Faculty Bibliography

BACKGROUND:Decisions involving the purchase of procedural equipment at the health system level require balancing efficacy, safety, physician preference, and cost. The application of efficient and low-cost pragmatic study designs has the potential to rapidly generate data to inform health system operations. METHODS:The aim of the pragmatic RAISE-EMR study is to determine physician preference between two commercially available radial artery introducer sheaths, one of which has a higher acquisition cost, to guide inventory selection in the hospital system's catheterization laboratories. Patients undergoing coronary angiography using 6-French radial artery access were prospectively identified and randomized through the health system's electronic medical record (EMR). Among 1696 eligible unique patients, 554 patients (32.7%) were randomized over 37 days across three hospitals. Randomization took place through the EMR after the attending interventional cardiologist signed a mandated pre-procedure note. The study was deemed non-human subject research and approved by the NYU Langone Health Quality Improvement Oversight Committee. The primary endpoint, a physician satisfaction score, will be ascertained by a mandated semi-quantitative survey within the electronic procedure note. All data, including co-variables and clinical outcomes, will be ascertained using structured data within the EMR. CONCLUSIONS:The RAISE-EMR study is designed to determine physician preference of two commercially available radial artery introducer sheaths and potentially reduce supply costs using an entirely EMR-based randomized study design. Pragmatic study designs leveraging structured data within an EMR can be used to rapidly provide data to inform operational decision-making and have implications for the future of evidence generation.

IMPORTANCE/UNASSIGNED:Hospital course (HC) summarization represents an increasingly onerous discharge summary component for physicians. Literature supports large language models (LLMs) for HC summarization, but whether physicians can effectively partner with electronic health record-embedded LLMs to draft HCs is unknown. OBJECTIVES/UNASSIGNED:To compare the editing effort required by time-constrained resident physicians to improve LLM- vs physician-generated HCs toward a novel 4Cs (complete, concise, cohesive, and confabulation-free) HC. DESIGN, SETTING, AND PARTICIPANTS/UNASSIGNED:Quality improvement study using a convenience sample of 10 internal medicine resident editors, 8 hospitalist evaluators, and randomly selected general medicine admissions in December 2023 lasting 4 to 8 days at New York University Langone Health. EXPOSURES/UNASSIGNED:Residents and hospitalists reviewed randomly assigned patient medical records for 10 minutes. Residents blinded to author type who edited each HC pair (physician and LLM) for quality in 3 minutes, followed by comparative ratings by attending hospitalists. MAIN OUTCOMES AND MEASURES/UNASSIGNED:Editing effort was quantified by analyzing the edits that occurred on the HC pairs after controlling for length (percentage edited) and the degree to which the original HCs' meaning was altered (semantic change). Hospitalists compared edited HC pairs with A/B testing on the 4Cs (5-point Likert scales converted to 10-point bidirectional scales). RESULTS/UNASSIGNED:Among 100 admissions, compared with physician HCs, residents edited a smaller percentage of LLM HCs (LLM mean [SD], 31.5% [16.6%] vs physicians, 44.8% [20.0%]; P < .001). Additionally, LLM HCs required less semantic change (LLM mean [SD], 2.4% [1.6%] vs physicians, 4.9% [3.5%]; P < .001). Attending physicians deemed LLM HCs to be more complete (mean [SD] difference LLM vs physicians on 10-point bidirectional scale, 3.00 [5.28]; P < .001), similarly concise (mean [SD], -1.02 [6.08]; P = .20), and cohesive (mean [SD], 0.70 [6.14]; P = .60), but with more confabulations (mean [SD], -0.98 [3.53]; P = .002). The composite scores were similar (mean [SD] difference LLM vs physician on 40-point bidirectional scale, 1.70 [14.24]; P = .46). CONCLUSIONS AND RELEVANCE/UNASSIGNED:Electronic health record-embedded LLM HCs required less editing than physician-generated HCs to approach a quality standard, resulting in HCs that were comparably or more complete, concise, and cohesive, but contained more confabulations. Despite the potential influence of artificial time constraints, this study supports the feasibility of a physician-LLM partnership for writing HCs and provides a basis for monitoring LLM HCs in clinical practice.

BACKGROUND:High-sensitivity cardiac troponin (hs-cTnI) assays can quantify troponin concentrations with low limits of detection, potentially expediting and enhancing myocardial infarction diagnoses. This study investigates the real-world impact of hs-cTnI implementation on operational metrics and downstream cardiac services in patients presenting to the emergency department with chest pain. METHODS AND RESULTS/RESULTS:[lt] 0.001) during the index encounter. CONCLUSION/CONCLUSIONS:Implementation of the hs-cTnI assay was associated with reduced hospital admissions, shorter length of stay, and decreases in most downstream cardiac testing.

BACKGROUND:Genetic testing is a cornerstone in the assessment of many cardiac diseases. However, variants are frequently classified as variants of unknown significance, limiting the utility of testing. Recently, the DeepMind group (Google) developed AlphaMissense, a unique artificial intelligence-based model, based on language model principles, for the prediction of missense variant pathogenicity. We aimed to report on the performance of AlphaMissense, accessed by VarCardio, an open web-based variant annotation engine, in a real-world cardiovascular genetics center. METHODS AND RESULTS/RESULTS:<0.001). Genotype-phenotype concordance was highly aligned using VarCard.io predictions, at 95.9% (95% CI, 92.8-97.9) concordance rate. For 109 variants classified as pathogenic, likely pathogenic, benign, or likely benign by ClinVar, concordance with VarCard.io was high (90.5%). CONCLUSIONS:AlphaMissense, accessed via VarCard.io, may be a highly efficient tool for cardiac genetic variant interpretation. The engine's notable performance in assessing variants that are classified as variants of unknown significance in ClinVar demonstrates its potential to enhance cardiac genetic testing.

BACKGROUND:Medical centers with varying levels of expertise treat gastroenteropancreatic neuroendocrine tumors (GEP-NETs), which are relatively rare tumors. This study assesses the impact of center volume on GEP-NET treatment outcomes. METHODS:We used the Surveillance, Epidemiology, and End Results (SEER) registry linked to Medicare claims data. The data includes patients diagnosed between 1995 and 2010 who had no health maintenance organization (HMO) coverage, participated in Medicare parts A and B, were older than 65 at diagnosis, had tumor differentiation information, and had no secondary cancer. We identified medical centers at which patients received GEP-NET treatment (surgery, chemotherapy, somatostatin analogues, or radiation therapy) using Medicare claims data. Center volume was divided into 3 tiers - low, medium, and high - based on the number of unique GEP-NET patients treated by a medical center over 2 years. We used Kaplan-Meier curves and Cox regression to assess the association between volume and disease-specific survival. RESULTS:We identified 899 GEP-NET patients, of whom 37, 45, and 18% received treatment at low, medium volume, and high-volume centers, respectively. Median disease-specific survival for patients at low and medium tiers were 1.4 years and 5.3 years, respectively, but was not reached for patients at high volume centers. Results showed that patients treated at high volume centers had better survival than those treated in low volume centers (HR: 0.63, 95% CI: 0.4-0.9), but showed no difference in outcomes between medium and high-volume centers. CONCLUSIONS:Our results suggest that for these increasingly common tumors, referral to a tertiary care center may be indicated. Physicians caring for GEP-NET patients should consider early referral to high volume centers.

OBJECTIVE:Frailty is a prevalent risk factor for adverse outcomes among patients with chronic lung disease. However, identifying frail patients who may benefit from interventions is challenging using standard data sources. We therefore sought to identify phrases in clinical notes in the electronic health record (EHR) that describe actionable frailty syndromes. MATERIALS AND METHODS:We used an active learning strategy to select notes from the EHR and annotated each sentence for 4 actionable aspects of frailty: respiratory impairment, musculoskeletal problems, fall risk, and nutritional deficiencies. We compared the performance of regression, tree-based, and neural network models to predict the labels for each sentence. We evaluated performance with the scaled Brier score (SBS), where 1 is perfect and 0 is uninformative, and the positive predictive value (PPV). RESULTS:We manually annotated 155 952 sentences from 326 patients. Elastic net regression had the best performance across all 4 frailty aspects (SBS 0.52, 95% confidence interval [CI] 0.49-0.54) followed by random forests (SBS 0.49, 95% CI 0.47-0.51), and multi-task neural networks (SBS 0.39, 95% CI 0.37-0.42). For the elastic net model, the PPV for identifying the presence of respiratory impairment was 54.8% (95% CI 53.3%-56.6%) at a sensitivity of 80%. DISCUSSION:Classification models using EHR notes can effectively identify actionable aspects of frailty among patients living with chronic lung disease. Regression performed better than random forest and neural network models. CONCLUSIONS:NLP-based models offer promising support to population health management programs that seek to identify and refer community-dwelling patients with frailty for evidence-based interventions.

INTRODUCTION:The TNM classification for lung cancer, originally designed for NSCLC, is applied to staging of bronchopulmonary carcinoid tumors. The validity of the eighth edition of the staging system for carcinoid tumors has not been assessed. In this study, we evaluated its prognostic accuracy by using data from a large national population-based cancer registry. METHODS:Patients with typical and atypical bronchopulmonary carcinoids diagnosed between 2000 and 2013 were identified from the National Cancer Institute's Surveillance, Epidemiology and End Results registry. We used competing risks analysis to compare 10-year disease-specific survival (DSS) across stages. RESULTS:Overall, 4645 patients with bronchopulmonary carcinoid tumors were identified. Worsening DSS with increasing TNM status and stage was demonstrated across both typical and atypical carcinoids, with overlaps between adjacent subcategories. The combined stages (I versus II, II versus III, and III versus IV) showed greater separation in DSS despite persistent overlaps between groups. For typical carcinoids, we found decreased DSS for stages II, III, and IV, with hazard ratios of 3.8 (95% confidence interval [CI]: 2.6-5.6), 4.3 (95% CI: 3.0-6.1), and 9.0 (95% CI: 6.1-13.1), respectively, compared with stage I. CONCLUSION:The combined stage categories of the eighth edition of the TNM staging system provide useful information on outcomes for typical and atypical carcinoids. However, persistent overlaps in combined stage and subcategories of the staging system limit the usefulness of the TNM staging system, particularly in intermediate stages. These limitations suggest the need for future further study and refinement.

PURPOSE:Current staging criteria for gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs), while useful, have limitations. In this study, we used a population-based registry to evaluate the prognostic utility of the current staging systems and assess whether evidence-based modifications can improve survival predictions. METHODS:We identified patients with confirmed GEP-NENs from the Surveillance, Epidemiology and End Results registry. We assigned tumour-node-metastasis status according to American Joint Committee on Cancer and European Neuroendocrine Tumor Society criteria. We derived a revised staging classification using Kaplan-Meier methods and Cox regression to assess disease-specific survival and compared the accuracy of potential models based on the Akaike Information Criterion (AIC) and Harrell's C-index. The revised classification was validated in an independent set. RESULTS:We identified 10,268 patients with GEP-NENs. We found that multiple stages, as determined by current criteria, misclassified patients' prognosis. In particular, stage IIIB (T1-4N1) had overlapping survival with stage IIIA (T4N0). A revised system which reclassifies N1 disease into different stages based on T status (T1-2N1, T3N1 and T4N1) had an improved AIC (difference = 38) and C-index (0.86) compared to current staging. These revisions improved predictions in patients with both low and high-grade tumours from all primary sites. Results also were confirmed across all primary sites in the validation set. CONCLUSION:Current staging guidelines misclassify the prognosis of N1 patients. Our results suggest that a revised system could lead to better prognostication for GEP-NEN patients. Further validation followed by implementation of these revisions may improve treatment selection and design of clinical trials.