Process Mining/ Deep Learning Model to Predict Mortality in Coronary Artery Disease Patients
Ashrafi, N.; Abdollahi, A.; Placencia, G.; Pishgar, M.
Show abstract
Patients with Coronary Artery Disease (CAD) are at high risk of death. CAD is the third leading cause of mortality worldwide. However, there is a lack of research concerning CAD patient mortality prediction; thus, more accurate prediction modeling is needed to predict the mortality of patients diagnosed with CAD. This paper demonstrates performance improvements in predicting the mortality of CAD patients. The proposed framework is a modification of the work used for the prediction of 30-day readmission for ICU patients with heart failure. Our framework demonstrates better performance with an Area Under the ROC Curve (AUC) score of 0.871 for the Neural Network (NN) model compared to traditional baseline machine learning models that we developed. Our framework uses the medical history of patients, the time related to the variables, and patients demographic information for prediction. This framework has the potential to be used by medical teams to make more accurate decisions for treatment and care for patients with CAD, increasing their life expectancy.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Signal from the Noise: A Mixed Methods Process Mining Approach to Evaluate Care Pathways. 96%
- Graph-Based Clinical Recommender: Predicting Specialists Procedure Orders using Graph Representation Learning 93%
- Mining for Equitable Health: Assessing the Impact of Missing Data in Electronic Health Records 92%
Similar papers in this journal
- Modeling physician variability to prioritize relevant medical record information 94%
- Characterizing subgroup performance of probabilistic phenotype algorithms within older adults: A case study for dementia, mild cognitive impairment, and Alzheimer’s and Parkinson’s diseases 92%
- Trajectories: a framework for detecting temporal clinical event sequences from health data standardized to the OMOP Common Data Model 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.