Back

Validity of the HEART Score as an Early Assessment Tool in Acute Coronary Syndrome in a Sri Lankan Population: A Single Centre Pilot Study

Welhenge, C.; Fernando, K.; Fernando, N.; Deshapriya, P.; Lekamge, D.; Kasturiratne, K.; De Silva, A.

2025-11-07 cardiovascular medicine
10.1101/2025.11.05.25339585 medRxiv
Show abstract

ObjectivesThe HEART score is a clinical tool used for early risk stratification in patients presenting with chest pain in emergency settings, which facilitates prognostication. Although limited, it has been validated in several countries throughout the world. This study aimed to assess the validity of HEART score, in a Sri Lankan population, as an early assessment tool, for risk prediction of acute coronary syndrome (ACS), in patients presenting with chest pain. MethodsData was collected from 74 patients presenting to the emergency department at a tertiary care centre in Sri Lanka. HEART score was calculated for each patient retrospectively and patients were categorized into low (0-3), intermediate (4-6), and high (7-10) risk groups. The predictive accuracy of the HEART score with a diagnosis of ACS and the occurrence of major adverse cardiac events (MACE) at 6 weeks was assessed. Statistical analysis was performed using R studio. ResultsAll patients in the low-risk group (n=8) were correctly identified as non-ACS, with no MACE. All high-risk patients (n=29) had ACS and experienced MACE. Among the intermediate risk group (n=37), 70.3% were diagnosed with ACS and 54% developed MACE at 6 weeks. Area under curve (AUC) for HEART score for a diagnosis of ACS, was 0.889 (95% CI: 0.8171-0.9609) while the AUC for occurrence of MACE was 0.9053 (95% CI: 0.8437 - 0.9669). ConclusionsThe HEART score is an effective early assessment tool which can be used in Sri Lankans, in prediction of the probability of ACS, and MACE within 6 weeks, in patients presenting with chest pain.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.