| Artificial Intelligence in Frailty Assessment for Patients with Acute Coronary Syndrome: A Comprehensive Review of Current Evidence |
| Paper ID : 1204-IGA |
| Authors |
|
Aurel Demiraj * UHC " Mother Teresa" , Tirana, Albania |
| Abstract |
| Background: Frailty is a determinant of the outcome of the patients diagnosed with acute coronary syndrome (ACS), but still underutilized in our clinical practice despite its strong prognostic value [1,2,3]. Artificial intelligence (AI) has demonstrated efficacy on risk stratifying and treatment personalising of those patients, but still remains underexplored [4,5]. . Aim: This study aims to review and synthesize the current evidence on the role of frailty assessment in ACS patients. It evaluate the application of AI to improve the risk prediction and clinical decision-making of frail patients. Methodology: A comprehensive literature review was conducted using PubMed, EMBASE, Google Scholar, Scopus, Web of Science, and Nature, including all the papers published from 2015 to 2025 focusing on frailty assessment in ACS patients and AI applications in ACS management. Key findings were analyzed, and categorized in base of frailty prevalence, impact on treatment decisions, and AI-driven methodologies. Results: Our study demonstrate that frailty prevalence in ACS patients ranges from 10% to 48%, with higher mortality rates in frail individuals (up to 24.6% at 12 months). Frail patients has been shown to be less likely to receive guideline-directed treatments, including PCI [6,7]. All this, due to concerns about procedural risks. The use of AI applications in ACS focus on the predictive modeling, risk stratification, and treatment optimization, but still remain limited. Standard frailty assessment tools used, such as the Clinical Frailty Scale (CFS) and Tilburg Frailty Indicator (TFI), demonstrate prognostic value but lack uniform clinical adoption[8]. Discussion and Conclusion: In summary, despite its prognostic significance, frailty assessment in ACS is applied inconsistently in the clinical settings, but it holds promise for improving frailty identification and guiding personalized management. Further research needs to be developed to accieve standardized AI-driven assessment models and integrate AI into clinical workflows, reducing selection bias in frailty-related trials. |
| Keywords |
| Frailty, Acute Coronary Syndrome, Artificial Intelligence, Risk Stratification, Clinical Outcomes, Geriatric Assessment, Cardiology |
| Status: Accepted |
