Doo-Young Kim^1#, Kang-Ho Choi^2,3#, Ja-Hae Kim^1,4, Jina Hong³, Seong-Min Choi², Man-Seok Park², Ki-Hyun Cho²

¹Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, Korea (the Republic of)
²Department of Neurology, Chonnam National University Medical School and Hospital, Gwangju, Korea (the Republic of)
³Department of Biomedical Sciences, Chonnam National University, Gwangju, Korea (the Republic of)
⁴Department of Nuclear Medicine, Chonnam National University Medical School and Hospital, Gwangju, Korea (the Republic of)
^#Contributed equally.

Correspondence to Professor Ja-Hae Kim, Professor Kang-Ho Choi

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.