Machine Learning & Knowledge Extraction Webinar | Clinical AI, 23 October 2026

Welcome message from the Chair:

In recent years, we have witnessed a substantial increase in machine learning research focused on medical diagnostics, with numerous studies reporting high accuracies on benchmark datasets. However, many of these studies do not sufficiently report learning dynamics of model training or address critical issues such as overfitting, data leakage, or absence of external validation. As a result, models that demonstrate strong performance in controlled settings frequently fail to generalize to real-world clinical environments, often due to methodological shortcomings or insufficient transparency in training and evaluation processes.

This brings us to the catch-22 of clinical AI diagnostics—to safely deploy AI systems in clinical workflows, we require physician oversight to verify outputs and catch errors; yet this is precisely the burden AI was designed to alleviate. We face a paradox where the clinical supervision necessary for safe AI use negates the efficiency gains that motivated adoption in the first place. Meanwhile, research has shown that automation bias can lead clinicians to trust system outputs without thorough verification, while negative experiences can cause algorithm aversion that excludes AI from decision-making entirely. Neither extreme serves patients well.

This webinar aims to address these challenges directly. We are here not only to discuss advances in accuracy but to examine how we can systematically demonstrate learning dynamics, avoid common pitfalls, and provide evidence for real-world clinical applicability. Our goal is to elevate methodological standards across the field and enable reproducibility, transparency, and genuine translation into clinical workflows.

I would like to sincerely thank our speakers for taking the time to share their work. We warmly invite you to join us for this insightful session and hope it stimulates new ideas and potential collaborations.

Dr. Milan Toma
Chair of the MAKE Webinar

Date: 23 October 2026
Time: 10:00 CEST

Program:

Speaker/Presentation	Time in CEST
Dr. Milan Toma (Chair) Welcome Message	10:00–10:10
Dr. Min Wang Mechanistic Interpretability of Brain–Computer Interface Models	10:10–10:30
Dr. Joshua Li Population-Scale Serial PSA Analysis with Deep Learning: Cancer Risk and Temporal Prediction in Hong Kong	10:30–10:50
Dr. Dror Malka Predicting Text Understanding from Beta-Band EEG	10:50–11:10
Dr. Ka Man Cheung AI-assisted medical diagnostics—From modelling to implementation	11:10–11:30
Q&A Session	11:30–11:40
Dr. Milan Toma Closing of Webinar	11:40–11:45

After registering, you will receive a confirmation email with information on how to join the webinar. Registrations with academic institutional email addresses will be prioritized.

Unable to attend? Feel free to register anyway; the session will be recorded, and we will let you know when the recording is available for viewing.

Webinar Chair and Speakers:

Dr. Milan Toma, Laboratory of Algorithmic Medicine, Department of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, New York, USA;
Dr. Min Wang, Collaborative Robotics Lab, Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, Australia;
Dr. Joshua Li, Department of Pathology, Queen Mary Hospital, The University of Hong Kong, Hong Kong SAR, China;
Dr. Dror Malka, Faculty of Engineering, Holon Institute of Technology (HIT), Holon 5810201, Israel;
Dr. Ka Man Cheung, Department of Clinical Oncology, Queen Elizabeth Hospital, Hong Kong SAR, China.

Relevant Special Issue:
“Clinically Robust and Transparent AI-Assisted Medical Diagnostics: From Learning Dynamics to Real-World Deployment”
Guest Editors: Dr. Milan Toma and Prof. Dr. Constantinos Pattichis
Deadline for manuscript submissions: 30 April 2027

For more information about this webinar, please visit the following website: https://sciforum.net/event/MAKE-1.

If you have any questions about this event, please contact: make@mdpi.com.

MAKE Webinar Secretariat