The CloudUPDRS smartphone software in Parkinson's study: cross-validation against blinded human raters.

Digital assessments of motor severity could improve the sensitivity of clinical trials and personalise treatment in Parkinson's disease (PD) but have yet to be widely adopted. Their ability to capture individual change across the heterogeneous motor presentations typical of PD remains inadequately tested against current clinical reference standards. We conducted a prospective, dual-site, crossover-randomised study to determine the ability of a 16-item smartphone-based assessment (the index test) to predict subitems from the Movement Disorder Society-Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS III) as assessed by three blinded clinical raters (the reference-standard). We analysed data from 60 subjects (990 smartphone tests, 2628 blinded video MDS-UPDRS III subitem ratings). Subject-level predictive performance was quantified as the leave-one-subject-out cross-validation (LOSO-CV) accuracy. A pre-specified analysis classified 70.3% (SEM 5.9%) of subjects into a similar category to any of three blinded clinical raters and was better than random (36.7%; SEM 4.3%) classification. Post hoc optimisation of classifier and feature selection improved performance further (78.7%, SEM 5.1%), although individual subtests were variable (range 53.2-97.0%). Smartphone-based measures of motor severity have predictive value at the subject level. Future studies should similarly mitigate against subjective and feature selection biases and assess performance across a range of motor features as part of a broader strategy to avoid overly optimistic performance estimates.

Sensory dominance and multisensory integration as screening tools in aging.

Multisensory information typically confers neural and behavioural advantages over unisensory information. We used a simple audio-visual detection task to compare healthy young (HY), healthy older (HO) and mild-cognitive impairment (MCI) individuals. Neuropsychological tests assessed individuals' learning and memory impairments. First, we provide much-needed clarification regarding the presence of enhanced multisensory benefits in both healthily and abnormally aging individuals. The pattern of sensory dominance shifted with healthy and abnormal aging to favour a propensity of auditory-dominant behaviour (i.e., detecting sounds faster than flashes). Notably, multisensory benefits were larger only in healthy older than younger individuals who were also visually-dominant. Second, we demonstrate that the multisensory detection task offers benefits as a time- and resource-economic MCI screening tool. Receiver operating characteristic (ROC) analysis demonstrated that MCI diagnosis could be reliably achieved based on the combination of indices of multisensory integration together with indices of sensory dominance. Our findings showcase the importance of sensory profiles in determining multisensory benefits in healthy and abnormal aging. Crucially, our findings open an exciting possibility for multisensory detection tasks to be used as a cost-effective screening tool. These findings clarify relationships between multisensory and memory functions in aging, while offering new avenues for improved dementia diagnostics.