Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format.

Importance: By law, patients have immediate access to discharge notes in their medical records. Technical language and abbreviations make notes difficult to read and understand for a typical patient. Large language models (LLMs [eg, GPT-4]) have the potential to transform these notes into patient-friendly language and format. Objective: To determine whether an LLM can transform discharge summaries into a format that is more readable and understandable. Design, Setting, and Participants: This cross-sectional study evaluated a sample of the discharge summaries of adult patients discharged from the General Internal Medicine service at NYU (New York University) Langone Health from June 1 to 30, 2023. Patients discharged as deceased were excluded. All discharge summaries were processed by the LLM between July 26 and August 5, 2023. Interventions: A secure Health Insurance Portability and Accountability Act-compliant platform, Microsoft Azure OpenAI, was used to transform these discharge summaries into a patient-friendly format between July 26 and August 5, 2023. Main Outcomes and Measures: Outcomes included readability as measured by Flesch-Kincaid Grade Level and understandability using Patient Education Materials Assessment Tool (PEMAT) scores. Readability and understandability of the original discharge summaries were compared with the transformed, patient-friendly discharge summaries created through the LLM. As balancing metrics, accuracy and completeness of the patient-friendly version were measured. Results: Discharge summaries of 50 patients (31 female [62.0%] and 19 male [38.0%]) were included. The median patient age was 65.5 (IQR, 59.0-77.5) years. Mean (SD) Flesch-Kincaid Grade Level was significantly lower in the patient-friendly discharge summaries (6.2 [0.5] vs 11.0 [1.5]; P < .001). PEMAT understandability scores were significantly higher for patient-friendly discharge summaries (81% vs 13%; P < .001). Two physicians reviewed each patient-friendly discharge summary for accuracy on a 6-point scale, with 54 of 100 reviews (54.0%) giving the best possible rating of 6. Summaries were rated entirely complete in 56 reviews (56.0%). Eighteen reviews noted safety concerns, mostly involving omissions, but also several inaccurate statements (termed hallucinations). Conclusions and Relevance: The findings of this cross-sectional study of 50 discharge summaries suggest that LLMs can be used to translate discharge summaries into patient-friendly language and formats that are significantly more readable and understandable than discharge summaries as they appear in electronic health records. However, implementation will require improvements in accuracy, completeness, and safety. Given the safety concerns, initial implementation will require physician review.

Cohort profile: a large EHR-based cohort with linked pharmacy refill and neighbourhood social determinants of health data to assess heart failure medication adherence.

PURPOSE: Clinic-based or community-based interventions can improve adherence to guideline-directed medication therapies (GDMTs) among patients with heart failure (HF). However, opportunities for such interventions are frequently missed, as providers may be unable to recognise risk patterns for medication non-adherence. Machine learning algorithms can help in identifying patients with high likelihood of non-adherence. While a number of multilevel factors influence adherence, prior models predicting non-adherence have been limited by data availability. We have established an electronic health record (EHR)-based cohort with comprehensive data elements from multiple sources to improve on existing models. We linked EHR data with pharmacy refill data for real-time incorporation of prescription fills and with social determinants data to incorporate neighbourhood factors. PARTICIPANTS: Patients seen at a large health system in New York City (NYC), who were >18 years old with diagnosis of HF or reduced ejection fraction (<40%) since 2017, had at least one clinical encounter between 1 April 2021 and 31 October 2022 and active prescriptions for any of the four GDMTs (beta-blocker, ACEi/angiotensin receptor blocker (ARB)/angiotensin receptor neprilysin inhibitor (ARNI), mineralocorticoid receptor antagonist (MRA) and sodium-glucose cotransporter 2 inhibitor (SGLT2i)) during the study period. Patients with non-geocodable address or outside the continental USA were excluded. FINDINGS TO DATE: Among 39 963 patients in the cohort, the average age was 73±14 years old, 44% were female and 48% were current/former smokers. The common comorbid conditions were hypertension (77%), cardiac arrhythmias (56%), obesity (33%) and valvular disease (33%). During the study period, 33 606 (84%) patients had an active prescription of beta blocker, 32 626 (82%) had ACEi/ARB/ARNI, 11 611 (29%) MRA and 7472 (19%) SGLT2i. Ninety-nine per cent were from urban metropolitan areas. FUTURE PLANS: We will use the established cohort to develop a machine learning model to predict medication adherence, and to support ancillary studies assessing associates of adherence. For external validation, we will include data from an additional hospital system in NYC.

Guideline-Directed Medical Therapy in Newly Diagnosed Heart Failure With Reduced Ejection Fraction in the Community.

BACKGROUND: Guideline-directed medical therapy (GDMT) dramatically improves outcomes in heart failure with reduced ejection fraction (HFrEF). Our goal was to examine GDMT use in community patients with newly diagnosed HFrEF. METHODS AND RESULTS: We performed a population-based, retrospective cohort study of all Olmsted County, Minnesota, residents with newly diagnosed HFrEF (EF ≤ 40%) 2007-2017. We excluded patients with contraindications to medication initiation. We examined the use of beta-blockers, HF beta-blockers (metoprolol succinate, carvedilol, bisoprolol), angiotensin converting enzyme inhibitors (ACEis), angiotensin receptor blockers (ARBs), angiotensin receptor neprilysin inhibitors (ARNIS), and mineralocorticoid receptor antagonists (MRAs) in the first year after HFrEF diagnosis. We used Cox models to evaluate the association of being seen in an HF clinic with the initiation of GDMT. From 2007 to 2017, 1160 patients were diagnosed with HFrEF (mean age 69.7 years, 65.6% men). Most eligible patients received beta-blockers (92.6%) and ACEis/ARBs/ARNIs (87.0%) in the first year. However, only 63.8% of patients were treated with an HF beta-blocker, and few received MRAs (17.6%). In models accounting for the role of an HF clinic in initiation of these medications, being seen in an HF clinic was independently associated with initiation of new GDMT across all medication classes, with a hazard ratio (95% CI) of 1.54 (1.15-2.06) for any beta-blocker, 2.49 (1.95-3.20) for HF beta-blockers, 1.97 (1.46-2.65) for ACEis/ARBs/ARNIs, and 2.14 (1.49-3.08) for MRAs. CONCLUSIONS: In this population-based study, most patients with newly diagnosed HFrEF received beta-blockers and ACEis/ARBs/ARNIs. GDMT use was higher in patients seen in an HF clinic, suggesting the potential benefit of referral to an HF clinic for patients with newly diagnosed HFrEF.

Development of Advanced Heart Failure: A Population-Based Study.

BACKGROUND: Some patients with heart failure (HF) will go on to develop advanced HF, characterized by severe HF symptoms despite attempts to optimize medical therapy. The goals of this study were to examine the risk of developing advanced HF in patients with newly diagnosed HF, identify risk factors for developing advanced HF, and evaluate the impact of advanced HF on outcomes. METHODS: This was a population-based, retrospective cohort study of Olmsted County, Minnesota, residents with a new clinical diagnosis of HF between 2007 and 2017. Risk factors for the development of advanced HF (2018 European Society of Cardiology criteria) were examined using cause-specific Cox proportional hazard regression models. The associations of development of advanced HF with risks of hospitalization and mortality were examined using the Andersen-Gill and Cox models, respectively. RESULTS: There were 4597 residents with incident HF from 2007 to 2017. The cumulative incidence of advanced HF was 11.5% (95% CI, 10.5%-12.5%) at 6 years after incident HF diagnosis overall and was 14.4% (95% CI, 12.3%-16.9%), 11.4% (95% CI, 8.9%-14.6%), and 11.7% (95% CI, 10.3%-13.2%) in patients with incident HF with reduced, mildly reduced, and preserved ejection fraction, respectively. Key demographics, comorbidities, and echocardiographic characteristics were independently associated with the development of advanced HF. Development of advanced HF was associated with increased risks of all-cause hospitalization (adjusted hazard ratio, 3.0 [95% CI, 2.7-3.4]; P<0.001), HF hospitalization (hazard ratio, 10.2 [95% CI, 8.7-12.1]), all-cause mortality (hazard ratio, 5.0 [95% CI, 4.5-5.6]; P<0.001), and cardiovascular mortality (hazard ratio, 7.8 [95% CI, 6.7-9.1]). CONCLUSIONS: In this population-based study, development of advanced HF was common and was associated with markedly increased morbidity and mortality.

A Behavioral Economics-Electronic Health Record Module to Promote Appropriate Diabetes Management in Older Adults: Protocol for a Pragmatic Cluster Randomized Controlled Trial.

BACKGROUND: The integration of behavioral economics (BE) principles and electronic health records (EHRs) using clinical decision support (CDS) tools is a novel approach to improving health outcomes. Meanwhile, the American Geriatrics Society has created the Choosing Wisely (CW) initiative to promote less aggressive glycemic targets and reduction in pharmacologic therapy in older adults with type 2 diabetes mellitus. To date, few studies have shown the effectiveness of combined BE and EHR approaches for managing chronic conditions, and none have addressed guideline-driven deprescribing specifically in type 2 diabetes. We previously conducted a pilot study aimed at promoting appropriate CW guideline adherence using BE nudges and EHRs embedded within CDS tools at 5 clinics within the New York University Langone Health (NYULH) system. The BE-EHR module intervention was tested for usability, adoption, and early effectiveness. Preliminary results suggested a modest improvement of 5.1% in CW compliance. OBJECTIVE: This paper presents the protocol for a study that will investigate the effectiveness of a BE-EHR module intervention that leverages BE nudges with EHR technology and CDS tools to reduce overtreatment of type 2 diabetes in adults aged 76 years and older, per the CW guideline. METHODS: A pragmatic, investigator-blind, cluster randomized controlled trial was designed to evaluate the BE-EHR module. A total of 66 NYULH clinics will be randomized 1:1 to receive for 18 months either (1) a 6-component BE-EHR module intervention + standard care within the NYULH EHR, or (2) standard care only. The intervention will be administered to clinicians during any patient encounter (eg, in person, telemedicine, medication refill, etc). The primary outcome will be patient-level CW compliance. Secondary outcomes will measure the frequency of intervention component firings within the NYULH EHR, and provider utilization and interaction with the BE-EHR module components. RESULTS: Study recruitment commenced on December 7, 2020, with the activation of all 6 BE-EHR components in the NYULH EHR. CONCLUSIONS: This study will test the effectiveness of a previously developed, iteratively refined, user-tested, and pilot-tested BE-EHR module aimed at providing appropriate diabetes care to elderly adults, compared to usual care via a cluster randomized controlled trial. This innovative research will be the first pragmatic randomized controlled trial to use BE principles embedded within the EHR and delivered using CDS tools to specifically promote CW guideline adherence in type 2 diabetes. The study will also collect valuable information on clinician workflow and interaction with the BE-EHR module, guiding future research in optimizing the timely delivery of BE nudges within CDS tools. This work will address the effectiveness of BE-inspired interventions in diabetes and chronic disease management. TRIAL REGISTRATION: ClinicalTrials.gov NCT04181307; https://clinicaltrials.gov/ct2/show/NCT04181307. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/28723.

Advanced Heart Failure Epidemiology and Outcomes: A Population-Based Study.

OBJECTIVES: The goal of this study was to evaluate the prevalence, characteristics, and outcomes of patients with advanced heart failure (HF) in a geographically defined population. BACKGROUND: Some patients with HF progress to advanced HF, characterized by debilitating HF symptoms refractory to therapy. Limited data are available on the epidemiology and outcomes of patients with advanced HF. METHODS: This was a population-based cohort study of all Olmsted County, Minnesota, adults with and without HF from 2007 to 2017. The 2018 European Society of Cardiology advanced HF diagnostic criteria were operationalized and applied to all patients with HF. Hospitalization and mortality in advanced HF, overall and according to ejection fraction (EF) type (reduced EF <40% [HFrEF], mid-range EF 40%-49% [HFmrEF], and preserved EF ≥50% [HFpEF]) were examined using Andersen-Gill and Cox models. RESULTS: Of 6,836 adults with HF, 936 (13.7%) met criteria for advanced HF. The prevalence of advanced HF increased with age and was higher in men. At advanced HF diagnosis, 396 (42.3%) patients had HFrEF, 134 (14.3%) had HFmrEF, and 406 (43.4%) had HFpEF. The median (interquartile range) time from advanced HF diagnosis to death was 12.2 months (3.7-29.9 months). The mean rate of hospitalization was 2.91 (95% CI: 2.78-3.06) per person-year in the first year after advanced HF diagnosis. There were no differences in risks of all-cause mortality or hospitalization by EF. Patients with advanced HFpEF were at lower risk for cardiovascular mortality compared with advanced HFrEF (HR: 0.79; 95% CI: 0.65-0.97). CONCLUSIONS: In this population-based study, more than one-half of patients with advanced HF had mid-range or preserved EF, and survival was poor regardless of EF.

Homelessness and Medicaid Churn.

Objectives: To identify ICD-10-CM diagnostic codes associated with the social determinants of health (SDOH), determine frequency of use of the code for homelessness across time, and examine the frequency of interrupted periods of Medicaid eligibility (ie, Medicaid churn) for beneficiaries with and without this code. Design: Retrospective data analyses of New York State (NYS) Medicaid claims data for years 2006-2017 to determine reliable indicators of SDOH hypothesized to affect Medicaid churn, and for years 2016-2017 to examine frequency of Medicaid churn among patients with and without an indicator for homelessness. Main Outcome Measures: Any interruption in the eligibility for Medicaid insurance (Medicaid churn), assessed via client identification numbers (CIN) for continuity. Methods: Analyses were conducted to assess the frequency of use and pattern of New York State Medicaid claims submission for SDOH codes. Analyses were conducted for Medicaid claims submitted for years 2016-2017 for Medicaid patients with and without a homeless code (ie, ICD-10-CM Z59.0) in 2017. Results: ICD-9-CM / ICD-10-CM codes for lack of housing / homelessness demonstrated linear reliability over time (ie, for years 2006-2017) with increased usage. In 2016-2017, 22.9% of New York Medicaid patients with a homelessness code in 2017 experienced at least one interruption of Medicaid eligibility, while 18.8% of Medicaid patients without a homelessness code experienced Medicaid churn. Conclusions: Medicaid policies would do well to take into consideration the barriers to continued enrollment for the Medicaid population. Measures ought to be enacted to reduce Medicaid churn, especially for individuals experiencing homelessness.

Early Lessons on Bundled Payment at an Academic Medical Center.

INTRODUCTION: Orthopaedic care is shifting to alternative payment models. We examined whether New York University Langone Medical Center achieved savings under the Centers for Medicare and Medicaid Services Bundled Payments for Care Improvement initiative. METHODS: This study was a difference-in-differences study of Medicare fee-for-service patients hospitalized from April 2011 to June 2012 and October 2013 to December 2014 for lower extremity joint arthroplasty, cardiac valve procedures, or spine surgery (intervention groups), or for congestive heart failure, major bowel procedures, medical peripheral vascular disorders, medical noninfectious orthopaedic care, or stroke (control group). We examined total episode costs and costs by service category. RESULTS: We included 2,940 intervention episodes and 1,474 control episodes. Relative to the trend in the control group, lower extremity joint arthroplasty episodes achieved the greatest savings: adjusted average episode cost during the intervention period decreased by $3,017 (95% confidence interval [CI], -$6,066 to $31). For cardiac procedures, the adjusted average episode cost decreased by $2,999 (95% CI, -$8,103 to $2,105), and for spinal fusion, it increased by $8,291 (95% CI, $2,879 to $13,703). Savings were driven predominantly by shifting postdischarge care from inpatient rehabilitation facilities to home. Spinal fusion index admission costs increased because of changes in surgical technique. DISCUSSION: Under bundled payment, New York University Langone Medical Center decreased total episode costs in patients undergoing lower extremity joint arthroplasty. For patients undergoing cardiac valve procedures, evidence of savings was not as strong, and for patients undergoing spinal fusion, total episode costs increased. For all three conditions, the proportion of patients referred to inpatient rehabilitation facilities upon discharge decreased. These changes were not associated with an increase in index hospital length of stay or readmission rate. CONCLUSION: Opportunities for savings under bundled payment may be greater for lower extremity joint arthroplasty than for other conditions.

Anger proneness, gender, and the risk of heart failure.

BACKGROUND: Evidence regarding the association of anger proneness with incidence of heart failure is lacking. METHODS AND RESULTS: Anger proneness was ascertained among 13,171 black and white participants of the Atherosclerosis Risk in Communities (ARIC) study cohort with the use of the Spielberger Trait Anger Scale. Incident heart failure events, defined as occurrence of ICD-9-CM code 428.x, were ascertained from participants' medical records during follow-up in the years 1990-2010. Relative hazard of heart failure across categories of trait anger was estimated with the use of Cox proportional hazard models. Study participants (mean age 56.9 [SD 5.7] years) experienced 1,985 incident HF events during 18.5 (SD 4.9) years of follow-up. Incidence of HF was greater among those with high, as compared to those with low or moderate trait anger, with higher incidence observed for men than for women. The relative hazard of incident HF was modestly high among those with high trait anger, compared with those with low or moderate trait anger (age-adjusted hazard ratio for men: 1.44 (95% confidence interval [CI] 1.23-1.69). Adjustment for comorbidities and depressive symptoms attenuated the estimated age-adjusted relative hazard in men to 1.26 (95% CI 1.00-1.60). CONCLUSIONS: Assessment of anger proneness may be necessary in successful prevention and clinical management of heart failure, especially in men.