OBJECTIVE: 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.
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.
CONCLUSIONS: 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.

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

BACKGROUND: aortic stenosis is a common heart valve disease that mainly affects older people in developed countries. Its early detection is crucial to prevent the irreversible disease progression and, eventually, death. A typical screening technique to detect stenosis uses echocardiograms; however, variations introduced by other tissues, camera movements, and uneven lighting can hamper the visual inspection, leading to misdiagnosis. To address these issues, effective solutions involve employing deep learning algorithms to assist clinicians in detecting and classifying stenosis by developing models that can predict this pathology from single heart views. Although promising, the visual information conveyed by a single image may not be sufficient for an accurate diagnosis, especially when using an automatic system; thus, this indicates that different solutions should be explored.
METHODS: following this rationale, this paper proposes a novel deep learning architecture, composed of a multi-view, multi-scale feature extractor, and a transformer encoder (MV-MS-FETE) to predict stenosis from parasternal long and short-axis views. In particular, starting from the latter, the designed model extracts relevant features at multiple scales along its feature extractor component and takes advantage of a transformer encoder to perform the final classification.
RESULTS: experiments were performed on the recently released Tufts medical echocardiogram public dataset, which comprises 27,788 images split into training, validation, and test sets. Due to the recent release of this collection, tests were also conducted on several state-of-the-art models to create multi-view and single-view benchmarks. For all models, standard classification metrics were computed (e.g., precision, F1-score). The obtained results show that the proposed approach outperforms other multi-view methods in terms of accuracy and F1-score and has more stable performance throughout the training procedure. Furthermore, the experiments also highlight that multi-view methods generally perform better than their single-view counterparts.
CONCLUSIONS: this paper introduces a novel multi-view and multi-scale model for aortic stenosis recognition, as well as three benchmarks to evaluate it, effectively providing multi-view and single-view comparisons that fully highlight the model\'s effectiveness in aiding clinicians in performing diagnoses while also producing several baselines for the aortic stenosis recognition task.

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.

UNASSIGNED: Left atrial (LA) volume indexing for body surface area (BSA) may underestimate LA size in obese and overweight people. Since LA volume is a risk marker for some cardiovascular events, it is suggested that indexing for height would be an alternative more appropriate method. The aims of this study were to find normal and the best cutoff values for LA volume indexed for height in our population.
UNASSIGNED: Echocardiograms from 2018 to 2021 were reviewed and patients without known cardiac disease and completely normal echocardiograms that had the left atrial volume (LAvol) measured by biplane Simpson\'s method were included. LAvol was indexed by BSA (ml/m2), by height (LAvol/m), by height raised to exponent 2.7 (ml/ m2.7) and by height squared (ml/h2).
UNASSIGNED: A total of 545 patients, 50.5 ± 13.4 y., 335 females (61,5%) were analyzed. There were 145 normal weight (26.6%), 215 overweight (39.4%), 154 obese (28.3%) and 31 low weight (5.7%) patients. To establish normal values we included only the normal weight group and considered normal values from 2SD below to 2SD above the mean. Mean and normal values were: LAvol/h 26.0 ±4.5, 17 - 35 ml/m, LAvol/ht2 16 ± 2.8, 10.4 - 21.6 ml/ ht2 and LAvol/ht2.7 11.4 ± 2.2, 7.0 - 15.8 ml/m2.7. The normal LAvol/ht2.7 differed between male and female (11.4 ± 2.4 and 12.8 ± 2.6, p < 0.001). LA diameter, LAvol, LAvol/h, LAvol/h2 and LAvol/ht2.7 increased progressively from low-weight, normal weight, overweight and obese patients (p< 0.0001), but not LAvol/BSA. When indexing LAvol for height, for height2 and for height2.7 20.8%, 22.7% and 21.4% of the obese patients, respectively, were reclassified as enlarged LA, and 7.4%, 8.8% and 8.4% of the overweight patients as well. Using ROC curve analysis, LAvol/h2 had the highest AUC ant the best predictive value to identify LA enlargement and LAvol/BSA the worst one.
UNASSIGNED: Normal values for LAvol indexed for height by three different methods are described in normal individuals. We reinforce that LAvol indexation for BSA underestimates LA size in obese and overweight patients and in these groups, specially, indexing for height2 is probably the best method to evaluate LAvol.

UNASSIGNED: Individuals with Acute Rheumatic Fever (ARF) often report a family history of ARF or Rheumatic Heart Disease (RHD) however the degree of familial susceptibility to RHD is poorly defined. This study aimed to determine RHD prevalence among first degree relatives of ARF patients using echocardiography.
UNASSIGNED: Children with ARF were recruited from Auckland, New Zealand. Parents and siblings ≥ 4years were offered echocardiography. Echocardiograms were reported according to World Heart Federation 2012 criteria. RHD prevalence in first degree relatives was compared to previously established population rates in the region.
UNASSIGNED: In total, 70 index cases with ARF were recruited. Echocardiography was performed in 94 parents and 132 siblings. There were 3 siblings with definite RHD and 9 with borderline RHD. There were 4 parents with definite RHD. Overall prevalence of RHD (definite and borderline) in siblings was 90/1,000 (95% CI 45-143/1,000) compared to 36/1,000 (95% CI 30-42/1,000) in New Zealand children from high ARF incidence populations (p 0.001). Prevalence of definite RHD in parents was 42/1,000 (95% CI 7-87/1,000) compared to 22/1,000 (95% CI 9-36/1,000) in adults from a high ARF incidence New Zealand population (p 0.249).
UNASSIGNED: RHD prevalence in siblings and parents of ARF cases is significantly greater than in comparable background populations. The contribution of hereditary versus environmental risk factors remains uncertain. We recommend targeted echocardiographic case-finding among siblings and parents of ARF/RHD cases in order to detect previously unrecognized latent RHD.

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.

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.

Tetralogy of Fallot (ToF) is the most common cyanotic congenital heart disease, making up 10% of all congenital heart defects. Annual follow-up echocardiograms are recommended in patients with repaired ToF, but evidence-based guidelines do not exist. We hypothesized that most echocardiograms performed in asymptomatic patients with repaired ToF and no physical exam change do not result in an actionable change (AC) in management. We retrospectively reviewed records of all patients with ToF and prior complete repair at our institution between January 2000 and September 2015. Changes in echocardiograms resulting in hospital admission, medication addition/change, cardiac catheterization, or surgical procedure were identified via chart review. These changes were referred to as an AC. A total of 1135 echocardiograms were reviewed from 233 patients (160 with initial complete repair, 70 with prior shunt, and 3 with other initial surgery). The median number of echocardiograms per patient was 5. Of the 1135 echocardiograms, 15 (1.3%) were associated with AC. Of the 15 patients with AC echocardiograms, 9 underwent a shunt prior to complete repair (9/70, 12.9%) and 6 had undergone an initial complete repair (6/160, 3.8%). The median age at AC was 6.3 years (IQR 4.4, 6.8) in the shunt group and 0.90 years (IQR 0.87, 1.1) in the initial complete repair group. In asymptomatic patients with repaired ToF and no physical exam change, echocardiograms rarely lead to a change in clinical management. In conclusion, the likelihood and timing of AC echocardiograms and reinterventions vary based on the type of initial surgery.

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.