Machine learning-based prediction of in-hospital death for patients with takotsubo syndrome: The InterTAK-ML model

Artificial intelligence in cardiovascular medicine: clinical applications

Clinical medicine requires the integration of various forms of patient data including demographics, symptom characteristics, electrocardiogram findings, laboratory values, biomarker levels, and imaging studies. Decision-making on the optimal management should be based on a high probability that the envisaged treatment is appropriate, provides benefit, and bears no or little potential harm. To that end, personalized risk-benefit considerations should guide the management of individual patients to achieve optimal results. These basic clinical tasks have become more and more challenging with the massively growing data now available; artificial intelligence and machine learning (AI/ML) can provide assistance for clinicians by obtaining and comprehensively preparing the history of patients, analysing face and voice and other clinical features, by integrating laboratory results, biomarkers, and imaging. Furthermore, AI/ML can provide a comprehensive risk assessment as a basis of optimal acute and chronic care. The clinical usefulness of AI/ML algorithms should be carefully assessed, validated with confirmation datasets before clinical use, and repeatedly re-evaluated as patient phenotypes change. This review provides an overview of the current data revolution that has changed and will continue to change the face of clinical medicine radically, if properly used, to the benefit of physicians and patients alike.

Machine learning-based risk prediction for major adverse cardiovascular events in a Brazilian hospital: Development, external validation, and interpretability

BACKGROUND

Studies of cardiovascular disease risk prediction by machine learning algorithms often do not assess their ability to generalize to other populations and few of them include an analysis of the interpretability of individual predictions. This manuscript addresses the development and validation, both internal and external, of predictive models for the assessment of risks of major adverse cardiovascular events (MACE). Global and local interpretability analyses of predictions were conducted towards improving MACE's model reliability and tailoring preventive interventions.

METHODS

The models were trained and validated on a retrospective cohort with the use of data from Ribeirão Preto Medical School (RPMS), University of São Paulo, Brazil. Data from Beth Israel Deaconess Medical Center (BIDMC), USA, were used for external validation. A balanced sample of 6,000 MACE cases and 6,000 non-MACE cases from RPMS was created for training and internal validation and an additional one of 8,000 MACE cases and 8,000 non-MACE cases from BIDMC was employed for external validation. Eight machine learning algorithms, namely Penalized Logistic Regression, Random Forest, XGBoost, Decision Tree, Support Vector Machine, k-Nearest Neighbors, Naive Bayes, and Multi-Layer Perceptron were trained to predict a 5-year risk of major adverse cardiovascular events and their predictive performance was evaluated regarding accuracy, ROC curve (receiver operating characteristic), and AUC (area under the ROC curve). LIME and Shapley values were applied towards insights about model interpretability.

FINDINGS

Random Forest showed the best predictive performance in both internal validation (AUC = 0.871 (0.859-0.882); Accuracy = 0.794 (0.782-0.808)) and external one (AUC = 0.786 (0.778-0.792); Accuracy = 0.710 (0.704-0.717)). Compared to LIME, Shapley values suggest more consistent explanations on exploratory analysis and importance of features.

CONCLUSIONS

Among the machine learning algorithms evaluated, Random Forest showed the best generalization ability, both internally and externally. Shapley values for local interpretability were more informative than LIME ones, which is in line with our exploratory analysis and global interpretation of the final model. Machine learning algorithms with good generalization and accompanied by interpretability analyses are recommended for assessments of individual risks of cardiovascular diseases and development of personalized preventive actions.

Vagal nerve stimulation in myocardial ischemia/reperfusion injury: from bench to bedside

The identification of acute cardioprotective strategies against myocardial ischemia/reperfusion (I/R) injury that can be applied in the catheterization room is currently an unmet clinical need and several interventions evaluated in the past at the pre-clinical level have failed in translation. Autonomic imbalance, sustained by an abnormal afferent signalling, is a key component of I/R injury. Accordingly, there is a strong rationale for neuromodulation strategies, aimed at reducing sympathetic activity and/or increasing vagal tone, in this setting. In this review we focus on cervical vagal nerve stimulation (cVNS) and on transcutaneous auricular vagus nerve stimulation (taVNS); the latest has the potential to overcome several of the issues of invasive cVNS, including the possibility of being used in an acute setting, while retaining its beneficial effects. First, we discuss the pathophysiology of I/R injury, that is mostly a consequence of the overproduction of reactive oxygen species. Second, we describe the functional anatomy of the parasympathetic branch of the autonomic nervous system and the most relevant principles of bioelectronic medicine applied to electrical vagal modulation, with a particular focus on taVNS. Then, we provide a detailed and comprehensive summary of the most relevant pre-clinical studies of invasive and non-invasive VNS that support its strong cardioprotective effect whenever there is an acute or chronic cardiac injury and specifically in the setting of myocardial I/R injury. The potential benefit in the emerging field of post cardiac arrest syndrome (PCAS) is also mentioned. Indeed, electrical cVNS has a strong anti-adrenergic, anti-inflammatory, antioxidants, anti-apoptotic and pro-angiogenic effect; most of the involved molecular pathways were already directly confirmed to take place at the cardiac level for taVNS. Pre-clinical data clearly show that the sooner VNS is applied, the better the outcome, with the possibility of a marked infarct size reduction and almost complete left ventricular reverse remodelling when VNS is applied immediately before and during reperfusion. Finally, we describe in detail the limited but very promising clinical experience of taVNS in I/R injury available so far.

Takotsubo syndrome: Impact of medical therapies on prognosis. A state of art review

Tako-Tsubo syndrome (TTS) presents as transient ventricular dysfunction, yet its underlying pathophysiology remains enigmatic. The prognosis of patients presenting with TTS appears to be impaired as compared to the general population and is similar to patients with acute coronary syndromes. Recent investigations have predominantly focused on elucidating therapeutic strategies associated with improved outcomes, particularly among post-menopausal female patients. Current evidence suggests that angiotensin-converting enzyme inhibitors (ACEi) may confer a survival advantage in TTS. Notably, ACEi emerges as the sole therapeutic modality demonstrating efficacy in both acute and chronic clinical courses of TTS. Despite this, the magnitude of survival benefit remains less pronounced than anticipated. This underscores the need for further research to explore additional therapeutic pathways and optimize management strategies for this unique patient cohort. Randomized clinical trials and meta-analysis are paramount in discerning the most effective therapeutic interventions aimed at enhancing survival and ameliorating outcomes in TTS. This review aims to comprehensively synthesize evidence pertaining to the prognostic implications of cardiovascular medications in TTS management.

2024 update in heart failure

In the last years, major progress has occurred in heart failure (HF) management. The 2023 ESC focused update of the 2021 HF guidelines introduced new key recommendations based on the results of the last years of science. First, two drugs, sodium-glucose co-transporter-2 (SGLT2) inhibitors and finerenone, a novel nonsteroidal, selective mineralocorticoid receptor antagonist (MRA), are recommended for the prevention of HF in patients with diabetic chronic kidney disease (CKD). Second, SGLT2 inhibitors are now recommended for the treatment of HF across the entire left ventricular ejection fraction spectrum. The benefits of quadruple therapy in patients with HF with reduced ejection fraction (HFrEF) are well established. Its rapid and early up-titration along with a close follow-up with frequent clinical and laboratory re-assessment after an episode of acute HF (the so-called 'high-intensity care' strategy) was associated with better outcomes in the STRONG-HF trial. Patients experiencing an episode of worsening HF might require a fifth drug, vericiguat. In the STEP-HFpEF-DM and STEP-HFpEF trials, semaglutide 2.4 mg once weekly administered for 1 year decreased body weight and significantly improved quality of life and the 6 min walk distance in obese patients with HF with preserved ejection fraction (HFpEF) with or without a history of diabetes. Further data on safety and efficacy, including also hard endpoints, are needed to support the addition of acetazolamide or hydrochlorothiazide to a standard diuretic regimen in patients hospitalized due to acute HF. In the meantime, PUSH-AHF supported the use of natriuresis-guided diuretic therapy. Further options and most recent evidence for the treatment of HF, including specific drugs for cardiomyopathies (i.e., mavacamten in hypertrophic cardiomyopathy and tafamidis in transthyretin cardiac amyloidosis), device therapies, cardiac contractility modulation and percutaneous treatment of valvulopathies, with the recent finding from the TRILUMINATE Pivotal trial, are also reviewed in this article.

Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years

BACKGROUND

Artificial intelligence (AI) can radically change almost every aspect of the human experience. In the medical field, there are numerous applications of AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, this fact being supported by the exponential increase in the number of publications in which the algorithms play an important role in data analysis, pattern discovery, identification of anomalies, and therapeutic decision making. Furthermore, with technological development, there have appeared new models of machine learning (ML) and deep learning (DP) that are capable of exploring various applications of AI in cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional cardiology, and many others. In this sense, the present article aims to provide a general vision of the current state of AI use in cardiology.

RESULTS

We identified and included a subset of 200 papers directly relevant to the current research covering a wide range of applications. Thus, this paper presents AI applications in cardiovascular imaging, arithmology, clinical or emergency cardiology, cardiovascular prevention, and interventional procedures in a summarized manner. Recent studies from the highly scientific literature demonstrate the feasibility and advantages of using AI in different branches of cardiology.

CONCLUSIONS

The integration of AI in cardiology offers promising perspectives for increasing accuracy by decreasing the error rate and increasing efficiency in cardiovascular practice. From predicting the risk of sudden death or the ability to respond to cardiac resynchronization therapy to the diagnosis of pulmonary embolism or the early detection of valvular diseases, AI algorithms have shown their potential to mitigate human error and provide feasible solutions. At the same time, limits imposed by the small samples studied are highlighted alongside the challenges presented by ethical implementation; these relate to legal implications regarding responsibility and decision making processes, ensuring patient confidentiality and data security. All these constitute future research directions that will allow the integration of AI in the progress of cardiology.