SCSamira Choudhury

Samira Choudhury

*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


Samira Choudhury has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Sex Differences in Phenomenology of Behavioral and Psychological Symptoms of Dementia

    by Samira Choudhury, Sarah Colman, Li Chu, Simon Jonathan Cheshire Davies, Peter Derkach, Sarah Elmi, Corinne E. Fischer, Philip Gerretsen, Ariel Graff-Guerrero, Maria Hussain, et al.

    Introduction: Behavioral and psychological symptoms in dementia (BPSD) are highly prevalent in patients with Alzheimer’s dementia (AD). We examined sex differences in the frequency and severity of BPSD in patients with AD living in long-term care homes or admitted to inpatient psychiatric units. Methods: Data were obtained from the Standardizing Care for Neuropsychiatric Symptoms and Quality of Life in Dementia (StaN) study (ClinicalTrials.gov/NCT03672201). BPSD were assessed using the Neuropsychiatric Inventory-Clinician rating scale (NPI-C), and symptom clusters were clustered as follows: (1) psychosis (hallucinations and delusions), (2) emotional distress cluster A (depression and anxiety), (3) emotional distress cluster B (depression, anxiety, and apathy), and (4) agitation (agitation, aggression, irritability, aberrant motor behavior, and aberrant vocalizations). Sex differences in frequency and severity of individual BPSD and clusters were compared using chi-square and Mann-Whitney U tests and generalized linear models while controlling for age and place of residence. Results: Females had higher frequency (males = 21.7% vs. females = 42.9%, χ2 = 8.83, N = 174, p = 0.003) and greater severity of delusions (mean [SD] males = 51.87 [44.15], mean [SD] females = 67.93 [70.53], U = 2,924, N = 174, p = 0.002). Males had higher frequency (males = 51.8% vs. females = 27.5%, χ2 = 10.80, N = 174, p = 0.001) and greater severity of sleep disorders (mean [SD] males = 2.94 [4.21], mean [SD] females = 1.76 [3.92], U = 2,885.50, N = 174, p = 0.002). After controlling for age and residence, sex differences remained significant for delusions (Wald χ2 = 3.97, N = 176, p = 0.046), but not for sleep disorders. There were no sex differences in the frequency or severity of any BPSD clusters. Conclusions: We observed sex differences in the frequency and severity of specific BPSD. Future studies should aim to understand potential mechanisms underlying these differences and to study their relevance in screening, and for individualized sex-specific management of BPSD.

  • Open Access

    Multimodal Detection of Agitation in People With Dementia in Clinical Settings: Observational Pilot Study

    by Abeer Badawi, Somayya Elmoghazy, Samira Choudhury, Sara Elgazzar, Khalid Elgazzar, Amer M Burhan

    Background: Dementia is a progressive neurodegenerative condition that affects millions worldwide, often accompanied by agitation and aggression (AA), which contribute to patient distress and increased health care burden. Existing assessment methods for AA rely heavily on caregiver reporting, introducing subjectivity and inconsistency. Objective: This study proposes a novel, multimodal system for predicting AA episodes in individuals with severe dementia, integrating wearable sensor data and privacy-preserving video analytics. Methods: A pilot study involving 10 participants was conducted at Ontario Shores Mental Health Institute. The system combines digital biomarkers collected from the EmbracePlus (Empatica Inc) wristband with video-based behavioral monitoring. Facial features in video frames were anonymized using a masking tool, and a deep learning model was used for AA detection. To determine optimal performance, various machine learning and deep learning models were evaluated for both wearable and video data streams. Results: The Extra Trees model achieved up to 99% accuracy for personalized wristband data, while the multilayer perceptron model performed best in general models with 98% accuracy. For video analysis, the gated recurrent unit model achieved 95% accuracy and 99% area under the curve, and the long short-term memory model demonstrated superior response time for real-time use. Importantly, the system predicted AA episodes at least 6 minutes in advance in all participants based on wearable data. Conclusions: The findings demonstrate the system’s potential to autonomously and accurately detect and predict AA events in real-time. This approach represents a significant advancement in the proactive management of behavioral symptoms in dementia care.


  • Informant‐based tools for assessment and monitoring of cognition, behavior, and function in neurocognitive disorders: Systematic review and report from a CCCDTD5 Working Group

    by Samira Choudhury, Sheena Ghodasara, Michael Stiffel, Corinne E. Fischer, David F. Tang‐Wai, Eric Edward Smith, Fadi Massoud, Ging‐Yuek Robin Hsiung, Linda Lee, Marie‐Andrée Bruneau, et al.

    Objective: As part of the fifth Canadian Consensus Conference on the Diagnosis and Treatment of Dementia, we assessed the literature on informant‐based tools for assessment and monitoring of cognition, behavior, and function in neurocognitive disorders (NCDs) to provide evidence‐based recommendations for clinicians and researchers.Methods: A systematic review was conducted following Preferred Reporting Items for Systematic Reviews and Meta‐Analyses standards guidelines. Publications that validated the informant‐based tools or described their key properties were reviewed. Quality of the studies was assessed using the modified Quality Assessment tool for Diagnostic Accuracy Studies.Results: Out of 386 publications identified through systematic search, 34 that described 19 informant‐based tools were included in the final review. Most of these tools are backed by good‐quality studies and are appropriate to use in clinical care or research. The tools vary in their psychometric properties, domains covered, comprehensiveness, completion time, and ability to detect longitudinal change. Based on these properties, we identify different tools that may be appropriate for primary care, specialized memory clinic, or research settings. We also identify barriers to use of these tools in routine clinical practice.Conclusion: There are several good‐quality tools available to collect informant‐report for assessment and monitoring of cognition, behavior, or function in patients with NCDs. Clinicians and researchers may choose a particular tool based on their specific needs such as domains of interest, desired psychometric properties, and feasibility. Further work is needed to make the tools more user‐friendly and to adopt them into routine clinical care.