Atherosclerotic-dose TMAO accentuates redox imbalances and motor dysfunctions in a MPTP mouse model of Parkinson's disease.

I arrive at the hospital early in the morning, grab my coffee and sit down to begin pre-charting on my patients. It's the start of a new rotation, and with a busy day ahead, I need to quickly familiarize myself with a long list of patients who have already spent several days in the hospital. I open the electronic health record (EHR) and begin reviewing one patient's chart, when I notice a newly integrated artificial intelligence (AI) feature. With a single click, it generates a concise summary of an otherwise lengthy and complex hospitalization, synthesizing consultant notes, laboratory results, imaging studies, procedures, medications, and the evolving plan of care into just a few paragraphs. By incorporating this tool into my workflow, I found myself reviewing patient histories more efficiently while preserving the clinical context. This made me realize that AI had quietly become part of my daily routine. As I noticed it was already changing the way I cared for patients, I reflected how it could impact an entire field built on anticipating risk and preventing disease? Preventive cardiology is, at its essence, the practice of estimating, interpreting and addressing cardiovascular risk. Every day we consider so many factors to guide our decisions, stemming from clinical symptoms, anthropometric measures, family/genetic profiles, comorbidities, serum biomarkers, wearable devices, advanced imaging techniques and sophisticated risk prediction tools such as the PREVENT equations. This growing volume and complexity of information have undoubtedly made preventive cardiology more precise, but they have also increased the cognitive reasoning demands placed on clinicians. In this setting, I believe AI can offer more than just the administrative efficiency I had just experienced. But also serve as a partner, helping us better make sense of the information we already have and empower clinicians, across all levels, to act more confidently in the sense of building a coherent, patient-centered plan, around guideline recommendations. Recent evidence suggests this is now becoming a reality across preventive cardiology. AI is reshaping clinical workflow through automating patient documentation, generating reports, communicating and supporting preventive therapeutic/behavioral interventions, while reducing administrative burden and efficiently enhancing our daily practice routine []. Furthermore, it has streamlined several processes within CV imaging, optimizing image acquisition/standardization, mitigating interobserver variability and allowing more reproducible assessment of ventricular function, coronary plaque burden and myocardial tissue phenotyping []. Beyond this, it is also uncovering clinically meaningful information (“digital biomarkers”) that weren’t being previously picked-up by us through accessible exams such as electrocardiograms (ECGs), point-of-care echocardiograms and chest X-rays []. These are now identifying patients at risk for conditions such as hypertrophic cardiomyopathy, transthyretin amyloidosis, and left ventricular dysfunction, while simultaneously using non-cardiac imaging, such as chest computed tomography (CT) scans, and assessing subclinical coronary atherosclerosis through opportunistic coronary artery calcium detection [,]. Consequently, integrating these information within EHRs and embedded risk calculators, derived from established prediction tools (i.e. PREVENT), creates an opportunity to prompt earlier CV risk recognition, readdress risk stratification, judicious therapy intensification, and facilitate personalized preventive care. Finally, it may also bring a potential to democratize cardiovascular expertise by expanding access to high-quality screening and expert-level clinical decision support in underserved and resource-limited settings. Emerging applications, such as AI-enabled ECG telehealth networks[,], illustrate how these technologies may improve triage, optimize resource allocation, and facilitate earlier identification of individuals at increased cardiovascular risk, regardless of geography or local availability of specialists.