what are the research outcomes. OBJECTIVE: The objectives of this scoping review were to examine studies that used health information technology for community engagement and to assess (1) the types of populations, (2) community engagement strategies, (3) types of health information technology tools, and (4) outcomes of interest. METHODS: We searched PubMed and PCORI Literature Explorer using terms related to health information technology, health informatics, community engagement, and stakeholder involvement. This search process yielded 967 papers for screening. After inclusion and exclusion criteria were applied, a total of 37 papers were analyzed for key themes and for approaches relevant to health information technology and community engagement research. RESULTS: This analysis revealed that the communities engaged were generally underrepresented populations in health-related research, including racial or ethnic minority communities such as Black/African American, American Indian/Alaska Native, Latino ethnicity, and communities from low socioeconomic backgrounds. The studies focused on various age groups, ranging from preschoolers to older adults. The studies were also geographically spread across the United States and the world. Community engagement strategies included collaborative development of health information technology tools and partnerships to promote use (encompassing collaborative development, use of community advisory boards, and focus groups for eliciting information needs) and use of health information technology to engage communities in research (eg, through citizen science). The types of technology varied across studies, with mobile or tablet-based apps being the most common platform. Outcomes measured included eliciting user needs and requirements, assessing health information technology tools and prototypes with participants, measuring knowledge, and advocating for community change. CONCLUSIONS: This study illustrates the current landscape at the intersection of health information technology tools and community-engaged research approaches. It highlights studies in which various community-engaged research approaches were used to design culturally centered health information technology tools, to promote health information technology uptake, or for engagement in health research and advocacy. Our findings can serve as a platform for generating future research upon which to expand the scope of health information technology tools and their use for meaningful stakeholder engagement. Studies that incorporate community context and needs have a greater chance of cocreating culturally centered health information technology tools and better knowledge to promote action and improve health outcomes.

Investigating Health Information Technology Usage by Sociodemographic Subpopulations to Increase Community Engagement in Healthcare: An Analysis of the Health Information National Trends Survey.

It is well known that the US is plagued by health inequities: unjust differences in morbidity and mortality rates by sociodemographic factors. A potential method to address such inequities lies in utilizing health information technologies (HIT) to reach under-resourced populations and increase their involvement in healthcare. Previous researchers have done just this, using HIT tools to engage under-resourced communities and improve outcomes. However, it is unclear how HIT usage varies by sociodemographic characteristics. This study investigated this question through analysis of the Health Information National Trends Survey (HINTS) and proposed tailored HIT interventions for specific subpopulations. Internet, smartphone, and wearable device usage were analyzed by age, race/ethnicity, educational attainment, and income; purposes of HIT usage were assessed; and logistic regression models were conducted to determine associations between purposes of HIT usage and sociodemographic predictors. Results showed that Black/African American, Latinx, and Asian populations all had significantly increased use of health videos, while participants with low educational attainment had significantly decreased use of many HIT tools. Thus, this study highlights effective interventions for specific racial/ethnic populations and showcases a need for HIT tools inclusive towards low education populations to increase their engagement in healthcare and reduce inequities.

Named Entity Recognition in Prehospital Trauma Care.

Natural language processing (NLP) methods would improve outcomes in the area of prehospital Emergency Medical Services (EMS) data collection and abstraction. This study evaluated off-the-shelf solutions for automating labelling of clinically relevant data from EMS reports. A qualitative approach for choosing the best possible ensemble of pretrained NLP systems was developed and validated along with a feature using word embeddings to test phrase synonymy. The ensemble showed increased performance over individual systems.