Search research articles

Related Concept Videos

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Deep Learning-Based Evaluation of Maxillary Dental Midline Deviation on Orthodontic Frontal Photographs.

Bioengineering (Basel, Switzerland)·2026

Same author

An Explainable Web-Based Diagnostic System for Alzheimer's Disease Using XRAI and Deep Learning on Brain MRI.

Diagnostics (Basel, Switzerland)·2025

Same author

A Web-Deployed, Explainable AI System for Comprehensive Brain Tumor Diagnosis.

Neurology international·2025

Same author

Enhancing Melanoma Diagnosis with Advanced Deep Learning Models Focusing on Vision Transformer, Swin Transformer, and ConvNeXt.

Dermatopathology (Basel, Switzerland)·2024

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

SeruNet-MS: A Two-Stage Interpretable Framework for Multiple Sclerosis Risk Prediction with SHAP-Based

Serra Aksoy¹, Pinar Demircioglu², Ismail Bogrekci²

¹Institute of Computer Science, Ludwig Maximilian University of Munich (LMU), Oettingenstrasse 67, 80538 Munich, Germany.

Neurology International

|September 26, 2025

Summary

A new two-stage machine learning model accurately predicts multiple sclerosis (MS) conversion from clinically isolated syndrome (CIS). Explainable AI (SHAP) provides transparent, patient-specific risk factors, enhancing clinical trust and adoption for MS diagnosis.

Keywords:

SHAP analysis SeruNet-MS clinical decision support clinically isolated syndrome (CIS)demographic bias disease progression explainable AI multiple sclerosis (MS)neurological biomarkers predictive modeling two-stage machine learning

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Jan 16, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

Neurology
Artificial Intelligence
Biostatistics

Background:

Multiple sclerosis (MS) diagnosis requires early identification of clinically isolated syndrome (CIS) to clinically definite MS.
Current machine learning (ML) models for MS prediction lack interpretability, hindering clinical trust.
A need exists for explainable AI (XAI) to address demographic bias and improve MS risk stratification.

Purpose of the Study:

Develop and validate a novel, interpretable two-stage ML framework (SeruNet-MS) for predicting CIS-to-MS conversion.
Mitigate demographic bias in MS risk prediction.
Enhance clinical adoption through transparent, patient-specific risk factor explanations.

Main Methods:

Analyzed 177 CIS patients using a two-stage ML framework (SeruNet-MS).
Stage 1: Logistic regression on demographic features. Stage 2: Incorporated 25 clinical/symptom features (MRI, CSF biomarkers, etc.).
Utilized SHAP (SHapley Additive exPlanations) for patient-level interpretability and risk factor attribution.

Main Results:

The two-stage model achieved high performance: ROC-AUC 0.909, accuracy 0.806, precision 0.842, recall 0.800.
Cross-validation confirmed stable performance (AUC 0.838 ± 0.095).
SHAP analysis identified periventricular lesions, oligoclonal bands, and symptom complexity as key predictors.

Conclusions:

The two-stage approach effectively separates demographic bias from clinical risk factors.
SHAP explanations provide clinicians with actionable, individualized insights for MS risk assessment.
This interpretable framework advances AI adoption in MS clinical practice.