Development and validation of a machine learning model for prediction of type 2 diabetes in patients with mental illness.

BACKGROUND: Type 2 diabetes (T2D) is approximately twice as common among individuals with mental illness compared with the background population, but may be prevented by early intervention on lifestyle, diet, or pharmacologically. Such prevention relies on identification of those at elevated risk (prediction). The aim of this study was to develop and validate a machine learning model for prediction of T2D among patients with mental illness. METHODS: The study was based on routine clinical data from electronic health records from the psychiatric services of the Central Denmark Region. A total of 74,880 patients with 1.59 million psychiatric service contacts were included in the analyses. We created 1343 potential predictors from 51 source variables, covering patient-level information on demographics, diagnoses, pharmacological treatment, and laboratory results. T2D was operationalised as HbA1c ≥48 mmol/mol, fasting plasma glucose ≥7.0 mmol/mol, oral glucose tolerance test ≥11.1 mmol/mol or random plasma glucose ≥11.1 mmol/mol. Two machine learning models (XGBoost and regularised logistic regression) were trained to predict T2D based on 85% of the included contacts. The predictive performance of the best performing model was tested on the remaining 15% of the contacts. RESULTS: The XGBoost model detected patients at high risk 2.7 years before T2D, achieving an area under the receiver operating characteristic curve of 0.84. Of the 996 patients developing T2D in the test set, the model issued at least one positive prediction for 305 (31%). CONCLUSION: A machine learning model can accurately predict development of T2D among patients with mental illness based on routine clinical data from electronic health records. A decision support system based on such a model may inform measures to prevent development of T2D in this high-risk population.

Lexical stability of psychiatric clinical notes from electronic health records over a decade.

OBJECTIVE: Natural language processing (NLP) methods hold promise for improving clinical prediction by utilising information otherwise hidden in the clinical notes of electronic health records. However, clinical practice - as well as the systems and databases in which clinical notes are recorded and stored - change over time. As a consequence, the content of clinical notes may also change over time, which could degrade the performance of prediction models. Despite its importance, the stability of clinical notes over time has rarely been tested. METHODS: The lexical stability of clinical notes from the Psychiatric Services of the Central Denmark Region in the period from January 1, 2011, to November 22, 2021 (a total of 14,811,551 clinical notes describing 129,570 patients) was assessed by quantifying sentence length, readability, syntactic complexity and clinical content. Changepoint detection models were used to estimate potential changes in these metrics. RESULTS: We find lexical stability of the clinical notes over time, with minor deviations during the COVID-19 pandemic. Out of 2988 data points, 17 possible changepoints (corresponding to 0.6%) were detected. The majority of these were related to the discontinuation of a specific note type. CONCLUSION: We find lexical and syntactic stability of clinical notes from psychiatric services over time, which bodes well for the use of NLP for predictive modelling in clinical psychiatry.

Introducing tomsup: Theory of mind simulations using Python.

Theory of mind (ToM) is considered crucial for understanding social-cognitive abilities and impairments. However, verbal theories of the mechanisms underlying ToM are often criticized as under-specified and mutually incompatible. This leads to measures of ToM being unreliable, to the extent that even canonical experimental tasks do not require representation of others' mental states. There have been attempts at making computational models of ToM, but these are not easily available for broad research application. In order to help meet these challenges, we here introduce the Python package tomsup: Theory of mind simulations using Python. The package provides a computational eco-system for investigating and comparing computational models of hypothesized ToM mechanisms and for using them as experimental stimuli. The package notably includes an easy-to-use implementation of the variational recursive Bayesian k-ToM model developed by (Devaine, Hollard, & Daunizeau, 2014b) and of simpler non-recursive decision models, for comparison. We provide a series of tutorials on how to: (i) simulate agents relying on the k-ToM model and on a range of simpler types of mechanisms; (ii) employ those agents to generate online experimental stimuli; (iii) analyze the data generated in such experimental setup, and (iv) specify new custom ToM and heuristic cognitive models.

Monitoring of COVID-19 pandemic-related psychopathology using machine learning.

The COVID-19 pandemic is believed to have a major negative impact on global mental health due to the viral disease itself as well as the associated lockdowns, social distancing, isolation, fear, and increased uncertainty. Individuals with preexisting mental illness are likely to be particularly vulnerable to these conditions and may develop outright 'COVID-19-related psychopathology'. Here, we trained a machine learning model on structured and natural text data from electronic health records to identify COVID-19 pandemic-related psychopathology among patients receiving care in the Psychiatric Services of the Central Denmark Region. Subsequently, applying this model, we found that pandemic-related psychopathology covaries with the pandemic pressure over time. These findings may aid psychiatric services in their planning during the ongoing and future pandemics. Furthermore, the results are a testament to the potential of applying machine learning to data from electronic health records.

The PSYchiatric clinical outcome prediction (PSYCOP) cohort: leveraging the potential of electronic health records in the treatment of mental disorders.

BACKGROUND: The quality of life and lifespan are greatly reduced among individuals with mental illness. To improve prognosis, the nascent field of precision psychiatry aims to provide personalised predictions for the course of illness and response to treatment. Unfortunately, the results of precision psychiatry studies are rarely externally validated, almost never implemented in clinical practice, and tend to focus on a few selected outcomes. To overcome these challenges, we have established the PSYchiatric Clinical Outcome Prediction (PSYCOP) cohort, which will form the basis for extensive studies in the upcoming years. METHODS: PSYCOP is a retrospective cohort study that includes all patients with at least one contact with the psychiatric services of the Central Denmark Region in the period from January 1, 2011, to October 28, 2020 (n = 119 291). All data from the electronic health records (EHR) are included, spanning diagnoses, information on treatments, clinical notes, discharge summaries, laboratory tests, etc. Based on these data, machine learning methods will be used to make prediction models for a range of clinical outcomes, such as diagnostic shifts, treatment response, medical comorbidity, and premature mortality, with an explicit focus on clinical feasibility and implementation. DISCUSSIONS: We expect that studies based on the PSYCOP cohort will advance the field of precision psychiatry through the use of state-of-the-art machine learning methods on a large and representative data set. Implementation of prediction models in clinical psychiatry will likely improve treatment and, hopefully, increase the quality of life and lifespan of those with mental illness.

Emotions on Twitter as crisis imprint in high-trust societies: Do ambient affiliations affect emotional expression during the pandemic?

During the Covid-19 crisis, citizens turned to Twitter for information seeking, emotional outlet and sense-making of the crisis, creating ad hoc social communities using crisis-specific hashtags. The theory of ambient affiliation posits that the use of hashtags upscales the call to affiliate with the values expressed in the tweet. Given the deep functional tie between values and emotions, hashtag use might further amplify certain emotions. While emotions in crises-hashtagged communities have been previously investigated, the hypothesis of amplification of emotions through hashtag use has not yet been tested. We investigate such effect during the Covid-19 crisis in a scenario of high-trust Nordic societies, focusing on non-hashtagged, crisis hashtagged (e.g., '#Covid-19') and threat hashtagged (e.g., '#misinformation') tweets. To do so we apply XLM-RoBERTa to estimate Anger, Fear, Sadness, Disgust, Joy and Optimism. Our results revealed that crisis-hashtagged (#Covid-19) tweets expressed more negative emotions (Anger, Fear, Disgust and Sadness) and less positive emotions (Optimism and Joy) than non-hashtagged Covid-19 tweets for all countries except Finland. Threat tweets (#misinformation) expressed even more negative emotions (Anger, Fear, Disgust) and less positive emotions (Optimism and Joy) than #Covid-19 tweets, with a particularly large effect for Anger. Our findings provide useful context for previous research on collective emotions during crises, as most Twitter content is not hashtagged, and given the faster spread of emotionally charged content, further support the special focus on specific ad hoc communities for crisis and threat management and monitoring.

Pandemic news information uncertainty-News dynamics mirror differential response strategies to COVID-19.

National differences in uncertainty, inequality, and trust have been accentuated by COVID-19. There are indications that the pandemic has impacted societies characterized by high uncertainty, inequality, and low trust harder than societies characterized by low uncertainty, equality, and high trust. This study investigates differential response strategies to COVID-19 as reflected in news media of two otherwise similar low uncertainty societies: Denmark and Sweden. The comparison is made using a recent approach to information dynamics in unstructured data. The main findings are that the news dynamics generally mirror public-health policies, capture fundamental socio-cultural variables related to uncertainty and trust, and may provide a measure of societal uncertainty. The findings can provide insights into evolutionary trajectories of decision-making under high uncertainty and, from a methodological level, be used to develop a media-based index of uncertainty and trust.