Deep learning-based Alzheimer's disease detection: reproducibility and the effect of modeling choices.

Introduction: Machine Learning (ML) has emerged as a promising approach in healthcare, outperforming traditional statistical techniques. However, to establish ML as a reliable tool in clinical practice, adherence to best practices in data handling, and modeling design and assessment is crucial. In this work, we summarize and strictly adhere to such practices to ensure reproducible and reliable ML. Specifically, we focus on Alzheimer's Disease (AD) detection, a challenging problem in healthcare. Additionally, we investigate the impact of modeling choices, including different data augmentation techniques and model complexity, on overall performance. Methods: We utilize Magnetic Resonance Imaging (MRI) data from the ADNI corpus to address a binary classification problem using 3D Convolutional Neural Networks (CNNs). Data processing and modeling are specifically tailored to address data scarcity and minimize computational overhead. Within this framework, we train 15 predictive models, considering three different data augmentation strategies and five distinct 3D CNN architectures with varying convolutional layers counts. The augmentation strategies involve affine transformations, such as zoom, shift, and rotation, applied either concurrently or separately. Results: The combined effect of data augmentation and model complexity results in up to 10% variation in prediction accuracy. Notably, when affine transformation are applied separately, the model achieves higher accuracy, regardless the chosen architecture. Across all strategies, the model accuracy exhibits a concave behavior as the number of convolutional layers increases, peaking at an intermediate value. The best model reaches excellent performance both on the internal and additional external testing set. Discussions: Our work underscores the critical importance of adhering to rigorous experimental practices in the field of ML applied to healthcare. The results clearly demonstrate how data augmentation and model depth-often overlooked factors- can dramatically impact final performance if not thoroughly investigated. This highlights both the necessity of exploring neglected modeling aspects and the need to comprehensively report all modeling choices to ensure reproducibility and facilitate meaningful comparisons across studies.

NLP-based tools for localization of the epileptogenic zone in patients with drug-resistant focal epilepsy.

Epilepsy surgery is an option for people with focal onset drug-resistant (DR) seizures but a delayed or incorrect diagnosis of epileptogenic zone (EZ) location limits its efficacy. Seizure semiological manifestations and their chronological appearance contain valuable information on the putative EZ location but their interpretation relies on extensive experience. The aim of our work is to support the localization of EZ in DR patients automatically analyzing the semiological description of seizures contained in video-EEG reports. Our sample is composed of 536 descriptions of seizures extracted from Electronic Medical Records of 122 patients. We devised numerical representations of anamnestic records and seizures descriptions, exploiting Natural Language Processing (NLP) techniques, and used them to feed Machine Learning (ML) models. We performed three binary classification tasks: localizing the EZ in the right or left hemisphere, temporal or extra-temporal, and frontal or posterior regions. Our computational pipeline reached performances above 70% in all tasks. These results show that NLP-based numerical representation combined with ML-based classification models may help in localizing the origin of the seizures relying only on seizures-related semiological text data alone. Accurate early recognition of EZ could enable a more appropriate patient management and a faster access to epilepsy surgery to potential candidates.

An overview of data integration in neuroscience with focus on Alzheimer's Disease.

This work represents the first attempt to provide an overview of how to face data integration as the result of a dialogue between neuroscientists and computer scientists. Indeed, data integration is fundamental for studying complex multifactorial diseases, such as the neurodegenerative diseases. This work aims at warning the readers of common pitfalls and critical issues in both medical and data science fields. In this context, we define a road map for data scientists when they first approach the issue of data integration in the biomedical domain, highlighting the challenges that inevitably emerge when dealing with heterogeneous, large-scale and noisy data and proposing possible solutions. Here, we discuss data collection and statistical analysis usually seen as parallel and independent processes, as cross-disciplinary activities. Finally, we provide an exemplary application of data integration to address Alzheimer's Disease (AD), which is the most common multifactorial form of dementia worldwide. We critically discuss the largest and most widely used datasets in AD, and demonstrate how the emergence of machine learning and deep learning methods has had a significant impact on disease's knowledge particularly in the perspective of an early AD diagnosis.