Applying Machine Learning Approaches to Suicide Prediction Using Healthcare Data: Overview and Future Directions.

Objective: Early identification of individuals who are at risk for suicide is crucial in supporting suicide prevention. Machine learning is emerging as a promising approach to support this objective. Machine learning is broadly defined as a set of mathematical models and computational algorithms designed to automatically learn complex patterns between predictors and outcomes from example data, without being explicitly programmed to do so. The model's performance continuously improves over time by learning from newly available data. Method: This concept paper explores how machine learning approaches applied to healthcare data obtained from electronic health records, including billing and claims data, can advance our ability to accurately predict future suicidal behavior. Results: We provide a general overview of machine learning concepts, summarize exemplar studies, describe continued challenges, and propose innovative research directions. Conclusion: Machine learning has potential for improving estimation of suicide risk, yet important challenges and opportunities remain. Further research can focus on incorporating evolving methods for addressing data imbalances, understanding factors that affect generalizability across samples and healthcare systems, expanding the richness of the data, leveraging newer machine learning approaches, and developing automatic learning systems.

Alcohol Use Disorder in the Age of Technology: A Review of Wearable Biosensors in Alcohol Use Disorder Treatment.

Biosensors enable observation and understanding of latent physiological occurrences otherwise unknown or invasively detected. Wearable biosensors monitoring physiological constructs across a wide variety of mental and physical health conditions have become an important trend in innovative research methodologies. Within substance use research, explorations of biosensor technology commonly focus on identifying physiological indicators of intoxication to increase understanding of addiction etiology and to inform treatment recommendations. In this review, we examine the state of research in this area as it pertains to treatment of alcohol use disorders specifically highlighting the gaps in our current knowledge with recommendations for future research. Annually, alcohol use disorders affect approximately 15 million individuals. A primary focus of existing wearable technology-based research among people with alcohol use disorders is identifying alcohol intoxication. A large benefit of wearable biosensors for this purpose is they provide continuous readings in a passive manner compared with the gold standard measure of blood alcohol content (BAC) traditionally measured intermittently by breathalyzer or blood draw. There are two primary means of measuring intoxication with biosensors: gait and sweat. Gait changes have been measured via smart sensors placed on the wrist, in the shoe, and mobile device sensors in smart phones. Sweat measured by transdermal biosensors detects the presence of alcohol in the blood stream correlating to BAC. Transdermal biosensors have been designed in tattoos/skin patches, shirts, and most commonly, devices worn on the ankle or wrist. Transdermal devices were initially developed to help monitor court-ordered sobriety among offenders with alcohol use disorder. These devices now prove most useful in continuously tracking consumption throughout clinical trials for behavioral treatment modalities. More recent research has started exploring the uses for physical activity trackers and physiological arousal sensors to guide behavioral interventions for relapse prevention. While research has begun to demonstrate wearable devices' utility in reducing alcohol consumption among individuals aiming to cutdown on their drinking, monitoring sustained abstinence in studies exploring contingency management for alcohol use disorders, and facilitating engagement in activity-based treatment interventions, their full potential to further aid in understanding of, and treatment for, alcohol use disorders has yet to be explored.

Cognitive-Behavioral Therapy for Insomnia to Reduce Chronic Migraine: A Sequential Bayesian Analysis.

BACKGROUND: Insomnia is frequently comorbid with chronic migraine, and small trials suggest that cognitive-behavioral treatment of insomnia (CBTi) may reduce migraine frequency. This study endeavored to provide a quantitative synthesis of existing CBTi trials for adults with chronic migraine using Bayesian statistical methods, given their utility in combining prior knowledge with sequentially gathered data. METHODS: Completer analyses of 2 randomized trials comparing CBTi to a sham control intervention (Calhoun and Ford, 2007; Smitherman et al, 2016) were used to quantify the effects of a brief course of treatment on headache frequency. Change in headache frequency from baseline to the primary endpoint (6-8 weeks posttreatment) was regressed on group status using a Gaussian linear model with each study specified in the order of completion. To estimate the combined effect, posterior distributions from the Calhoun and Ford study were used as informative priors for conditioning on the Smitherman et al data. RESULTS: In a combined analysis of these prior studies, monthly headache frequency of the treatment group decreased by 6.2 days (95%CrI: -9.7 to -2.7) more than the control group, supporting an interpretation that there is a 97.5% chance that the treatment intervention is at least 2.7 days better than the control intervention. The analysis supports the hypothesis that at least for those who complete treatment, there is high probability that individuals who receive CBTi experience greater headache reduction than those who receive a control intervention equated for therapist time and out-of-session skills practice. CONCLUSION: Cognitive-behavioral interventions for comorbid insomnia hold promise for reducing headache frequency among those with chronic migraine. These findings add to a small but growing body of literature that migraineurs with comorbid conditions often respond well to behavioral interventions, and that targeting comorbidities may improve migraine itself.

Perceived triggers of primary headache disorders: A meta-analysis.

Objective To quantitatively synthesize extant literature on perceived triggers of primary headache disorders. Methods A meta-analytic review of headache trigger survey studies was conducted. Endorsement rates, assessment method, and headache and sample characteristics were extracted from included articles. Separate random-effects models were used to assess trigger endorsement rates and post-hoc meta-regressions examined potential moderator variables. Results 85 articles from 1958 to 2015 were included, involving 27,122 participants and querying 420 unique triggers (collapsed into 15 categories). Four-fifths (0.81; 95% CI .75 to .86) of individuals with migraine or tension-type headache endorsed at least one trigger. Rates increased with the number of categories queried (OR: 1.18, 1.08-1.30) and year of publication (OR: 1.04, 1.00-1.08). The triggers most commonly endorsed were stress (.58, .53-.63) and sleep (.41, .36-.47). Conclusions Extreme heterogeneity characterizes the headache trigger literature. Most individuals with a primary headache disorder perceive their attacks to be triggered by one or more precipitants, the most common of which are stress and sleep. However, trigger endorsement is influenced by method of assessment. Enhancing methodological consistency and prioritizing experimental studies would improve our understanding of headache triggers.

Alcohol Use as a Comorbidity and Precipitant of Primary Headache: Review and Meta-analysis.

PURPOSE OF REVIEW: In contrast to well-established relationships between headache and affective disorders, the role of alcohol use in primary headache disorders is less clear. This paper provides a narrative overview of research on alcohol use disorders (AUDs) in primary headache and presents a meta-analysis of the role of alcohol as a trigger (precipitant) of headache. RECENT FINDINGS: The majority of studies on AUDs in headache have failed to find evidence that migraine or tension-type headache (TTH) is associated with increased risk for AUDs or problematic alcohol use. The meta-analysis indicated that 22% (95% CI: 17-29%) of individuals with primary headache endorsed alcohol as a trigger. No differences were found between individuals with migraine (with or without aura) or TTH. Odds of endorsing red wine as a trigger were over 3 times greater than odds of endorsing beer. An absence of increased risk for AUDs among those with primary headache may be attributable to alcohol's role in precipitating headache attacks for some susceptible individuals. Roughly one fifth of headache sufferers believe alcohol precipitates at least some of their attacks. Considerable study heterogeneity limits fine-grained comparisons across studies and suggests needs for more standardized methods for studying alcohol-headache relationships and rigorous experimental designs.