SWSamuel L. Warren

Samuel L. Warren

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Samuel L. Warren has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Ecological Digital Phenotyping of Apathy and Anhedonia (Project ECOCAPTURE@HOME-MOTIVATION): Protocol for Characterising Overlapping and Distinct Behavioural Signatures in bvFTD and Alzheimer’s Disease (Preprint)

    by Julie Behenská, Claire Elise Berner, Elena Karpinski, Samuel L. Warren, Katia Andrade, Monica N. Toba, Emmanuelle Volle, Raffaella Migliaccio, Théophile Bieth, Richard Levy, et al.

    BACKGROUND Despite growing interest in Neuropsychiatric symptoms (NPS) in dementia, reliable methods for objectively and accurately monitoring these disturbances in real-world settings remain limited. This study focuses on two prominent motivational NPS: (i) apathy, defined as a reduction in goal-directed behaviour, and (ii) anhedonia, defined as a decreased ability to experience and pursue pleasure. Although conceptually distinct, these symptoms frequently co-occur in people with Alzheimer’s disease (AD) and behavioural variant of frontotemporal dementia (bvFTD), with substantial consequences for autonomy and quality of life. Validated objective and reliable markers of these symptoms are needed to improve symptom and disease monitoring and inform the development and evaluation of targeted interventions. OBJECTIVE To develop a framework for the remote ecological assessment of behavioural markers of apathy and anhedonia in people living with dementia. This approach will provide digital phenotypes of apathy and anhedonia useful for symptom monitoring in real-world settings. METHODS By capturing these digital biomarkers within participants’ natural home environments, this approach provides a novel assessment strategy to NPS. At the Institut du Cerveau in Paris, recruitment will consist of 24 patient-carer dyads with AD, 24 patient-carer dyads with bvFTD and 24 healthy control dyads. Participants will wear Empatica EmbracePlusTM smartwatches equipped with multiple physiological and motion sensors, including an accelerometer and an electrodermal activity sensor. These data will be combined with targeted behavioural questionnaires and ecological momentary assessments (EMA). Given the high-fidelity, multimodal nature of the data collected, machine learning methods will be utilised to explore profiles of apathy and anhedonia at both group and individual levels. We hypothesise that apathy and anhedonia can be reliably identified and monitored in dementia using ECOCAPTURE digital biomarkers. Specifically, we propose that markers of apathy will exhibit momentary fluctuations contingent on context and environment, whereas markers of anhedonia will show greater temporal stability across the day. RESULTS Recruitment is expected to start in late 2026 and continue through 2028. Preliminary analyses are expected from 2027, with final results anticipated in 2029. CONCLUSIONS This project aims to provide novel, objective and ecologically valid behavioural indices of NPS of dementia that can be implemented in the home environment. These digital biomarkers may provide valuable information to identify windows of opportunity for intervention. Moreover, our approach may enable the therapeutic monitoring of targeted interventions aimed at supporting the autonomy of people living with dementia, alleviating carers’ stress and burden, and enabling aging in place. CLINICALTRIAL This protocol is registered in the French ethics committee repertory under the reference number: 26.00946.000424 - 2026-A00614-47. The protocol was approved on the 15th of July 2026 by the Comité de protection des personnes (CPP) Est II.

  • Open Access

    Multidimensional motivation in aging: a person-centred framework spanning goal-directed behaviour, social reward and pleasure

    by Samuel L. Warren, Aria Somasundaram, Kristina Horne, Gail A. Robinson, Julie Behenská, Kathy Nguyen, Anita M.Y. Goh, Yun-Hee Jeon, Lee-Fay Low, Chang Xu, et al.

    Motivational changes are determinants of healthy aging, social engagement, and functional independence, and may signal early neurodegenerative risk. Existing assessment approaches in aging typically treat motivation as a unitary construct. Here, we introduce MotDem, an age-appropriate measure of motivation co-designed with people living with dementia, carers, and clinicians. Across a broad adult lifespan sample (18-80 years), MotDem revealed a robust three-domain motivational architecture encompassing goal-directed behaviour, social reward, and pleasure, with a fourth satiety factor retained as exploratory. This structure was replicated in an independent older cohort (45-80 years) from a different national context. MotDem showed strong convergence with established measures of apathy and anhedonia, alongside more modest associations with depressive symptomatology. Together, these findings show that motivational aging is multifaceted and poorly captured by traditional unitary assessment. MotDem provides a multidimensional framework for measuring distinct motivational drivers of heterogeneous aging trajectories, with implications for resilience, wellbeing, and neurodegenerative risk.


  • Open Access

    Utility of a Subdomain‑Based ACE‑III Online Dementia Screening Tool

    by David Foxe, Omar Arnaiz, James Carrick, Sau Chi Cheung, Rebekah Ahmed, Manisha Narasimhan, Yun Tae Hwang, Nicholas J. Cordato, Muireann Irish, Samuel Warren, et al.

    Introduction: The Addenbrooke’s Cognitive Examination-III (ACE-III) is a widely used dementia screening tool. It provides a total score out of 100 based on five cognitive subdomains: attention, memory, fluency, language, and visuospatial ability. Clinicians often rely on total-score cut-offs (88/100; 82/100) to detect impairment, but patterns across domains may improve diagnostic accuracy. Study aims: (i) develop an optimal model using ACE-III subdomain profiles with probability thresholds; (ii) create an interactive online screening tool.Methods: Participants were from the FRONTIER Research Group: 431 patients with dementia, 107 controls, yielding 1,068 ACE-III assessments. Logistic regression models were developed and validated in an independent cohort from the Sydney Memory and Ageing Study (64 dementia, 273 controls).Results: The best model used all five subdomains (Tjur’s R²=0.819), correctly classifying 91.95% of cases at 95% risk threshold, outperforming total-score models (p<0.05).Discussion: The online ACE-III tool supports personalised dementia risk estimation based on subdomain patterns.

  • Open Access

    Functional and Clinical: An Explainable Deep Learning Model for Multimodal Alzheimer's Disease Classification

    by Samuel L. Warren, Ahmed A. Moustafa

    Purpose: Functional magnetic resonance imaging (fMRI) and deep learning models can classify Alzheimer's disease (AD) with high accuracy. These models are highly adaptable and work with a plethora of architectures, data types, and AD stages. However, fMRI deep learning models lack clinical application due to issues with small datasets, explainability, and reliability (e.g., data leakage). Methods: In this study, we address these issues using multimodal and explainable artificial intelligence (XAI) methods. Specifically, we overcome data size limitations by supplementing fMRI data with clinical tests, use a strict leave‐one‐out cross‐validation regime to control for data leakage, and apply perturbation ranking to explain the importance of features in our model. Our 3D convolutional neural network model was trained and validated on 52 participants from ADNI using five clinical tests and fMRI of the default mode network. Findings: The resulting multimodal model classified AD from controls with an accuracy of 90% and outperformed the same architecture without clinical data (58% accuracy). Our feature rankings showed that clinical tests changed in importance within our model depending on the diagnostic group. For example, our model found the MoCA to be highly important for classifying controls but not for AD. This trend of feature importance was seen across almost all fMRI and clinical features. Conclusion: Our model was highly accurate and highlighted the importance of combining fMRI and clinical data for AD classification. These findings have implications for the refinement of multimodal deep learning models; however, our small sample and need for external validation are also noted.


  • Open Access

    Towards Clinical Diagnoses: Classifying Alzheimer's Disease Using Single fMRI, Small Datasets, and Transfer Learning

    by Samuel L. Warren, Ahmed A. Moustafa, For The Alzheimer'S Disease Neuroimaging Initiative

    Purpose: Deep learning and functional magnetic resonance imaging (fMRI) are two unique methodologies that can be combined to diagnose Alzheimer's disease (AD). Multiple studies have harnessed these methods to diagnose AD with high accuracy. However, there are difficulties in adapting this research to real‐world diagnoses. For example, the two key issues of data availability and model usability limit clinical applications. These two areas are concerned with problems of accessibility, generalizability, and methodology that may limit model adoption. For example, fMRI deep learning models require a large amount of training data, which is not widely available. Contemporary models are also not typically formatted for clinical data or created for use by non‐specialized populations. In this study, we develop a deep‐learning fMRI pipeline that addresses some of these issues.Method: We use transfer learning to address problems with data availability. We also use semi‐automated and single‐image techniques (i.e., one fMRI volume per participant) to make a model that is usable for non‐specialized populations. Our model was initially trained on 524 participants from the Autism Brain Imaging Data Exchange (ABIDE; Autism and controls). Our model was then transferred and fine‐tuned to a small sample of 64 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI; AD and controls).Findings and Conclusion: This transfer learning model achieved an AD classification accuracy of 77% and outperformed the same model without transfer learning by approximately 30%. Accordingly, our model showed that small AD samples can be accurately classified in a clinically friendly manner.


  • Open Access

    Assistive tools for classifying neurological disorders using fMRI and deep learning: A guide and example

    by Samuel L. Warren, Danish M. Khan, Ahmed A. Moustafa

    Background: Deep‐learning (DL) methods are rapidly changing the way researchers classify neurological disorders. For example, combining functional magnetic resonance imaging (fMRI) and DL has helped researchers identify functional biomarkers of neurological disorders (e.g., brain activation and connectivity) and pilot innovative diagnostic models. However, the knowledge required to perform DL analyses is often domain‐specific and is not widely taught in the brain sciences (e.g., psychology, neuroscience, and cognitive science). Conversely, neurological diagnoses and neuroimaging training (e.g., fMRI) are largely restricted to the brain and medical sciences. In turn, these disciplinary knowledge barriers and distinct specializations can act as hurdles that prevent the combination of fMRI and DL pipelines. The complexity of fMRI and DL methods also hinders their clinical adoption and generalization to real‐world diagnoses. For example, most current models are not designed for clinical settings or use by nonspecialized populations such as students, clinicians, and healthcare workers. Accordingly, there is a growing area of assistive tools (e.g., software and programming packages) that aim to streamline and increase the accessibility of fMRI and DL pipelines for the diagnoses of neurological disorders.Objectives and Methods: In this study, we present an introductory guide to some popular DL and fMRI assistive tools. We also create an example autism spectrum disorder (ASD) classification model using assistive tools (e.g., Optuna, GIFT, and the ABIDE preprocessed repository), fMRI, and a convolutional neural network.Results: In turn, we provide researchers with a guide to assistive tools and give an example of a streamlined fMRI and DL pipeline.Conclusions: We are confident that this study can help more researchers enter the field and create accessible fMRI and deep‐learning diagnostic models for neurological disorders.


  • Common Neuropsychiatric Symptoms in Alzheimer’s Disease, Mild Cognitive Impairment, and Subjective Memory Complaints: A Unified Framework

    by Samuel L. Warren, Eid Abo Hamza, Richard Tindle, Edwina Reid, Paige Whitfield, Adam Doumit, Ahmed A. Moustafa

    The Alzheimer’s disease (AD) continuum is a unique spectrum of cognitive impairment that typically involves the stages of subjective memory complaints (SMC), mild cognitive impairment (MCI), and AD dementia. Neuropsychiatric symptoms (NPS), such as apathy, anxiety, stress, and depression, are highly common throughout the AD continuum. However, there is a dearth of research on how these NPS vary across the AD continuum, especially SMC. There is also disagreement on the effects of specific NPS on each stage of the AD continuum due to their collinearity with other NPS, cognitive decline, and environmental factors (e.g., stress). In this article, we conduct a novel perspective review of the scientific literature to understand the presence of NPS across the AD continuum. Specifically, we review the effects of apathy, depression, anxiety, and stress in AD, MCI, and SMC. We then build on this knowledge by proposing two theories of NPS’ occurrence across the AD continuum. Consequently, we highlight the current landscape, limitations (e.g., differing operationalization), and contentions surrounding the NPS literature. We also outline theories that could clear up contention and inspire future NPS research


  • Open Access

    Cognitive and behavioral abnormalities in individuals with Alzheimer’s disease, mild cognitive impairment, and subjective memory complaints

    by Samuel L. Warren, Edwina Reid, Paige Whitfield, Ahmed M. Helal, Eid G. Abo Hamza, Richard Tindle, Ahmed A. Moustafa, Mohamed S. Hamid

    In this study, we investigated the ability of commonly used neuropsychological tests to detect cognitive and functional decline across the Alzheimer’s disease (AD) continuum. Moreover, as preclinical AD is a key area of investigation, we focused on the ability of neuropsychological tests to distinguish the early stages of the disease, such as individuals with Subjective Memory Complaints (SMC). This study included 595 participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset who were cognitively normal (CN), SMC, mild cognitive impairment (MCI; early or late stage), or AD. Our cognitive measures included the Rey Auditory Verbal Learning Test (RAVLT), the Everyday Cognition Questionnaire (ECog), the Functional Abilities Questionnaire (FAQ), the Alzheimer’s Disease Assessment Scale–Cognitive Subscale (ADAS-Cog), the Montreal Cognitive Assessment scale (MoCA), and the Trail Making test (TMT-B). Overall, our results indicated that the ADAS-13, RAVLT (learning), FAQ, ECog, and MoCA were all predictive of the AD progression continuum. However, TMT-B and the RAVLT (immediate and forgetting) were not significant predictors of the AD continuum. Indeed, contrary to our expectations ECog self-report (partner and patient) were the two strongest predictors in the model to detect the progression from CN to AD. Accordingly, we suggest using the ECog (both versions), RAVLT (learning), ADAS-13, and the MoCA to screen all stages of the AD continuum. In conclusion, we infer that these tests could help clinicians effectively detect the early stages of the disease (e.g., SMC) and distinguish the different stages of AD.


  • Top Cited Papers
    Open Access

    Functional magnetic resonance imaging, deep learning, and Alzheimer's disease: A systematic review

    by Samuel L. Warren, Ahmed A. Moustafa

    Alzheimer's disease (AD) is currently diagnosed using a mixture of psychological tests and clinical observations. However, these diagnoses are not perfect, and additional diagnostic tools (e.g., MRI) can help improve our understanding of AD as well as our ability to detect the disease. Accordingly, a large amount of research has been invested into innovative diagnostic methods for AD. Functional MRI (fMRI) is a form of neuroimaging technology that has been used to diagnose AD; however, fMRI is incredibly noisy, complex, and thus lacks clinical use. Nonetheless, recent innovations in deep learning technology could enable the simplified and streamlined analysis of fMRI. Deep learning is a form of artificial intelligence that uses computer algorithms based on human neural networks to solve complex problems. For example, in fMRI research, deep learning models can automatically denoise images and classify AD by detecting patterns in participants’ brain scans. In this systematic review, we investigate how fMRI (specifically resting‐state fMRI) and deep learning methods are used to diagnose AD. In turn, we outline the common deep neural network, preprocessing, and classification methods used in the literature. We also discuss the accuracy, strengths, limitations, and future direction of fMRI deep learning methods. In turn, we aim to summarize the current field for new researchers, suggest specific areas for future research, and highlight the potential of fMRI to aid AD diagnoses.


  • Open Access

    Subjective memory complaints as a predictor of mild cognitive impairment and Alzheimer’s disease

    by Samuel L. Warren, Edwina Reid, Paige Whitfield, Ahmed A. Moustafa

    While there is a multitude of studies on mild cognitive impairment (MCI; more than 80,000 articles), subjective memory complaints (SMC) have received less attention as a prodromal stage of Alzheimer’s disease (AD; less than 2000 articles). In this perspective review article, we argue that SMC should also be considered as another risk factor for the development of AD, and perhaps a pre-MCI condition. This recognition of SMC could help clinicians to identify individuals at risk of developing dementia and could provide protective treatment for them. Accordingly, in this perspective article, we review key studies that outline the nature of SMC, discuss how SMC is measured, explore SMC in MCI, introduce some approaches to SMC treatment, and we discuss future directions for SMC research. Overall, we argue that, like MCI, there should be more research on SMC as a risk factor for developing AD. Consequentially, we aim to highlight the need for further research on SMC and the condition’s role as a potential neuroprotector against AD (e.g., early-stage marker).