Multimodal Digital Phenotyping of Behavior in a Neurology Clinic: Development of the Neurobooth Platform and the First Two Years of Data Collection

Early detection of neurodegenerative diseases like Alzheimer’s and Parkinson’s is crucial for improving patient care and enabling timely interventions. Artificial intelligence (AI) offers innovative approaches to analyzing complex medical datasets, revolutionizing the detection of these diseases at early stages. This review discusses key AI methodologies, including machine learning (ML), deep learning (DL), natural language processing (NLP), and reinforcement learning (RL), and their applications in early diagnosis. ML models excel in predicting disease risk and classifying imaging and biometric data, while DL techniques, such as convolutional and recurrent neural networks, are effective in processing unstructured data like images and speech. NLP facilitates extracting critical insights from clinical notes and patient narratives, and RL enhances decision-making in diagnostic workflows. Integrating multimodal data—such as genomics, neuroimaging, wearable device metrics, and electronic health records—further strengthens diagnostic precision. Despite its promise, the widespread implementation of AI faces challenges, including the need for standardized data, ethical considerations, and clinical validation. Overcoming these obstacles is essential for AI to transform early detection and management of neurodegenerative diseases. This review emphasizes the significance of interdisciplinary efforts and sustained research to unlock AI’s full potential in medical applications.

The identification of neurodegenerative diseases at an early stage is still a significant problem in the differential diagnosis.Thus, in the context of this work, we established and tested a new biomarker set for improving early diagnosis of these disorders.We selected three specific biomarkers, namely Amyloid-beta 42, Tau Protein, and Neurofilament Light Chain based on the levels found in a sample of a hundred participants, half of whom were controls and the other half were neurodegenerative cases.The results shown that there was a high level of these biomarkers in the neurodegenerative group than the control group.The validation phase revealed that the biomarker panel particularly Panel 1 (Amyloid-beta 42 and Tau Protein) yielded better accuracy with sensitivity of 85 percent, specificity of 90 percent and AUC of 0. 93.Hence, this panel was shown to be more sensitive and specific compared to traditional diagnostic procedures including CSF analysis and MRI.Furthermore, the correlations calculated for the biomarkers were high and significant between each other particularly between Amyloid-beta 42 and Tau Protein.These results suggest that this new biomarker panel could enhance the early detection and diagnosis of neurodegenerative diseases by a large margin.More studies are needed to replicate these results in the different and more extensive samples and to evaluate the panel in the clinical context.

Background: Neurodegenerative diseases, including Alzheimer’s, Parkinson’s, and Huntington’s, present a growing public health challenge due to their progressive nature and lack of curative treatments. Early detection using biomarkers, such as imaging, cerebrospinal fluid proteins, and blood-based markers, has emerged as a critical strategy to improve patient outcomes. Nurses and emergency care teams, as frontline healthcare providers, play vital roles in implementing early detection strategies. However, their contributions to leveraging biomarkers remain underexplored, particularly in acute and emergency settings where early signs often present. Aim: This paper examines the evolving roles of nurses and emergency care professionals in the early detection of neurodegenerative diseases through the utilization of biomarkers, highlighting their contributions to patient screening, education, and interdisciplinary care. Methods: A systematic literature review was conducted using databases including PubMed, CINAHL, and Google Scholar. Studies relevant to nursing and emergency care roles in biomarker utilization and neurodegenerative disease management were selected. Qualitative analysis identified current practices, barriers, and opportunities in this domain. Results: The findings indicate that nurse- and emergency-led biomarker screening programs significantly enhance early detection efforts. However, barriers such as insufficient training on biomarkers and limited access to advanced diagnostic tools were identified. Collaborative approaches and specialized training programs were shown to improve outcomes and expand the contributions of nursing and emergency teams. Conclusion: Nurses and emergency care professionals are integral to the early detection of neurodegenerative diseases through biomarker application. Enhancing education, resource access, and fostering interprofessional collaboration are essential for optimizing care. Future research should focus on developing standardized frameworks to support their roles in this evolving field.

Background Neurodegenerative diseases, including Alzheimer's disease (AD), Parkinson's disease (PD), and vascular and frontotemporal dementia (FTD), are characterized by progressive cognitive and motor decline. So, timely detection, especially early in the disease process, is crucial. Positron Emission Tomography (PET), Functional Magnetic Resonance Imaging (fMRI), and Diffusion Tensor Imaging (DTI) are advanced neuroimaging techniques that have shown promise for early diagnosis. Objective This review evaluates the diagnostic accuracy and clinical utility of PET, fMRI, and DTI in the early detection of neurodegenerative diseases. Methods A systematic search was conducted using PubMed, Google Scholar, and Cochrane Library for studies published between 2014 and 2024. Inclusion criteria focused on phase 2 and 3 clinical trials involving adult patients with AD, PD, and FTD. Studies were assessed for diagnostic accuracy, sensitivity, specificity, and identification of early biomarkers using PET, fMRI, and DTI. Data were extracted and analyzed from 14 selected studies. Results PET imaging with tracers like 18F‐flortaucipir provided visualization of amyloid and tau aggregates in AD and dopaminergic changes in PD. PET showed a strong association with amyloid and tau pathology in AD, with up to 95% diagnostic performance. Another useful technique in identifying early changes in the brain networks was resting‐state fMRI (rs‐fMRI), with a diagnostic accuracy of 80%–95%. DTI offered essential data on white matter connectivity and showed microstructural alterations that pointed to early neurodegenerative processes. Integrating these neuroimaging modalities with machine learning models further enhanced diagnostic accuracy. Conclusion PET, fMRI, and DTI are valuable tools for the early diagnosis of neurodegenerative diseases. These techniques can identify structural and functional changes in the brain before the onset of clinical signs. Integrating these imaging techniques with machine learning improves diagnostic outcomes. Further large‐scale studies with standardized methodologies are needed to validate these findings and implement these techniques in clinical practice.

BackgroundAround 50 million people have dementia worldwide, with nearly 10 million new cases every year. Diagnosis is complex and often relies on expensive and invasive measures, with most patients accessing medical support when they already experience symptoms.MethodThe Early Detection of Neurodegenerative diseases (EDoN) initiative, spearheaded by Alzheimer’s Research UK, brings together over 60 experts from 49 universities, research projects, patient cohorts and technology providers to create machine learning models to detect the earliest stages of dementia‐causing diseases. EDoN has reviewed behavioural and physiological modalities with the strongest association with pre‐clinical disease.ResultOver 140 modalities were identified from the review and were shortlisted to create the version 1 digital toolkit. This first version includes Mezurio and Longevity smartphone apps, a Fitbit charge 4 activity tracker and Dreem 3 sleep headband. This Toolkit was further refined through patient and public involvement studies and collects 26 measures related to 7 aspects of behaviour and physiology (cognition, neural activity, physical activity, heart rate, fine motor movement, sleep, language and speech). The Toolkit is now being used to collect digital data in four international cohorts (Boston University Alzheimer’s Disease Research Center ‐ BU ADRC; The predictors of COgnitive DECline in attenders of memory clinic using digital devices ‐ CODEC‐2; Western Australia Memory Study ‐ WAMS; Healthy Brain Aging ‐ HBA), alongside prospective and retrospective clinical data, to inform the development of machine learning models.ConclusionEDoN will build models with digital markers, validating them against other biomarkers to predict dementia subtypes and individualised disease trajectories. Based on the outputs of the initial models, EDoN will go through a series of iterations of cohort engagement, modality and tool refinement, and data collection. Workstreams are underway to inform data security, privacy, ethics and open policy research, as well as considering the integration of the final EDoN Toolkit into healthcare systems globally. EDoN aims to deliver a cost‐effective, low burden and population‐wide method for early detection of dementia‐causing diseases that will benefit the public, patients, carers, researchers and clinicians, as well as the broader healthcare system and the delivery of new therapies.

BackgroundArtificial intelligence (AI) plays a promising role in ophthalmic imaging by providing innovative, non-invasive tools for the early detection of neurodegenerative diseases such as Alzheimer’s disease (AD) and Parkinson’s disease (PD). Since early diagnosis is crucial for slowing disease progression and improving patient outcomes, leveraging AI-assisted ophthalmic imaging retinal imaging can enhance detection accuracy and clinical decision-making.MethodsThis review examines clinical applications of AI in identifying retinal biomarkers associated with neurodegenerative diseases. Relevant data was gathered through a comprehensive literature review using PubMed, ScienceDirect, and Google Scholar to evaluate studies utilizing AI algorithms for retinal imaging analysis, focusing on diagnostic performance, sensitivity, specificity, and clinical relevance.ResultsAI-assisted ophthalmic imaging retinal imaging enhances the early identification of neurodegenerative diseases by detecting microscopic structural and vascular changes in the retina. Studies have demonstrated that AI models analyzing Optical Coherence Tomography (OCT) and fundus images achieve high diagnostic accuracy. Studies have reported an area under the curve (AUC) of up to 0.918 in PD detection, with sensitivity ranging from 80 to 100% and specificity up to 85%. Similarly, AI-assisted OCT angiography (OCT-A) analysis has successfully identified retinal vascular alterations in AD patients, correlating with cognitive decline and an AUC of 0.73–0.91. These findings highlight AI’s potential to detect preclinical disease stages before significant neurological symptoms manifest.DiscussionThe integration of AI technologies into ophthalmic imaging holds the potential to improve early diagnosis and transform patient outcomes. However, challenges such as model interpretability, dataset biases, and ethical considerations must be addressed to ensure the responsible integration of AI into clinical practice. Future research should focus on refining AI algorithms, integrating multimodal imaging techniques, and developing predictive biomarkers to optimize early intervention strategies for neurodegenerative diseases.Clinical trial numberNot applicable.

Dementia is characterized by the acquired loss of cognitive and emotional abilities to an extent that it interrupts and inconveniences everyday life. It is not a disease, but rather, is used to describe a group of symptoms that occur when the brain cells stop working properly. Dementia has a prolonged onset period and can go unnoticed for years before significant symptoms manifest or a diagnosis. An early diagnosis for patients with dementia or its subtypes could open the door to better treatment and care as well as give patients the time and opportunity to plan their future while they still can do so. Neuroimaging techniques such as brain magnetic resonance imaging (MRI) and positron emission tomography (PET) are currently used as one of the ‘gold standard’ tools for diagnosing dementia causing diseases. However, these methods can be invasive, carry a risk to the patient, are time consuming and a burden on healthcare and financial resources. For this reason, the Early Detection of Neurodegenerative diseases (EDoN) initiative aims to develop an alternate approach for the large-scale early identification of individuals at risk for dementia causing diseases in a low burden, cost effective manner. EDoN is collecting digital data (e.g., from wearables and smartphone apps) and low burden clinical measures (e.g., blood tests) to use with machine learning models that can detect specific dementia causing diseases decades before noticeable cognitive symptoms manifest In order to validate the new detection methods and digital biomarkers developed within EDoN, a comparison against the ‘gold standard’ biomarkers coming from neuroimages is needed. In this report we provide an overview of medical imaging data relevant to dementia causing diseases. We explore the availability of neuroimaging data and open access or access upon request databases. We elaborate on the challenges of accessing the data and give the details of those databases we were able to gain access to, in terms of number of subjects as well as their age and gender, and the imaging modalities used.

People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimer's and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules voting, product, mean, median, maximum and minimum to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers a single classification algorithm using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.

Neurological disorders are found to be influencing the peripheral tissues outside CNS. Recent developments in biomarkers for CNS have emerged with various diagnostic and therapeutic shortcomings. The role of central biomarkers including CSF-based and molecular imaging-based probes are still unclear for early diagnosis of major neurological diseases. Current trends show that early detection of neurodegenerative diseases with non-invasive methods is a major focus of researchers, and the development of biomarkers aiming peripheral tissues is in demand. Alzheimer's and Parkinson's diseases are known for the progressive loss in neural structures or functions, including the neural death. Various dysfunctions of metabolic and biochemical pathways are associated with early occurrence of neuro-disorders in peripheral tissues including skin, blood cells, and eyes. This article reviews the peripheral biomarkers explored for early detection of Alzheimer's and Parkinson's diseases including blood cells, skin fibroblast, proteomics, saliva, olfactory, stomach and colon, heart and peripheral nervous system, and others. Graphical Abstract.

BackgroundThe benefits of the early detection of the neurodegenerative and vascular pathologies which cause dementia are widely acknowledged. These include the opportunity to initiate risk‐reduction strategies, disease‐modifying therapies, and future care planning. However, current pathological biomarkers have several important drawbacks, as they are typically invasive, expensive, impractical, insensitive, or lack real‐world validation. Conversely, the targeted utilization of non‐invasive and inexpensive digital technologies which can be integrated into everyday life raises the possibility of capturing a ‘digital‐fingerprint’ of early disease.MethodThe Early Detection of Neurodegenerative diseases (EDoN) initiative is a meta‐cohort study spearheaded by Alzheimer’s Research UK. EDoN is acquiring high‐dimensional data from a ‘digital toolkit’ comprising a smartwatch (Fitbit Charge 4/5), smartphone software (Mezurio and Longevity), and an electroencephalography headband (Dreem 3). In combination with conventional digital, cognitive and biological markers, these data will inform the development of powerful machine learning models to detect dementia‐causing diseases at the very earliest stages. The initial phase, incorporating four cohorts across three continents, is already underway, and will recruit nearly 900 participants. Cohorts are recruiting healthy individuals, as well as patients with subjective/mild cognitive impairment, or established dementia. Data from version‐1 of the toolkit is being collected over two‐week periods at 3‐monthly intervals for a minimum of 12 months.ResultWe will present early insights from the implementation of the EDoN digital toolkit version‐1. These will include sample characteristics, feasibility and acceptability, and participants’ compliance. PPI data confirmed good acceptability but the potential for inequity due to technical problems and poor digital literacy. Pilot data indicate that six‐month adherence to the EDoN digital tools varies between 82‐89%. The forthcoming AAIC presentation will include important recruitment, toolkit acceptability and analytic updates.ConclusionThe initial implementation of the EDoN digital toolkit suggests that it is feasible and acceptable to collect high‐dimensional digital data over a six‐month period. These ‘digital‐fingerprints’ will form the basis of the initial development of machine learning models to identify dementia‐causing pathologies substantially earlier. The insights gained will also inform the development of version‐2 of the EDoN digital toolkit which will be incorporated into the next meta‐cohort prospective study of around 4,000 participants.

Parkinson’s disease is a high prevalent neurodegenerative disease. The exact pathogenesis of this disease remains to be fully elucidated; however, regardless of the underlying mechanisms, the ultimate outcome is the progressive loss of dopaminergic neurons. Cuproptosis is a recently discovered form of copper-induced regulated cell death. Its morphology, biochemical properties, and mechanism of action differ from known forms of cell death such as apoptosis, autophagy, necrosis, and pyroptosis. Copper binds to the lipoylated components of the tricarboxylic acid cycle, causing proteotoxic stress, which eventually results in cell cuproptosis. The pathological biochemical hallmarks of Parkinson’s disease include mitochondrial dysfunction and lower brain levels of copper and glutathione. These processes are intricately associated with the underlying mechanism of cuproptosis. However, the specific aspects of the interplay between the pathogenesis of Parkinson’s disease and cuproptosis have yet to be fully explored. The article summarizes the available evidence on cuproptosis as the cause of neuronal death in Parkinson’s disease, and its role in the pathogenesis of Parkinson’s disease. Cuproptosis offers a novel and promising approach to understanding the role of copper dysregulation in the pathogenesis of neurodegenerative diseases. A comprehensive understanding of the mechanisms underlying copper-induced cell death will facilitate the development of novel therapeutic strategies, particularly to address medical conditions associated with copper imbalance, including Wilson’s disease and Parkinson’s disease. The therapeutic potential of targeting cuproptosis using copper chelation strategies has already been confirmed in various experimental models that demonstrate significant improvement in cognitive functions and symptoms of the disease. The incorporation of the concept of cuproptosis into clinical practice promises to enhance diagnostic accuracy and treatment efficacy by personalizing medical approaches, facilitating early intervention, and enabling precise regulation of copper levels. The further investigation of the complex molecular mechanisms of cuproptosis, the development of specific biomarkers for the early detection of neurodegenerative diseases, and the optimization of therapeutic protocols to ensure the safety and efficacy of treatment are all essential. Addressing these challenges will play a pivotal role in the successful integration of novel scientific advances into clinical practice, thereby enhancing patient care and overall quality of life.

Background: The medulla oblongata, a critical brainstem structure, governs essential autonomic functions such as respiration, heart rate, and blood pressure. Understanding its anatomical and volumetric characteristics is vital for diagnosing neurological and neurodegenerative disorders, forensic investigations, and neurosurgical planning. Despite advancements in neuroimaging, normative data—especially population-specific information related to age and gender—remain limited, particularly in the western region of Gujarat. This study aims to establish normative volumetric data for the medulla oblongata using 1.5 Tesla MRI in the Western Gujarat population. Method: This retrospective observational study was conducted on 50 subjects (26 males and 24 females) aged 20 to 66 years who underwent MRI brain scans at a tertiary care hospital from March 2023 to February 2024. Only scans with normal brain findings were included. MRI images were analyzed using Radiant DICOM Viewer 2023, and volumetric parameters such as length (MOL), width (MOW), height (MOH), and volume (MOV) of the medulla oblongata were measured. Results: The study found significant differences in MOH and MOV between males and females (p < 0.001). Males had a higher average MOV (2274 mm³) than females (1752 mm³). Age-wise comparisons showed significant differences in MOL and MOW across age groups (p <0.024 and p < 0.020, respectively). Post-hoc analysis revealed that MOL significantly differed between the 20–29 and 30–39 age groups (p < 0.035), and MOW differed between the 50–59 and 60–69 groups (p < 0.036). Within-gender analysis found that MOV significantly varied among males across age groups (p < 0.022), while MOW varied among females (p < 0.048). Strong positive correlations were observed between MOV and individual medullary dimensions (p < 0.001). Conclusion: This study establishes foundational normative data on the volumetric parameters of the medulla oblongata for the Western Gujarat population. Significant gender and age-related differences were observed, emphasizing the importance of demographic specificity in clinical assessments. These findings have potential applications in forensic science for gender identification, neurosurgical planning, and early detection of neurodegenerative diseases.

This research utilizes deep learning methods to introduce a new method for the classification and early detection of neurodegenerative diseases, particularly Alzheimer's disease. Our approach utilizes cutting-edge deep learning architectures, such as convolutional neural networks (CNNs), residual network (ResNet), to evaluate medical imaging data, including neuroimaging sequences and MRI images. Our deep learning model has been trained using a comprehensive and diverse dataset that encompasses neuroimaging samples from both healthy individuals and those diagnosed with Alzheimer's disease. The trained model demonstrates strong performance, achieving high sensitivity, specificity, and accuracy levels.

Neurodegenerative diseases, such as Alzheimer’s disease (AD), pose significant challenges in early diagnosis, leading to irreversible brain damage and cognitive decline. In this study, we present a novel diagnostic approach that utilizes whole molecule analysis of neuron-derived cell-free DNA (cfDNA) as a biomarker for early detection of neurodegenerative diseases. By analyzing Differential Methylation Regions (DMRs) between purified cortical neurons and blood plasma samples, we identified robust biomarkers that accurately distinguish between neuronal and non-neuronal cfDNA. The use of cfDNA offers the advantage of convenient and minimally invasive sample collection compared to traditional cerebrospinal fluid or tissue biopsies, making this approach more accessible and patient friendly. Targeted sequencing at the identified DMR locus demonstrated that a conservative cutoff of 5% of neuron-derived cfDNA in blood plasma accurately identifies 100% of patients diagnosed with AD, showing promising potential for early disease detection. Additionally, this method effectively differentiated between patients with mild cognitive impairment (MCI) who later progressed to AD and those who did not, highlighting its prognostic capabilities. Importantly, the differentiation between patients with neurodegenerative diseases and healthy controls demonstrated the specificity of our approach. Furthermore, this cfDNA-based diagnostic strategy outperforms recently developed protein-based assays, which often lack accuracy and convenience. While our current approach focused on a limited set of loci, future research should explore the development of a more comprehensive model incorporating multiple loci to increase diagnostic accuracy further. Although certain limitations, such as technical variance associated with PCR amplification and bisulfite conversion, need to be addressed, this study emphasizes the potential of cfDNA analysis as a valuable tool for pre-symptomatic detection and monitoring of neurodegenerative diseases. With further development and validation, this innovative diagnostic strategy has the potential to significantly impact the field of neurodegenerative disease research and patient care, offering a promising avenue for early intervention and personalized therapeutic approaches.

Reduction of systematic errors in diffusion tensor imaging of the human brain as a prospect for increasing the precision of planning neurosurgical operations with particular emphasis on fiber tracking.