Table 1.
Summary of sources of data collection, AI/precision medicine and digital divide.
| Topics | Resources (R) and gaps (G) | What's available (A)/What's missing (M) |
|---|---|---|
| Need for expanded patient access | - Local, state, national, international networks. R. - Cardiologists and oncologist' collaboration. G. - Telemedicine, wearables. R. |
- Advocacy, education, cardio oncology programs. A. - Increased community practices involvement. M. |
| Data collection of clinical information | - Electronic health records (EHR). R. - Prospective registries. R. - Large clinical trials in cardio oncology. G. |
- Clinical, laboratory, imaging, and pharmacy data sharing for clinical and research collaborations. A. - Observational uniform data collection to evaluate outcomes. A. |
| Precision medicine | - Epigenomics, proteomics, populomics. R. - Pharmacogenomics, Environmentomics. R. |
- Dedicated cancer platforms and cancer LinQ. A. - AHA: Institute for Precision CV medicine. A. - Broad utilization in CV medicine. M. |
| Big data | - American College of Cardiology NCDR. R. - Medicine dataset. R. - SEER. R. - Healthcare Cost and Utilization Project (HCUP). R. - European Health Research and Innovation Cloud. R. |
- Complex datasets. A. - Use of technology to transform data into clinical and research knowledge. A. - Large prospective datasets. M. |
| AI/machine learning | - Computers AI simulate human intelligence at much higher speeds. R. - Monitoring risk of cancer treatment related cardiotoxicities. R. - Established clinical practice. G. |
- ML identified cardiotoxicity predictors: troponin, pro BNP, atrial fibrillation, CAD, CHF, CVA. A. - AI algorithms in echocardiography and imaging for diagnosis, prognosis, and surveillance. A. |
| Digital divide and health care disparities | - Racial minorities higher incidence of cardiotoxicity. G. - Individuals of lower socioeconomic status have poorer CV outcomes. G. - At-risk patients in rural areas have limited access to cardio oncology. G. |
- Socioeconomic and racial data gaps need to be incorporated into AI/machine learning to ensure adequate representation and equitable solutions. M. |
AHA, American Heart Association; CV, cardiovascular; NCDR, National Cardiovascular Data Registry; AI, Artificial Intelligence; SEER, Surveillance, Epidemiology and End Results; ML, Machine learning; BNP, Beta natriuretic peptide; CAD, coronary artery disease; CHF, heart failure; CVA, cerebrovascular accident.