Faculty Bibliography

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.

IMPORTANCE/UNASSIGNED: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/UNASSIGNED:To determine whether an LLM can transform discharge summaries into a format that is more readable and understandable. DESIGN, SETTING, AND PARTICIPANTS/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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.

BACKGROUND/OBJECTIVES/OBJECTIVE:Little is known about trajectories of recovery 12-months after hospitalization for severe COVID. METHODS:We conducted a prospective, longitudinal cohort study of patients with and without neurological complications during index hospitalization for COVID-19 from March 10, 2020-May 20, 2020. Phone follow-up batteries were performed at 6- and 12-months post-COVID symptom onset. The primary 12-month outcome was the modified Rankin Scale (mRS) comparing patients with or without neurological complications using multivariable ordinal analysis. Secondary outcomes included: activities of daily living (Barthel Index), telephone Montreal Cognitive Assessment (t-MoCA) and Neuro-QoL batteries for anxiety, depression, fatigue and sleep. Changes in outcome scores from 6 to 12-months were compared using non-parametric paired-samples sign test. RESULTS:Twelve-month follow-up was completed in N=242 patients (median age 65, 64% male, 34% intubated during hospitalization) and N=174 completed both 6- and 12-month follow-up. At 12-months 197/227 (87%) had ≥1 abnormal metric: mRS>0 (75%), Barthel<100 (64%), t-MoCA≤18 (50%), high anxiety (7%), depression (4%), fatigue (9%) and poor sleep (10%). 12-month mRS scores did not differ significantly among those with (N=113) or without (N=129) neurological complications during hospitalization after adjusting for age, sex, race, pre-COVID mRS and intubation status (adjusted OR 1.4, 95% CI0.8-2.5), though those with neurological complications had higher fatigue scores (T-score 47 vs 44, P=0.037). Significant improvements in outcome trajectories from 6- to 12-months were observed in t-MoCA scores (56% improved, median difference 1 point, P=0.002), and Neuro-QoL anxiety scores (45% improved, P=0.003). Non-significant improvements occurred in fatigue, sleep and depression scores in 48%, 48% and 38% of patients, respectively. Barthel and mRS scores remained unchanged between 6 and 12-months in >50% of patients. DISCUSSION/CONCLUSIONS:At 12-months post-hospitalization for severe COVID, 87% of patients had ongoing abnormalities in functional, cognitive or Neuro-QoL metrics and abnormal cognition persisted in 50% of patients without a prior history of dementia/cognitive abnormality. Only fatigue severity differed significantly between patients with or without neurological complications during index hospitalization. However, significant improvements in cognitive (t-MoCA) and anxiety (Neuro-QoL) scores occurred in 56% and 45% of patients, respectively, between 6- to 12-months. These results may not be generalizable to those with mild/moderate COVID.

BACKGROUND:Elevated serum creatinine levels are a common finding in patients with urinoma (i.e. presence of urine outside of the urinary tract). Therefore, in the clinical circumstance of an urinoma, utilizing a creatinine-based estimated GFR (eGFR) to determine renal function is unreliable, as it fails to distinguish true renal failure from pseudorenal failure in patients with a urine leakage. Cystatin C, a 13 kDA molecular mass protein ubiquitously expressed by nucleated cells, offers superior accuracy in the setting of an urinoma, since unlike creatinine, it is essentially absent in excreted urine and poorly reabsorbed from the peritoneum and retroperitoneal space. METHODS:We present the first case report to demonstrate the utility of cystatin C in an adult patient with native kidney function that experienced significant retro-peritoneal bladder leakage. RESULTS:Our results demonstrate that cystatin C may be a more accurate measurement of GFR than the commonly used creatinine in the setting of an urinoma. CONCLUSION/CONCLUSIONS:In order to achieve an accurate estimated GFR in the setting of a urinoma, physicians should consider the use of Cystatin C, which is less vulnerable to inaccurate interpretation.