Cynthia Sandor
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (6)
Year:
2026
Year:
2025
Background Pre-existing long-term health conditions are highly prevalent in people living with dementia. There is an established relationship between these conditions, trajectories of decline and outcomes in dementia post-diagnosis. An understanding of when these conditions first occur and how they manifest over time within dementia populations remains unclear. The pathophysiology across major bodily systems changes before and after the clinical onset of dementia. However, the timing of various complex, chronic conditions, how they interact and their association with dementia are not yet fully understood. Understanding the complex relationship between multiple long-term conditions and dementia can enhance our understanding of the mechanisms of disease. This understanding can help identify "windows of opportunity" for early interventions in at-risk populations. Long-term conditions also continue to affect individual decline as the disease progresses. We set out to map these key comorbidities chronologically, specific to diagnoses of Alzheimer's Disease and Vascular Dementia. Method We map comorbidities based on International Classification of Diseases (10th revision) system, in a population of people with Alzheimer's Disease and Vascular Dementia from 20 years before through to 10 years after diagnosis. We used inpatient hospital electronic healthcare record data from 10,696 UK Biobank participants, with records spanning a median of 16.90 years (IQR = 10.10 years) for participants with dementia and 13.36 years (IQR = 13.52) for controls (no diagnosis of dementia). Controls were validated with lower polygenic risk scores than either dementia group. Results Characteristic comorbidity signatures were observed in individuals with Alzheimer's Disease and Vascular Dementia. Up to 20 years before diagnosis, depressive episodes, osteoporosis, arthritis and irritable bowel syndrome are characteristic of Alzheimer's Disease, but not Vascular Dementia or control cohorts. From 15 years before diagnosis, type 1 diabetes, functional intestinal disorder and chronic obstructive pulmonary disease begin to emerge. Up to 10 years before, symptoms involving fluid and food intake are uniquely associated with the cohort of people diagnosed with Alzheimer's Disease. In Vascular Dementia, 20 years before diagnosis cerebral infarctions, type 1 diabetes, cerebrovascular disease, peripheral vascular disease, intestinal disorders and rheumatoid arthritis are early conditions in the Vascular Dementia cohort, not seen in control or Alzheimer's Disease cohorts. 15 years before Vascular Dementia, an increase in mental health conditions emerge such as depressive episodes as well as rheumatoid arthritis. 10 years before Vascular Dementia, an additional burden of cerebrovascular diseases, hypotension and dorsalgia. From 5 years up to diagnosis of Vascular Dementia, intra-cerebral haemorrhage, mental and behavioural disorders due to tobacco begin to emerge within this population. In the years following Alzheimer's Disease diagnosis, acute lower respiratory infections and skin conditions such as decubitus ulcer emerge up to 2 years after diagnosis. After a diagnosis of Vascular Dementia, pneumonitis and decubitus ulcer and pressure area, are unique to this cohort. Conclusion In this study, comorbid conditions were mapped in relation to Alzheimer's Disease and Vascular Dementia pre- and post-diagnosis. Understanding prodromal and progressive changes in health over the course of these dementia sub-types could uncover opportunities for targeted screening, preventative measures and early interventions.
Year:
2025
Background Use of digital sensors to passively collect long-term offers a step change in our ability to screen for early signs of disease in the general population. Smartwatch data has been shown to identify Parkinson’s disease (PD) several years before the clinical diagnosis, however, has not been evaluated in comparison to biological and pathological markers such as dopaminergic imaging (DaTscan) or cerebrospinal fluid (CSF) alpha-synuclein seed amplification assay (SAA) in an at-risk cohort. Methods To address this, we performed a cohort study using longitudinal clinical assessment data from the Parkinson’s Progression Marker Initiative (PPMI) cohort collected between 2010 and 2020 with additional long-term (mean: 485 days) at-home digital monitoring data (collected 2018-2020) from the Verily Study Watch. We derived a digital risk score and evaluated it in an at-risk cohort (N = 109) consisting of people with genetic markers ( LRRK2, GBA ) or prodromal symptoms (hyposmia, polysomnography-proven Rapid-Eye-Movement behavioral sleep disorder) without a diagnosis of PD for whom all modalities were available (digital, DaTscan, SAA). The digital risk score was compared to the Movement Disorder Society (MDS) research criteria for prodromal PD, alpha-synuclein SAA and DaTscan. Findings In the at-risk cohort (N=109, mean age = 64.62±6.86, 37% male), the digital risk correlated with the MDS research criteria for prodromal PD (r = 0.36, p-value = 1.46x10 -4 ) and was increased in individuals with subthreshold Parkinsonism (UPDRS III > 6) (p-value = 4.99x10 -6 ) and hyposmia (p-value = 3.77x10 -2 ). Notably, the digital risk was correlated with DaTscan putamen binding ratio (r = -0.32, p-value = 6.64x10 -4 ) and CSF SAA (r = 0.2, p-value = 3.9x10 -2 ). The digital risk achieved higher sensitivity in identifying people with SAA positivity (0.71 vs 0.43) or DaTscan positivity (0.43 vs 0.14) than the MDS prodromal score but performed on-par or worse than hyposmia (SAA+: 0.71 vs 0.71, DaT+: 0.48 vs 0.57). Interpretation A digital risk score from smartwatch data could be used as a sensitive screening tool for early detection of PD followed by more specific tests.
Year:
2024
Background Agitation affects around 30% of people living with dementia (PLwD), increasing carer burden and straining care services. Agitation screening typically relies on subjective clinical scales and direct patient observation, which are resource-intensive and challenging to incorporate into routine care. Clinical applicability of data-driven methods for agitation screening is limited by constraints such as short observational periods, data granularity, and lack of interpretability and generalisability. Current interventions for agitation are primarily medication-based, which may lead to severe side effects and lack personalisation. Understanding how real-world factors affect agitation within home settings offers a promising avenue towards identifying potential personalised non-pharmacological interventions. Methods We used longitudinal data (32,896 person-days from n=63 PLwD) collected using in-home monitoring devices. Employing machine learning techniques, we developed a screening tool to determine the weekly risk of agitation. We incorporated a traffic-light system for risk stratification to aid clinical decision-making and employed the SHapley Additive exPlanations (SHAP) framework to increase interpretability. We designed an interactive tool that enables the exploration of personalised non-pharmacological interventions, such as modifying ambient light and temperature. Results Light Gradient-boosting Machine (LightGBM) achieved the highest performance in identifying agitation with a sensitivity of 71.32 ± 7.38% and specificity of 75.28%. Implementing the traffic-light system for risk stratification increased specificity by 15% and improved all metrics. Significant contributors to agitation included low nocturnal respiratory rate, heightened alertness during sleep, and increased indoor illuminance, as revealed by statistical and feature importance analysis. Using our interactive tool, we identified that adjusting indoor lighting levels and temperature were promising and feasible interventions within our cohort. Conclusions Our interpretable framework for agitation screening, developed using data from a dementia care study, showcases significant clinical value. The accompanying interactive interface allows for the in-silico simulation of non-pharmacological interventions, facilitating the design of personalised interventions that can improve in-home dementia care.
Year:
2024
A major challenge in medical genomics is to understand why individuals with the same disorder have different clinical symptoms and why those who carry the same mutation may be affected by different disorders. In every complex disorder, identifying the contribution of different genetic and non-genetic risk factors is a key obstacle to understanding disease mechanisms. Genetic studies rely on precise phenotypes and are unable to uncover the genetic contributions to a disorder when phenotypes are imprecise. To address this challenge, deeply phenotyped cohorts have been developed for which detailed, fine-grained data have been collected. These cohorts help us to investigate the underlying biological pathways and risk factors to identify treatment targets, and thus to advance precision medicine. The neurodegenerative disorder Parkinson's disease has a diverse phenotypical presentation and modest heritability, and its underlying disease mechanisms are still being debated. As such, considerable efforts have been made to develop deeply phenotyped cohorts for this disorder. Here, we focus on Parkinson's disease and explore how deep phenotyping can help address the challenges raised by genetic and phenotypic heterogeneity. We also discuss recent methods for data collection and computation, as well as methodological challenges that have to be overcome.
Year:
2022
Collaborators (6)
Ramin Nilforooshan
Professor in Psychiatry
University of Surrey
Mina Ryten
University College London
Payam Barnaghi
Professor of Machine Intelligence Applied to Medicine
Imperial College London
Samaneh Kouchaki
Lecturer
University of Surrey
Neil Harrison
Clinical Professor Neuroimaging
Cardiff University
Valentina Escott-Price
Professor
Cardiff University
Make your next move.
Prepare your application
Review drafts before you send them.