Machine Learning - Based Bleeding Risk Predictions in Atrial Fibrillation Patients on Direct Oral Anticoagulants.

Importance: Accurately predicting major bleeding events in non-valvular atrial fibrillation (AF) patients on direct oral anticoagulants (DOACs) is crucial for personalized treatment and improving patient outcomes, especially with emerging alternatives like left atrial appendage closure devices. The left atrial appendage closure devices reduce stroke risk comparably but with significantly fewer non-procedural bleeding events. Objective: To evaluate the performance of machine learning (ML) risk models in predicting clinically significant bleeding events requiring hospitalization and hemorrhagic stroke in non-valvular AF patients on DOACs compared to conventional bleeding risk scores (HAS-BLED, ORBIT, and ATRIA) at the index visit to a cardiologist for AF management. Design: Prognostic modeling with retrospective cohort study design using electronic health record (EHR) data, with clinical follow-up at one-, two-, and five-years. Setting: University of Pittsburgh Medical Center (UPMC) system. Participants: 24,468 non-valvular AF patients aged ≥18 years treated with DOACs, excluding those with prior history of significant bleeding, other indications for DOACs, on warfarin or contraindicated to DOACs. Exposures: DOAC therapy for non-valvular AF. Main Outcomes and Measures: The primary endpoint was clinically significant bleeding requiring hospitalization within one year of index visit. The models incorporated demographic, clinical, and laboratory variables available in the EHR at the index visit. Results: Among 24,468 patients, 553 (2.3%) had bleeding events within one year, 829 (3.5%) within two years, and 1,292 (5.8%) within five years of index visit. We evaluated multivariate logistic regression and ML models including random forest, classification trees, k-nearest neighbor, naive Bayes, and extreme gradient boosting (XGBoost) which modestly outperformed HAS-BLED, ATRIA, and ORBIT scores in predicting clinically significant bleeding at 1-year follow-up. The best performing model (random forest) showed area under the curve (AUC-ROC) 0.76 (0.70-0.81), G-Mean score of 0.67, net reclassification index 0.14 compared to 0.57 (0.50-0.63), G-Mean score of 0.57 for HASBLED score, p-value for difference <0.001. The ML models had improved performance compared to conventional risk across time-points of 2-year and 5-years and within the subgroup of hemorrhagic stroke. SHAP analysis identified novel risk factors including measures from body mass index, cholesterol profile, and insurance type beyond those used in conventional risk scores. Conclusions and Relevance: Our findings demonstrate the superior performance of ML models compared to conventional bleeding risk scores and identify novel risk factors highlighting the potential for personalized bleeding risk assessment in AF patients on DOACs.

Meta-Analysis of the Performance of AI-Driven ECG Interpretation in the Diagnosis of Valvular Heart Diseases.

Valvular heart diseases (VHDs) significantly impact morbidity and mortality rates worldwide. Early diagnosis improves patient outcomes. Artificial intelligence (AI) applied to electrocardiogram (ECG) interpretation presents a promising approach for early VHD detection. We conducted a meta-analysis on the efficacy of AI models in this context. We reviewed databases including PubMed, MEDLINE, Embase, Scopus, and Cochrane until August 20, 2023, focusing on AI for ECG-based VHD detection. The outcomes included pooled accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value. The pooled proportions were derived using a random-effects model with 95% confidence intervals (CIs). Study heterogeneity was evaluated with the I-squared statistic. Our analysis included 10 studies, involving ECG data from 713,537 patients. The AI algorithms mainly screened for aortic stenosis (n = 6), mitral regurgitation (n = 4), aortic regurgitation (n = 3), mitral stenosis (n = 1), mitral valve prolapse (n = 2), and tricuspid regurgitation (n = 1). A total of 9 studies used convolution neural network models, whereas 1 study combined the strengths of support vector machine logistic regression and multilayer perceptron for ECG interpretation. The collective AI models demonstrated a pooled accuracy of 81% (95% CI 73 to 89, I² = 92%), sensitivity was 83% (95% CI 77 to 88, I² = 86%), specificity was 72% (95% CI 68 to 75, I² = 52%), PPV was 13% (95% CI 7 to 19, I² = 90%), and negative predictive value was 99% (95% CI 97 to 99, I² = 50%). The subgroup analyses for aortic stenosis and mitral regurgitation detection yielded analogous outcomes. In conclusion, AI-driven ECG offers high accuracy in VHD screening. However, its low PPV indicates the need for a combined approach with clinical judgment, especially in primary care settings.

Primary palliative care for heart failure provided within ambulatory cardiology: A randomized pilot trial.

BACKGROUND: Heart failure is characterized by physical and emotional symptoms and decreased quality of life (QoL). Palliative care can reduce burdens of serious illness but often is limited to inpatient or academic settings. OBJECTIVES: To develop and test the Primary Education for Nurses in Palliative care-HF (PENPal-HF) intervention, training outpatient cardiology nurses to address symptom burden, patient priorities for care and QoL, and advance care planning as part of quarterly HF visits. METHODS: We conducted a pilot randomized clinical trial for adults with NYHA Stage III or IV HF and ≥ 2 hospitalizations in the past 12 months, recruited from a community-based cardiology clinic. Participants were randomized 2:1, PENPal-HF plus usual care versus usual care alone. Primary outcomes were feasibility and acceptability. RESULTS: We randomized 30 adults with Stage III HF - 20 to PENPal-HF and 10 to usual care. Most in the intervention group (71%) and in the control group (62%) completed the study through the final outcome assessment in week 56; 5 participants died. Of 20 participants in the intervention, 14 (70%) remained in the study through the end of intervention visits; 11 (55%) completed all visits. Most intervention participants (93.75%) agreed or strongly agreed that they were satisfied with their care, and 87.5% agreed or strongly agreed that all people with HF should receive the intervention. Most intervention group participants (93.75%) reported a perceived improvement in physical symptoms, mood, and/or QoL. CONCLUSIONS: This pilot study suggests that nurse-led primary palliative care in outpatient cardiology settings is promising. Research is warranted to determine efficacy and effectiveness.

Management of cardiac diseases in liver transplant recipients: Comprehensive review and multidisciplinary practice-based recommendations.

Cardiac diseases are one of the most common causes of morbidity and mortality following liver transplantation (LT). Prior studies have shown that cardiac diseases affect close to one-third of liver transplant recipients (LTRs) long term and that their incidence has been on the rise. This rise is expected to continue as more patients with advanced age and/or non-alcoholic steatohepatitis undergo LT. In view of the increasing disease burden, a multidisciplinary initiative was developed to critically review the existing literature (between January 1, 1990 and March 17, 2021) surrounding epidemiology, risk assessment, and risk mitigation of coronary heart disease, arrhythmia, heart failure, and valvular heart disease and formulate practice-based recommendations accordingly. In this review, the expert panel emphasizes the importance of optimizing management of metabolic syndrome and its components in LTRs and highlights the cardioprotective potential for the newer diabetes medications (e.g., sodium glucose transporter-2 inhibitors) in this high-risk population. Tailoring the multidisciplinary management of cardiac diseases in LTRs to the cardiometabolic risk profile of the individual patient is critical. The review also outlines numerous knowledge gaps to pave the road for future research in this sphere with the ultimate goal of improving clinical outcomes.

Perceptions of Need for Palliative Care in Recently Hospitalized Patients With Systolic Heart Failure.

CONTEXT: The symptom burden associated with heart failure (HF) remains high despite improvements in therapy and calls for the integration of palliative care into traditional HF care. Little is also known about how patients with HF perceive palliative care and patient-level characteristics associated with the need for palliative care, which could influence the utilization of palliative care in HF management. OBJECTIVES: To identify characteristics of HF patients associated with perceived need for palliative care. METHODS: We analyzed data from the Hopeful Heart Trial, which studied the efficacy of a collaborative care intervention for treating both systolic HF and depression. Palliative care preferences were collected during routine study follow-up. We assessed the association of perceived need for palliative care during study follow-up and baseline data on sociodemographics, clinical measures, and patient-centered outcomes. We then used descriptive statistics and logistic regression to analyze our data. RESULTS: Participants were on average 64 years old, male, and reported severe HF symptoms and poor to below average quality of life (. Most had unfavorable impressions of palliative care, but many still perceived a need for palliative care. Factors associated with perceived need for palliative care included depression, non-white race, more severe HF symptoms, and lower mental & physical health-related quality of life. CONCLUSION: HF patients' beliefs about palliative care may affect utilization of palliative care. Specific characteristics can help identify patients with HF who may benefit from palliative care involvement. Education targeted towards patients with selected attributes may help incorporate palliative care into HF management.

SafeNET: Initial development and validation of a real-time tool for predicting mortality risk at the time of hospital transfer to a higher level of care.

BACKGROUND: Processes for transferring patients to higher acuity facilities lack a standardized approach to prognostication, increasing the risk for low value care that imposes significant burdens on patients and their families with unclear benefits. We sought to develop a rapid and feasible tool for predicting mortality using variables readily available at the time of hospital transfer. METHODS AND FINDINGS: All work was carried out at a single, large, multi-hospital integrated healthcare system. We used a retrospective cohort for model development consisting of patients aged 18 years or older transferred into the healthcare system from another hospital, hospice, skilled nursing or other healthcare facility with an admission priority of direct emergency admit. The cohort was randomly divided into training and test sets to develop first a 54-variable, and then a 14-variable gradient boosting model to predict the primary outcome of all cause in-hospital mortality. Secondary outcomes included 30-day and 90-day mortality and transition to comfort measures only or hospice care. For model validation, we used a prospective cohort consisting of all patients transferred to a single, tertiary care hospital from one of the 3 referring hospitals, excluding patients transferred for myocardial infarction or maternal labor and delivery. Prospective validation was performed by using a web-based tool to calculate the risk of mortality at the time of transfer. Observed outcomes were compared to predicted outcomes to assess model performance. The development cohort included 20,985 patients with 1,937 (9.2%) in-hospital mortalities, 2,884 (13.7%) 30-day mortalities, and 3,899 (18.6%) 90-day mortalities. The 14-variable gradient boosting model effectively predicted in-hospital, 30-day and 90-day mortality (c = 0.903 [95% CI:0.891-0.916]), c = 0.877 [95% CI:0.864-0.890]), and c = 0.869 [95% CI:0.857-0.881], respectively). The tool was proven feasible and valid for bedside implementation in a prospective cohort of 679 sequentially transferred patients for whom the bedside nurse calculated a SafeNET score at the time of transfer, taking only 4-5 minutes per patient with discrimination consistent with the development sample for in-hospital, 30-day and 90-day mortality (c = 0.836 [95%CI: 0.751-0.921], 0.815 [95% CI: 0.730-0.900], and 0.794 [95% CI: 0.725-0.864], respectively). CONCLUSIONS: The SafeNET algorithm is feasible and valid for real-time, bedside mortality risk prediction at the time of hospital transfer. Work is ongoing to build pathways triggered by this score that direct needed resources to the patients at greatest risk of poor outcomes.

Long-Term Outcomes of Primary Cardiac Malignancies: Multi-Institutional Results From the National Cancer Database.

BACKGROUND: Data on primary cardiac malignancies are limited to small single-center studies. OBJECTIVES: The aim of the current study was to provide detailed outcomes for treatment of primary cardiac malignancies from a multi-institutional database. METHODS: Outcomes were acquired from the National Cancer Database for all solid primary cardiac malignancies from 2004 to 2016. The primary outcome was long-term survival. Logistic regression was used to determine factors associated with mortality. RESULTS: A total of 100,317 cardiac tumors were identified, of which 826 (0.8%) were primary malignant tumors. After exclusion criteria, the cohort consisted of 747 patients (median age 53 years, 47.5% women). Most tumors were primary sarcomas (88.5%), the majority of which were hemangiosarcoma (40.4%). A total of 136 patients received no therapy, 113 received just chemotherapy, and 20 received just radiation. Surgery was performed in 442 (59.2%) patients including 255 patients undergoing multimodal therapy (surgery with chemotherapy, radiation, or chemoradiation). With surgery alone, 90-day mortality was 29.4%. Overall 30-day, 1-year, and 5-year survival rates were 81.2%, 45.3%, and 11.5%, respectively. The surgery group as compared with the no surgery groups had significantly better long-term survival (p < 0.0001). For stage III disease, there was a statistically significant improvement in survival with the addition of chemotherapy to surgery. CONCLUSIONS: Primary cardiac malignancies are rare cancers with dismal long-term survival despite mode of treatment. Patients who underwent surgery and those with stage III disease who received peri-operative chemotherapy had better survival compared with those who did not. However, there was likely a significant selection bias in patients chosen for surgical or medical therapy.

A Comprehensive Review of Outcome Predictors in Low MELD Patients.

Risk scoring for patients with cirrhosis has evolved greatly over the past several decades. However, patients with low Model for End-Stage Liver Disease-Sodium scores still suffer from liver-related morbidity and mortality. Unfortunately, it is not clear which of these low Model for End-Stage Liver Disease-Sodium score patients would benefit from earlier consideration of liver transplantation. This article reviews the literature of risk prediction in patients with cirrhosis, identifies which patients may benefit from earlier interventions, such as transplantation, and proposes directions for future research.