Enhancing Brain Disease Diagnosis with XAI: A Review of Recent Studies

• Published in: ACM transactions on computing for healthcare 2025-04, Vol.6 (2), p.1-35
• Main Authors: Bibi, Nighat, Courtney, Jane, McGuinness, Kevin
• Format: Article
• Language: English
• Subjects: Applied computing; Applied computing / Life and medical sciences; Applied computing / Life and medical sciences / Bioinformatics; Applied computing / Life and medical sciences / Consumer health; Applied computing / Life and medical sciences / Health care information systems; Applied computing / Life and medical sciences / Health informatics; Computing methodologies; Computing methodologies / Machine learning; Computing methodologies / Machine learning / Machine learning approaches; Computing methodologies / Machine learning / Machine learning approaches / Neural networks; Social and professional topics; Social and professional topics / Computing / technology policy; Social and professional topics / Computing / technology policy / Medical information policy
• ISSN: 2637-8051; 2637-8051
• DOI: 10.1145/3709152

The area of eXplainable Artificial Intelligence (XAI) has shown remarkable progress in the past few years, with the aim of enhancing the transparency and interpretability of the machine learning (ML) and deep learning (DL) models. This review paper presents an in-depth review of the current state-of-the-art XAI techniques applied to the diagnosis of brain diseases. The challenges encountered by traditional ML and DL models within this domain are thoroughly examined, emphasising the pivotal role of XAI in providing the transparency and interpretability of these models. Furthermore, this paper presents a comprehensive survey of the XAI methodologies used for making diagnoses of various brain disorders. Recent studies utilising XAI for diagnosing a range of brain illnesses, including Alzheimer, brain tumours, dementia, Parkinson, multiple sclerosis, autism, epilepsy, and stroke, are critically reviewed. Finally, the limitations inherent in current XAI techniques are discussed, along with prospective avenues for future research. The key goal of this study is to provide researchers with a roadmap that shows the potential of XAI techniques in improving the interpretability and transparency of DL and ML algorithms for the diagnosis of brain diseases, while also delineating the challenges that require concerted research efforts.