I’m thrilled to share our latest research, recently published in Brain Informatics and Brain Sciences. Our studies focus on enhancing the prediction of Alzheimer’s disease (AD) progression from mild cognitive impairment (MCI) using advanced explainable AI techniques.

In Brain Informatics, we demonstrated how Random Survival Forests (RSF) combined with SHapley Additive exPlanations (SHAP) improve the accuracy and interpretability of predicting AD conversion risk. Key biomarkers like FDG-PET, ABETA42, and the Hypometabolic Convergence Index (HCI) emerged as critical factors.

Building on this, our Brain Sciences article delves into the sex-specific differences in AD risk prediction. We found that while men and women share common influential biomarkers, significant differences exist in the importance of hippocampal volume and cognitive measures such as verbal memory and executive function. Our models revealed that females generally have a higher predicted risk of progressing to AD, emphasizing the need for sex-specific diagnostic approaches.

These studies underscore the potential of combining neuroimaging with explainable AI to enhance early diagnosis and personalized treatment for Alzheimer’s patients.

#AlzheimersDisease #AIinHealthcare #Neuroscience #SexDifferences #BrainHealth #MedicalResearch