Related Experiment Video
Updated: Sep 17, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Development and validation of a combined clinical and MRI-based biomarker model to differentiate mild cognitive
Zohreh Hosseini1, Alisa Mohebbi2, Iman Kiani2
1Department of Psychiatry Tehran University of Medical Sciences Tehran Iran.
Background:
Two of the most common complaints seen in neurology clinics are Alzheimer's disease (AD) and mild cognitive impairment (MCI), characterized by similar symptoms. The aim of this study was to develop and internally validate the diagnostic value of combined neurological and radiological predictors in differentiating mild AD from MCI as the outcome variable, which helps in preventing AD development.
Methods:
A cross-sectional study of 161 participants was conducted in a general healthcare setting, including 30 controls, 71 mild AD, and 60 MCI. Binary logistic regression was used to identify predictors of interest, with collinearity assessment conducted prior to model development. Model performance was assessed through calibration, shrinkage, and decision-curve analyses. Finally, the combined clinical and radiological model was compared to models utilizing only clinical or radiological predictors.
Results:
The final model included age, sex, education status, Montreal cognitive assessment, Global Cerebral Atrophy Index, Medial Temporal Atrophy Scale, mean hippocampal volume, and Posterior Parietal Atrophy Index, with the area under the curve of 0.978 (0.934-0.996). Internal validation methods did not show substantial reduction in diagnostic performance. Combined model showed higher diagnostic performance compared to clinical and radiological models alone. Decision curve analysis highlighted the usefulness of this model for differentiation across all probability levels.
Conclusion:
A combined clinical-radiological model has excellent diagnostic performance in differentiating mild AD from MCI. Notably, the model leveraged straightforward neuroimaging markers, which are relatively simple to measure and interpret, suggesting that they could be integrated into practical, formula-driven diagnostic workflows without requiring computationally intensive deep learning models.
Insights
A new model combining clinical and radiological data accurately differentiates mild Alzheimer's disease (AD) from mild cognitive impairment (MCI). This tool aids early diagnosis and intervention for AD prevention.
Area of Science:
- Neurology
- Radiology
- Biostatistics
Background:
- Alzheimer's disease (AD) and mild cognitive impairment (MCI) present similar symptoms, posing diagnostic challenges in clinical settings.
- Accurate differentiation is crucial for timely intervention and potentially preventing AD progression.
Purpose of the Study:
- To develop and validate a diagnostic model combining neurological and radiological predictors for distinguishing mild AD from MCI.
- To assess the diagnostic value of this combined model in a clinical setting.
Main Methods:
- A cross-sectional study included 161 participants (30 controls, 71 mild AD, 60 MCI).
- Binary logistic regression identified key predictors, with collinearity assessed.
- Model performance was evaluated using calibration, shrinkage, and decision-curve analyses.
Main Results:
- The final model incorporated age, sex, education, cognitive scores, and neuroimaging markers (atrophy indices, hippocampal volume).
- The combined model achieved an area under the curve of 0.978, demonstrating excellent diagnostic performance.
- Internal validation confirmed robust diagnostic capabilities, outperforming models using only clinical or radiological data.
Conclusions:
- A combined clinical-radiological model offers high accuracy in differentiating mild AD from MCI.
- The model utilizes easily measurable neuroimaging markers, facilitating integration into practical diagnostic workflows.
- This approach avoids the need for complex deep learning models, offering a more accessible diagnostic tool.
