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.

Validation of American Society of Echocardiography Guideline-Recommended Parameters of Right Ventricular Dysfunction Using Artificial Intelligence Compared With Cardiac Magnetic Resonance Imaging.

BACKGROUND: Right ventricular (RV) function is important in the evaluation of cardiac function, but its assessment using standard transthoracic echocardiography (TTE) remains challenging. Cardiac magnetic resonance imaging (CMR) is considered the gold standard. The American Society of Echocardiography recommends surrogate measures of RV function and RV ejection fraction (RVEF) by TTE, including fractional area change (FAC), free wall strain (FWS), and tricuspid annular planar systolic excursion (TAPSE), but they require technical expertise in acquisition and quantification. METHODS: The aim of this study was to evaluate the sensitivity, specificity, and positive and negative predictive values of FAC, FWS, and TAPSE derived using a rapid, novel artificial intelligence (AI) software (LVivoRV) from a single-plane transthoracic echocardiographic apical four-chamber, RV-focused view without ultrasound-enhancing agents for detecting abnormal RV function compared with CMR-derived RVEF. RV dysfunction was defined as RVEF < 50% and RVEF < 40% on CMR. RESULTS: TTE and CMR were performed within a median of 10 days (interquartile range, 2-32 days) of each other in 225 consecutive patients without interval procedural or pharmacologic intervention. The sensitivity and negative predictive value to detect CMR-defined RV dysfunction when all three AI-derived parameters (FAC, FWS, and TAPSE) were abnormal were 91% and 96%, while those of expert physician reads were 91% and 97%. Specificity and positive predictive value were lower (50% and 32%) compared with expert physician-read echocardiograms (82% and 56%). CONCLUSIONS: AI-derived measurements of FAC, FWS, and TAPSE had excellent sensitivity and negative predictive value for ruling out significant RV dysfunction (CMR RVEF < 40%), comparable with that of expert physician readers, but lower specificity. Thus AI, using American Society of Echocardiography guidelines, may serve as a useful screening tool for rapid bedside assessment to exclude significant RV dysfunction.

Left Ventricular Thrombus Following Acute Myocardial Infarction: JACC State-of-the-Art Review.

The incidence of left ventricular (LV) thrombus following acute myocardial infarction has markedly declined in recent decades caused by advancements in reperfusion and antithrombotic therapies. Despite this, embolic events remain the most feared complication of LV thrombus necessitating systemic anticoagulation. Mechanistically, LV thrombus development depends on Virchow's triad (ie, endothelial injury from myocardial infarction, blood stasis from LV dysfunction, and hypercoagulability triggered by inflammation, with each of these elements representing potential therapeutic targets). Diagnostic modalities include transthoracic echocardiography with or without ultrasound-enhancing agents and cardiac magnetic resonance. Most LV thrombi develop within the first 2 weeks post-acute myocardial infarction, and the role of surveillance imaging appears limited. Vitamin K antagonists remain the mainstay of therapy because the efficacy of direct oral anticoagulants is less well established. Only meager data support the routine use of prophylactic anticoagulation, even in high-risk patients.

Assessment and validation of a novel fast fully automated artificial intelligence left ventricular ejection fraction quantification software.

BACKGROUND: Quantification of left ventricular ejection fraction (LVEF) by transthoracic echocardiography (TTE) is operator-dependent, time-consuming, and error-prone. LVivoEF by DIA is a new artificial intelligence (AI) software, which displays the tracking of endocardial borders and rapidly quantifies LVEF. We sought to assess the accuracy of LVivoEF compared to cardiac magnetic resonance imaging (cMRI) as the reference standard and to compare LVivoEF to the standard-of-care physician-measured LVEF (MD-EF) including studies with ultrasound enhancing agents (UEAs). METHODS: In 273 consecutive patients, we compared MD-EF and AI-derived LVEF to cMRI. AI-derived LVEF was obtained from a non-UEA four-chamber view without manual correction. Thirty-one patients were excluded: 25 had interval interventions or incomplete TTE or cMRI studies and six had uninterpretable non-UEA apical views. RESULTS: In the 242 subjects, the correlation between AI and cMRI was r = .890, similar to MD-EF and cMRI with r = .891 (p = 0.48). Of the 126 studies performed with UEAs, the correlation of AI using the unenhanced four-chamber view was r = .89, similar to MD-EF with r = .90. In the 116 unenhanced studies, AI correlation was r = .87, similar to MD-EF with r = .84. From Bland-Altman analysis, LVivoEF underreported the LVEF with a bias of 3.63 ± 7.40% EF points compared to cMRI while MD-EF to cMRI had a bias of .33 ± 7.52% (p = 0.80). CONCLUSIONS: Compared to cMRI, LVivoEF can accurately quantify LVEF from a standard apical four-chamber view without manual correction. Thus, LVivoEF has the ability to improve and expedite LVEF quantification.

Using Clinical and Echocardiographic Characteristics to Characterize the Risk of Ischemic Stroke in Patients with COVID-19.

BACKGROUND: COVID-19 has been associated with an increased incidence of ischemic stroke. The use echocardiography to characterize the risk of ischemic stroke in patients hospitalized with COVID-19 has not been explored. METHODS: We conducted a retrospective study of 368 patients hospitalized between 3/1/2020 and 5/31/2020 who had laboratory-confirmed infection with SARS-CoV-2 and underwent transthoracic echocardiography during hospitalization. Patients were categorized according to the presence of ischemic stroke on cerebrovascular imaging following echocardiography. Ischemic stroke was identified in 49 patients (13.3%). We characterized the risk of ischemic stroke using a novel composite risk score of clinical and echocardiographic variables: age <55, systolic blood pressure >140 mmHg, anticoagulation prior to admission, left atrial dilation and left ventricular thrombus. RESULTS: Patients with ischemic stroke had no difference in biomarkers of inflammation and hypercoagulability compared to those without ischemic stroke. Patients with ischemic stroke had significantly more left atrial dilation and left ventricular thrombus (48.3% vs 27.9%, p = 0.04; 4.2% vs 0.7%, p = 0.03). The unadjusted odds ratio of the composite novel COVID-19 Ischemic Stroke Risk Score for the likelihood of ischemic stroke was 4.1 (95% confidence interval 1.4-16.1). The AUC for the risk score was 0.70. CONCLUSIONS: The COVID-19 Ischemic Stroke Risk Score utilizes clinical and echocardiographic parameters to robustly estimate the risk of ischemic stroke in patients hospitalized with COVID-19 and supports the use of echocardiography to characterize the risk of ischemic stroke in patients hospitalized with COVID-19.

Echocardiography in the time of Covid-19: Ultrasound enhancing agents save time and augment diagnostic information.

BACKGROUND: There are currently no clear guidelines regarding the use of ultrasound enhancing agents (UEAs) with transthoracic echocardiography (TTE) for patients hospitalized with Covid-19. We investigated whether the performance of TTE with UEAs provides more diagnostic information and allows for shorter acquisition time compared to unenhanced TTE imaging in this patient population. METHODS: We analyzed the TTEs of 107 hospitalized Covid-19 patients between April and June 2020 who were administered UEAs (Definity®, Lantheus). The time to acquire images with and without UEAs was calculated. A level III echocardiographer determined if new, clinically significant findings were visualized with the addition of UEAs. RESULTS: There was a mean of 11.84±3.59 UEA cineloops/study vs 20.74±8.10 non-UEA cineloops/study (p < 0.0001). Mean time to acquire UEA cineloop images was 72.28±28.18 s/study compared to 188.07±86.04 s/study for non-UEA cineloop images (p < 0.0001). Forty-eight patients (45%) had at least one new finding on UEA imaging, with a total of 62 new findings seen. New information gained with UEAs was more likely to be found in patients with acute respiratory distress syndrome (21 vs 9, p < 0.001) and in those on mechanical ventilation (21 vs 15, p = 0.046). CONCLUSIONS: TTE with UEAs required less time and fewer cineloop images compared to non-UEA imaging in patients hospitalized with Covid-19. Additionally, Covid-19 patients with severe respiratory disease benefited most with regard to new diagnostic information. Health care personnel should consider early use of UEAs in select hospitalized Covid-19 patients in order to reduce exposure and optimize diagnostic yield.

Racial and ethnic differences in severity of coronary calcification among patients undergoing PCI: Results from a single-center multiethnic PCI registry.

BACKGROUND: Although population-based studies have demonstrated racial heterogeneity in coronary artery calcium (CAC) burden, the degree to which such associations extend to percutaneous coronary intervention (PCI) cohorts remains poorly characterized. We sought to evaluate the associations between race/ethnicity and CAC in a PCI population. METHODS: This single center retrospective study analyzed 1025 patients with prior CAC who underwent PCI between January 1, 2012 and May 15, 2020. Patients were grouped as non-Hispanic White (NHW, N = 779), non-Hispanic Black (NHB, N = 81) and Hispanic (H, N = 165). Associations between race and CAC (Agatston units) were examined using negative binomial regression while adjusting for baseline parameters. RESULTS: Among the 1025 patients (mean age 65.8, 70% male) who underwent PCI, NHW, NHB, and H populations had median CAC scores of 760, 500, and 462 Agatston units, respectively (p < 0.0001). Hispanic patients displayed a higher burden of diabetes mellitus, hypertension and hyperlipidemia compared with other groups. After adjusting for baseline differences and compared with NHW, the inverse association between Hispanic and CAC persisted (ß = -324.1, p < 0.0001) whereas differences were not significant for NHB (ß = -51.5, p = 0.67). CONCLUSIONS: Despite a higher risk clinical phenotype, Hispanic patients who underwent PCI had significantly lower CAC compared with non-Hispanic patients. Thus, current risk stratification models using universalized CAC scores may underestimate the risk for the Hispanic population. Race/ethnicity-informed CAC thresholds may better guide clinical decisions.

Prognostic Value of Electrocardiographic QRS Diminution in Patients Hospitalized With COVID-19 or Influenza.

During the clinical care of hospitalized patients with COVID-19, diminished QRS amplitude on the surface electrocardiogram (ECG) was observed to precede clinical decompensation, culminating in death. This prompted investigation into the prognostic utility and specificity of low QRS complex amplitude (LoQRS) in COVID-19. We retrospectively analyzed consecutive adults admitted to a telemetry service with SARS-CoV-2 (n = 140) or influenza (n = 281) infection with a final disposition-death or discharge. LoQRS was defined as a composite of QRS amplitude <5 mm or <10 mm in the limb or precordial leads, respectively, or a ≥50% decrease in QRS amplitude on follow-up ECG during hospitalization. LoQRS was more prevalent in patients with COVID-19 than influenza (24.3% vs 11.7%, p = 0.001), and in patients who died than survived with either COVID-19 (48.1% vs 10.2%, p <0.001) or influenza (38.9% vs 9.9%, p <0.001). LoQRS was independently associated with mortality in patients with COVID-19 when adjusted for baseline clinical variables (odds ratio [OR] 11.5, 95% confidence interval [CI] 3.9 to 33.8, p <0.001), presenting and peak troponin, D-dimer, C-reactive protein, albumin, intubation, and vasopressor requirement (OR 13.8, 95% CI 1.3 to 145.5, p = 0.029). The median time to death in COVID-19 from the first ECG with LoQRS was 52 hours (interquartile range 18 to 130). Dynamic QRS amplitude diminution is a strong independent predictor of death over not only the course of COVID-19 infection, but also influenza infection. In conclusion, this finding may serve as a pragmatic prognostication tool reflecting evolving clinical changes during hospitalization, over a potentially actionable time interval for clinical reassessment.

Atrial Fibrillation in Patients Hospitalized With COVID-19: Incidence, Predictors, Outcomes, and Comparison to Influenza.

OBJECTIVES: The goal of this study is to determine the incidence, predictors, and outcomes of atrial fibrillation (AF) or atrial flutter (AFL) in patients hospitalized with coronavirus disease-2019 (COVID-19). BACKGROUND: COVID-19 results in increased inflammatory markers previously associated with atrial arrhythmias. However, little is known about their incidence or specificity in COVID-19 or their association with outcomes. METHODS: This is a retrospective analysis of 3,970 patients admitted with polymerase chain reaction-positive COVID-19 between February 4 and April 22, 2020, with manual review performed of 1,110. The comparator arm included 1,420 patients with influenza hospitalized between January 1, 2017, and January 1, 2020. RESULTS: Among 3,970 inpatients with COVID-19, the incidence of AF/AFL was 10% (n = 375) and in patients without a history of atrial arrhythmias it was 4% (n = 146). Patients with new-onset AF/AFL were older with increased inflammatory markers including interleukin 6 (93 vs. 68 pg/ml; p < 0.01), and more myocardial injury (troponin-I: 0.2 vs. 0.06 ng/ml; p < 0.01). AF and AFL were associated with increased mortality (46% vs. 26%; p < 0.01). Manual review captured a somewhat higher incidence of AF/AFL (13%, n = 140). Compared to inpatients with COVID-19, patients with influenza (n = 1,420) had similar rates of AF/AFL (12%, n = 163) but lower mortality. The presence of AF/AFL correlated with similarly increased mortality in both COVID-19 (relative risk: 1.77) and influenza (relative risk: 1.78). CONCLUSIONS: AF/AFL occurs in a subset of patients hospitalized with either COVID-19 or influenza and is associated with inflammation and disease severity in both infections. The incidence and associated increase in mortality in both cohorts suggests that AF/AFL is not specific to COVID-19, but is rather a generalized response to the systemic inflammation of severe viral illnesses.

A Personalized Approach to Chronic Kidney Disease and Cardiovascular Disease: JACC Review Topic of the Week.

Cardiovascular disease is the most common cause of death in patients with end-stage renal disease (ESRD). The initiation of dialysis for treatment of ESRD exacerbates chronic electrolyte and hemodynamic perturbations. Rapid large shifts in effective intravascular volume and electrolyte concentrations ultimately lead to subendocardial ischemia, increased left ventricular wall mass, and diastolic dysfunction, and can precipitate serious arrhythmias through a complex pathophysiological process. These factors, unique to advanced kidney disease and its treatment, increase the overall incidence of acute coronary syndrome and sudden cardiac death. To date, risk prediction models largely fail to incorporate the observed cardiovascular mortality in the CKD population; however, multimodality imaging may provide an additional prognostication and risk stratification. This comprehensive review discusses the cardiovascular risks associated with hemodialysis, and explores the pathophysiology and the novel utilization of multimodality imaging in CKD to promote a personalized approach for these patients with implications for future research.

Transcatheter embolic coils to treat peridevice leaks after left atrial appendage closure.

BACKGROUND: Left atrial appendage closure (LAAC) has proven to be an effective alternative to long-term oral anticoagulation in the prevention of thromboembolic events in patients with atrial fibrillation. In a minority of patients, inadequate seal may result in persistent peridevice flow and inability of the appendage to fully thrombose, thereby representing a potential source for thromboembolism. OBJECTIVE: The purpose of this study was to study the use of endovascular coiling of the appendage to address persistent peridevice leak in patients undergoing LAAC with the Watchman device. METHODS: This is a retrospective single-center analysis involving patients who underwent placement of a LAAC device and returned for endovascular coiling to address persistent device leak between 2018 and 2020. Baseline characteristics, procedural outcomes, and follow-up echocardiograms were analyzed to demonstrate the feasibility and safety of this technique. RESULTS: Patients (N = 20) were identified with a mean leak size of 3.8 ± 1.3 mm (range 2.5-7 mm), all of whom had a non-thrombosed appendage. Acute procedural success was achieved in 95% of patients. Complete or significant reduction in flow beyond the LAAC device was achieved in 61% and 33% of patients, respectively. The 1 procedure-related adverse event was a pericardial effusion before coil deployment, requiring percutaneous drainage. CONCLUSION: The clinical impact of residual peridevice leak post-Watchman implantation is a matter of continuing investigation. However, appendage coiling represents a new therapeutic tool to address this potential source for thromboembolism. Further studies should address the clinical impact of this technique, including the safety of discontinuing anticoagulation after successful coiling.

Abnormal left ventricular global longitudinal strain by speckle tracking echocardiography in COVID-19 patients.

COVID-19 infection can affect the cardiovascular system. We sought to determine if left ventricular global longitudinal strain (LVGLS) is affected by COVID-19 and if this has prognostic implications. Materials & methods: Retrospective study, with LVGLS was measured in 58 COVID-19 patients. Patients discharged were compared with those who died. Results: The mean LV ejection fraction (LVEF) and LVGLS for the cohort was 52.1 and -12.9 ± 4.0%, respectively. Among 30 patients with preserved LVEF (>50%), LVGLS was -15.7 ± 2.8%, which is lower than the reference mean LVGLS for a normal, healthy population. There was no significant difference in LVGLS or LVEF when comparing patients who survived to discharge or died. Conclusion: LVGLS was reduced in COVID-19 patients, although not significantly lower in those who died compared with survivors.

Biventricular strain by speckle tracking echocardiography in COVID-19: findings and possible prognostic implications.

The COVID-19 infection adversely affects the cardiovascular system. Transthoracic echocardiography has demonstrated diagnostic, prognostic and therapeutic utility. We report biventricular myocardial strain in COVID-19. Methods: Biventricular strain measurements were performed for 12 patients. Patients who were discharged were compared with those who needed intubation and/or died. Results: Seven patients were discharged and five died or needed intubation. Right ventricular strain parameters were decreased in patients with poor outcomes compared with those discharged. Left ventricular strain was decreased in both groups but was not statistically significant. Conclusion: Right ventricular strain was decreased in patients with poor outcomes and left ventricular strain was decreased regardless of outcome. Right ventricular strain measurements may be important for risk stratification and prognosis. Further studies are needed to confirm these findings.

Malignant Arrhythmias in Patients With COVID-19: Incidence, Mechanisms, and Outcomes.

BACKGROUND: Patients with coronavirus disease 2019 (COVID-19) who develop cardiac injury are reported to experience higher rates of malignant cardiac arrhythmias. However, little is known about these arrhythmias-their frequency, the underlying mechanisms, and their impact on mortality. METHODS: We extracted data from a registry (NCT04358029) regarding consecutive inpatients with confirmed COVID-19 who were receiving continuous telemetric ECG monitoring and had a definitive disposition of hospital discharge or death. Between patients who died versus discharged, we compared a primary composite end point of cardiac arrest from ventricular tachycardia/fibrillation or bradyarrhythmias such as atrioventricular block. RESULTS: Among 800 patients with COVID-19 at Mount Sinai Hospital with definitive dispositions, 140 patients had telemetric monitoring, and either died (52) or were discharged (88). The median (interquartile range) age was 61 years (48-74); 73% men; and ethnicity was White in 34%. Comorbidities included hypertension in 61%, coronary artery disease in 25%, ventricular arrhythmia history in 1.4%, and no significant comorbidities in 16%. Compared with discharged patients, those who died had elevated peak troponin I levels (0.27 versus 0.02 ng/mL) and more primary end point events (17% versus 4%, P=0.01)-a difference driven by tachyarrhythmias. Fatal tachyarrhythmias invariably occurred in the presence of severe metabolic imbalance, while atrioventricular block was largely an independent primary event. CONCLUSIONS: Hospitalized patients with COVID-19 who die experience malignant cardiac arrhythmias more often than those surviving to discharge. However, these events represent a minority of cardiovascular deaths, and ventricular tachyarrhythmias are mainly associated with severe metabolic derangement. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04358029.

Trimming the need for invasive ventilation: pragmatic critical care during the COVID-19 pandemic.

COVID-19 has challenged all medical professionals to optimise non-invasive positive pressure ventilation (NIV) as a means of limiting intubation. We present a case of a middle-aged man with a voluminous beard for religious reasons who developed progressive hypoxic respiratory failure secondary to COVID-19 infection which became refractory to NIV. After gaining permission to trim the patient's facial hair by engaging with the patient, his family and religious leaders, his mask fit objectively improved, his hypoxaemia markedly improved and an unnecessary intubation was avoided. Trimming of facial hair should be considered in all patients on NIV who might have any limitations with mask fit and seal that would hamper ventilation, including patients who have facial hair for religious reasons.