Mengmeng Ji

Pulmonary hypertension (PH) is a progressive cardiopulmonary disorder associated with high morbidity and mortality. Delayed diagnosis, heterogeneous disease phenotypes, and variable treatment responses remain major clinical challenges. Artificial intelligence (AI), including machine learning and deep learning, has emerged as a promising tool for improving PH management. AI-based models have demonstrated promising performance in screening, diagnosis, classification, risk stratification, and prognosis prediction using multimodal data such as electrocardiography, chest radiography, computed tomography, cardiac magnetic resonance imaging, echocardiography, and electronic health records. Furthermore, AI may support individualized risk assessment, treatment-response prediction, early identification of right ventricular deterioration, and longitudinal remote monitoring. Emerging technologies, including explainable AI, federated learning, large language models, and digital twins, may further advance precision medicine in PH. Despite these advances, data quality, interpretability, privacy, and clinical implementation of AI remain challenges. This review summarizes current applications, opportunities, and challenges of AI in PH and discusses future directions for AI-assisted precision healthcare.

Background: Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome characterized by frequent underdiagnosis, diverse etiologies, and limited therapeutic options. Given its complexity, artificial intelligence (AI) and machine learning (ML) offer promising avenues to decode high-dimensional, multi-modal healthcare data. This review aims to synthesize the current landscape of AI/ML applications in HFpEF, evaluating their potential to address critical unmet clinical needs. Methods: We conducted a comprehensive review of the literature focusing on AI/ML paradigms in HFpEF. Key methodological frameworks were examined, including supervised, unsupervised, semi-supervised, and reinforcement learning, alongside advanced techniques such as deep learning and natural language processing (NLP). The analysis focused on the application of these techniques across four domains: diagnosis, sub-phenotyping, risk prediction, and optimization of diagnostic modalities, with specific emphasis on studies incorporating external validation. Results: Current evidence demonstrates that AI approaches effectively enhance diagnostic accuracy and facilitate the identification of distinct HFpEF phenotypes beyond traditional classifications. These technologies show significant utility in refining prognostic assessments and optimizing diagnostic testing strategies. Furthermore, ML-driven analytics provide a robust framework for improving patient selection and streamlining clinical trial design, potentially overcoming historical barriers to drug development in this population. Conclusions: AI represents a transformative tool capable of dissecting the heterogeneity of HFpEF to enable precision medicine. While the potential to improve clinical outcomes is substantial, challenges regarding model interpretability, bias, and clinical integration persist. Future efforts must focus on rigorous external validation and prospective trials to ensure the responsible translation of these technologies into routine clinical practice.

Heart failure (HF) imposes a significant burden on public health, affecting over 56.19 million people worldwide. Right ventricular (RV) dysfunction may occur in HF patients due to various factors, including adverse interventricular interactions, ischemic heart disease, and HF-correlated pulmonary hypertension. Additionally, the deterioration of RV function plays a critical role in the progression of HF, regardless of left ventricular (LV) systolic function, suggesting an unfavorable outcome. Throughout the progression of HF and increasing afterload, the right ventricle undergoes adaptive remodeling to preserve adequate cardiac output. Right ventricular-pulmonary artery (RV-PA) coupling integrates the dynamic adaptation of RV systolic function to afterload and has been considered a stronger predictor of HF prognosis than other conventional parameters. Thus, accurate evaluations of RV-PA coupling are significant in the clinical diagnosis and management of HF patients, along with prognostic speculation. In this review, we summarize the basic principles and measurements of RV-PA coupling and focus on its clinical significance across each subtype of HF.

Atrioventricular coupling refers to the synchronized interaction between the atrial and ventricular phases of contraction and relaxation within the cardiac cycle. Atrioventricular coupling can be assessed by the left atrioventricular coupling index and right atrioventricular coupling index. These indices provide a comprehensive assessment of the functional interdependence between the atrial and ventricular chambers, and offer insights into cardiac performance beyond traditional markers. Atrioventricular coupling indices are critical for aiding in risk stratification and clinical decision‐making, ultimately improving patient outcomes. This review focuses on the clinical utility of atrioventricular coupling in various cardiac pathologies.

Pulmonary regurgitation usually leads to right heart dilatation and eventually right heart dysfunction, which is associated with a poor prognosis. Transcatheter pulmonary valve replacement is a developing treatment for pulmonary valve dysfunction that can take the place of traditional surgery and make up for the shortcomings of a large injury. Echocardiography plays a significant role in assessing ventricular function; however, conventional echocardiographic parameters have several limitations. Speckle tracking echocardiography has been regarded as a more accurate tool for quantifying cardiac function than conventional echocardiography. Therefore, the aim of this review was to summarize the application of speckle tracking echocardiography for evaluating right and left ventricular functions in patients after transcatheter pulmonary valve replacement.

Heart failure with preserved ejection fraction (HFpEF) is defined as HF with left ventricular ejection fraction (LVEF) not less than 50%. HFpEF accounts for more than 50% of all HF patients, and its prevalence is increasing year to year with the aging population, with its prognosis worsening. The clinical assessment of cardiac function and prognosis in patients with HFpEF remains challenging due to the normal range of LVEF and the nonspecific symptoms and signs. In recent years, new echocardiographic techniques have been continuously developed, particularly speckle-tracking echocardiography (STE), which provides a sensitive and accurate method for the comprehensive assessment of cardiac function and prognosis in patients with HFpEF. Therefore, this article reviewed the clinical utility of STE in patients with HFpEF.

Primary cardiac tumors (PCTs) are rare, with benign PCTs being relatively common in approximately 75% of all PCTs. Benign PCTs are usually asymptomatic, and they are found incidentally by imaging. Even if patients present with symptoms, they are usually nonspecific. Before the application of imaging modalities to the heart, our understanding of these tumors is limited to case reports and autopsy studies. The advent and improvement of various imaging technologies have enabled the non-invasive evaluation of benign PCTs. Although echocardiography is the most commonly used imaging examination, it is not the best method to describe the histological characteristics of tumors. At present, cardiac magnetic resonance (CMR) and cardiac computed tomography (CCT) are often used to assess benign PCTs providing detailed information on anatomical and tissue features. In fact, each imaging modality has its own advantages and disadvantages, multimodality imaging uses two or more imaging types to provide valuable complementary information. With the widespread use of multimodality imaging, these techniques play an indispensable role in the management of patients with benign PCTs by providing useful diagnostic and prognostic information to guide treatment. This article reviews the multimodality imaging characterizations of common benign PCTs.

Atrial fibrillation (AF) is the most common arrhythmia with significant morbidity and mortality. Exacerbated by the aging population, the prevalence of AF is gradually increasing. Accurate evaluation of structure and function of left atrium (LA) has important prognostic significance in patients with AF. Echocardiography is the imaging technique of first choice to assess LA structure and function due to its better availability, accessibility and safety over cardiac computed tomography and cardiac magnetic resonance. Therefore, the aim of this review is to summarize the recent research progress of evaluating LA size by three-dimensional echocardiography and LA function by speckle tracking echocardiography (STE) in predicting the occurrence and recurrence of AF and determining the risk of stroke in AF. In addition, we summarized the role of traditional echocardiography in detecting AF patients that are at high risk of heart failure or cardiovascular death.

Patients with heart failure (HF) have high morbidity and mortality. Accurate assessment of right ventricular (RV) function has important prognostic significance in patients with HF. However, conventional echocardiographic parameters of RV function have limitations in RV assessments due to the complex geometry of right ventricle. In recent years, speckle tracking echocardiography (STE) has been developed as promising imaging technique to accurately evaluate RV function. RV longitudinal strain (RVLS) using STE, as a sensitive index for RV function evaluation, displays the powerfully prognostic value in patients with HF. Therefore, the aim of the present review was to summarize the utility of RVLS in patients with HF.