A machine learning model in predicting hemodynamically significant coronary artery disease: A prospective cohort
Yan Liu1,2, Haoxing Ren3, Hanna Fanous1
1Dell Medical School, The University of Texas at Austin, Austin, Texas.
Insights
Machine learning accurately predicts hemodynamically significant coronary artery disease (CAD) using routine clinical data. This approach shows promise in improving noninvasive diagnostic capabilities for CAD.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Coronary artery disease (CAD) is a leading cause of death and incurs significant healthcare costs.
- Existing noninvasive diagnostic tools for CAD have limitations.
- There is a need for improved methods to predict significant CAD.
Purpose of the Study:
- To evaluate the efficacy of machine learning (ML) in predicting hemodynamically significant CAD.
- To utilize routine demographic, clinical, and laboratory data for ML-based prediction.
- To compare ML model accuracy with current noninvasive diagnostic modalities.
Main Methods:
- A prospective cohort study of 185 patients undergoing cardiac catheterization was conducted.
- A random forest model was developed using 18 points of clinical data, including demographics, comorbidities, risk factors, and lab results.
- Model performance was assessed using the area under the receiver operating characteristic curve.
Main Results:
- The machine learning model achieved a sensitivity of 81% ± 7.8% and specificity of 61% ± 14.4% in predicting hemodynamically significant CAD.
- The model also predicted 90-day major adverse cardiovascular and renal events (MACREs) with a sensitivity of 57.13% ± 18.70% and specificity of 44.61% ± 14.39%.
Conclusions:
- Machine learning models can effectively predict hemodynamically significant CAD.
- The accuracy of these ML models approaches that of current noninvasive functional tests.
- Routine clinical data is sufficient for developing predictive models for significant CAD.
Background:
Coronary artery disease (CAD) costs healthcare billions of dollars annually and is the leading cause of death despite available noninvasive diagnostic tools.
Objective:
This study aims to examine the usefulness of machine learning in predicting hemodynamically significant CAD using routine demographics, clinical factors, and laboratory data.
Methods:
Consecutive patients undergoing cardiac catheterization between March 17, 2015, and July 15, 2016, at UNC Chapel Hill were screened for comorbidities and CAD risk factors. In this pilot, single-center, prospective cohort study, patients were screened and selected for moderate CAD risk (n = 185). Invasive coronary angiography and CAD prediction with machine learning were independently performed. Results were blinded from operators and patients. Outcomes were followed up for up to 90 days for major adverse cardiovascular and renal events (MACREs). Greater than 70% stenosis or a fractional flow reserve less than or equal to 0.8 represented hemodynamically significant coronary disease. A random forest model using demographic, comorbidities, risk factors, and lab data was trained to predict CAD severity. The Random Forest Model predictive accuracy was assessed by area under the receiver operating characteristic curve with comparison to the final diagnoses made from coronary angiography.
Results:
Hemodynamically significant CAD was predicted by 18-point clinical data input with a sensitivity of 81% ± 7.8%, and specificity of 61% ± 14.4% by the established model. The best machine learning model predicted a 90-day MACRE with specificity of 44.61% ± 14.39%, and sensitivity of 57.13% ± 18.70%.
Conclusion:
Machine learning models based on routine demographics, clinical factors, and lab data can be used to predict hemodynamically significant CAD with accuracy that approximates current noninvasive functional modalities.
More Related Videos
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
