Identifying individuals at high risk for dementia in primary care: Development and validation of the DemRisk risk prediction model using routinely collected patient data.

INTRODUCTION: Health policy in the UK and globally regarding dementia, emphasises prevention and risk reduction. These goals could be facilitated by automated assessment of dementia risk in primary care using routinely collected patient data. However, existing applicable tools are weak at identifying patients at high risk for dementia. We set out to develop improved risk prediction models deployable in primary care. METHODS: Electronic health records (EHRs) for patients aged 60-89 from 393 English general practices were extracted from the Clinical Practice Research Datalink (CPRD) GOLD database. 235 and 158 practices respectively were randomly assigned to development and validation cohorts. Separate dementia risk models were developed for patients aged 60-79 (development cohort n = 616,366; validation cohort n = 419,126) and 80-89 (n = 175,131 and n = 118,717). The outcome was incident dementia within 5 years and more than 60 evidence-based risk factors were evaluated. Risk models were developed and validated using multivariable Cox regression. RESULTS: The age 60-79 development cohort included 10,841 incident cases of dementia (6.3 per 1,000 person-years) and the age 80-89 development cohort included 15,994 (40.2 per 1,000 person-years). Discrimination and calibration for the resulting age 60-79 model were good (Harrell's C 0.78 (95% CI: 0.78 to 0.79); Royston's D 1.74 (1.70 to 1.78); calibration slope 0.98 (0.96 to 1.01)), with 37% of patients in the top 1% of risk scores receiving a dementia diagnosis within 5 years. Fit statistics were lower for the age 80-89 model but dementia incidence was higher and 79% of those in the top 1% of risk scores subsequently developed dementia. CONCLUSION: Our models can identify individuals at higher risk of dementia using routinely collected information from their primary care record, and outperform an existing EHR-based tool. Discriminative ability was greatest for those aged 60-79, but the model for those aged 80-89 may also be clinical useful.

Identifying psychosis spectrum disorder from experience sampling data using machine learning approaches.

The ubiquity of smartphones opened up the possibility of widespread use of the Experience Sampling Method (ESM). The method is used to collect longitudinal data of participants' daily life experiences and is ideal to capture fluctuations in emotions (momentary mental states) as an indicator for later mental ill-health. In this study, ESM data of patients with psychosis spectrum disorder and controls were used to examine daily life emotions and higher order patterns thereof. We attempted to determine whether aggregated ESM data, in which statistical measures represent the distribution and dynamics of the original data, were able to distinguish patients from controls in a predictive modeling framework. Variable importance, recursive feature elimination, and ReliefF methods were used for feature selection. Model training, tuning, and testing were performed in nested cross-validation, based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Logistic Regression, and Neural Networks. ROC analysis was used to post-process these models. Stability of model performance was studied using Monte Carlo simulations. The results provide evidence that patterns in emotion changes can be captured by applying a combination of these techniques. Acceleration in the variables anxious and insecure was particularly successful in adding further predictive power to the models. The best results were achieved by Support Vector Machines with radial kernel (accuracy = 82% and sensitivity = 82%). This proof-of-concept work demonstrates that synergistic machine learning and statistical modeling may be used to harness the power of ESM data in the future.

A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: Results from the European Medical Information Framework for Alzheimer disease biomarker discovery cohort.

INTRODUCTION: Machine learning (ML) may harbor the potential to capture the metabolic complexity in Alzheimer Disease (AD). Here we set out to test the performance of metabolites in blood to categorize AD when compared to CSF biomarkers. METHODS: This study analyzed samples from 242 cognitively normal (CN) people and 115 with AD-type dementia utilizing plasma metabolites (n = 883). Deep Learning (DL), Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were used to differentiate AD from CN. These models were internally validated using Nested Cross Validation (NCV). RESULTS: On the test data, DL produced the AUC of 0.85 (0.80-0.89), XGBoost produced 0.88 (0.86-0.89) and RF produced 0.85 (0.83-0.87). By comparison, CSF measures of amyloid, p-tau and t-tau (together with age and gender) produced with XGBoost the AUC values of 0.78, 0.83 and 0.87, respectively. DISCUSSION: This study showed that plasma metabolites have the potential to match the AUC of well-established AD CSF biomarkers in a relatively small cohort. Further studies in independent cohorts are needed to validate whether this specific panel of blood metabolites can separate AD from controls, and how specific it is for AD as compared with other neurodegenerative disorders.

A New Machine Learning Framework for Understanding the Link Between Cannabis Use and First-Episode Psychosis.

Lately, several studies started to investigate the existence of links between cannabis use and psychotic disorders. This work proposes a refined Machine Learning framework for understanding the links between cannabis use and 1st episode psychosis. The novel framework concerns extracting predictive patterns from clinical data using optimised and post-processed models based on Gaussian Processes, Support Vector Machines, and Neural Networks algorithms. The cannabis use attributes' predictive power is investigated, and we demonstrate statistically and with ROC analysis that their presence in the dataset enhances the prediction performance of the models with respect to models built on data without these specific attributes.

Utilising symptom dimensions with diagnostic categories improves prediction of time to first remission in first-episode psychosis.

There has been much recent debate concerning the relative clinical utility of symptom dimensions versus conventional diagnostic categories in patients with psychosis. We investigated whether symptom dimensions rated at presentation for first-episode psychosis (FEP) better predicted time to first remission than categorical diagnosis over a four-year follow-up. The sample comprised 193 FEP patients aged 18-65years who presented to psychiatric services in South London, UK, between 2006 and 2010. Psychopathology was assessed at baseline with the Positive and Negative Syndrome Scale and five symptom dimensions were derived using Wallwork/Fortgang's model; baseline diagnoses were grouped using DSM-IV codes. Time to start of first remission was ascertained from clinical records. The Bayesian Information Criterion (BIC) was used to find the best fitting accelerated failure time model of dimensions, diagnoses and time to first remission. Sixty percent of patients remitted over the four years following first presentation to psychiatric services, and the average time to start of first remission was 18.3weeks (SD=26.0, median=8). The positive (BIC=166.26), excited (BIC=167.30) and disorganised/concrete (BIC=168.77) symptom dimensions, and a diagnosis of schizophrenia (BIC=166.91) predicted time to first remission. However, a combination of the DSM-IV diagnosis of schizophrenia with all five symptom dimensions led to the best fitting model (BIC=164.35). Combining categorical diagnosis with symptom dimension scores in FEP patients improved the accuracy of predicting time to first remission. Thus our data suggest that the decision to consign symptom dimensions to an annexe in DSM-5 should be reconsidered at the earliest opportunity.