Local large language models for privacy-preserving accelerated review of historic echocardiogram reports.

OBJECTIVES: The study developed framework that leverages an open-source Large Language Model (LLM) to enable clinicians to ask plain-language questions about a patient's entire echocardiogram report history. This approach is intended to streamline the extraction of clinical insights from multiple echocardiogram reports, particularly in patients with complex cardiac diseases, thereby enhancing both patient care and research efficiency. MATERIALS AND METHODS: Data from over 10 years were collected, comprising echocardiogram reports from patients with more than 10 echocardiograms on file at the Mount Sinai Health System. These reports were converted into a single document per patient for analysis, broken down into snippets and relevant snippets were retrieved using text similarity measures. The LLaMA-2 70B model was employed for analyzing the text using a specially crafted prompt. The model's performance was evaluated against ground-truth answers created by faculty cardiologists. RESULTS: The study analyzed 432 reports from 37 patients for a total of 100 question-answer pairs. The LLM correctly answered 90% questions, with accuracies of 83% for temporality, 93% for severity assessment, 84% for intervention identification, and 100% for diagnosis retrieval. Errors mainly stemmed from the LLM's inherent limitations, such as misinterpreting numbers or hallucinations. CONCLUSION: The study demonstrates the feasibility and effectiveness of using a local, open-source LLM for querying and interpreting echocardiogram report data. This approach offers a significant improvement over traditional keyword-based searches, enabling more contextually relevant and semantically accurate responses; in turn showing promise in enhancing clinical decision-making and research by facilitating more efficient access to complex patient data.

Short-term safety and feasibility of a practical approach to combined atrial and ventricular physiological pacing: An initial single-center experience.

Background: Traditional right atrial appendage (RAA) pacing accentuates conduction disturbances as opposed to Bachmann bundle pacing (BBP). Objective: The purpose of this study was to evaluate the feasibility, efficacy, and safety of routine anatomically guided high right atrial septal (HRAS) pacing with activation of Bachmann bundle combined with routine left bundle branch area pacing (LBBAP). Methods: This retrospective single-center study included 96 consecutive patients who underwent 1 of 2 strategies: physiological pacing (PP) (n = 32) with HRAS and LBBAP leads and conventional pacing (CP) (n = 64) with traditional RAA and right ventricular apical leads. Baseline characteristics, sensing, pacing thresholds, and impedances were recorded at implantation and follow-up. Results: The PP and CP cohorts were of similar age (74.2 ± 13.8 years vs 73.9 ± 9.9 years) and sex (28.1% vs 40.6% female). There were no differences in procedural time (95.0 ± 31.4 minutes vs 86.5 ± 33.3 minutes; P = .19) or fluoroscopy time (12.1 ± 4.5 minutes vs 12.3 ± 13.5 minutes; P = .89) between cohorts. After excluding patients who received >2 leads, these parameters became significantly shorter in the CP cohort. The PP cohort exhibited higher atrial pacing thresholds (1.5 ± 1.1 mV vs 0.8 ± 0.3 mV; P <.001) and lower p waves (1.8 ± 0.8 mV vs 3.8 ± 2.3 mV; P <.001) at implantation and at follow-up. In the PP cohort, 72% of implants met criteria for BBP; of the ventricular leads, 94% demonstrated evidence of LBBAP. One lead-related complication occurred in each cohort. Conclusion: Routine placement of leads in the HRAS is a feasible and safe alternative to standard RAA pacing, allowing for BBP in 72% of patients. HRAS pacing can be combined with LBBAP as a routine strategy.

Quantitative Prediction of Right Ventricular Size and Function From the ECG.

BACKGROUND: Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored. METHODS AND RESULTS: We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m2), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; P=0.031). CONCLUSIONS: Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.