Potential Applications of Artificial Intelligence in Clinical Trials for Alzheimer’s Disease

Integrating AI in fighting advancing Alzheimer: diagnosis, prevention, treatment, monitoring, mechanisms, and clinical trials

The application of artificial intelligence (AI) in neurology is a growing field offering opportunities to improve accuracy of diagnosis and treatment of complicated neuronal disorders, plus fostering a deeper understanding of the aetiologies of these diseases through AI-based analyses of large omics data. The most common neurodegenerative disease, Alzheimer's disease (AD), is characterized by brain accumulation of specific pathological proteins, accompanied by cognitive impairment. In this review, we summarize the latest progress on the use of AI in different AD-related fields, such as analysis of neuroimaging data enabling early and accurate AD diagnosis; prediction of AD progression, identification of patients at higher risk and evaluation of new treatments; improvement of the evaluation of drug response using AI algorithms to analyze patient clinical and neuroimaging data; the development of personalized AD therapies; and the use of AI-based techniques to improve the quality of daily life of AD patients and their caregivers.

Predicting amyloid positivity from FDG-PET images using radiomics: A parsimonious model

BACKGROUND AND OBJECTIVE

Amyloid plaques are one of the physical hallmarks of Alzheimer's disease. The objective of this study is to predict amyloid positivity non-invasively from FDG-PET images using a radiomics approach.

METHODS

We obtained FDG-PET images of 301 individuals from various groups, including control normal (CN), mild cognitive impairment (MCI), and Alzheimer's Disease (AD), from the ADNI database. Following the utilization of the CSF Aβ1-42 (192) and Standardized Uptake Value Ratio (SUVR) (1.11) thresholds derived from Florbetapir scans, the subjects were categorized into two categories: those with a positive amyloid status (n = 185) and those with a negative amyloid status (n = 116). The process of segmenting the entire brain into 95 classes using the DKT-atlas was utilized. Following that, we obtained 120 characteristics for each of the 95 regions of interest (ROIs). We employed eight feature selection methods to analyze the features. Additionally, we utilized eight different classifiers on the 20 most significant features extracted from each feature selection method. Finally, in order to improve interpretability, we selected the most important features and ROIs.

RESULT

We found that the GNB classifier and the LASSO feature selection method had the best performance with an average accuracy of (AUC=0.924) while using 18 features on 15 ROIs. We were then able to reduce the model to three regions (Hippocampus, inferior parietal, and isthmus cingulate) and three gray-level based features (AUC=0.853).

CONCLUSION

The FDG-PET images which serve to study metabolic activity can be used to predict amyloid positivity without the use of invasive methods or another PET tracer and study. The proposed method has superior prediction accuracy with respect to similar studies reported in the literature using other imaging modalities. Only three brain regions had a high impact on amyloid positivity results.

A multimodal deep learning approach for the prediction of cognitive decline and its effectiveness in clinical trials for Alzheimer's disease

Alzheimer's disease is one of the most important health-care challenges in the world. For decades, numerous efforts have been made to develop therapeutics for Alzheimer's disease, but most clinical trials have failed to show significant treatment effects on slowing or halting cognitive decline. Among several challenges in such trials, one recently noticed but unsolved is biased allocation of fast and slow cognitive decliners to treatment and placebo groups during randomization caused by the large individual variation in the speed of cognitive decline. This allocation bias directly results in either over- or underestimation of the treatment effect from the outcome of the trial. In this study, we propose a stratified randomization method using the degree of cognitive decline predicted by an artificial intelligence model as a stratification index to suppress the allocation bias in randomization and evaluate its effectiveness by simulation using ADNI data set.

Addressing the Discrepancies Between Animal Models and Human Alzheimer's Disease Pathology: Implications for Translational Research

Animal models, particularly transgenic mice, are extensively used in Alzheimer's disease (AD) research to emulate key disease hallmarks, such as amyloid plaques and neurofibrillary tangles formation. Although these models have contributed to our understanding of AD pathogenesis and can be helpful in testing potential therapeutic interventions, their reliability is dubious. While preclinical studies have shown promise, clinical trials often yield disappointing results, highlighting a notable gap and disparity between animal models and human AD pathology. Existing models frequently overlook early-stage human pathologies and other key AD characteristics, thereby limiting their application in identifying optimal therapeutic interventions. Enhancing model reliability necessitates rigorous study design, comprehensive behavioral evaluations, and biomarker utilization. Overall, a nuanced understanding of each model's neuropathology, its fidelity to human AD, and its limitations is essential for accurate interpretation and successful translation of findings. This article analyzes the discrepancies between animal models and human AD pathology that complicate the translation of findings from preclinical studies to clinical applications. We also delve into AD pathogenesis and attributes to propose a new perspective on this pathology and deliberate over the primary limitations of key experimental models. Additionally, we discuss several fundamental problems that may explain the translational failures and suggest some possible directions for more effective preclinical studies.

The Major Hypotheses of Alzheimer's Disease: Related Nanotechnology-Based Approaches for Its Diagnosis and Treatment

Alzheimer's disease (AD) is a well-known chronic neurodegenerative disorder that leads to the progressive death of brain cells, resulting in memory loss and the loss of other critical body functions. In March 2019, one of the major pharmaceutical companies and its partners announced that currently, there is no drug to cure AD, and all clinical trials of the new ones have been cancelled, leaving many people without hope. However, despite the clear message and startling reality, the research continued. Finally, in the last two years, the Food and Drug Administration (FDA) approved the first-ever medications to treat Alzheimer's, aducanumab and lecanemab. Despite researchers' support of this decision, there are serious concerns about their effectiveness and safety. The validation of aducanumab by the Centers for Medicare and Medicaid Services is still pending, and lecanemab was authorized without considering data from the phase III trials. Furthermore, numerous reports suggest that patients have died when undergoing extended treatment. While there is evidence that aducanumab and lecanemab may provide some relief to those suffering from AD, their impact remains a topic of ongoing research and debate within the medical community. The fact is that even though there are considerable efforts regarding pharmacological treatment, no definitive cure for AD has been found yet. Nevertheless, it is strongly believed that modern nanotechnology holds promising solutions and effective clinical strategies for the development of diagnostic tools and treatments for AD. This review summarizes the major hallmarks of AD, its etiological mechanisms, and challenges. It explores existing diagnostic and therapeutic methods and the potential of nanotechnology-based approaches for recognizing and monitoring patients at risk of irreversible neuronal degeneration. Overall, it provides a broad overview for those interested in the evolving areas of clinical neuroscience, AD, and related nanotechnology. With further research and development, nanotechnology-based approaches may offer new solutions and hope for millions of people affected by this devastating disease.

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer's disease?

Alzheimer's disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there is no cure, detecting AD early is important for the development of a therapeutic plan and a care plan that may preserve cognitive function and prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), has served as a critical tool in establishing diagnostic indicators of AD during the preclinical stage. However, as neuroimaging technology quickly advances, there is a challenge in analyzing and interpreting vast amounts of brain imaging data. Given these limitations, there is great interest in using artificial Intelligence (AI) to assist in this process. AI introduces limitless possibilities in the future diagnosis of AD, yet there is still resistance from the healthcare community to incorporate AI in the clinical setting. The goal of this review is to answer the question of whether AI should be used in conjunction with neuroimaging in the diagnosis of AD. To answer the question, the possible benefits and disadvantages of AI are discussed. The main advantages of AI are its potential to improve diagnostic accuracy, improve the efficiency in analyzing radiographic data, reduce physician burnout, and advance precision medicine. The disadvantages include generalization and data shortage, lack of in vivo gold standard, skepticism in the medical community, potential for physician bias, and concerns over patient information, privacy, and safety. Although the challenges present fundamental concerns and must be addressed when the time comes, it would be unethical not to use AI if it can improve patient health and outcome.

Digital Intervention For The Management Of Alzheimer's Disease

Alzheimer's disease (AD) is a progressive, multifactorial, chronic, neurodegenerative disease with high prevalence and limited therapeutic options, making it a global health crisis. Being the most common cause of dementia, AD erodes the cognitive, functional, and social abilities of the individual and causes escalating medical and psychosocial needs. As yet, this disorder has no cure and current treatment options are palliative in nature. There is an urgent need for novel therapy to address this pressing challenge. Digital therapeutics (Dtx) is one such novel therapy that is gaining popularity globally. Dtx provides evidence based therapeutic interventions driven by internet and software, employing tools such as mobile devices, computers, videogames, apps, sensors, virtual reality aiding in the prevention, management, and treatment of ailments like neurological abnormalities and chronic diseases. Dtx acts as a supportive tool for the optimization of patient care, individualized treatment and improved health outcomes. Dtx uses visual, sound and other non-invasive approaches for instance-consistent therapy, reminiscence therapy, computerised cognitive training, semantic and phonological assistance devices, wearables and computer-assisted rehabilitation environment to find applications in Alzheimer's disease for improving memory, cognition, functional abilities and managing motor symptom. A few of the Dtx-based tools employed in AD include "Memory Matters", "AlzSense", "Alzheimer Assistant", "smart robotic dog", "Immersive virtual reality (iVR)" and the most current gamma stimulation. The purpose of this review is to summarize the current trends in digital health in AD and explore the benefits, challenges, and impediments of using Dtx as an adjunctive therapy for the management of AD.

Deep Learning for Brain MRI Confirms Patterned Pathological Progression in Alzheimer's Disease

Deep learning (DL) on brain magnetic resonance imaging (MRI) data has shown excellent performance in differentiating individuals with Alzheimer's disease (AD). However, the value of DL in detecting progressive structural MRI (sMRI) abnormalities linked to AD pathology has yet to be established. In this study, an interpretable DL algorithm named the Ensemble of 3-dimensional convolutional neural network (Ensemble 3DCNN) with enhanced parsing techniques is proposed to investigate the longitudinal trajectories of whole-brain sMRI changes denoting AD onset and progression. A set of 2369 T1-weighted images from the multi-centre Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies cohorts are applied to model derivation, validation, testing, and pattern analysis. An Ensemble-3DCNN-based P-score is generated, based on which multiple brain regions, including amygdala, insular, parahippocampal, and temporal gyrus, exhibit early and connected progressive neurodegeneration. Complex individual variability in the sMRI is also observed. This study combining non-invasive sMRI and interpretable DL in detecting patterned sMRI changes confirmed AD pathological progression, shedding new light on predicting AD progression using whole-brain sMRI.

Reference theories and future perspectives on robot-assisted rehabilitation in people with neurological conditions: A scoping review and recommendations from the Italian Consensus Conference on Robotics in Neurorehabilitation (CICERONE)

BACKGROUND

Robot-based treatments are developing in neurorehabilitation settings. Recently, the Italian National Health Systems recognized robot-based rehabilitation as a refundable service. Thus, the Italian neurorehabilitation community promoted a national consensus on this topic.

OBJECTIVE

To conceptualize undisclosed perspectives for research and applications of robotics for neurorehabilitation, based on a qualitative synthesis of reference theoretical models.

METHODS

A scoping review was carried out based on a specific question from the consensus Jury. A foreground search strategy was developed on theoretical models (context) of robot-based rehabilitation (exposure), in neurological patients (population). PubMed and EMBASE® databases were searched and studies on theoretical models of motor control, neurobiology of recovery, human-robot interaction and economic sustainability were included, while experimental studies not aimed to investigate theoretical frameworks, or considering prosthetics, were excluded.

RESULTS

Overall, 3699 records were screened and finally 9 papers included according to inclusion and exclusion criteria. According to the population investigated, structured information on theoretical models and indications for future research was summarized in a synoptic table.

CONCLUSION

The main indication from the Italian consensus on robotics in neurorehabilitation is the priority to design research studies aimed to investigate the role of robotic and electromechanical devices in promoting neuroplasticity.