Background: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and is the most common cause of dementia. Early diagnosis of Alzheimer’s disease is critical for better management and treatment outcomes, but it remains a challenging task due to the complex nature of the disease. Clinical data, including a range of cognitive, functional, and demographic variables, play a crucial role in Alzheimer’s disease classification. Also, challenges such as data imbalance and high-dimensional feature sets often hinder model performance. Objective: This paper aims to propose a computationally efficient, reliable, and transparent machine learning-based framework for the classification of Alzheimer’s disease patients. This framework is interpretable and helps medical practitioners learn complex patterns in patients. Method: This study addresses these issues by employing boosting algorithms, for enhanced classification accuracy. To mitigate data imbalance, a random sampling technique is applied, ensuring a balanced representation of Alzheimer’s and healthy cases. Extensive feature analysis was conducted to identify the most impactful clinical features followed by feature reduction techniques to focus on the most informative clinical features, reducing model complexity and overfitting risks. Explainable AI tools, such as SHAP, LIME, ALE, and ELI5 are integrated to provide transparency into the model’s decision-making process, highlighting key features influencing the classification and allowing clinicians to understand and trust the key features driving the predictions. Results: This approach results in a robust, interpretable, and clinically relevant framework for Alzheimer’s disease diagnosis. The proposed approach achieved the best accuracy of 95%, demonstrating its effectiveness and potential for reliable early diagnosis of Alzheimer’s disease. Conclusions: This study demonstrates that integrating ensemble learning algorithms and explainable AI, while using a balanced dataset with feature selection, improves quantitative results and interpretability. This approach offers a promising method for early and better-informed clinical decisions.

Background: Deep learning models have been used in the past for non-invasive liver fibrosis classification based on liver ultrasound scans. After numerous improvements in the network architectures, optimizers, and development of hybrid methods, the performance of these models has barely improved. This creates a need for a sophisticated method that helps improve this slow-improving performance. Methods: We propose LivSCP, a method to train liver fibrosis classification models for better accuracy than the traditional supervised learning (SL). Our method needs no changes in the network architecture, optimizer, etc. Results: The proposed method achieves state-of-the-art performance, with an accuracy, precision, recall, and F1-score of 98.10% each, and an AUROC of 0.9972. A major advantage of LivSCP is that it does not require any modification to the network architecture. Our method is particularly well-suited for scenarios with limited labeled data and computational resources. Conclusions: In this work, we successfully propose a training method for liver fibrosis classification models in low-data and computation settings. By comparing the proposed method with our baseline (Vision Transformer with SL) and multiple models, we demonstrate the state-of-the-art performance of our method.