Browsing by Author "Harle, Christopher A."
Now showing 1 - 10 of 54
Results Per Page
Sort Options
Item A framework for a consistent and reproducible evaluation of manual review for patient matching algorithms(Oxford University Press, 2022) Gupta, Agrayan K.; Kasthurirathne, Suranga N.; Xu, Huiping; Li, Xiaochun; Ruppert, Matthew M.; Harle, Christopher A.; Grannis, Shaun J.; Medicine, School of MedicineHealthcare systems are hampered by incomplete and fragmented patient health records. Record linkage is widely accepted as a solution to improve the quality and completeness of patient records. However, there does not exist a systematic approach for manually reviewing patient records to create gold standard record linkage data sets. We propose a robust framework for creating and evaluating manually reviewed gold standard data sets for measuring the performance of patient matching algorithms. Our 8-point approach covers data preprocessing, blocking, record adjudication, linkage evaluation, and reviewer characteristics. This framework can help record linkage method developers provide necessary transparency when creating and validating gold standard reference matching data sets. In turn, this transparency will support both the internal and external validity of recording linkage studies and improve the robustness of new record linkage strategies.Item A large language model for electronic health records(Springer Nature, 2022-12-26) Yang, Xi; Chen, Aokun; PourNejatian, Nima; Shin, Hoo Chang; Smith, Kaleb E.; Parisien, Christopher; Compas, Colin; Martin, Cheryl; Costa, Anthony B.; Flores, Mona G.; Zhang, Ying; Magoc, Tanja; Harle, Christopher A.; Lipori, Gloria; Mitchell, Duane A.; Hogan, William R.; Shenkman, Elizabeth A.; Bian, Jiang; Wu, Yonghui; Health Policy and Management, Richard M. Fairbanks School of Public HealthThere is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model—GatorTron—using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on five clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve five clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_ogItem A novel method for evaluating physician communication: A pilot study testing the feasibility of parent-assisted audio recordings via Zoom(Elsevier, 2022) Staras, Stephanie A. S.; Bylund, Carma L.; Desai, Shivani; Harle, Christopher A.; Richardson, Eric; Khalil, Georges E.; Thompson, Lindsay A.; Health Policy and Management, Richard M. Fairbanks School of Public HealthObjective: Quality of physician consultations are best assessed via direct observation, but require intensive in-clinic research staffing. To evaluate physician consultation quality remotely, we pilot tested the feasibility of parents using their personal mobile phones to facilitate audio recordings of pediatric visits. Methods: Across four academic pediatric primary care clinics, we invited all physicians with a patient panel (n=20). For participating physicians, we identified scheduled patients from medical records. We invited parents to participate via text message and phone calls. During their adolescent's appointment, parents used their mobile phone to connect to Zoom for remote research staff to audio record. Results: In Spring 2021, five of 20 (25%) physicians participated. During a nine-week period, we invited parents of all 54 patients seen by participating physicians of which 15 (28%) completed adult consent and adolescent assent and 10 (19%) participated. For 9 recordings, at least 45% of the conversation was audible. Conclusions: It was feasible and acceptable to directly observe physician consultations virtually with Zoom, although participation rates and potentially audio quality were lower. Innovation: Patients used their cellular phone calling features to connect to Zoom where research staff audio-recorded their physician consultation to evaluate communication quality.Item Acceptance of Automated Social Risk Scoring in the Emergency Department: Clinician, Staff, and Patient Perspectives(University of California, 2024) Mazurenko, Olena; Hirsh, Adam T.; Harle, Christopher A.; McNamee, Cassidy; Vest, Joshua R.; Health Policy and Management, Richard M. Fairbanks School of Public HealthIntroduction: Healthcare organizations are under increasing pressure from policymakers, payers, and advocates to screen for and address patients' health-related social needs (HRSN). The emergency department (ED) presents several challenges to HRSN screening, and patients are frequently not screened for HRSNs. Predictive modeling using machine learning and artificial intelligence, approaches may address some pragmatic HRSN screening challenges in the ED. Because predictive modeling represents a substantial change from current approaches, in this study we explored the acceptability of HRSN predictive modeling in the ED. Methods: Emergency clinicians, ED staff, and patient perspectives on the acceptability and usage of predictive modeling for HRSNs in the ED were obtained through in-depth semi-structured interviews (eight per group, total 24). All participants practiced at or had received care from an urban, Midwest, safety-net hospital system. We analyzed interview transcripts using a modified thematic analysis approach with consensus coding. Results: Emergency clinicians, ED staff, and patients agreed that HRSN predictive modeling must lead to actionable responses and positive patient outcomes. Opinions about using predictive modeling results to initiate automatic referrals to HRSN services were mixed. Emergency clinicians and staff wanted transparency on data inputs and usage, demanded high performance, and expressed concern for unforeseen consequences. While accepting, patients were concerned that prediction models can miss individuals who required services and might perpetuate biases. Conclusion: Emergency clinicians, ED staff, and patients expressed mostly positive views about using predictive modeling for HRSNs. Yet, clinicians, staff, and patients listed several contingent factors impacting the acceptance and implementation of HRSN prediction models in the ED.Item Accuracy of Electronic Health Record Food Insecurity, Housing Instability, and Financial Strain Screening in Adult Primary Care(American Medical Association, 2023) Harle, Christopher A.; Wu, Wei; Vest, Joshua R.; Psychology, School of ScienceItem An Electronic Tool to Support Patient-Centered Broad Consent: A Multi-Arm Randomized Clinical Trial in Family Medicine(Annals of Family Medicine, Inc., 2021) Golembiewski, Elizabeth H.; Mainous, Arch G., III; Rahmanian, Kiarash P.; Brumback, Babette; Rooks, Benjamin J.; Krieger, Janice L.; Goodman, Kenneth W.; Moseley, Ray E.; Harle, Christopher A.; Health Policy and Management, Richard M. Fairbanks School of Public HealthPurpose: Patients are frequently asked to share their personal health information. The objective of this study was to compare the effects on patient experiences of 3 electronic consent (e-consent) versions asking patients to share their health records for research. Methods: A multi-arm randomized controlled trial was conducted from November 2017 through November 2018. Adult patients (n = 734) were recruited from 4 family medicine clinics in Florida. Using a tablet computer, participants were randomized to (1) a standard e-consent (standard), (2) an e-consent containing standard information plus hyperlinks to additional interactive details (interactive), or (3) an e-consent containing standard information, interactive hyperlinks, and factual messages about data protections and researcher training (trust-enhanced). Satisfaction (1 to 5), subjective understanding (0 to 100), and other outcomes were measured immediately, at 1 week, and at 6 months. Results: A majority of participants (94%) consented to future uses of their health record information for research. No differences in study outcomes between versions were observed at immediate or 1-week follow-up. At 6-month follow-up, compared with the standard e-consent, participants who used the interactive e-consent reported greater satisfaction (B = 0.43; SE = 0.09; P <.001) and subjective understanding (B = 18.04; SE = 2.58; P <.001). At 6-month follow-up, compared with the interactive e-consent, participants who used the trust-enhanced e-consent reported greater satisfaction (B = 0.9; SE = 1.0; P <.001) and subjective understanding (B = 32.2; SE = 2.6, P <.001). Conclusions: Patients who used e-consents with interactive research details and trust-enhancing messages reported higher satisfaction and understanding at 6-month follow-up. Research institutions should consider developing and further validating e-consents that interactively deliver information beyond that required by federal regulations, including facts that may enhance patient trust in research.Item Analgesic Management of Pain in Elite Athletes: A Systematic Review(Wolters Kluwer, 2018-09) Harle, Christopher A.; Danielson, Elizabeth C.; Derman, Wayne; Stuart, Mark; Dvorak, Jiri; Smith, Lisa; Hainline, Brian; Health Policy and Management, School of Public HealthObjective: To identify the prevalence, frequency of use, and effects of analgesic pain management strategies used in elite athletes. Design: Systematic literature review. Data Sources: Six databases: Ovid/Medline, SPORTDiscus, CINAHL, Embase, Cochrane Library, and Scopus. Eligibility Criteria for Selecting Studies: Empirical studies involving elite athletes and focused on the use or effects of medications used for pain or painful injury. Studies involving recreational sportspeople or those that undertake general exercise were excluded. Main Results: Of 70 articles found, the majority examined the frequency with which elite athletes use pain medications, including nonsteroidal anti-inflammatory drugs (NSAIDs), corticosteroids, anesthetics, and opioids. A smaller set of studies assessed the effect of medications on outcomes such as pain, function, and adverse effects. Oral NSAIDs are reported to be the most common medication, being used in some international sporting events by over 50% of athletes. Studies examining the effects of pain medications on elite athletes typically involved small samples and lacked control groups against which treated athletes were compared. Conclusions: Existing empirical research does not provide a sufficient body of evidence to guide athletes and healthcare professionals in making analgesic medication treatment decisions. Based on the relatively robust evidence regarding the widespread use of NSAIDs, clinicians and policymakers should carefully assess their current recommendations for NSAID use and adhere to a more unified consensus-based strategy for multidisciplinary pain management in elite athletes. In the future, we hope to see more rigorous, prospective studies of various pain management strategies in elite athletes, thus enabling a shift from consensus-based recommendations to evidence-based recommendations.Item An Analysis of Primary Care Clinician Communication About Risk, Benefits, and Goals Related to Chronic Opioid Therapy(SAGE Publications, 2019-12-10) Danielson, Elizabeth C.; Mazurenko, Olena; Andraka-Christou, Barbara T.; DiIulio, Julie; Downs, Sarah M.; Hurley, Robert W.; Harle, Christopher A.; Health Policy and Management, School of Public HealthBackground. Safe opioid prescribing and effective pain care are particularly important issues in the United States, where decades of widespread opioid prescribing have contributed to high rates of opioid use disorder. Because of the importance of clinician-patient communication in effective pain care and recent initiatives to curb rising opioid overdose deaths, this study sought to understand how clinicians and patients communicate about the risks, benefits, and goals of opioid therapy during primary care visits. Methods. We recruited clinicians and patients from six primary care clinics across three health systems in the Midwest United States. We audio-recorded 30 unique patients currently receiving opioids for chronic noncancer pain from 12 clinicians. We systematically analyzed transcribed, clinic visits to identify emergent themes. Results. Twenty of the 30 patient participants were females. Several patients had multiple pain diagnoses, with the most common diagnoses being osteoarthritis (n = 10), spondylosis (n = 6), and low back pain (n = 5). We identified five themes: 1) communication about individual-level and population-level risks, 2) communication about policies or clinical guidelines related to opioids, 3) communication about the limited effectiveness of opioids for chronic pain conditions, 4) communication about nonopioid therapies for chronic pain, and 5) communication about the goal of the opioid tapering. Conclusions. Clinicians discuss opioid-related risks in varying ways during patient visits, which may differentially affect patient experiences. Our findings may inform the development and use of more standardized approaches to discussing opioids during primary care visits.Item Assessing the use of a clinical decision support tool for pain management in primary care(Oxford University Press, 2022-09-15) Apathy, Nate C.; Sanner, Lindsey; Adams, Meredith C.B.; Mamlin, Burke W.; Grout, Randall W.; Fortin, Saura; Hillstrom, Jennifer; Saha, Amit; Teal, Evgenia; Vest, Joshua R.; Menachemi, Nir; Hurley, Robert W.; Harle, Christopher A.; Mazurenko, Olena; Health Policy and Management, School of Public HealthObjective: Given time constraints, poorly organized information, and complex patients, primary care providers (PCPs) can benefit from clinical decision support (CDS) tools that aggregate and synthesize problem-specific patient information. First, this article describes the design and functionality of a CDS tool for chronic noncancer pain in primary care. Second, we report on the retrospective analysis of real-world usage of the tool in the context of a pragmatic trial. Materials and methods: The tool known as OneSheet was developed using user-centered principles and built in the Epic electronic health record (EHR) of 2 health systems. For each relevant patient, OneSheet presents pertinent information in a single EHR view to assist PCPs in completing guideline-recommended opioid risk mitigation tasks, review previous and current patient treatments, view patient-reported pain, physical function, and pain-related goals. Results: Overall, 69 PCPs accessed OneSheet 2411 times (since November 2020). PCP use of OneSheet varied significantly by provider and was highly skewed (site 1: median accesses per provider: 17 [interquartile range (IQR) 9-32]; site 2: median: 8 [IQR 5-16]). Seven "power users" accounted for 70% of the overall access instances across both sites. OneSheet has been accessed an average of 20 times weekly between the 2 sites. Discussion: Modest OneSheet use was observed relative to the number of eligible patients seen with chronic pain. Conclusions: Organizations implementing CDS tools are likely to see considerable provider-level variation in usage, suggesting that CDS tools may vary in their utility across PCPs, even for the same condition, because of differences in provider and care team workflows.Item The benefits of health information exchange: an updated systematic review(Oxford Academic, 2018-09) Menachemi, Nir; Rahurkar, Saurabh; Harle, Christopher A.; Vest, Joshua R.; Health Policy and Management, School of Public HealthObjective Widespread health information exchange (HIE) is a national objective motivated by the promise of improved care and a reduction in costs. Previous reviews have found little rigorous evidence that HIE positively affects these anticipated benefits. However, early studies of HIE were methodologically limited. The purpose of the current study is to review the recent literature on the impact of HIE. Methods We used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to conduct our systematic review. PubMed and Scopus databases were used to identify empirical articles that evaluated HIE in the context of a health care outcome. Results Our search strategy identified 24 articles that included 63 individual analyses. The majority of the studies were from the United States representing 9 states; and about 40% of the included analyses occurred in a handful of HIEs from the state of New York. Seven of the 24 studies used designs suitable for causal inference and all reported some beneficial effect from HIE; none reported adverse effects. Conclusions The current systematic review found that studies with more rigorous designs all reported benefits from HIE. Such benefits include fewer duplicated procedures, reduced imaging, lower costs, and improved patient safety. We also found that studies evaluating community HIEs were more likely to find benefits than studies that evaluated enterprise HIEs or vendor-mediated exchanges. Overall, these finding bode well for the HIEs ability to deliver on anticipated improvements in care delivery and reduction in costs.