BACKGROUND : Many Cardiovascular disease (CVD) patients die young. Assessing CVD risks is essential to creating prediction models that accurately predict CVD mortality overall and in subgroups like young adults. Machine Learning Algorithms (MLA), a subfield of Artificial Intelligence (AI), must be used to detect heart diseases early to prevent further coronary artery damage and save lives. OBJECTIVE To predict death versus a life outcome among young adults (18-45 years) with CVD using the Chi-squared Automatic Interaction Detector (CHAID) algorithms, an artificial intelligence (AI) technique. METHODS A retrospective design for retrieving large-scale data from the electronic health records (EHRs) for 809 young adult patients with CVD was used. Data were collected for Jordanian young adults who were admitted to public health hospitals from the year 2015 to the end of 2021. RESULTS Out of seven prediction models created and based on the accuracy level and area under curve, the CHAID algorithm was the selected model for predicting death versus life among young adults (18-45 years old) with CVD. The sequence of prediction algorithms for death was first for the pulse pressure (PP), then the diastolic blood pressure (DBP), then the ischemic heart disease (IHD), ended with the geographical location. CONCLUSIONS As demonstrated by the CHAID model used in our study, the mortality rate was categorized and distributed among numerous factors. Therefore, we could assert that the AI model could add more detail on how various factors are articulated in relation to CVD patient death cases.
No takes yet. Share an insight, caveat, or question.
Ahmad et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: