**Authors and Affiliations**
Jose R Medina-Inojosa,
Betsy J Medina-Inojosa,
Zachi Attia,
Michal Shelly,
Abraham Baez Suarez,
Paul Friedman,
Rickey Carter and
Francisco Lopez-Jimenez
Mayo Clinic

**Background**
We developed a deep learning algorithm that detects coronary artery calcium (CAC) score using 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that the output from the CAC-ECG algorithm would be associated with incident atherosclerotic cardiovascular disease (ASCVD) events and that the CAC- ECG would refine the AHA/ACC Pooled Cohort Equation’s (PCE) predictive capabilities.

**Methods**
A community-based cohort of consecutive patients seeking primary care in Olmsted County, MN, between 1998-2000 with passive follow-up via record linkage. Inclusion was identical to the PCE. The original CAC-ECG was developed in 43,210 subjects yielding an AUC of 0.83. Herein, we used the CAC-ECG output to predict a high CAC (≥ 300). Primary outcome was ASCVD defined as fatal and non-fatal myocardial infarction and ischemic stroke, secondary outcome was Major Adverse Cardiovascular Events (MACE) further including PCI, CABG, and mortality. Events were validated in duplicate. Cox proportional hazard models adjusted for variables included in the PCE and were stratified to evaluate the effect of the CAC-ECG on PCE-predicted risk. Follow-up was truncated at 10 years for PCE analyses.

**Results**
We included 24,793 subjects, mean ± SD age 53.9 ± 12.1, 52% women, 95% white. After 16.7±3.7 yrs follow-up, 2,366 (9.5%) had ASCVD and 3,401 (13.7%) had MACE. Risk of ASCVD and MACE increased with CAC-ECG probability quintiles, independent of risk factors, p for trend <0.001 (Fig. A-B). The CAC-EC  G enhanced the predicted capabilities of the PCE across all ASCVD risk groups (Fig. C) . Net re classification improved 13.7% with comparable C-statistic from 0.77 vs. 0.78 for PCE and CAC-ECG.

**Conclusion**
CAC-ECG was associated with ASCVD and MACE and improved PCE predicted risk. The CAC-ECG algorithm could identify individuals at risk in primary prevention; Unlike the PCE, the CAC-ECG can be applied without chart review or performing a computer tomography and may be reliably used retrospectively in cohorts with digitally stored ECGs.



**Authors and Affiliations**
[Jose R Medina-Inojosa](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Betsy J Medina-Inojosa](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Zachi Attia](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Michal Shelly](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Abraham Baez Suarez](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Paul Friedman](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#),
[Rickey Carter](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#) and
[Francisco Lopez-Jimenez](https://www.ahajournals.org/doi/10.1161/circ.147.suppl_1.42#)
Mayo Clinic

**Background**
We developed a deep learning algorithm that detects coronary artery calcium (CAC) score using 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that the output from the CAC-ECG algorithm would be associated with incident atherosclerotic cardiovascular disease (ASCVD) events and that the CAC- ECG would refine the AHA/ACC Pooled Cohort Equation’s (PCE) predictive capabilities.

**Methods**
A community-based cohort of consecutive patients seeking primary care in Olmsted County, MN, between 1998-2000 with passive follow-up via record linkage. Inclusion was identical to the PCE. The original CAC-ECG was developed in 43,210 subjects yielding an AUC of 0.83. Herein, we used the CAC-ECG output to predict a high CAC (≥ 300). Primary outcome was ASCVD defined as fatal and non-fatal myocardial infarction and ischemic stroke, secondary outcome was Major Adverse Cardiovascular Events (MACE) further including PCI, CABG, and mortality. Events were validated in duplicate. Cox proportional hazard models adjusted for variables included in the PCE and were stratified to evaluate the effect of the CAC-ECG on PCE-predicted risk. Follow-up was truncated at 10 years for PCE analyses.

**Results**
We included 24,793 subjects, mean ± SD age 53.9 ± 12.1, 52% women, 95% white. After 16.7±3.7 yrs follow-up, 2,366 (9.5%) had ASCVD and 3,401 (13.7%) had MACE. Risk of ASCVD and MACE increased with CAC-ECG probability quintiles, independent of risk factors, _p_ for trend <0.001 [(Fig. A-B).](https://drive.google.com/file/d/1lS5UhrXXezG_66g203mIIVdNVIFm0ibI/view?usp=sharing) The CAC-EC  G enhanced the predicted capabilities of the PCE across all ASCVD risk groups [(Fig. C)](https://drive.google.com/file/d/1lS5UhrXXezG_66g203mIIVdNVIFm0ibI/view?usp=sharing) . Net re classification improved 13.7% with comparable C-statistic from 0.77 vs. 0.78 for PCE and CAC-ECG.

**Conclusion**
CAC-ECG was associated with ASCVD and MACE and improved PCE predicted risk. The CAC-ECG algorithm could identify individuals at risk in primary prevention; Unlike the PCE, the CAC-ECG can be applied without chart review or performing a computer tomography and may be reliably used retrospectively in cohorts with digitally stored ECGs.



Artificial Intelligence Electrocardiogram to Detect Coronary Calcification and to Predict Atherosclerotic Cardiovascular Events in the Community

Artificial Intelligence Electrocardiogram to Detect Coronary Calcification and to Predict Atherosclerotic Cardiovascular Events in the Community