Dataset Information

A machine learning approach predicts future risk to suicidal ideation from social media data.

ABSTRACT: Machine learning analysis of social media data represents a promising way to capture longitudinal environmental influences contributing to individual risk for suicidal thoughts and behaviors. Our objective was to generate an algorithm termed "Suicide Artificial Intelligence Prediction Heuristic (SAIPH)" capable of predicting future risk to suicidal thought by analyzing publicly available Twitter data. We trained a series of neural networks on Twitter data queried against suicide associated psychological constructs including burden, stress, loneliness, hopelessness, insomnia, depression, and anxiety. Using 512,526 tweets from N?=?283 suicidal ideation (SI) cases and 3,518,494 tweets from 2655 controls, we then trained a random forest model using neural network outputs to predict binary SI status. The model predicted N?=?830 SI events derived from an independent set of 277 suicidal ideators relative to N?=?3159 control events in all non-SI individuals with an AUC of 0.88 (95% CI 0.86-0.90). Using an alternative approach, our model generates temporal prediction of risk such that peak occurrences above an individual specific threshold denote a ~7 fold increased risk for SI within the following 10 days (OR?=?6.7?±?1.1, P?=?9?×?10^-71). We validated our model using regionally obtained Twitter data and observed significant associations of algorithm SI scores with county-wide suicide death rates across 16 days in August and in October, 2019, most significantly in younger individuals. Algorithmic approaches like SAIPH have the potential to identify individual future SI risk and could be easily adapted as clinical decision tools aiding suicide screening and risk monitoring using available technologies.

SUBMITTER: Roy A

PROVIDER: S-EPMC7250902 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning approach predicts future risk to suicidal ideation from social media data.

Roy Arunima A Nikolitch Katerina K McGinn Rachel R Jinah Safiya S Klement William W Kaminsky Zachary A ZA

NPJ digital medicine 20200526

Machine learning analysis of social media data represents a promising way to capture longitudinal environmental influences contributing to individual risk for suicidal thoughts and behaviors. Our objective was to generate an algorithm termed "Suicide Artificial Intelligence Prediction Heuristic (SAIPH)" capable of predicting future risk to suicidal thought by analyzing publicly available Twitter data. We trained a series of neural networks on Twitter data queried against suicide associated psych ...[more]

PMID: 32509975

Similar Datasets

Project description:Depression is one of the most common mental illnesses but remains underdiagnosed. Suicide, as a core symptom of depression, urgently needs to be monitored at an early stage, i.e., the suicidal ideation (SI) stage. Depression and subsequent suicidal ideation should be supervised on social media. In this research, we investigated depression and concomitant suicidal ideation by identifying individuals' linguistic characteristics through machine learning approaches. On Weibo, we sampled 487,251 posts from 3196 users from the depression super topic community (DSTC) as the depression group and 357,939 posts from 5167 active users on Weibo as the control group. The results of the logistic regression model showed that the SCLIWC (simplified Chinese version of LIWC) features such as affection, positive emotion, negative emotion, sadness, health, and death significantly predicted depression (Nagelkerke's R2 = 0.64). For model performance: F-measure = 0.78, area under the curve (AUC) = 0.82. The independent samples' t-test showed that SI was significantly different between the depression (0.28 ± 0.5) and control groups (-0.29 ± 0.72) (t = 24.71, p < 0.001). The results of the linear regression model showed that the SCLIWC features, such as social, family, affection, positive emotion, negative emotion, sadness, health, work, achieve, and death, significantly predicted suicidal ideation. The adjusted R2 was 0.42. For model performance, the correlation between the actual SI and predicted SI on the test set was significant (r = 0.65, p < 0.001). The topic modeling results were in accordance with the machine learning results. This study systematically investigated depression and subsequent SI-related linguistic characteristics based on a large-scale Weibo dataset. The findings suggest that analyzing the linguistic characteristics on online depression communities serves as an efficient approach to identify depression and subsequent suicidal ideation, assisting further prevention and intervention.

Project description:AimsProspective studies on the mental health of university students highlighted a major concern. Specifically, young adults in academia are affected by markedly worse mental health status than their peers or adults in other vocations. This situation predisposes to exacerbated disability-adjusted life-years.MethodsWe enroled 1,388 students at the baseline, 557 of whom completed follow-up after 6 months, incorporating their demographic information and self-report questionnaires on depressive, anxiety and obsessive-compulsive symptoms. We applied multiple regression modelling to determine associations - at baseline - between demographic factors and self-reported mental health measures and supervised machine learning algorithms to predict the risk of poorer mental health at follow-up, by leveraging the demographic and clinical information collected at baseline.ResultsApproximately one out of five students reported severe depressive symptoms and/or suicidal ideation. An association of economic worry with depression was evidenced both at baseline (when high-frequency worry odds ratio = 3.11 [1.88-5.15]) and during follow-up. The random forest algorithm exhibited high accuracy in predicting the students who maintained well-being (balanced accuracy = 0.85) or absence of suicidal ideation but low accuracy for those whose symptoms worsened (balanced accuracy = 0.49). The most important features used for prediction were the cognitive and somatic symptoms of depression. However, while the negative predictive value of worsened symptoms after 6 months of enrolment was 0.89, the positive predictive value is basically null.ConclusionsStudents' severe mental health problems reached worrying levels, and demographic factors were poor predictors of mental health outcomes. Further research including people with lived experience will be crucial to better assess students' mental health needs and improve the predictive outcome for those most at risk of worsening symptoms.

Dataset Information

A machine learning approach predicts future risk to suicidal ideation from social media data.

Publications

A machine learning approach predicts future risk to suicidal ideation from social media data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets