Outpatient Engagement and Predicted Risk of Suicide Attempts in Fibromyalgia

Abstract

This is the first study to successfully apply machine learning to reliably detect suicidality in FM, identifying novel risk factors for suicidality and highlighting outpatient engagement as a protective factor against suicide. This article is protected by copyright. All rights reserved.

Suicidality in Fibromyalgia: A Systematic Review of the Literature

“…Interestingly, among a sample of either FM patients, lower back pain patients, or healthy controls, it was found that FM patients had significantly more passive and active SI than patients with either lower back pain or no pain, after adjusting for age and gender ( 36 ). In contrast, one case-control study of almost 15,000 suicide attempters at a major US hospital as compared to general patients at the hospital found that only 1.1% of the FM sample exhibited SI ( 39 ).…”

“…However, this association became non-significant after controlling for age, gender, medical comorbidities, and psychiatric comorbidities ( 28 ). Interestingly, McKernan and colleagues’ ( 39 ) large scale study examining suicide attempters as compared to the general patient population at a major US hospital indicated that only 0.4% of FM patients reported suicide attempts. Similarly, another study examining almost 200,000 patients with a variety of chronic pain conditions, as well as healthy controls, found that only 31 FM patients per 100,000 person-years [i.e., the number of participants multiplied by the length of time the participants were followed for ( 46 )] exhibited SB ( 32 ).…”

“…An additional study corroborated these results, finding that FM patients with SI scored significantly higher on the BDI than FM patients without SI ( 34 ). Also, in the realm of mood disorders, a study by McKernan and colleagues ( 39 ) found an elevated risk of SI among FM patients diagnoses with Bipolar Disorder-Not Otherwise Specified compared to those without this comorbid disorder ( 39 ).…”

The Differences Between Individuals Engaging in Nonsuicidal Self-Injury and Suicide Attempt Are Complex (vs. Complicated or Simple)

“…On balance, some studies indicate that bootstrap optimism correction methods perform similarly to other internal validation methods (73,74), random forest models can generalize well to new data (75,76), and random forest combined with bootstrap optimism correction performs similarly to other internal validation methods and other machine learning techniques (73,77,78). There is also evidence that Walsh et al's algorithm (64) using this approach generalizes well to new samples and new suicide-related outcomes (79,80). Nonetheless, much remains unknown about how various methods perform under various conditions, so at a minimum these discrepancies indicate that it would be prudent to conduct analyses with multiple internal validation techniques.…”

Discovering the Unclassified Suicide Cases Among Undetermined Drug Overdose Deaths Using Machine Learning Techniques

“…The current advancements in machine learning technologies provide a new opportunity to remedy classification problems, when utilized as a supplement to recommended changes in death scene investigation practices (Stone, Holland, Bartholow, Crosby et al., ; Stone, Holland, Bartholow, Logan et al., ). Machine learning has already begun to be used to identify living cases at risk for suicide (Colic, Richardson, Reilly, & Hasey, ; Kessler et al., ; McKernan, Lenert, Crofford, & Walsh, ; Ryu, Lee, Lee, & Park, ), paving the way for the natural extension of its use for the retrospective prediction of missed suicides among the deceased (Esty et al., ).…”