# Pre-trained Artificial Intelligence Models in the Prediction and Classification of Atherosclerotic Cardiovascular Disease

## TL;DR

This paper reviews how AI models can help predict and manage atherosclerotic cardiovascular disease, highlighting their potential and challenges.

## Contribution

The study systematically reviews AI applications in ASCVD prediction and management, emphasizing novel models and their limitations.

## Key findings

- AI models like BERT and CNNs show promise in analyzing clinical text and imaging data for ASCVD risk prediction.
- Challenges such as data bias and model interpretability hinder the clinical adoption of AI in ASCVD management.
- Multicenter validation and explainable AI techniques are needed to improve reliability and trust in AI-based ASCVD tools.

## Abstract

Atherosclerotic cardiovascular disease (ASCVD) is one of the leading causes of global morbidity and mortality. The current study provides a systematic review of the use of artificial intelligence (AI) technologies applied to the prediction and management of ASCVD. Traditional risk assessment approaches have their restrictions, leading to a growing preference for AI and machine learning techniques in risk assessment.

First, this study tackles the complex pathophysiology of ASCVD and the problems associated with the current diagnosis, followed by an in-depth analysis of the wide variety of AI models that can be applied to electronic health records, medical imaging data, and other biomarkers. Special attention will be paid toward the potential of natural language processing models like bidirectional encoder representations from transformers in predicting risk from textual clinical data, and the overwhelming success of convolutional neural networks such as residual neural network and visual geometry group in plaque-based analysis through imaging modalities.

Although the research results show that these models have a lot to offer in the clinical world, the authors also describe some serious disadvantages: data bias, interpretability of the model, and computational needs. It highlights, in particular, the need for multicenter validation studies as well as developing explainable AI techniques.

Overall, AI-based approaches may pave the way for a new paradigm inASCVD management. Nevertheless, deploying these technologies in everyday clinicalpractice will require overcoming technical, ethical, and regulatory challenges. As such, interdisciplinary collaboration and thorough clinical validationstudies are essential for fulfilling the promise of these novel strategies to enhance patient outcomes.