An integrated clinical approach to children at genetic risk for neurodevelopmental and psychiatric conditions: interdisciplinary collaboration and research infrastructure.

BACKGROUND: A sizeable proportion of pathogenic genetic variants identified in young children tested for congenital differences are associated with neurodevelopmental psychiatric disorders (NPD). In this growing group, a genetic diagnosis often precedes the emergence of diagnosable developmental concerns. Here, we describe DAGSY (Developmental Assessment of Genetically Susceptible Youth), a novel interdisciplinary 'genetic-diagnosis-first' clinic integrating psychiatric, psychological and genetic expertise, and report our first observations and feedback from families and referring clinicians. METHODS: We retrieved data on referral sources and indications, genetic and NPD diagnoses and recommendations for children seen at DAGSY between 2018 and 2022. Through a survey, we obtained feedback from twenty families and eleven referring clinicians. RESULTS: 159 children (mean age 10.2 years, 57.2% males) completed an interdisciplinary (psychiatry, psychology, genetic counselling) DAGSY assessment during this period. Of these, 69.8% had a pathogenic microdeletion or microduplication, 21.5% a sequence-level variant, 4.4% a chromosomal disorder, and 4.4% a variant of unknown significance with emerging evidence of pathogenicity. One in four children did not have a prior NPD diagnosis, and referral to DAGSY was motivated by their genetic vulnerability alone. Following assessment, 76.7% received at least one new NPD diagnosis, most frequently intellectual disability (24.5%), anxiety (20.7%), autism spectrum (18.9%) and specific learning (16.4%) disorder. Both families and clinicians responding to our survey expressed satisfaction, but also highlighted some areas for potential improvement. CONCLUSIONS: DAGSY addresses an unmet clinical need for children identified with genetic variants that confer increased vulnerability for NPD and provides a crucial platform for research in this area. DAGSY can serve as a model for interdisciplinary clinics integrating child psychiatry, psychology and genetics, addressing both clinical and research needs for this emerging population.

Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories.

Gaussian processes (GPs) are a versatile nonparametric model for nonlinear regression and have been widely used to study spatiotemporal phenomena. However, standard GPs offer limited interpretability and generalizability for datasets with naturally occurring hierarchies. With large-scale, rapidly-updating electronic health record (EHR) data, we want to study patient trajectories across diverse patient cohorts while preserving patient subgroup structure. In this work, we partition our cohort of over 2000 COVID-19 patients by sex and ethnicity. We develop and apply a hierarchical Gaussian process and a mixture of experts (MOE) hierarchical GP model to fit patient trajectories on clinical markers of disease progression. A case study for albumin, an effective predictor of COVID-19 patient outcomes, highlights the predictive performance of these models. These hierarchical spatiotemporal models of EHR data bring us a step closer toward our goal of building flexible approaches to capture patient data that can be used in real-time systems*.

Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning.

A principal challenge in the analysis of tissue imaging data is cell segmentation-the task of identifying the precise boundary of every cell in an image. To address this problem we constructed TissueNet, a dataset for training segmentation models that contains more than 1 million manually labeled cells, an order of magnitude more than all previously published segmentation training datasets. We used TissueNet to train Mesmer, a deep-learning-enabled segmentation algorithm. We demonstrated that Mesmer is more accurate than previous methods, generalizes to the full diversity of tissue types and imaging platforms in TissueNet, and achieves human-level performance. Mesmer enabled the automated extraction of key cellular features, such as subcellular localization of protein signal, which was challenging with previous approaches. We then adapted Mesmer to harness cell lineage information in highly multiplexed datasets and used this enhanced version to quantify cell morphology changes during human gestation. All code, data and models are released as a community resource.