Objective: Neuropsychiatric symptoms (NPS) may be the first manifestation of an underlying neurocognitive disorder. We undertook a review to provide an update on the epidemiology and etiological mechanisms of NPS that occur in mild cognitive impairment (MCI) and just before the onset of MCI. We discuss common clinical presentations and the implications for diagnosis and care. Method: The authors conducted a selective review of the literature regarding the emergence of NPS in late life, before and after the onset of MCI. We discuss recent publications that explore the epidemiology and etiological mechanisms of NPS in the earliest clinical stages of these disorders. Results: NPS have been reported in 35% to 85% of adults with MCI and also occur in advance of cognitive decline. The occurrence of NPS for the first time in later life should increase suspicion for an underlying neurocognitive disorder. The presenting symptom may provide a clue regarding the etiology of the underlying disorder, and the co-occurrence of NPS may herald a more accelerated cognitive decline. Conclusions: NPS are prevalent in the early clinical stages of neurocognitive disorders and can serve as both useful diagnostic and prognostic indicators. Recognition of NPS as early manifestations of neurocognitive disorders will become increasingly important as we move towards preventative strategies and disease-modifying treatments that may be most effective when deployed in the earliest stages of disease.

Drug-induced parkinsonism affects many older adults with dementia, often causing gait disturbances. New advances in vision-based human pose- estimation have opened possibilities for frequent and unobtrusive analysis of gait in long-term care settings. This work leverages spatial-temporal graph convolutional network (ST-GCN) architectures and training procedures to predict clinical scores of parkinsonism in gait from video of individuals with dementia. We propose a two-stage training approach consisting of a self-supervised pretraining stage that encourages the ST-GCN model to learn about gait patterns before predicting clinical scores in the finetuning stage. The proposed ST-GCN models are evaluated on joint trajectories extracted from video and are compared against traditional (ordinal, linear, random forest) regression models and temporal convolutional network baselines. Three 2D human pose-estimation libraries (OpenPose, Detectron, AlphaPose) and the Microsoft Kinect (2D and 3D) are used to extract joint trajectories of 4787 natural walking bouts from 53 older adults with dementia. A subset of 399 walks from 14 participants is annotated with scores of parkinsonism severity on the gait criteria of the Unified Parkinson's Disease Rating Scale (UPDRS) and the Simpson-Angus Scale (SAS). Our results demonstrate that ST-GCN models operating on 3D joint trajectories extracted from the Kinect consistently outperform all other models and feature sets. Prediction of parkinsonism scores in natural walking bouts of unseen participants remains a challenging task, with the best models achieving macro-averaged F1-scores of 0.53 ± 0.03 and 0.40 ± 0.02 for UPDRS-gait and SAS-gait, respectively. Pre-trained model and demo code for this work is available. ¹