Deep Learning in Prediction of Late Major Bleeding After Transcatheter Aortic Valve Replacement

Machine-learning approaches for risk prediction in transcatheter aortic valve implantation: Systematic review and meta-analysis

OBJECTIVES

With the expanding integration of artificial intelligence (AI) and machine learning (ML) into the structural heart domain, numerous ML models have emerged for the prediction of adverse outcomes after transcatheter aortic valve implantation (TAVI). We aim to identify, describe, and critically appraise ML prediction models for adverse outcomes after TAVI. Key objectives consisted in summarizing model performance, evaluating adherence to reporting guidelines, and transparency.

METHODS

We searched PubMed, SCOPUS, and Embase through August 2023. We selected published machine learning models predicting TAVI outcomes. Two reviewers independently screened articles, extracted data, and assessed the study quality according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Outcomes included summary C-statistics and model risk of bias assessed with the Prediction Model Risk of Bias Assessment Tool. C-statistics were pooled using a random-effects model.

RESULTS

Twenty-one studies (118,153 patients) employing various ML algorithms (76 models) were included in the systematic review. Predictive ability of models varied: 11.8% inadequate (C-statistic <0.60), 26.3% adequate (C-statistic 0.60-0.70), 31.6% acceptable (C-statistic 0.70-0.80), and 30.3% demonstrated excellent (C-statistic >0.80) performance. Meta-analyses revealed excellent predictive performance for early mortality (C-statistic: 0.81; 95% confidence interval [CI], 0.65-0.91), acceptable performance for 1-year mortality (C-statistic: 0.76; 95% CI, 0.67-0.84), and acceptable performance for predicting permanent pacemaker implantation (C-statistic: 0.75; 95% CI, 0.51-0.90).

CONCLUSIONS

ML models for TAVI outcomes exhibit adequate-to-excellent performance, suggesting potential clinical utility. We identified concerns in methodology and transparency, emphasizing the need for improved scientific reporting standards.

Machine learning for predicting outcomes of transcatheter aortic valve implantation: A systematic review

BACKGROUND

Transcatheter aortic valve implantation (TAVI) therapy has demonstrated its clear benefits such as low invasiveness, to treat aortic stenosis. Despite associated benefits, still post-procedural complications might occur. The severity of these complications depends on pre-existing clinical conditions and patient specific complex anatomical features. Accurate prediction of TAVI outcomes will assist in the precise risk assessment for patients undergoing TAVI. Throughout the past decade, different machine learning (ML) approaches have been utilized to predict outcomes of TAVI. This systematic review aims to assess the application of ML in TAVI for the purpose of outcome prediction.

METHODS

Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline was adapted for searching the PubMed and Scopus databases on ML use in TAVI outcomes prediction. Once the studies that meet the inclusion criteria were identified, data from these studies were retrieved and were further examined. 17 parameters relevant to TAVI outcomes were carefully identified for assessing the quality of the included studies.

RESULTS

Following the search of the mentioned databases, 78 studies were initially retrieved, and 17 of these studies were included for further assessment. Most of the included studies focused on mortality prediction, utilizing datasets of varying sizes and diverse ML algorithms. The most employed ML algorithms were random forest, logistics regression, and gradient boosting. Among the studied parameters, serum creatinine, age, BMI, hemoglobin, and aortic valve mean gradient were identified as key predictors for TAVI outcomes. These predictors were found to be well aligned with established associations in current literature.

CONCLUSION

ML presents a promising opportunity for improving the success and safety of TAVI and enhancing patient-centered care. While currently retrospective studies with low generalizability and heterogeneity form the basis of ML TAVI research, future prospective investigations with highly heterogeneous patient TAVI cohorts will be critically important for firmly establishing the applicability of ML in predicting TAVI outcomes.

Antithrombotic Therapy in Patients Undergoing Transcatheter Aortic Valve Implantation

Transcatheter aortic valve implantation (TAVI) now represents the mainstay of treatment for severe aortic stenosis. Owing to its exceptional procedural efficacy and safety, TAVI has been extended to include patients at lower surgical risk, thus now encompassing a diverse patient population receiving this treatment. Yet, long-term outcomes also depend on optimal medical therapy for secondary vascular prevention, with antithrombotic therapy serving as the cornerstone. Leveraging data from multiple randomized controlled trials, the current guidelines generally recommend single antithrombotic therapy, with either single antiplatelet therapy (SAPT) or oral anticoagulation (OAC) alone in those patients without or with atrial fibrillation, respectively. Yet, individualization of this pattern, as well as specific case uses, may be needed based on individual patient characteristics and concurrent procedures. This review aims to discuss the evidence supporting antithrombotic treatments in patients treated with TAVI, indications for a standardized treatment, as well as specific considerations for an individualized approach to treatment.

CT imaging post-TAVI: Murphy's first law in action-preparing to recognize the unexpected

Transfemoral aortic valve implantation (TAVI) has been long considered the standard of therapy for high-risk patients with severe aortic-stenosis and is now effectively employed in place of surgical aortic valve replacement also in intermediate-risk patients. The potential lasting consequences of minor complications, which might have limited impact on elderly patients, could be more noteworthy in the longer term when occurring in younger individuals. That's why a greater focus on early diagnosis, correct management, and prevention of post-procedural complications is key to achieve satisfactory results. ECG-triggered multidetector computed tomography angiography (CTA) is the mainstay imaging modality for pre-procedural planning of TAVI and is also used for post-interventional early detection of both acute and long-term complications. CTA allows detailed morphological analysis of the valve and its movement throughout the entire cardiac cycle. Moreover, stent position, coronary artery branches, and integrity of the aortic root can be precisely evaluated. Imaging reliability implies the correct technical setting of the computed tomography scan, knowledge of valve type, normal post-interventional findings, and awareness of classic and life-threatening complications after a TAVI procedure. This educational review discusses the main post-procedural complications of TAVI with a specific imaging focus, trying to clearly describe the technical aspects of CTA Imaging in post-TAVI and its clinical applications and challenges, with a final focus on future perspectives and emerging technologies. CRITICAL RELEVANCE STATEMENT: This review undertakes an analysis of the role computed tomography angiography (CTA) plays in the assessment of post-TAVI complications. Highlighting the educational issues related to the topic, empowers radiologists to refine their clinical approach, contributing to enhanced patient care. KEY POINTS: Prompt recognition of TAVI complications, ranging from value issues to death, is crucial. Adherence to recommended scanning protocols, and the optimization of tailored protocols, is essential. CTA is central in the diagnosis of TAVI complications and functions as a gatekeeper to treatment.

Artificial Intelligence in Transcatheter Aortic Valve Replacement: Its Current Role and Ongoing Challenges

Transcatheter aortic valve replacement (TAVR) has emerged as a viable alternative to surgical aortic valve replacement, as accumulating clinical evidence has demonstrated its safety and efficacy. TAVR indications have expanded beyond high-risk or inoperable patients to include intermediate and low-risk patients with severe aortic stenosis. Artificial intelligence (AI) is revolutionizing the field of cardiology, aiding in the interpretation of medical imaging and developing risk models for at-risk individuals and those with cardiac disease. This article explores the growing role of AI in TAVR procedures and assesses its potential impact, with particular focus on its ability to improve patient selection, procedural planning, post-implantation monitoring and contribute to optimized patient outcomes. In addition, current challenges and future directions in AI implementation are highlighted.

Artificial Intelligence in the Screening, Diagnosis, and Management of Aortic Stenosis

The integration of artificial intelligence (AI) into clinical management of aortic stenosis (AS) has redefined our approach to the assessment and management of this heterogenous valvular heart disease (VHD). While the large-scale early detection of valvular conditions is limited by socioeconomic constraints, AI offers a cost-effective alternative solution for screening by utilizing conventional tools, including electrocardiograms and community-level auscultations, thereby facilitating early detection, prevention, and treatment of AS. Furthermore, AI sheds light on the varied nature of AS, once considered a uniform condition, allowing for more nuanced, data-driven risk assessments and treatment plans. This presents an opportunity to re-evaluate the complexity of AS and to refine treatment using data-driven risk stratification beyond traditional guidelines. AI can be used to support treatment decisions including device selection, procedural techniques, and follow-up surveillance of transcatheter aortic valve replacement (TAVR) in a reproducible manner. While recognizing notable AI achievements, it is important to remember that AI applications in AS still require collaboration with human expertise due to potential limitations such as its susceptibility to bias, and the critical nature of healthcare. This synergy underpins our optimistic view of AI's promising role in the AS clinical pathway.

Recent advancement in integrating artificial intelligence and information technology with real-world data for clinical decision-making in China: A scoping review

OBJECTIVE

Striking innovations and advancements have been achieved with the use of artificial intelligence and healthcare information technology being integrated into clinical real-world data. The current scoping review aimed to provide an overview of the current status of artificial intelligence-/information technology-based clinical decision support tools in China.

METHODS

PubMed/MEDLINE, Embase, China National Knowledge Internet, and Wanfang data were searched for both English and Chinese literature. The gray literature search was conducted for commercially available tools. Original studies that focused on clinical decision support tools driven by artificial intelligence or information technology in China and were published between 2010 and February 2022 were included. Information extracted from each article was further synthesized by themes based on three types of clinical decision-making.

RESULTS

A total of 37 peer-reviewed publications and 13 commercially available tools were included in the final analysis. Among them, 32.0% were developed for disease diagnosis, 54.0% for risk prediction and classification, and 14.0% for disease management. Chronic diseases were the most popular therapeutic areas of exploration, with particular emphasis on cardiovascular and cerebrovascular diseases. Single-center electronic medical records were the mainstream data sources leveraged to inform clinical decision-making, with internal validation being predominately used for model evaluation.

CONCLUSIONS

To effectively promote the extensive use of real-world data and drive a paradigm shift in clinical decision-making in China, multidisciplinary collaboration of key stakeholders is urgently needed.

An artificial intelligence method for predicting postoperative urinary incontinence based on multiple anatomic parameters of MRI

Background

Deep learning methods are increasingly applied in the medical field; however, their lack of interpretability remains a challenge. Captum is a tool that can be used to interpret neural network models by computing feature importance weights. Although Captum is an interpretable model, it is rarely used to study medical problems, and there is a scarcity of data regarding MRI anatomical measurements for patients with prostate cancer after undergoing Robotic-Assisted Radical Prostatectomy (RARP). Consequently, predictive models for continence that use multiple types of anatomical MRI measurements are limited.

Methods

We explored the energy efficiency of deep learning models for predicting continence by analyzing MRI measurements. We analyzed and compared various statistical models and provided reference examples for the clinical application of interpretable deep-learning models. Patients who underwent RARP at our institution between July 2019 and December 2020 were included in this study. A series of clinical MRI anatomical measurements from these patients was used to discover continence features, and their impact on continence was primarily evaluated using a series of statistical methods and computational models.

Results

Age and six other anatomical measurements were identified as the top seven features of continence by the proposed model UINet7 with an accuracy of 0.97, and the first four of these features were also found by primary statistical analysis.

Conclusions

This study fills the gaps in the in-depth investigation of continence features after RARP due to the limitations of clinical data and applicable models. We provide a pioneering example of the application of deep-learning models to clinical problems. The interpretability analysis of deep learning models has the potential for clinical applications.

Latest Developments in Adapting Deep Learning for Assessing TAVR Procedures and Outcomes

Aortic valve defects are among the most prevalent clinical conditions. A severely damaged or non-functioning aortic valve is commonly replaced with a bioprosthetic heart valve (BHV) via the transcatheter aortic valve replacement (TAVR) procedure. Accurate pre-operative planning is crucial for a successful TAVR outcome. Assessment of computational fluid dynamics (CFD), finite element analysis (FEA), and fluid-solid interaction (FSI) analysis offer a solution that has been increasingly utilized to evaluate BHV mechanics and dynamics. However, the high computational costs and the complex operation of computational modeling hinder its application. Recent advancements in the deep learning (DL) domain can offer a real-time surrogate that can render hemodynamic parameters in a few seconds, thus guiding clinicians to select the optimal treatment option. Herein, we provide a comprehensive review of classical computational modeling approaches, medical imaging, and DL approaches for planning and outcome assessment of TAVR. Particularly, we focus on DL approaches in previous studies, highlighting the utilized datasets, deployed DL models, and achieved results. We emphasize the critical challenges and recommend several future directions for innovative researchers to tackle. Finally, an end-to-end smart DL framework is outlined for real-time assessment and recommendation of the best BHV design for TAVR. Ultimately, deploying such a framework in future studies will support clinicians in minimizing risks during TAVR therapy planning and will help in improving patient care.