Citations

Background: Pulmonary hypertension (PH) is a complex condition associated with significant morbidity and mortality. Traditional diagnostic and management approaches for PH often face limitations, leading to delays in diagnosis and potentially suboptimal treatment outcomes. Artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL) offers a transformative approach to PH care. Materials and Methods: We systematically searched PubMed, Scopus, and Web of Science for original studies on AI applications in PH, using predefined keywords. Out of more than 500 initial articles, 45 relevant studies were selected. Risk of bias was evaluated using PROBAST (Prediction model Risk of Bias Assessment Tool). Results: This review examines the potential applications of AI in PH, focusing on its role in enhancing diagnosis, disease classification, and prognostication. We discuss how AI-powered analysis of medical data can improve the accuracy and efficiency of detecting PH. Furthermore, we explore the potential of AI in risk stratification, leading to treatment optimization for PH. Conclusions: While acknowledging the existing challenges and limitations and the need for continued exploration and refinement of AI-driven tools, this review highlights the significant promise of AI in revolutionizing PH management to improve patient outcomes.

Background: Acute promyelocytic leukemia (APL) is one of the most treatable leukemias in the current era, with cure rates upwards of 90%. Early mortality due to coagulopathies often seen at diagnosis is a major driver of adverse outcomes. Prompt initiation of all-trans retinoic acid (ATRA) is crucial for suspected APL, as it is known to reverse these coagulopathies. Chemotherapy-free protocols consisting of arsenic trioxide (ATO) and ATRA have become the standard of care for low-risk APL with high cure rates and reduced hematologic toxicities. For high-risk disease, there are multiple treatment options that have not been compared. Since APL is rare, there is a lack of real-world data for this disease. This retrospective review aimed to assess the outcomes of APL patients (pts) across multiple institutions and to examine the most common induction regimens, characteristics linked to early (30-day) mortality, and supportive care strategies. Methods: This retrospective study involved 9 institutions in the US and was conducted through the Consortium on Myeloid Malignancies and Neoplastic Diseases (COMMAND). Data included pts admitted from 8/5/2006 through 2/3/2024 with a confirmed diagnosis of APL. Each institution received a data-collection form and contributed data on APL pts from presentation to last follow-up. Key data categories included patient demographics, presenting laboratory and molecular data, treatment regimen, supportive care, and patient outcomes. Results: Data for 412 pts were identified with a median age of 51 (range 17-90) and 49% were female. Cardiovascular comorbidities were present in 44% of pts and 16% had a known pulmonary comorbidity. At presentation 109 (27%) had high risk-disease, defined as a white blood cell count (WBC) greater than 10 x 109/L. A FLT3 mutation was seen in 50% of tested pts, WT1 (22%), KRAS (3.6%), and NRAS (6.5%). The median WBC at presentation was 2 x 109/L (range: 0-166 x 109/L) and the median platelet count was 27 x 109/L (range: 2.0-315 109/L). Twenty-six percent presented with grade 2+ thrombosis, bleeding, or both. A higher percentage of pts with high-risk vs. low-risk disease presented with grade 2+ thrombosis, bleeding, or both (43% vs. 20%), DIC (60% vs. 36%), and mutated FLT3 (81% vs. 37%). The majority of pts received a chemotherapy-free induction regimen consisting of ATRA plus ATO. It was determined that 36 (8.7%) pts received induction with intermittent ATO plus ATRA (Burnett AK, Lancet Oncol 2015), 276 (67%) received daily ATO plus ATRA (Ravandi F, J Clin Oncol 2009 and Lo Coco, NEJM 2013), and 70 (17%) received a regimen inclusive of an anthracycline plus ATRA. Eleven pts did not start an induction regimen other than single-agent ATRA due to early death, while 19 had their regimen classified as “other” because they did not follow a conventional induction path. In total, 295/358 (82%) received ATRA within 24 hours of admission. At least 1 dose of gemtuzumab ozogamicin was given to 58 (14%) pts, of which 35 (60%) were considered high risk. The incidence of differentiation syndrome (DS) was 37% (n=154). Among the 243 pts who received steroid prophylaxis, 30% developed DS, compared to 52% of those who did not receive prophylaxis. Among the 360 pts with at least 1 available PCR result after starting induction, 94% achieved PCR-negativity. The 30-day mortality rate was 6.6%. On univariate analysis, presenting variables associated with a higher 30-day mortality include older age, diabetes, cardiovascular comorbidities, thrombosis or bleeding, DIC, eGFR < 60, elevated total bilirubin and D-dimer levels, and high-risk disease. The median overall survival (OS) of the cohort was not reached, and the 5- and 10-year OS was 88% (95% CI: 84-91%) and 79% (95% CI: 72-87%) respectively. The cumulative incidence of relapse at 3 years was 2.7% (95% CI: 1.4 - 5.1%), with no additional relapses observed. The incidence of CNS relapse at 3 years was 0.9% (95% CI: 0.3% - 2.8%), with 2 of the 4 pts classified as high-risk. Conclusion: This is the largest real-world evidence data collection in the US evaluating the outcome of pts with APL in the current era, inclusive of ATO as front-line induction. Outcomes for this disease remain extremely positive, with low 30-day mortality rates noted in this study along with durable OS rates and low incidence of relapse. Additional information on outcomes, safety, and supportive care will be presented at the meeting.

Abstract Aims The increasing need for diagnostic echocardiography tests presents challenges in preserving the quality and promptness of reports. While Large Language Models (LLMs) have proven effective in summarizing clinical texts, their application in echo remains underexplored. Methods and results Adult echocardiography studies, conducted at the Mayo Clinic from 1 January 2017 to 31 December 2017, were categorized into two groups: development (all Mayo locations except Arizona) and Arizona validation sets. We adapted open-source LLMs (Llama-2, MedAlpaca, Zephyr, and Flan-T5) using In-Context Learning and Quantized Low-Rank Adaptation fine-tuning (FT) for echo report summarization from ‘Findings’ to ‘Impressions.’ Against cardiologist-generated Impressions, the models’ performance was assessed both quantitatively with automatic metrics and qualitatively by cardiologists. The development dataset included 97 506 reports from 71 717 unique patients, predominantly male (55.4%), with an average age of 64.3 ± 15.8 years. EchoGPT, a fine-tuned Llama-2 model, outperformed other models with win rates ranging from 87% to 99% in various automatic metrics, and produced reports comparable to cardiologists in qualitative review (significantly preferred in conciseness (P < 0.001), with no significant preference in completeness, correctness, and clinical utility). Correlations between automatic and human metrics were fair to modest, with the best being RadGraph F1 scores vs. clinical utility (r = 0.42) and automatic metrics showed insensitivity (0–5% drop) to changes in measurement numbers. Conclusion EchoGPT can generate draft reports for human review and approval, helping to streamline the workflow. However, scalable evaluation approaches dedicated to echo reports remains necessary.

Introduction/Background: Loeys-Dietz syndrome (LDS) is a rare autosomal dominant aortic aneurysm syndrome characterized by arterial tortuosity resulting in arterial aneurysms and dissections, with unique craniofacial and skeletal features including bifid uvula, cleft palate and hypertelorism. While the presence of atrial fibrillation (Afib) and arrhythmias have been reported in LDS patients, limited investigation has been completed regarding the associated risk and severity of vascular complications in relationship to these arrhythmias1,2. Research Questions/Hypothesis: Are there any differences in vascular outcomes in patients with LDS when experiencing various forms of tachyarrhythmia? Goals/Aims: To evaluate the relationship between various types of arrhythmias and vascular outcomes in patients with LDS, including arterial dissection, stroke, revascularization, and death. Methods/Approach: A large sample of LDS patients (n=436) from a single tertiary referral center was assessed for ICD-10 diagnoses of arrhythmia and outcomes of interest. Arrhythmias assessed included Afib, atrial flutter (AFL), premature ventricular contractions (PVCs), and supraventricular tachycardia (SVT). Outcomes were arterial dissection, hemorrhagic and ischemic stroke, revascularization, and all-cause mortality. Results/Data: Our cohort (n=436) had an average age of 47 and was 57.8% female. A total of 26 patients had a documented history of tachyarrhythmia: 16 (3.4%) Afib, 2 (0.5%) AFL, 6 (1.4%) SVT, and 2 (0.5%) PVC. LDS patients with Afib were at significantly higher risk of arterial dissection (25% vs 6.0%, OR: 5.3, p<0.01), revascularization (18.8% vs 3.3%, OR: 8.1, p<0.01), stroke (25% vs 3.6%, OR: 9.0, p<0.001), and death (25% vs 4.3%, OR: 7.4, p<0.01) compared to those without a documented history of arrhythmia. Other arrhythmia types evaluated were not significant. Predictors of any arrhythmia type included hypertension (78% vs 31%, OR: 1.5, p<0.001) and heart failure (39% vs 5.0%, OR: 2.3, p<0.001). Conclusion: Although rare, Afib in LDS patients is associated with adverse vascular outcomes and mortality compared to those without a history of arrhythmia. Furthermore, the magnitude of increased risk is striking. Early identification and management of Afib in LDS patients may be critical in mitigating the risk of potential vascular complications.

Background: Atrial fibrillation (AF), the most common clinically managed cardiac arrhythmia, is known to increase the risk of heart failure, stroke, and mortality. Lipoprotein(a) [Lp(a)], a well-established risk factor for atherosclerotic cardiovascular disease (ASCVD), also plays a role in cardiovascular health. However, the influence of Lp(a) on the development of AF, independent of its association with ASCVD, remains unclear. Hypothesis: Elevated Lp(a) may be associated with increased risk of new-onset AF. Methods: A retrospective study was conducted on patients from the three Mayo Clinic sites who had their Lp(a) levels measured and had no prior history of AF. Patients were categorized into two groups based on their serum Lp(a) concentrations: high Lp(a) (≥50 mg/dL) and low Lp(a) (<50 mg/dL). New AF diagnoses were identified during the follow-up period. Survival probabilities between the two Lp(a) groups were compared using the Kaplan–Meier curve and the Log-Rank test. Cox regression analyses, both univariable and multivariable, were performed to evaluate established risk factors and compare the risk of new-onset AF between the high and low Lp(a) groups. Results: A total of 108,930 patients were included (median age: 55 years, 58% males), with a follow-up duration for up to 10 years. Incident AF was detected in 8432 (7.7%) patients. Median serum levels of Lp(a) were significantly higher in patients with AF versus non-AF patients: 15 (IQR 43) vs. 12 (IQR 34) mg/dL, p<0.001. The percentage of patients having elevated Lp(a) was significantly higher in the AF group versus non-AF group: 2119 (25%) vs 21151 (21%), p<0.001. Survival probability for new-onset AF was significantly lower in patients with elevated Lp(a) compared with those with low Lp(a) (log rank p<0.001, Figure 1). In the univariate analysis, high Lp(a) levels were associated with a 17% increase in the risk of AF (HR = 1.17, 95% CIs: 1.12 to 1.23). The multivariate analysis adjusted for well-established risk factors for AF showed a less strong but still significant association, with a 10% increase in AF risk (HR = 1.10, 95% CI: 1.05 to 1.15). Conclusion: Our study suggests that elevated Lp(a) (≥50 mg/dL) seems to be an independent risk factor for new-onset AF. Future prospective studies are still warranted to validate our results.

Abstract Background Cardiac metastasis from neuroendocrine tumors (NET) is rare and has been thought to potentially result in life threatening sequalae. Peptide receptor radionucleotide therapy (PRRT), such as Lutetium-177 (Lu-177) DOTATATE, has been validated as effective treatment for patients with NET who have progressed on somatostatin analogue (SSA) therapy and more recently suggested for use in SAA-naïve higher risk grade 2 and grade 3 NETs. However, Lu-177 DOTATATE therapy has been found to have potentially serious adverse effects both locally and systemically. Overall, the clinical significance of cardiac metastasis of NET, as well as the safety and efficacy of Lu-177 DOTATATE in this cohort, has not been thoroughly evaluated. Purpose This study assessed the outcomes and clinical consequences of cardiac metastatic involvement in patients with NET. Furthermore, this study investigated the safety of Lu-177 DOTATATE therapy in patients with cardiac metastases from NET. Methods All patients who underwent 68Ga-DOTATATE positron emission tomography for evaluation of NET across three tertiary centers between 2016 and 2022 were retrospectively evaluated. Patients with evidence of cardiac metastasis were further evaluated. Baseline characteristics, treatment modality, and clinical outcomes including mortality, arrhythmia or conduction disease, carcinoid heart disease, and heart failure admissions were recorded. Patients with cardiac metastases were grouped and compared based on therapeutic modality (conservative therapy with surveillance or SSA, Lu-177 DOTATATE therapy, or surgical resection of metastases). Results From 3253 patients with NET, 51 patients were identified to have cardiac metastases (mean age 66.7 ± 12.2 years, 54% male). Three patients underwent surgical resection of cardiac metastases, and in two of whom this was concomitant while undergoing valve surgery for carcinoid heart disease. Patients with cardiac metastasis had significantly higher mortality than patients without cardiac metastasis (HR 2.12, 95%CI 1.00 – 4.52, p = 0.049, Figure 1A). Median follow-up from diagnosis of cardiac metastasis was 3.64 years [IQR 1.59 – 5.64]. There was no significant difference in clinical outcomes between patients that received Lu-177 DOTATATE therapy (n = 27) and conservative therapy (n = 21). Specifically, there was no significant difference in mortality risk at five years post the diagnosis of cardiac metastasis between these groups (p = 0.47, Figure 1B). Conclusion Patients with cardiac metastasis from NETs have worse clinical outcomes than NET patients without cardiac metastatic involvement. Lu-177 DOTATATE therapy appears to be safe in patients with cardiac metastasis from NET.Figure 1AFigure 1B

Lipoprotein (a) is a complex lipid molecule that has sparked immense interest in recent years, after studies demonstrated its significant association with several cardiovascular conditions. Lp(a) promotes cardiovascular disease through its combined proatherogenic, pro-inflammatory, and prothrombotic effects. While the measurement of Lp(a) has become widely available, effective methods to reduce its concentration are currently limited. However, emerging data from ongoing clinical trials involving antisense oligonucleotides have indicated promising outcomes in effectively reducing Lp(a) concentrations. This may serve as a potential therapeutic target in the management and prevention of myocardial infarction, calcific aortic stenosis, and cerebrovascular accidents. In contrast, the role of Lp(a) in atrial fibrillation, in-stent restenosis, cardiac allograft vasculopathy, and bioprosthetic aortic valve degeneration remains unclear. This review article aims to thoroughly review the existing literature and provide an updated overview of the evidence surrounding the association of Lp(a) and these cardiovascular diseases. We seek to highlight controversies in the existing literature and offer directions for future investigations to better understand Lp(a)’s precise role in these conditions, while providing a summary of its unique molecular characteristics.

Coronary CT angiography (CCTA) is now endorsed by all major cardiology guidelines for the investigation of chest pain and assessment for coronary artery disease (CAD) in appropriately selected patients. CAD is a leading cause of morbidity and mortality. There is extensive literature to support CCTA diagnostic and prognostic value both for stable and acute symptoms. It enables rapid and cost-effective rule-out of CAD, and permits quantification and characterization of coronary plaque and associated significance. In this comprehensive review, we detail the road traveled as CCTA evolved to include quantitative assessment of plaque stenosis and extent, characterization of plaque characteristics including high-risk features, functional assessment including fractional flow reserve-CT (FFR-CT), and CT perfusion techniques. The state of current guideline recommendations and clinical applications are reviewed, as well as future directions in the rapidly advancing field of CT technology, including photon counting and applications of artificial intelligence (AI).