Validation of prediction algorithm for risk estimation of intracranial aneurysm development using real-world data

Abstract

Abstract Intracranial aneurysm (IA) is difficult to detect, and most patients remain undiagnosed, as screening tests have potential risks and high costs. Thus, it is important to develop risk assessment system for efficient and safe screening strategy. Through previously published research, we have developed a prediction model for the incidence risk of IA using cohort observational data. This study was designed to verify whether such a prediction model also demonstrates sufficient clinical performance in predicting the prevalence risk at the point of health screening, using cross-sectional data. The study population comprised individuals who visited the Chonnam National University Hwasun Hospital Health Promotion Center in Korea for voluntary medical checkups between 2007 and 2019. All participants had no history of cerebrovascular disease and underwent brain CTA for screening purpose. Presence of IA was evaluated by two specialized radiologists. The risk score was calculated using the previously developed AI model, and 0 point represents the lowest risk and 100 point represents the highest risk. To compare the prevalence according to the risk, age-sex standardization using national database was performed. A study collected data from 5942 health examinations, including brain CTA data, with participants ranging from 20 to 87 years old and a mean age of 52 years. The age-sex standardized prevalence of IA was 3.20%. The prevalence in each risk group was 0.18% (lowest risk, 0–19), 2.12% (lower risk, 20–39), 2.37% (mid-risk, 40–59), 4.00% (higher risk, 60–79), and 6.44% (highest risk, 80–100). The odds ratio between the lowest and highest risk groups was 38.50. The adjusted proportions of IA patients in the higher and highest risk groups were 26.7% and 44.5%, respectively. The median risk scores among IA patients and normal participants were 74 and 54, respectively. The optimal cut-off risk score was 60.5 with an area under the curve of 0.70. We have confirmed that the incidence risk prediction model built through machine learning also shows viable clinical performance in predicting prevalence risk. By utilizing this prediction system, we can effectively predict not only the incidence risk but also the prevalence risk, which is the probability of already having the disease, using health screening data. This may enable us to consider strategies for the early detection of intracranial aneurysms.