Efficient Explainable Models for Alzheimer’s Disease Classification
Author Information
Author(s): Dubey Yogita, Bhongade Aditya, Palsodkar Prachi, Fulzele Punit
Primary Institution: Yeshwantrao Chavan College of Engineering, Nagpur, India
Hypothesis
This paper aims to propose a computationally efficient, reliable, and transparent machine learning-based framework for the classification of Alzheimer’s disease patients.
Conclusion
The proposed approach achieved the best accuracy of 95%, demonstrating its effectiveness and potential for reliable early diagnosis of Alzheimer’s disease.
Supporting Evidence
- The proposed framework integrates explainable AI tools to enhance model transparency.
- Random sampling was used to mitigate data imbalance.
- Feature analysis identified the most impactful clinical features for Alzheimer's diagnosis.
- Ensemble learning algorithms were employed to improve classification accuracy.
Takeaway
This study created a smart computer program to help doctors figure out if someone has Alzheimer's disease by looking at their health data.
Methodology
The study used boosting algorithms, random sampling for data balancing, and feature selection techniques to improve model performance.
Potential Biases
The model may be biased if the dataset is not representative of the broader population.
Limitations
The study may not generalize well across different populations due to the specific dataset used.
Participant Demographics
Patients aged 60 to 90, with a majority being female.
Statistical Information
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website