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.

Adult congenital heart disease care in a municipal public health system

Specialty care is associated with improved outcomes for adults with adult CHD and must be extended to the underserved. A retrospective cohort study was performed to describe the provision of care to adult CHD patients in America's largest municipal public health system including patient demographics, diagnostic and therapeutic procedures, and adherence to guideline-recommended surveillance. We identified 229 adult CHD patients aged >18 years through electronic medical records. The most common diagnoses were atrial septal defect, ventricular septal defect, patent ductus arteriosus, and valvular pulmonary stenosis. In total, 65% had moderate or greater anatomic complexity. A large number of patients were uninsured (45%), non-white (96%), and non-English speaking (44%). One hundred forty-six patients (64%) presented with unrepaired primary defects. Fifty eight patients underwent primary repair during the study period; 48 of those repairs were surgical and 10 were transcatheter. Collaboration with an affiliated Comprehensive Care Center was utilised for 28% of patients. A high proportion of patients received adult CHD speciality visits (78%), echocardiograms (66%), and electrocardiograms (56%) at the guideline-recommended frequency throughout the study period. There was no significant difference in the rate of adherence to guideline-recommended surveillance based on insurance status, race/ethnicity, or primary language status. The proportion of patients who had guideline-recommended adult CHD visits, echocardiograms, and electrocardiograms was significantly lower for those with more advanced physiological stages. These results can inform the provision of adult CHD care in other public health system settings.

Cardiac evaluation in pregnant patients with dyspnea and palpitations

BACKGROUND

Symptoms of underlying cardiac disease in pregnancy can often be mistaken for common complaints because of normal physiological changes in pregnancy. Echocardiographic evaluation of patients with symptoms of palpitations and dyspnea can detect structural changes and identify high-risk features.

OBJECTIVE

This study aimed to examine transthoracic echocardiograms of perinatal individuals completed for palpitations or dyspnea to determine the frequency of identifying structural changes.

STUDY DESIGN

This was a retrospective cohort study of all perinatal individuals with a transthoracic echocardiogram at a single academic center between October 1, 2017, and May 1, 2022. The indication for the echocardiogram, demographics, and clinical characteristics were recorded. Transthoracic echocardiograms with any abnormal findings noted in the transthoracic echocardiogram report were reviewed and categorized into findings of congenital heart disease, valvular disease, pericardial effusion, evidence of ischemia or wall motion abnormalities, abnormal diastolic or systolic function, and other.

RESULTS

Of 539 transthoracic echocardiograms completed on 478 individuals who were pregnant or in the 12-week postpartum period, 96 (17.8%) had an indication of palpitations, and 32 (5.9%) had an indication of dyspnea. Abnormal findings were seen in 21.9% of patients with palpitations and in 34.4% of patients with dyspnea. In patients with palpitations who had abnormal findings, 33.3% had congenital heart disease; 33.3% had mild valvular disease, including mitral valve prolapse; 19.0% had a pericardial effusion; and 14.3% had evidence of ischemia or wall motion defects. Abnormal transthoracic echocardiogram findings in the dyspnea cohort included ischemia or wall motion defects (27.3%), mild valvular disease or mitral valve prolapse (36.4%), and abnormal systolic or diastolic function (36.4%).

CONCLUSION

Many of the transthoracic echocardiograms completed for patients with dyspnea or palpitations identified no structural abnormality; however, in 1 of 3 to 1 of 4 patients, underlying structural heart disease was identified. Although some of these abnormalities were unlikely to change delivery plans, such as mild valvular disease or small effusions, other abnormalities, such as ischemia, congenital abnormalities, and abnormal systolic or diastolic function, were likely to have implications for pregnancy and postpartum management.

Calcium Identification and Scoring Based on Echocardiography. An Exploratory Study on Aortic Valve Stenosis

Currently, an echocardiography expert is needed to identify calcium in the aortic valve, and a cardiac CT-Scan image is needed for calcium quantification. When performing a CT-scan, the patient is subject to radiation, and therefore the number of CT-scans that can be performed should be limited, restricting the patient's monitoring. Computer Vision (CV) has opened new opportunities for improved efficiency when extracting knowledge from an image. Applying CV techniques on echocardiography imaging may reduce the medical workload for identifying the calcium and quantifying it, helping doctors to maintain a better tracking of their patients. In our approach, a simple technique to identify and extract the calcium pixel count from echocardiography imaging, was developed by using CV. Based on anonymized real patient echocardiographic images, this approach enables semi-automatic calcium identification. As the brightness of echocardiography images (with the highest intensity corresponding to calcium) vary depending on the acquisition settings, echocardiographic adaptive image binarization has been performed. Given that blood maintains the same intensity on echocardiographic images-being always the darker region-blood areas in the image were used to create an adaptive threshold for binarization. After binarization, the region of interest (ROI) with calcium, was interactively selected by an echocardiography expert and extracted, allowing us to compute a calcium pixel count, corresponding to the spatial amount of calcium. The results obtained from these experiments are encouraging. With this technique, from echocardiographic images collected for the same patient with different acquisition settings and different brightness, obtaining a calcium pixel count, where pixel values show an absolute pixel value margin of error of 3 (on a scale from 0 to 255), achieving a Pearson Correlation of 0.92 indicating a strong correlation with the human expert assessment of calcium area for the same images.

Diagnosis and treatment of adults with congenital heart disease

Approximately 50 million adults worldwide have known congenital heart disease (CHD). Among the most common types of CHD defects in adults are atrial septal defects and ventricular septal defects followed by complex congenital heart lesions such as tetralogy of Fallot. Adults with CHDs are more likely to have hypertension, cerebral vascular disease, diabetes and chronic kidney disease than age-matched controls without CHD. Moreover, by the age of 50, adults with CHD are at a greater than 10% risk of experiencing cardiac dysrhythmias and approximately 4% experience sudden death. Consequently, adults with CHD require healthcare that is two- to four-times greater than adults without CHD. This paper discusses the diagnosis and treatment of adults with atrial septal defects, ventricular septal defects and tetralogy of Fallot.

Neurocardiovascular deficits in the Q175 mouse model of Huntington's disease

Cardiovascular dysautonomia as well as the deterioration of circadian rhythms are among the earliest detectable pathophysiological changes in individuals with Huntington's disease (HD). Preclinical research requires mouse models that recapitulate disease symptoms and the Q175 knock-in model offers a number of advantages but potential autonomic dysfunction has not been explored. In this study, we sought to test the dual hypotheses that cardiovascular dysautonomia can be detected early in disease progression in the Q175 model and that this dysfunction varies with the daily cycle. Using radiotelemetry implants, we observed a significant reduction in the diurnal and circadian activity rhythms in the Q175 mutants at the youngest ages. By middle age, the autonomically driven rhythms in core body temperature were highly compromised, and the Q175 mutants exhibited striking episodes of hypothermia that increased in frequency with mutant huntingtin gene dosage. In addition, Q175 mutants showed higher resting heart rate (HR) during sleep and greatly reduced correlation between activity and HR HR variability was reduced in the mutants in both time and frequency domains, providing more evidence of autonomic dysfunction. Measurement of the baroreceptor reflex revealed that the Q175 mutant could not appropriately increase HR in response to a pharmacologically induced decrease in blood pressure. Echocardiograms showed reduced ventricular mass and ejection fraction in mutant hearts. Finally, cardiac histopathology revealed localized points of fibrosis resembling those caused by myocardial infarction. Thus, the Q175 mouse model of HD exhibits cardiovascular dysautonomia similar to that seen in HD patients with prominent sympathetic dysfunction during the resting phase of the activity rhythm.