Back

ChineseCVD: first-in-world, web-based, Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects

Chang, C.; Tse, G.; Lee, Q.; Chou, O. H. I.; Lee, T. T. L.; Leung, B. K.-h.; Ngai, A. L.; Khan, A.; Wong, W. T.; Wai, A. K. C.; Chen, K. Y.; Liu, T.; Zhou, J.

2023-10-28 cardiovascular medicine
10.1101/2023.10.27.23297656 medRxiv
Show abstract

BackgroundWeb-based risk prediction tools for cardiovascular diseases are crucial for providing rapid risk estimates for busy clinicians, but there is none available specifically for Chinese subjects. This study developed ChineseCVD, first-in-world web-based Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects. MethodsAdult patients attending government-funded family medicine clinics in Hong Kong between 1st January 2000 and 31st December 2003 were included. The primary outcome was major adverse cardiovascular events (MACE) defined as a composite of myocardial infarction, heart failure, transient ischaemic attacks/ischaemic strokes, and cardiovascular mortality. ResultsA total of 155,066 patients were used as the derivation cohort. Over a median follow-up of 16.1 (11.6-17.8) years, 31,061 (20.44%) had MACE. Cox regression identified male gender, age, comorbidities, cardiovascular medications, systolic and diastolic blood pressure, and laboratory test results (neutrophil-lymphocyte ratio, creatinine, ALP, AST, ALT, HbA1c, fasting glucose, triglyceride, LDL and HDL) as significant predictors of the above outcomes. ChineseCVD further incorporates the impact of smoking status, COVID-19 infection, number of COVID-19 vaccination doses, and modifier effects of newest medication classes of PCSK9i and SGLT2i. The calculator enables clinicians to demonstrate to patients how risks vary with different medications. ConclusionsThe ChineseCVD risk calculator enables rapid web-based risk assessment for adverse cardiovascular outcomes, thereby facilitating clinical decision-making at the bedside or in the clinic.

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.