Identifying long-term and imminent suicide predictors in a general population and a clinical sample with machine learning.

BACKGROUND: Machine learning (ML) is increasingly used to predict suicide deaths but their value for suicide prevention has not been established. Our first objective was to identify risk and protective factors in a general population. Our second objective was to identify factors indicating imminent suicide risk. METHODS: We used survival and ML models to identify lifetime predictors using the Cohort of Norway (n=173,275) and hospital diagnoses in a Saskatoon clinical sample (n=12,614). The mean follow-up times were 17 years and 3 years for the Cohort of Norway and Saskatoon respectively. People in the clinical sample had a longitudinal record of hospital visits grouped in six-month intervals. We developed models in a training set and these models predicted survival probabilities in held-out test data. RESULTS: In the general population, we found that a higher proportion of low-income residents in a county, mood symptoms, and daily smoking increased the risk of dying from suicide in both genders. In the clinical sample, the only predictors identified were male gender and older age. CONCLUSION: Suicide prevention probably requires individual actions with governmental incentives. The prediction of imminent suicide remains highly challenging, but machine learning can identify early prevention targets.

The UK Research Excellence Framework and the Matthew effect: Insights from machine learning.

With the high cost of the research assessment exercises in the UK, many have called for simpler and less time-consuming alternatives. In this work, we gathered publicly available REF data, combined them with library-subscribed data, and used machine learning to examine whether the overall result of the Research Excellence Framework 2014 could be replicated. A Bayesian additive regression tree model predicting university grade point average (GPA) from an initial set of 18 candidate explanatory variables was developed. One hundred and nine universities were randomly divided into a training set (n = 79) and test set (n = 30). The model "learned" associations between GPA and the other variables in the training set and was made to predict the GPA of universities in the test set. GPA could be predicted from just three variables: the number of Web of Science documents, entry tariff, and percentage of students coming from state schools (r-squared = .88). Implications of this finding are discussed and proposals are given.

Sunshine, Sea, and Season of Birth: MS Incidence in Wales.

Maternal sun exposure in gestation and throughout the lifetime is necessary for vitamin D synthesis, and living near the sea is a population level index of seafood consumption. The aim of this study was to estimate the incidence rate of multiple sclerosis (MS) in Wales and examine its association with sun exposure, coastal living, and latitude. The study used a database of MS hospital visits and admissions in Wales between 2002 and 2013. For the 1,909 lower layer super output areas (LSOAs) in Wales, coastal status, population, longitude/latitude, and average sunshine hours per day were obtained. Age-specific and age-standardised MS incidence were calculated and modelled using Poisson regression. The distribution of births by month was compared between MS cases and the combined England and Wales population. There were 3,557 new MS cases between 2002 and 2013, with an average annual incidence of 8.14 (95% CI: 7.69-8.59) among males and 12.97 (95% CI: 12.44-13.50) among females per 100,000 population. The female-to-male ratio was 1.86:1. For both sexes combined, the average annual incidence rate was 9.10 (95% CI: 8.80-9.40). All figures are age-standardized to the 1976 European standard population. Compared to the combined England and Wales population, more people with MS were born in April, observed-to-expected ratio: 1.21 (95% CI: 1.08-1.36). MS incidence varied directly with latitude and inversely with sunshine hours. Proximity to the coast was associated with lower MS incidence only in easterly areas. This study shows that MS incidence rate in Wales is comparable to the rate in Scotland and is associated with environmental factors that probably represent levels of vitamin D.