Sensory Processing Abnormalities in Community-Dwelling Older Adults with Cognitive Impairment: A Mixed Methods Study

DeepGAMI: deep biologically guided auxiliary learning for multimodal integration and imputation to improve genotype-phenotype prediction

BACKGROUND

Genotypes are strongly associated with disease phenotypes, particularly in brain disorders. However, the molecular and cellular mechanisms behind this association remain elusive. With emerging multimodal data for these mechanisms, machine learning methods can be applied for phenotype prediction at different scales, but due to the black-box nature of machine learning, integrating these modalities and interpreting biological mechanisms can be challenging. Additionally, the partial availability of these multimodal data presents a challenge in developing these predictive models.

METHOD

To address these challenges, we developed DeepGAMI, an interpretable neural network model to improve genotype-phenotype prediction from multimodal data. DeepGAMI leverages functional genomic information, such as eQTLs and gene regulation, to guide neural network connections. Additionally, it includes an auxiliary learning layer for cross-modal imputation allowing the imputation of latent features of missing modalities and thus predicting phenotypes from a single modality. Finally, DeepGAMI uses integrated gradient to prioritize multimodal features for various phenotypes.

RESULTS

We applied DeepGAMI to several multimodal datasets including genotype and bulk and cell-type gene expression data in brain diseases, and gene expression and electrophysiology data of mouse neuronal cells. Using cross-validation and independent validation, DeepGAMI outperformed existing methods for classifying disease types, and cellular and clinical phenotypes, even using single modalities (e.g., AUC score of 0.79 for Schizophrenia and 0.73 for cognitive impairment in Alzheimer's disease).

CONCLUSION

We demonstrated that DeepGAMI improves phenotype prediction and prioritizes phenotypic features and networks in multiple multimodal datasets in complex brains and brain diseases. Also, it prioritized disease-associated variants, genes, and regulatory networks linked to different phenotypes, providing novel insights into the interpretation of gene regulatory mechanisms. DeepGAMI is open-source and available for general use.

Are behavioral and psychological symptoms of dementia related to sensory processing?

Problems with sensory processing may have an impact on the behavioral and psychological symptoms that can be seen in Alzheimer's patients. Examining the relationship between the two factors may provide a new perspective for the management of behavioral and psychological symptoms of dementia. Mid-stage Alzheimer's patients completed the Neuropsychiatric Inventory and Adolescent/Adult Sensory Profile. The relationship between behavioral and psychological symptoms of dementia and sensory processing was investigated. Sixty individuals with a mean age of 75.35 (7.86) years and diagnosed with Alzheimer's Dementia 6.6 (2.92) years ago participated in the study. Individuals with severe behavioral and psychological symptoms had higher scores than individuals with moderate behavioral and psychological symptoms in low registration and sensory sensitivity quadrants . A relationship was found between sensory processing and behavioral and psychological symptoms of dementia in mid-stage Alzheimer's patients. This study highlighted the sensory processing differences in patients with Alzheimer's dementia. In future studies, interventions for sensory processing skills may play a role in improving the quality of life of individuals by contributing to the management of behavioral and psychological symptoms of dementia.

Sensory processing sensitivity and social pain: a hypothesis and theory

Sensory-processing sensitivity (SPS) defined, as a personality trait, seems to be characterized by emotional sensitivity, and stronger reactivity to both external and internal stimuli. SPS can represent a risk factor for developing clinical conditions during childhood and adolescence. This personality trait is not to be considered a pathological clinical condition, however, can expose to greater environmental vulnerability. In particular, the recent studies about SPS can be contextualized to social situations that evoke traumatic and stressful emotional responses such as social exclusion. We hypothesize that highly sensitive people (HSP) are more vulnerable to social exclusion and social pain. This hypothesis could help structure new educational and intervention models designed to improve coping strategies and promote HSP's psychophysical and social well-being.

Being in Place: Toward a Situational Perspective on Care

An optimum focus in any care situation is creating and sustaining environments that facilitate an ongoing sense of "being in place" for all involved. Using this rationale, we propose a Situational Model of Care for exploring dynamic relationships among aging persons receiving care, the convoy of persons offering this care and support, and the place where this occurs, as evolving situations throughout the course of a disease. The model is grounded in extant literature and illustrated through a case study derived from in-home observations and interviews. Emphasizing an underlying goal of fostering a sense of being in place as a desirable outcome facilitates situationally nuanced directions in research and clinical care.