Randomized Trial of Metformin, Ivermectin, and Fluvoxamine for Covid-19.

BACKGROUND: Early treatment to prevent severe coronavirus disease 2019 (Covid-19) is an important component of the comprehensive response to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic. METHODS: In this phase 3, double-blind, randomized, placebo-controlled trial, we used a 2-by-3 factorial design to test the effectiveness of three repurposed drugs - metformin, ivermectin, and fluvoxamine - in preventing serious SARS-CoV-2 infection in nonhospitalized adults who had been enrolled within 3 days after a confirmed diagnosis of infection and less than 7 days after the onset of symptoms. The patients were between the ages of 30 and 85 years, and all had either overweight or obesity. The primary composite end point was hypoxemia (≤93% oxygen saturation on home oximetry), emergency department visit, hospitalization, or death. All analyses used controls who had undergone concurrent randomization and were adjusted for SARS-CoV-2 vaccination and receipt of other trial medications. RESULTS: A total of 1431 patients underwent randomization; of these patients, 1323 were included in the primary analysis. The median age of the patients was 46 years; 56% were female (6% of whom were pregnant), and 52% had been vaccinated. The adjusted odds ratio for a primary event was 0.84 (95% confidence interval [CI], 0.66 to 1.09; P = 0.19) with metformin, 1.05 (95% CI, 0.76 to 1.45; P = 0.78) with ivermectin, and 0.94 (95% CI, 0.66 to 1.36; P = 0.75) with fluvoxamine. In prespecified secondary analyses, the adjusted odds ratio for emergency department visit, hospitalization, or death was 0.58 (95% CI, 0.35 to 0.94) with metformin, 1.39 (95% CI, 0.72 to 2.69) with ivermectin, and 1.17 (95% CI, 0.57 to 2.40) with fluvoxamine. The adjusted odds ratio for hospitalization or death was 0.47 (95% CI, 0.20 to 1.11) with metformin, 0.73 (95% CI, 0.19 to 2.77) with ivermectin, and 1.11 (95% CI, 0.33 to 3.76) with fluvoxamine. CONCLUSIONS: None of the three medications that were evaluated prevented the occurrence of hypoxemia, an emergency department visit, hospitalization, or death associated with Covid-19. (Funded by the Parsemus Foundation and others; COVID-OUT ClinicalTrials.gov number, NCT04510194.).

Favorable Antiviral Effect of Metformin on SARS-CoV-2 Viral Load in a Randomized, Placebo-Controlled Clinical Trial of COVID-19.

BACKGROUND: Metformin has antiviral activity against RNA viruses including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The mechanism appears to be suppression of protein translation via targeting the host mechanistic target of rapamycin pathway. In the COVID-OUT randomized trial for outpatient coronavirus disease 2019 (COVID-19), metformin reduced the odds of hospitalizations/death through 28 days by 58%, of emergency department visits/hospitalizations/death through 14 days by 42%, and of long COVID through 10 months by 42%. METHODS: COVID-OUT was a 2 × 3 randomized, placebo-controlled, double-blind trial that assessed metformin, fluvoxamine, and ivermectin; 999 participants self-collected anterior nasal swabs on day 1 (n = 945), day 5 (n = 871), and day 10 (n = 775). Viral load was quantified using reverse-transcription quantitative polymerase chain reaction. RESULTS: The mean SARS-CoV-2 viral load was reduced 3.6-fold with metformin relative to placebo (-0.56 log10 copies/mL; 95% confidence interval [CI], -1.05 to -.06; P = .027). Those who received metformin were less likely to have a detectable viral load than placebo at day 5 or day 10 (odds ratio [OR], 0.72; 95% CI, .55 to .94). Viral rebound, defined as a higher viral load at day 10 than day 5, was less frequent with metformin (3.28%) than placebo (5.95%; OR, 0.68; 95% CI, .36 to 1.29). The metformin effect was consistent across subgroups and increased over time. Neither ivermectin nor fluvoxamine showed effect over placebo. CONCLUSIONS: In this randomized, placebo-controlled trial of outpatient treatment of SARS-CoV-2, metformin significantly reduced SARS-CoV-2 viral load, which may explain the clinical benefits in this trial. Metformin is pleiotropic with other actions that are relevant to COVID-19 pathophysiology. CLINICAL TRIALS REGISTRATION: NCT04510194.

Preferences for Management of Pediatric Pneumonia: A Clinician Survey of Artificially Generated Patient Cases.

BACKGROUND: It is unknown which factors are associated with chest radiograph (CXR) and antibiotic use for suspected community-acquired pneumonia (CAP) in children. We evaluated factors associated with CXR and antibiotic preferences among clinicians for children with suspected CAP using case scenarios generated through artificial intelligence (AI). METHODS: We performed a survey of general pediatric, pediatric emergency medicine, and emergency medicine attending physicians employed by a private physician contractor. Respondents were given 5 unique, AI-generated case scenarios. We used generalized estimating equations to identify factors associated with CXR and antibiotic use. We evaluated the cluster-weighted correlation between clinician suspicion and clinical prediction model risk estimates for CAP using 2 predictive models. RESULTS: A total of 172 respondents provided responses to 839 scenarios. Factors associated with CXR acquisition (OR, [95% CI]) included presence of crackles (4.17 [2.19, 7.95]), prior pneumonia (2.38 [1.32, 4.20]), chest pain (1.90 [1.18, 3.05]) and fever (1.82 [1.32, 2.52]). The decision to use antibiotics before knowledge of CXR results included past hospitalization for pneumonia (4.24 [1.88, 9.57]), focal decreased breath sounds (3.86 [1.98, 7.52]), and crackles (3.45 [2.15, 5.53]). After revealing CXR results to clinicians, these results were the sole predictor associated with antibiotic decision-making. Suspicion for CAP correlated with one of 2 prediction models for CAP (Spearman's rho = 0.25). Factors associated with a greater suspicion of pneumonia included prior pneumonia, duration of illness, worsening course of illness, shortness of breath, vomiting, decreased oral intake or urinary output, respiratory distress, head nodding, focal decreased breath sounds, focal rhonchi, fever, and crackles, and lower pulse oximetry. CONCLUSIONS: Ordering preferences for CXRs demonstrated similarities and differences with evidence-based risk models for CAP. Clinicians relied heavily on CXR findings to guide antibiotic ordering. These findings can be used within decision support systems to promote evidence-based management practices for pediatric CAP.

Impact of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Vaccination and Booster on Coronavirus Disease 2019 (COVID-19) Symptom Severity Over Time in the COVID-OUT Trial.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination has decreasing protection from acquiring any infection with emergence of new variants; however, vaccination continues to protect against progression to severe coronavirus disease 2019 (COVID-19). The impact of vaccination status on symptoms over time is less clear. METHODS: Within a randomized trial on early outpatient COVID-19 therapy testing metformin, ivermectin, and/or fluvoxamine, participants recorded symptoms daily for 14 days. Participants were given a paper symptom diary allowing them to circle the severity of 14 symptoms as none (0), mild (1), moderate (2), or severe (3). This is a secondary analysis of clinical trial data on symptom severity over time using generalized estimating equations comparing those unvaccinated, SARS-CoV-2 vaccinated with primary vaccine series only, or vaccine-boosted. RESULTS: The parent clinical trial prospectively enrolled 1323 participants, of whom 1062 (80%) prospectively recorded some daily symptom data. Of these, 480 (45%) were unvaccinated, 530 (50%) were vaccinated with primary series only, and 52 (5%) vaccine-boosted. Overall symptom severity was least for the vaccine-boosted group and most severe for unvaccinated at baseline and over the 14 days (P < .001). Individual symptoms were least severe in the vaccine-boosted group including cough, chills, fever, nausea, fatigue, myalgia, headache, and diarrhea, as well as smell and taste abnormalities. Results were consistent over Delta and Omicron variant time periods. CONCLUSIONS: SARS-CoV-2 vaccine-boosted participants had the least severe symptoms during COVID-19, which abated the quickest over time. Clinical Trial Registration. NCT04510194.

Outpatient metformin use is associated with reduced severity of COVID-19 disease in adults with overweight or obesity.

Observational studies suggest outpatient metformin use is associated with reduced mortality from coronavirus disease-2019 (COVID-19). Metformin is known to decrease interleukin-6 and tumor-necrosis factor-α, which appear to contribute to morbidity in COVID-19. We sought to understand whether outpatient metformin use was associated with reduced odds of severe COVID-19 disease in a large US healthcare data set. Retrospective cohort analysis of electronic health record (EHR) data that was pooled across multiple EHR systems from 12 hospitals and 60 primary care clinics in the Midwest between March 4, 2020 and December 4, 2020. Inclusion criteria: data for body mass index (BMI) > 25 kg/m2 and a positive SARS-CoV-2 polymerase chain reaction test; age ≥ 30 and ≤85 years. Exclusion criteria: patient opt-out of research. Metformin is the exposure of interest, and death, admission, and intensive care unit admission are the outcomes of interest. Metformin was associated with a decrease in mortality from COVID-19, OR 0.32 (0.15, 0.66; p = .002), and in the propensity-matched cohorts, OR 0.38 (0.16, 0.91; p = .030). Metformin was associated with a nonsignificant decrease in hospital admission for COVID-19 in the overall cohort, OR 0.78 (0.58-1.04, p = .087). Among the subgroup with a hemoglobin HbA1c available (n = 1193), the adjusted odds of hospitalization (including adjustment for HbA1c) for metformin users was OR 0.75 (0.53-1.06, p = .105). Outpatient metformin use was associated with lower mortality and a trend towards decreased admission for COVID-19. Given metformin's low cost, established safety, and the mounting evidence of reduced severity of COVID-19 disease, metformin should be prospectively assessed for outpatient treatment of COVID-19.

Defragmenting Heart Failure Care: Medical Records Integration.

Heart failure management requires intensive care coordination. Guideline-directed medical therapies have been shown to save lives but are practically challenging to implement because of the fragmented care that heart failure patients experience. Electronic health record adoption has transformed the collection and storage of clinical data, but accessing these data often remains prohibitively difficult. Current legislation aims to increase the interoperability of software systems so that providers and patients can easily access the clinical information they desire. Novel heart failure devices and technologies leverage patient-generated data to manage heart failure patients, whereas new data standards make it possible for this information to guide clinical decision-making.

The Reflux Improvement and Monitoring (TRIM) Program Is Associated With Symptom Improvement and Weight Reduction for Patients With Obesity and Gastroesophageal Reflux Disease.

OBJECTIVES: Current healthcare systems do not effectively promote weight reduction in patients with obesity and gastroesophageal reflux disease (GERD). The Reflux Improvement and Monitoring (TRIM) program provides personalized, multidisciplinary, health education and monitoring over 6 months. In this study we aimed to (i) measure the effectiveness of TRIM on GERD symptoms, quality of life, and weight, and (ii) examine patient health beliefs related to TRIM. METHODS: This prospective mixed methods feasibility study was performed at a single center between September 2015 and February 2017, and included adult patients with GERD and a body mass index ≥30 kg/m2. Quantitative analysis consisted of a pre- to post-intervention analysis of TRIM participants (+TRIM Cohort) and a multivariable longitudinal mixed model analysis of +TRIM vs. patients who declined TRIM (-TRIM Cohort). Primary outcomes were change in patient-reported GERD symptom severity (GerdQ) and quality of life (GerdQ-DI), and change in percent excess body weight (%EBW). Qualitative analysis was based on two focus groups of TRIM participants. RESULTS: Among the +TRIM cohort (n=52), mean baseline GerdQ scores (8.7±2.9) decreased at 3 months (7.5±2.2; P<0.01) and 6 months (7.4±1.9; P=0.02). Mean GerdQ-DI scores decreased, but did not reach statistical significance. Compared with the -TRIM cohort (n=89), reduction in %EBW was significantly greater at 3, 6, and 12 months among the +TRIM cohort (n=52). In qualitative analysis, patients unanimously appreciated the multidisciplinary approach and utilized weight loss effectively to improve GERD symptoms. CONCLUSIONS: In this mixed methods feasibility study, participation in TRIM was associated with symptom improvement, weight reduction, and patient engagement.

A Framework for Tracking Former Patients in the Electronic Health Record Using an Educational Registry.

One challenge of contemporary medical education is that shorter lengths of stay and time-limited clerkships often interrupt a student's relationship with a patient before a diagnosis is made or treatment is completed, limiting the learning experience. Medical students sometimes use electronic health records (EHRs) to overcome these limitations. EHRs provide access to patients' future medical records, enabling students to track former patients across care venues to audit their diagnostic impressions and observe outcomes. While this activity has potential to improve clinical training, there is a risk of unintended harm to patients through loss of privacy. Students need guidance on how to perform this activity appropriately. This article describes an ethical framework for tracking using an "educational registry," a list of former patients housed within the EHR that one follows longitudinally for educational purposes. Guiding principles include obtaining permission from patients, having legitimate educational intent, and restricting review of records to those essential for training. This framework could serve as a foundation for institutions seeking to develop a policy on tracking former patients, and may facilitate research on the use of EHRs to improve medical education, such as reducing diagnostic error and promoting self-directed learning.

Learning bundled care opportunities from electronic medical records.

OBJECTIVE: The traditional fee-for-service approach to healthcare can lead to the management of a patient's conditions in a siloed manner, inducing various negative consequences. It has been recognized that a bundled approach to healthcare - one that manages a collection of health conditions together - may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. In this study, we investigate if a data-driven approach can automatically learn potential bundles. METHODS: We designed a framework to infer health condition collections (HCCs) based on the similarity of their clinical workflows, according to electronic medical record (EMR) utilization. We evaluated the framework with data from over 16,500 inpatient stays from Northwestern Memorial Hospital in Chicago, Illinois. The plausibility of the inferred HCCs for bundled care was assessed through an online survey of a panel of five experts, whose responses were analyzed via an analysis of variance (ANOVA) at a 95% confidence level. We further assessed the face validity of the HCCs using evidence in the published literature. RESULTS: The framework inferred four HCCs, indicative of (1) fetal abnormalities, (2) late pregnancies, (3) prostate problems, and (4) chronic diseases, with congestive heart failure featuring prominently. Each HCC was substantiated with evidence in the literature and was deemed plausible for bundled care by the experts at a statistically significant level. CONCLUSIONS: The findings suggest that an automated EMR data-driven framework conducted can provide a basis for discovering bundled care opportunities. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation.

Patients' and healthcare providers' perceptions of a mobile portal application for hospitalized patients.

BACKGROUND: Hospital-based patient portals have the potential to better inform and engage patients in their care. We sought to assess patients' and healthcare providers' perceptions of a hospital-based portal and identify opportunities for design enhancements. METHODS: We developed a mobile patient portal application including information about the care team, scheduled tests and procedures, and a list of active medications. Patients were offered use of tablet computers, with the portal application, during their hospitalization. We conducted semi-structured interviews of patients and provider focus groups. Text from transcribed interviews and focus groups was independently coded by two investigators using a constant comparative approach. Codes were reviewed by a third investigator and discrepancies resolved via consensus. RESULTS: Overall, 18 patients completed semi-structured interviews and 21 providers participated in three focus groups. Patients found information provided by the portal to be useful, especially regarding team members and medications. Many patients described frequent use of games and non-clinical applications and felt the tablet helped them cope with their acute illness. Patients expressed a desire for additional detail about medications, test results, and the ability to record questions. Providers felt the portal improved patient engagement, but worried that additional features might result in a volume and complexity of information that could be overwhelming for patients. Providers also expressed concern over an enhanced portal's impact on patient-provider communication and workflow. CONCLUSIONS: Optimizing a hospital-based patient portal will require attention to type, timing and format of information provided, as well as the impact on patient-provider communication and workflow.

Building bridges across electronic health record systems through inferred phenotypic topics.

OBJECTIVE: Data in electronic health records (EHRs) is being increasingly leveraged for secondary uses, ranging from biomedical association studies to comparative effectiveness. To perform studies at scale and transfer knowledge from one institution to another in a meaningful way, we need to harmonize the phenotypes in such systems. Traditionally, this has been accomplished through expert specification of phenotypes via standardized terminologies, such as billing codes. However, this approach may be biased by the experience and expectations of the experts, as well as the vocabulary used to describe such patients. The goal of this work is to develop a data-driven strategy to (1) infer phenotypic topics within patient populations and (2) assess the degree to which such topics facilitate a mapping across populations in disparate healthcare systems. METHODS: We adapt a generative topic modeling strategy, based on latent Dirichlet allocation, to infer phenotypic topics. We utilize a variance analysis to assess the projection of a patient population from one healthcare system onto the topics learned from another system. The consistency of learned phenotypic topics was evaluated using (1) the similarity of topics, (2) the stability of a patient population across topics, and (3) the transferability of a topic across sites. We evaluated our approaches using four months of inpatient data from two geographically distinct healthcare systems: (1) Northwestern Memorial Hospital (NMH) and (2) Vanderbilt University Medical Center (VUMC). RESULTS: The method learned 25 phenotypic topics from each healthcare system. The average cosine similarity between matched topics across the two sites was 0.39, a remarkably high value given the very high dimensionality of the feature space. The average stability of VUMC and NMH patients across the topics of two sites was 0.988 and 0.812, respectively, as measured by the Pearson correlation coefficient. Also the VUMC and NMH topics have smaller variance of characterizing patient population of two sites than standard clinical terminologies (e.g., ICD9), suggesting they may be more reliably transferred across hospital systems. CONCLUSIONS: Phenotypic topics learned from EHR data can be more stable and transferable than billing codes for characterizing the general status of a patient population. This suggests that EHR-based research may be able to leverage such phenotypic topics as variables when pooling patient populations in predictive models.

Disparities in Patient Portal Use Among Adults With Chronic Conditions.

Importance: Disparities in patient access and use of health care portals have been documented. Limited research has evaluated disparities in portal use during and after the COVID-19 pandemic. Objective: To assess prevalence of health care portal use before, during, and after the most restrictive phase of the pandemic (2019-2022) among the COVID-19 & Chronic Conditions (C3) cohort and to investigate any disparities in use by sociodemographic factors. Design, Setting, and Participants: This cohort study uses data from the C3 study, an ongoing, longitudinal, telephone-based survey of participants with multiple chronic conditions. Participants were middle aged and older-adult primary care patients who had an active portal account, recruited from a single academic medical center in Chicago, Illinois, between 2019 and 2022. Data were analyzed between March and June 2022. Main Outcomes and Measures: Outcomes of portal use (ie, number of days of portal login by year) were recorded for all study participants by the electronic data warehouse. All parent studies had uniform sociodemographic data and measures of social support, self-efficacy, health literacy, and health activation. Results: Of 536 participants (mean [SD] age, 66.7 [12.0] years; 336 [62.7%] female), 44 (8.2%) were Hispanic or Latinx, 142 (26.5%) were non-Hispanic Black, 322 (60.1%) were non-Hispanic White, and 20 individuals (3.7%) identified as other race, including Asian, Native American or Alaskan Native, and self-reported other race. In multivariable analyses, portal login activity was higher during the 3 years of the COVID-19 pandemic compared with the 2019 baseline. Higher portal login activity was associated with adequate health literacy (incidence rate ratio [IRR], 1.51; 95% CI, 1.18-1.94) and multimorbidity (IRR, 1.38; 95% CI, 1.17-1.64). Lower portal activity was associated with older age (≥70 years: IRR, 0.69; 95% CI, 0.55-0.85) and female sex (IRR, 0.77; 95% CI, 0.66-0.91). Compared with non-Hispanic White patients, lower portal activity was observed among Hispanic or Latinx patients (IRR, 0.66; 95% CI, 0.49-0.89), non-Hispanic Black patients (IRR, 0.68; 95% CI, 0.56-0.83), and patients who identified as other race (IRR, 0.42; 95% CI, 0.28-0.64). Conclusions and Relevance: This cohort study using data from the C3 study identified changes in portal use over time and highlighted populations that had lower access to health information. The COVID-19 pandemic was associated with an increase in portal use. Sociodemographic disparities by sex and age were reduced, although disparities by health literacy widened. A brief validated health literacy measure may serve as a useful digital literacy screening tool to identify patients who need further support.

A Comparison of Recruitment Methods for a Remote, Nationwide Clinical Trial for COVID-19 Treatment.

This study describes decentralized recruitment and enrollment for a COVID-19 treatment trial, while comparing 5 primary recruitment methods: search engine ads, paid advertising within a national testing company, paid advertising within a regional testing company, electronic health record messages, and word of mouth. These are compared across patient demographics, efficiency, and cost. Clinical Trials Registration: NCT04510194.

Pediatric Gastrointestinal Outcomes During the Post-Acute Phase of COVID-19: Findings from RECOVER Initiative from 29 Hospitals in the US.

Importance: The profile of gastrointestinal (GI) outcomes that may affect children in post-acute and chronic phases of COVID-19 remains unclear. Objective: To investigate the risks of GI symptoms and disorders during the post-acute phase (28 days to 179 days after SARS-CoV-2 infection) and the chronic phase (180 days to 729 days after SARS-CoV-2 infection) in the pediatric population. Design: We used a retrospective cohort design from March 2020 to Sept 2023. Setting: twenty-nine healthcare institutions. Participants: A total of 413,455 patients aged not above 18 with SARS-CoV-2 infection and 1,163,478 patients without SARS-CoV-2 infection. Exposures: Documented SARS-CoV-2 infection, including positive polymerase chain reaction (PCR), serology, or antigen tests for SARS-CoV-2, or diagnoses of COVID-19 and COVID-related conditions. Main Outcomes and Measures: Prespecified GI symptoms and disorders during two intervals: post-acute phase and chronic phase following the documented SARS-CoV-2 infection. The adjusted risk ratio (aRR) was determined using a stratified Poisson regression model, with strata computed based on the propensity score. Results: Our cohort comprised 1,576,933 patients, with females representing 48.0% of the sample. The analysis revealed that children with SARS-CoV-2 infection had an increased risk of developing at least one GI symptom or disorder in both the post-acute (8.64% vs. 6.85%; aRR 1.25, 95% CI 1.24-1.27) and chronic phases (12.60% vs. 9.47%; aRR 1.28, 95% CI 1.26-1.30) compared to uninfected peers. Specifically, the risk of abdominal pain was higher in COVID-19 positive patients during the post-acute phase (2.54% vs. 2.06%; aRR 1.14, 95% CI 1.11-1.17) and chronic phase (4.57% vs. 3.40%; aRR 1.24, 95% CI 1.22-1.27). Conclusions and Relevance: In the post-acute phase or chronic phase of COVID-19, the risk of GI symptoms and disorders was increased for COVID-positive patients in the pediatric population.

Northwestern University resource and education development initiatives to advance collaborative artificial intelligence across the learning health system.

Introduction: The rapid development of artificial intelligence (AI) in healthcare has exposed the unmet need for growing a multidisciplinary workforce that can collaborate effectively in the learning health systems. Maximizing the synergy among multiple teams is critical for Collaborative AI in Healthcare. Methods: We have developed a series of data, tools, and educational resources for cultivating the next generation of multidisciplinary workforce for Collaborative AI in Healthcare. We built bulk-natural language processing pipelines to extract structured information from clinical notes and stored them in common data models. We developed multimodal AI/machine learning (ML) tools and tutorials to enrich the toolbox of the multidisciplinary workforce to analyze multimodal healthcare data. We have created a fertile ground to cross-pollinate clinicians and AI scientists and train the next generation of AI health workforce to collaborate effectively. Results: Our work has democratized access to unstructured health information, AI/ML tools and resources for healthcare, and collaborative education resources. From 2017 to 2022, this has enabled studies in multiple clinical specialties resulting in 68 peer-reviewed publications. In 2022, our cross-discipline efforts converged and institutionalized into the Center for Collaborative AI in Healthcare. Conclusions: Our Collaborative AI in Healthcare initiatives has created valuable educational and practical resources. They have enabled more clinicians, scientists, and hospital administrators to successfully apply AI methods in their daily research and practice, develop closer collaborations, and advanced the institution-level learning health system.

An exploratory survey about using ChatGPT in education, healthcare, and research.

Objective ChatGPT is the first large language model (LLM) to reach a large, mainstream audience. Its rapid adoption and exploration by the population at large has sparked a wide range of discussions regarding its acceptable and optimal integration in different areas. In a hybrid (virtual and in-person) panel discussion event, we examined various perspectives regarding the use of ChatGPT in education, research, and healthcare. Materials and Methods We surveyed in-person and online attendees using an audience interaction platform (Slido). We quantitatively analyzed received responses on questions about the use of ChatGPT in various contexts. We compared pairwise categorical groups with Fisher's Exact. Furthermore, we used qualitative methods to analyze and code discussions. Results We received 420 responses from an estimated 844 participants (response rate 49.7%). Only 40% of the audience had tried ChatGPT. More trainees had tried ChatGPT compared with faculty. Those who had used ChatGPT were more interested in using it in a wider range of contexts going forwards. Of the three discussed contexts, the greatest uncertainty was shown about using ChatGPT in education. Pros and cons were raised during discussion for the use of this technology in education, research, and healthcare. Discussion There was a range of perspectives around the uses of ChatGPT in education, research, and healthcare, with still much uncertainty around its acceptability and optimal uses. There were different perspectives from respondents of different roles (trainee vs faculty vs staff). More discussion is needed to explore perceptions around the use of LLMs such as ChatGPT in vital sectors such as education, healthcare and research. Given involved risks and unforeseen challenges, taking a thoughtful and measured approach in adoption would reduce the likelihood of harm.

An exploratory survey about using ChatGPT in education, healthcare, and research.

OBJECTIVE: ChatGPT is the first large language model (LLM) to reach a large, mainstream audience. Its rapid adoption and exploration by the population at large has sparked a wide range of discussions regarding its acceptable and optimal integration in different areas. In a hybrid (virtual and in-person) panel discussion event, we examined various perspectives regarding the use of ChatGPT in education, research, and healthcare. MATERIALS AND METHODS: We surveyed in-person and online attendees using an audience interaction platform (Slido). We quantitatively analyzed received responses on questions about the use of ChatGPT in various contexts. We compared pairwise categorical groups with a Fisher's Exact. Furthermore, we used qualitative methods to analyze and code discussions. RESULTS: We received 420 responses from an estimated 844 participants (response rate 49.7%). Only 40% of the audience had tried ChatGPT. More trainees had tried ChatGPT compared with faculty. Those who had used ChatGPT were more interested in using it in a wider range of contexts going forwards. Of the three discussed contexts, the greatest uncertainty was shown about using ChatGPT in education. Pros and cons were raised during discussion for the use of this technology in education, research, and healthcare. DISCUSSION: There was a range of perspectives around the uses of ChatGPT in education, research, and healthcare, with still much uncertainty around its acceptability and optimal uses. There were different perspectives from respondents of different roles (trainee vs faculty vs staff). More discussion is needed to explore perceptions around the use of LLMs such as ChatGPT in vital sectors such as education, healthcare and research. Given involved risks and unforeseen challenges, taking a thoughtful and measured approach in adoption would reduce the likelihood of harm.

Machine learning identification of patient clusters for cutaneous melanoma.

BACKGROUND: Cutaneous melanoma is a cancer arising in melanocyte skin cells and is the deadliest form of skin cancer worldwide. Although some risk factors are known, accurate prediction of disease progression and probability for metastasis are difficult to ascertain, given the complexity of the disease and the absence of reliable predictive markers. Since early detection and treatment are essential to enhance survival, this study utilizing machine learning (ML) aims to further delineate additional risk factors associated with cutaneous melanoma. METHODS: A Bayesian Gaussian Mixture ML model was created with data from 2056 patients diagnosed with cutaneous melanoma and then used to group the patients into six Clusters based on a Silhouette Score analysis. A t-distributed stochastic neighbor embedding (t-SNE) model was used to visualize the six Clusters. RESULTS: Statistical analysis revealed that Cluster 4 showed a significantly higher rate of metastatic disease, as well as higher Breslow depth at diagnosis, compared to the other five Clusters. Compared to the other five Clusters, patients represented in Cluster 4 also had lower healthcare utilization, fewer dermatology clinic visits, fewer primary care providers, and less frequent colonoscopies and mammograms, and were more likely to smoke and less likely to have a prior diagnosis of basal cell carcinoma. CONCLUSIONS: This study uncovers gaps in healthcare utilization of services among patient groups with cutaneous melanoma as well as possible implications for management of disease progression. Data-driven analyses emphasize the importance of routine clinic visits to dermatologists and/or primary care physicians (PCPs) for early detection and management of cutaneous melanoma. The findings from this study demonstrate that unsupervised ML methodology may serve to define the best candidate patients to benefit from enhanced dermatology/primary care which, in turn, is expected to improve outcomes for cutaneous melanoma.

Identifying Patients With Peripheral Artery Disease Using the Electronic Health Record: A Pragmatic Approach.

BACKGROUND: Peripheral artery disease (PAD) is underdiagnosed due to poor patient and clinician awareness. Despite this, no widely accepted PAD screening is recommended. OBJECTIVES: The authors used machine learning to develop an automated risk stratification tool for identifying patients with a high likelihood of PAD. METHODS: Using data from the electronic health record (EHR), ankle-brachial indices (ABIs) were extracted for 3,298 patients. In addition to ABI, we extracted 60 other patient characteristics and used a random forest model to rank the features by association with ABI. The model identified several features independently correlated with PAD. We then built a logistic regression model to predict PAD status on a validation set of patients (n = 1,089), an external cohort of patients (n = 2,922), and a national database (n = 2,488). The model was compared to an age-based and random forest model. RESULTS: The model had an area under the curve (AUC) of 0.68 in the validation set. When evaluated on an external population using EHR data, it performed similarly with an AUC of 0.68. When evaluated on a national database, it had an AUC of 0.72. The model outperformed an age-based model (AUC: 0.62; P < 0.001). A random forest model with inclusion of all 60 features did not perform significantly better (AUC: 0.71; P = 0.31). CONCLUSIONS: Statistical techniques can be used to build models which identify individuals at high risk for PAD using information accessible from the EHR. Models such as this may allow large health care systems to efficiently identify patients that would benefit from aggressive preventive strategies or targeted-ABI screening.