•  
  •  
 

Abstract

Cardiovascular disease (CVD) is the leading cause of death and disability worldwide. By harnessing the power of artificial intelligence (AI), we introduce state-of-the-art approaches for risk prediction i) cardiovascular risk for the general population, and ii) diabetic complications for patients with type 2 diabetes mellitus, using data from routinely collected electronic medical records (EMRs). This review explores the increasing use of electronic medical records (EMRs) in developing AI-powered support tools for predicting CVD and complications. The advantage of EMRs is the integration of several data sources (medical history, laboratory results, imaging, prescriptions and demographics). Large sample sizes provide generalisability across populations. Longitudinal data capture patient trends and patterns over time, identifying risk factors in disease progression. EMRs have the potential to support clinical decision-making by providing real-time risk predictions directly to healthcare providers at the point of care. This integration allows clinicians to make informed decisions about prevention, early intervention and treatment strategies, leading to improved patient outcomes enabling precision medicine. By incorporating artificial intelligence into clinical workflows, EMRs offer valuable decision support. This review paper illustrates novelty from a multidisciplinary background to implement AI-driven risk prediction models that are patient-specific, overcoming the barrier of traditional models.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Download

Share

COinS