Multimodal Data-Driven Prognostic Model for Predicting Long-Term Prognosis in Patients With Ischemic Cardiomyopathy and Heart Failure With Preserved Ejection Fraction After Coronary Artery Bypass Grafting: A Multicenter Cohort Study

Multimodal Visualization and Explainable Machine Learning-Driven Markers Enable Early Identification and Prognosis Prediction for Symptomatic Aortic Stenosis and Heart Failure With Preserved Ejection Fraction After Transcatheter Aortic Valve Replacement: Multicenter Cohort Study

BACKGROUND

Currently, there is a paucity of literature addressing personalized risk stratification using multimodal data in patients with symptomatic aortic stenosis and heart failure with preserved ejection fraction (HFpEF) following transcatheter aortic valve replacement (TAVR).

OBJECTIVE

This study aimed to enhance the performance of risk assessment models in this patient population by developing a predictive model for adverse outcomes using various machine learning (ML) techniques.

METHODS

This multicenter cohort study included 326 patients diagnosed with severe AS and HFpEF who underwent TAVR between January 2017 and December 2023. Patients were allocated to training (n=195) and independent validation (n=131) sets based on hospital affiliation. A dual-phase feature selection process, combining least absolute shrinkage and selection operator logistic regression and the Boruta algorithm, was used to identify relevant variables from the multimodal dataset. A total of 5 ML model-decision trees, K-nearest neighbors, random forest, support vector machine, and extreme gradient boosting were used to construct a visualization and explainable predictive framework to elucidate model decision-making processes.

RESULTS

The primary features identified included age, N-terminal pro-brain natriuretic peptide, fasting blood glucose, triglyceride/high-density lipoprotein cholesterol ratio, triglyceride glucose index, triglyceride glucose-BMI index, atherogenic index of plasma index, and Apolipoprotein B. Among the 5 models, the support vector machine demonstrated the best predictive performance for major adverse cardiovascular and cerebrovascular events in patients with severe AS and HFpEF following TAVR, achieving an area under the curve of 0.756 (95% CI 0.631-0.881) in the independent validation set. The model exhibited good calibration and robust predictive power in both training and validation sets and demonstrated the highest net benefit in decision curve analysis compared to other models. To extract significant variables influencing the algorithm and ensure model appropriateness, we interpreted cohort and personalized model predictions using Shapley Additive Explanations values.

CONCLUSIONS

Our ML-based multimodal model, incorporating 8 readily accessible predictors, demonstrated robust predictive capability for 12 months of major adverse cardiovascular and cerebrovascular events risk. This model can be used to identify high-risk individuals with AS and HFpEF following TAVR, potentially aiding in risk stratification and personalized treatment strategies.

Associations of Gla-rich protein and interleukin-1β with coronary artery calcification risk in patients with suspected coronary artery disease

Background

Gla-rich protein (GRP) and interleukin-1β (IL-1β) are recognized as reliable biomarkers for evaluating inflammation and are effective predictors of cardiovascular disease. However, the relationship between GRP, IL-1β, and coronary artery calcification (CAC) in patients with suspected coronary artery disease (CAD) remains unclear. Therefore, we investigated the association between these inflammatory biomarkers (GRP and IL-1β) and CAC in patients with suspected CAD.

Methods

This prospective study included patients with suspected CAD who underwent coronary computed tomography angiography (CTA). Fasting venous blood samples were collected at admission, and GRP and IL-1β levels were quantified using enzyme-linked immunosorbent assays (ELISA). The Agatston score was calculated to assess coronary artery calcification (CAC) based on coronary CTA findings.

Results

A total of 120 patients were included in this study. Multivariate logistic regression analysis revealed that GRP [odds ratio (OR), 1.202; 95% confidence interval (CI), 1.065-1.356; p = 0.003] and IL-1β (OR, 1.011; 95% CI, 1.002-1.020; p = 0.015) were independent risk factors for CAC severity. Receiver operating characteristic (ROC) curve analysis demonstrated that GRP had a predictive ability for CAC, with an area under the curve (AUC) of 0.830 [95% CI (0.755, 0.904)]. IL-1β exhibited an AUC of 0.753 [95% CI (0.660, 0.847)]. The combination of GRP and IL-1β in a predictive model improved the AUC to 0.835. Additionally, GRP and IL-1β levels showed a strong positive correlation (r = 0.6861, p < 0.05), and GRP was significantly associated with CAC severity (r = 0.5018, p < 0.05).

Conclusions

Elevated levels of GRP and IL-1β, as inflammatory biomarkers, were associated with CAC in patients with suspected CAD. These biomarkers may provide valuable insights into the pathophysiology of coronary artery calcification and contribute to improved risk stratification in this patient population.

Hyper-DREAM, a Multimodal Digital Transformation Hypertension Management Platform Integrating Large Language Model and Digital Phenotyping: Multicenter Development and Initial Validation Study

Within the mHealth framework, systematic research that collects and analyzes patient data to establish comprehensive digital health archives for hypertensive patients, and leverages large language models (LLMs) to assist clinicians in health management and Blood Pressure (BP) control remains limited. In this study, our aims to describe the design, development and usability evaluation process of a management platform (Hyper-DREAM) for hypertension. Our multidisciplinary team employed an iterative design approach over the course of a year to develop the Hyper-DREAM platform. This platform's primary functionalities encompass multimodal data collection (personal hypertensive digital phenotype archive), multimodal interventions (BP measurement, medication assistance, behavior modification, and hypertension education) and multimodal interactions (clinician-patient engagement and BP Coach component). In August 2024, the mHealth App Usability Questionnaire (MAUQ) was conducted involving 51 hypertensive patients recruited from three distinct centers. In parallel, six clinicians engaged in management activities and contributed feedback via the Doctor's Software Satisfaction Questionnaire (DSSQ). Concurrently, a real-world comparative experiment was conducted to evaluate the usability of the BP Coach, ChatGPT-4o Mini, ChatGPT-4o and clinicians. The comparative experiment demonstrated that the BP Coach achieved significantly higher scores in utility (mean scores 4.05, SD 0.87) and completeness (mean scores 4.12, SD 0.78) when compared to ChatGPT-4o Mini, ChatGPT-4o, and clinicians. In terms of clarity, the BP Coach was slightly lower than clinicians (mean scores 4.03, SD 0.88). In addition, the BP Coach exhibited lower performance in conciseness (mean scores 3.00, SD 0.96). Clinicians reported a marked improvement in work efficiency (2.67 vs. 4.17, P < .001) and experienced faster and more effective patient interactions (3.0 vs. 4.17, P = .004). Furthermore, the Hyper-DREAM platform significantly decreased work intensity (2.5 vs. 3.5, P = .01) and minimized disruptions to daily routines (2.33 vs. 3.55, P = .004). The Hyper-DREAM platform demonstrated significantly greater overall satisfaction compared to the WeChat-based standard management (3.33 vs. 4.17, P = .01). Additionally, clinicians exhibited a markedly higher willingness to integrate the Hyper-DREAM platform into clinical practice (2.67 vs. 4.17, P < .001). Furthermore, patient management time decreased from 11.5 min (SD 1.87) with Wechat-based standard management to 7.5 min (SD 1.84, P = .01) with Hyper-DREAM. Hypertensive patients reported high satisfaction with the Hyper-DREAM platform, including ease of use (mean scores 1.60, SD 0.69), system information arrangement (mean scores 1.69, SD 0.71), and usefulness (mean scores 1.57, SD 0.58). In conclusion, our study presents Hyper-DREAM, a novel artificial intelligence-driven platform for hypertension management, designed to alleviate clinician workload and exhibiting significant promise for clinical application. The Hyper-DREAM platform is distinguished by its user-friendliness, high satisfaction rates, utility, and effective organization of information. Furthermore, the BP Coach component underscores the potential of LLMs in advancing mHealth approaches to hypertension management.

Predictors of Adverse Cardiovascular Events After CABG in Patients with Previous Heart Failure

Coronary artery disease (CAD) is the primary risk factor for heart failure (HF) development. Coronary artery bypass graft (CABG) surgery remains the gold-standard treatment for multivessel coronary artery disease. The purpose of this study was to identify predictors of cardiovascular events in patients after CABG by looking at clinical parameters, examining biomarkers of inflammation and fibrosis, and assessing patients' adherence to heart failure therapy before CABG. The prospective observational study included consecutively hospitalized patients with HF and CAD eligible for CABG (n = 82). The study's primary endpoint was a combination (MACE) of cardiac death, hospitalization with HF, acute ischemic events requiring unplanned revascularization, or stroke. The enzyme-linked immunosorbent assay was performed to assess serum levels of NGAL, GDF-15, NTproBNP, TGF beta, and hsCRP. The participants' medication adherence level was assessed using the Morisky-Green scale. A total of 37 events were registered (45.1%) at follow-up (36 (26; 43) months). All patients were divided into two groups: Group 1 (n = 45) comprised patients without the combined endpoint, and Group 2 (n = 37) comprised patient who suffered adverse cardiovascular events. A high GDF-15 level and low adherence based on the Morisky-Green scale were independent predictors of a MACE at follow-up. The median time before the development of the MACE which was predicted based on Kaplan-Meier analysis in the group with a GDF-15 value less than 2064 pg/mL was 64 (50; 80) months, and in the group with a GDF-15 value more than or equal to 2064 pg/mL, it was 40 (34; 46) months (p < 0.001). Higher GDF-15 values and poor adherence to treatment are associated with adverse cardiovascular events in patients with HF and CAD who have undergone CABG. However, further studies are needed to support the use of GDF-15 as a prognostic marker in real-life clinical practice.

Noninvasive Oral Hyperspectral Imaging-Driven Digital Diagnosis of Heart Failure With Preserved Ejection Fraction: Model Development and Validation Study

BACKGROUND

Oral microenvironmental disorders are associated with an increased risk of heart failure with preserved ejection fraction (HFpEF). Hyperspectral imaging (HSI) technology enables the detection of substances that are visually indistinguishable to the human eye, providing a noninvasive approach with extensive applications in medical diagnostics.

OBJECTIVE

The objective of this study is to develop and validate a digital, noninvasive oral diagnostic model for patients with HFpEF using HSI combined with various machine learning algorithms.

METHODS

Between April 2023 and August 2023, a total of 140 patients were recruited from Renmin Hospital of Wuhan University to serve as the training and internal testing groups for this study. Subsequently, from August 2024 to September 2024, an additional 35 patients were enrolled from Three Gorges University and Yichang Central People's Hospital to constitute the external testing group. After preprocessing to ensure image quality, spectral and textural features were extracted from the images. We extracted 25 spectral bands from each patient image and obtained 8 corresponding texture features to evaluate the performance of 28 machine learning algorithms for their ability to distinguish control participants from participants with HFpEF. The model demonstrating the optimal performance in both internal and external testing groups was selected to construct the HFpEF diagnostic model. Hyperspectral bands significant for identifying participants with HFpEF were identified for further interpretative analysis. The Shapley Additive Explanations (SHAP) model was used to provide analytical insights into feature importance.

RESULTS

Participants were divided into a training group (n=105), internal testing group (n=35), and external testing group (n=35), with consistent baseline characteristics across groups. Among the 28 algorithms tested, the random forest algorithm demonstrated superior performance with an area under the receiver operating characteristic curve (AUC) of 0.884 and an accuracy of 82.9% in the internal testing group, as well as an AUC of 0.812 and an accuracy of 85.7% in the external testing group. For model interpretation, we used the top 25 features identified by the random forest algorithm. The SHAP analysis revealed discernible distinctions between control participants and participants with HFpEF, thereby validating the diagnostic model's capacity to accurately identify participants with HFpEF.

CONCLUSIONS

This noninvasive and efficient model facilitates the identification of individuals with HFpEF, thereby promoting early detection, diagnosis, and treatment. Our research presents a clinically advanced diagnostic framework for HFpEF, validated using independent data sets and demonstrating significant potential to enhance patient care.

TRIAL REGISTRATION

China Clinical Trial Registry ChiCTR2300078855; https://www.chictr.org.cn/showproj.html?proj=207133.