Cost-effectiveness of strengthening blood pressure classification in South Korea: comparing the 2017 ACC/AHA and KSH guidelines

BACKGROUND

Hypertension is a significant risk factor for cardiovascular disease (CVD), with hypertension-related deaths increasing annually. While South Korea uses the Korean Society of Hypertension (KSH) guideline of 140/90 mmHg, the American College of Cardiology (ACC) and American Heart Association (AHA) updated their guidelines in 2017 to 130/80 mmHg. This study evaluates the cost-effectiveness of transitioning to the 2017 ACC/AHA guidelines by estimating early treatment impacts and potential CVD risk reduction.

METHODS

A Markov state-transition simulation model with a 10-year horizon was used to estimate cost-effectiveness, focusing on strengthening target blood pressure. Quality-adjusted life years (QALYs) served as the measure of effectiveness. Cohorts of 10,000 individuals representing South Koreans in their 20s through 80s were compared in scenario analyses from the healthcare system perspective. A 4.5% annual discount rate was applied to costs and effectiveness. Primary outcomes were incremental cost-effectiveness ratio (ICER) and net monetary benefit (NMB). The willingness-to-pay (WTP) threshold was < KRW 30,000,000/QALY gained. Probabilistic sensitivity analyses (PSAs) addressed model input parameter uncertainties.

RESULTS

The base-case analysis showed an ICER value of KRW 1,328,395/QALY gained across all populations. ICER values increased with age, from - KRW 3,138,071/QALY for 20-year-olds to KRW 16,613,013/QALY for individuals over 80. The 60s age group showed the greatest benefit with an incremental QALY gain of 0.46. All scenarios had ICERs below the WTP threshold, with a PSA probability of 98.0% that strengthening blood pressure classification could be cost-effective.

CONCLUSIONS

This economic evaluation found that adopting the 2017 ACC/AHA guidelines may result in early treatment, reduce the potential incidence of CVD events, and be cost-effective across all age groups. The study findings have implications for policymakers deciding whether and when to revise official guidelines regarding target blood pressure levels, considering the impacts on public health and budgetary concerns.

Deep learning-based personalised outcome prediction after acute ischaemic stroke

BACKGROUND

Whether deep learning models using clinical data and brain imaging can predict the long-term risk of major adverse cerebro/cardiovascular events (MACE) after acute ischaemic stroke (AIS) at the individual level has not yet been studied.

METHODS

A total of 8590 patients with AIS admitted within 5 days of symptom onset were enrolled. The primary outcome was the occurrence of MACEs (a composite of stroke, acute myocardial infarction or death) over 12 months. The performance of deep learning models (DeepSurv and Deep-Survival-Machines (DeepSM)) and traditional survival models (Cox proportional hazards (CoxPH) and random survival forest (RSF)) were compared using the time-dependent concordance index ([Formula: see text] index).

RESULTS

Given the top 1 to all 60 clinical factors according to feature importance, CoxPH and RSF yielded [Formula: see text] index of 0.7236-0.8222 and 0.7279-0.8335, respectively. Adding image features improved the performance of deep learning models and traditional models assisted by deep learning models. DeepSurv and DeepSM yielded the best [Formula: see text] index of 0.8496 and 0.8531 when images were added to all 39 relevant clinical factors, respectively. In feature importance, brain image was consistently ranked highly. Deep learning models automatically extracted the image features directly from personalised brain images and predicted the risk and date of future MACEs at the individual level.

CONCLUSIONS

Deep learning models using clinical data and brain images could improve the prediction of MACEs and provide personalised outcome prediction for patients with AIS. Deep learning models will allow us to develop more accurate and tailored prognostic prediction systems that outperform traditional models.