Optimising the use of electronic medical records for large scale research in psychiatry.

The explosion and abundance of digital data could facilitate large-scale research for psychiatry and mental health. Research using so-called "real world data"-such as electronic medical/health records-can be resource-efficient, facilitate rapid hypothesis generation and testing, complement existing evidence (e.g. from trials and evidence-synthesis) and may enable a route to translate evidence into clinically effective, outcomes-driven care for patient populations that may be under-represented. However, the interpretation and processing of real-world data sources is complex because the clinically important 'signal' is often contained in both structured and unstructured (narrative or "free-text") data. Techniques for extracting meaningful information (signal) from unstructured text exist and have advanced the re-use of routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey the opportunities, risks and progress made in the use of electronic medical record (real-world) data for psychiatric research.

Anemia, hemoglobin concentration and cognitive function in the Longitudinal Ageing Study in India-Harmonized Diagnostic Assessment of Dementia (LASI-DAD) and the Health and Retirement Study.

Background: In India, anemia is widely researched in children and women of reproductive age, however, studies in older populations are lacking. Given the adverse effect of anemia on cognitive function and dementia this older population group warrants further study. The Longitudinal Ageing Study in India - Harmonized Diagnostic Assessment of Dementia (LASI-DAD) dataset contains detailed measures to allow a better understanding of anaemia as a potential risk factor for dementia. Method: 2,758 respondents from the LASI-DAD cohort, aged 60 or older, had a complete blood count measured from venous blood as well as cognitive function tests including episodic memory, executive function and verbal fluency. Linear regression was used to test the associations between blood measures (including anemia and hemoglobin concentration (g/dL)) with 11 cognitive domains. All models were adjusted for age and gender with the full model containing adjustments for rural location, years of education, smoking, region, BMI and population weights.Results from LASI-DAD were validated using the USA-based Health and Retirement Study (HRS) cohort (n=5720) to replicate associations between blood cell measures and global cognition. Results: In LASI-DAD, we showed an association between anemia and poor memory (p=0.0054). We found a positive association between hemoglobin concentration and ten cognitive domains tested (ß=0.041-0.071, p<0.05). The strongest association with hemoglobin was identified for memory-based tests (immediate episodic, delayed episodic and broad domain memory, ß=0.061-0.071, p<0.005). Positive associations were also shown between the general cognitive score and the other red blood count tests including mean corpuscular hemoglobin concentration (MCHC, ß=0.06, p=0.0001) and red cell distribution width (RDW, ß =-0.11, p<0.0001). In the HRS cohort, positive associations were replicated between general cognitive score and other blood count tests (Red Blood Cell, MCHC and RDW, p<0.05). Conclusion: We have established in a large South Asian population that low hemoglobin and anaemia are associated with low cognitive function, therefore indicating that anaemia could be an important modifiable risk factor. We have validated this result in an external cohort demonstrating both the variability of this risk factor cross-nationally and its generalizable association with cognitive outcomes.

Artificial intelligence for biomarker discovery in Alzheimer's disease and dementia.

With the increase in large multimodal cohorts and high-throughput technologies, the potential for discovering novel biomarkers is no longer limited by data set size. Artificial intelligence (AI) and machine learning approaches have been developed to detect novel biomarkers and interactions in complex data sets. We discuss exemplar uses and evaluate current applications and limitations of AI to discover novel biomarkers. Remaining challenges include a lack of diversity in the data sets available, the sheer complexity of investigating interactions, the invasiveness and cost of some biomarkers, and poor reporting in some studies. Overcoming these challenges will involve collecting data from underrepresented populations, developing more powerful AI approaches, validating the use of noninvasive biomarkers, and adhering to reporting guidelines. By harnessing rich multimodal data through AI approaches and international collaborative innovation, we are well positioned to identify clinically useful biomarkers that are accurate, generalizable, unbiased, and acceptable in clinical practice. HIGHLIGHTS: Artificial intelligence and machine learning approaches may accelerate dementia biomarker discovery. Remaining challenges include data set suitability due to size and bias in cohort selection. Multimodal data, diverse data sets, improved machine learning approaches, real-world validation, and interdisciplinary collaboration are required.

Artificial intelligence for neurodegenerative experimental models.

INTRODUCTION: Experimental models are essential tools in neurodegenerative disease research. However, the translation of insights and drugs discovered in model systems has proven immensely challenging, marred by high failure rates in human clinical trials. METHODS: Here we review the application of artificial intelligence (AI) and machine learning (ML) in experimental medicine for dementia research. RESULTS: Considering the specific challenges of reproducibility and translation between other species or model systems and human biology in preclinical dementia research, we highlight best practices and resources that can be leveraged to quantify and evaluate translatability. We then evaluate how AI and ML approaches could be applied to enhance both cross-model reproducibility and translation to human biology, while sustaining biological interpretability. DISCUSSION: AI and ML approaches in experimental medicine remain in their infancy. However, they have great potential to strengthen preclinical research and translation if based upon adequate, robust, and reproducible experimental data. HIGHLIGHTS: There are increasing applications of AI in experimental medicine. We identified issues in reproducibility, cross-species translation, and data curation in the field. Our review highlights data resources and AI approaches as solutions. Multi-omics analysis with AI offers exciting future possibilities in drug discovery.

Artificial intelligence for dementia genetics and omics.

Genetics and omics studies of Alzheimer's disease and other dementia subtypes enhance our understanding of underlying mechanisms and pathways that can be targeted. We identified key remaining challenges: First, can we enhance genetic studies to address missing heritability? Can we identify reproducible omics signatures that differentiate between dementia subtypes? Can high-dimensional omics data identify improved biomarkers? How can genetics inform our understanding of causal status of dementia risk factors? And which biological processes are altered by dementia-related genetic variation? Artificial intelligence (AI) and machine learning approaches give us powerful new tools in helping us to tackle these challenges, and we review possible solutions and examples of best practice. However, their limitations also need to be considered, as well as the need for coordinated multidisciplinary research and diverse deeply phenotyped cohorts. Ultimately AI approaches improve our ability to interrogate genetics and omics data for precision dementia medicine. HIGHLIGHTS: We have identified five key challenges in dementia genetics and omics studies. AI can enable detection of undiscovered patterns in dementia genetics and omics data. Enhanced and more diverse genetics and omics datasets are still needed. Multidisciplinary collaborative efforts using AI can boost dementia research.

Replication study of plasma proteins relating to Alzheimer's pathology.

INTRODUCTION: This study sought to discover and replicate plasma proteomic biomarkers relating to Alzheimer's disease (AD) including both the "ATN" (amyloid/tau/neurodegeneration) diagnostic framework and clinical diagnosis. METHODS: Plasma proteins from 972 subjects (372 controls, 409 mild cognitive impairment [MCI], and 191 AD) were measured using both SOMAscan and targeted assays, including 4001 and 25 proteins, respectively. RESULTS: Protein co-expression network analysis of SOMAscan data revealed the relation between proteins and "N" varied across different neurodegeneration markers, indicating that the ATN variants are not interchangeable. Using hub proteins, age, and apolipoprotein E ε4 genotype discriminated AD from controls with an area under the curve (AUC) of 0.81 and MCI convertors from non-convertors with an AUC of 0.74. Targeted assays replicated the relation of four proteins with the ATN framework and clinical diagnosis. DISCUSSION: Our study suggests that blood proteins can predict the presence of AD pathology as measured in the ATN framework as well as clinical diagnosis.

Dickkopf-1 Overexpression in vitro Nominates Candidate Blood Biomarkers Relating to Alzheimer's Disease Pathology.

BACKGROUND: Previous studies suggest that Dickkopf-1 (DKK1), an inhibitor of Wnt signaling, plays a role in amyloid-induced toxicity and hence Alzheimer's disease (AD). However, the effect of DKK1 expression on protein expression, and whether such proteins are altered in disease, is unknown. OBJECTIVE: We aim to test whether DKK1 induced protein signature obtained in vitro were associated with markers of AD pathology as used in the amyloid/tau/neurodegeneration (ATN) framework as well as with clinical outcomes. METHODS: We first overexpressed DKK1 in HEK293A cells and quantified 1,128 proteins in cell lysates using aptamer capture arrays (SomaScan) to obtain a protein signature induced by DKK1. We then used the same assay to measure the DKK1-signature proteins in human plasma in two large cohorts, EMIF (n = 785) and ANM (n = 677). RESULTS: We identified a 100-protein signature induced by DKK1 in vitro. Subsets of proteins, along with age and apolipoprotein E ɛ4 genotype distinguished amyloid pathology (A + T-N-, A+T+N-, A+T-N+, and A+T+N+) from no AD pathology (A-T-N-) with an area under the curve of 0.72, 0.81, 0.88, and 0.85, respectively. Furthermore, we found that some signature proteins (e.g., Complement C3 and albumin) were associated with cognitive score and AD diagnosis in both cohorts. CONCLUSIONS: Our results add further evidence for a role of DKK regulation of Wnt signaling in AD and suggest that DKK1 induced signature proteins obtained in vitro could reflect theATNframework as well as predict disease severity and progression in vivo.

Red blood cell indices and anaemia as causative factors for cognitive function deficits and for Alzheimer's disease.

BACKGROUND: Studies have shown that low haemoglobin and anaemia are associated with poor cognition, and anaemia is known to be associated with Alzheimer's disease (AD), but the mechanism of this risk is unknown. Here, we first seek to confirm the association between cognition and anaemia and secondly, in order to further understand the mechanism of this association, to estimate the direction of causation using Mendelian randomisation. METHODS: Two independent cohorts were used in this analysis: AddNeuroMed, a longitudinal study of 738 subjects including AD and age-matched controls with blood cell measures, cognitive assessments and gene expression data from blood; and UK Biobank, a study of 502,649 healthy participants, aged 40-69 years with cognitive test measures and blood cell indices at baseline. General linear models were calculated using cognitive function as the outcome with correction for age, sex and education. In UK Biobank, SNPs with known blood cell measure associations were analysed with Mendelian randomisation to estimate direction of causality. In AddNeuroMed, gene expression data was used in pathway enrichment analysis to identify associations reflecting biological function. RESULTS: Both sample sets evidence a reproducible association between cognitive performance and mean corpuscular haemoglobin (MCH), a measure of average mass of haemoglobin per red blood cell. Furthermore, in the AddNeuroMed cohort, where longitudinal samples were available, we showed a greater decline in red blood cell indices for AD patients when compared to controls (p values between 0.05 and 10-6). In the UK Biobank cohort, we found lower haemoglobin in participants with reduced cognitive function. There was a significant association for MCH and red blood cell distribution width (RDW, a measure of cell volume variability) compared to four cognitive function tests including reaction time and reasoning (p < 0.0001). Using Mendelian randomisation, we then showed a significant effect of MCH on the verbal-numeric and numeric traits, implying that anaemia has causative effect on cognitive performance. CONCLUSIONS: Lower haemoglobin levels in blood are associated to poor cognitive function and AD. We have used UK Biobank SNP data to determine the relationship between cognitive testing and haemoglobin measures and suggest that haemoglobin level and therefore anaemia does have a primary causal impact on cognitive performance.

Genomic alterations underlie a pan-cancer metabolic shift associated with tumour hypoxia.

BACKGROUND: Altered metabolism is a hallmark of cancer. However, the role of genomic changes in metabolic genes driving the tumour metabolic shift remains to be elucidated. Here, we have investigated the genomic and transcriptomic changes underlying this shift across ten different cancer types. RESULTS: A systematic pan-cancer analysis of 6538 tumour/normal samples covering ten major cancer types identified a core metabolic signature of 44 genes that exhibit high frequency somatic copy number gains/amplifications (>20 % cases) associated with increased mRNA expression (ρ > 0.3, q < 10(-3)). Prognostic classifiers using these genes were confirmed in independent datasets for breast and kidney cancers. Interestingly, this signature is strongly associated with hypoxia, with nine out of ten cancer types showing increased expression and five out of ten cancer types showing increased gain/amplification of these genes in hypoxic tumours (P ≤ 0.01). Further validation in breast and colorectal cancer cell lines highlighted squalene epoxidase, an oxygen-requiring enzyme in cholesterol biosynthesis, as a driver of dysregulated metabolism and a key player in maintaining cell survival under hypoxia. CONCLUSIONS: This study reveals somatic genomic alterations underlying a pan-cancer metabolic shift and suggests genomic adaptation of these genes as a survival mechanism in hypoxic tumours.