The Prediction of Suicidal Ideation as a Function of Daily Mood and Anxiety Scores Collected Using mHealth Technology in Patients Undergoing Treatment for Depression
Bibliographic record
Abstract
Background Suicide is one of the most common causes of death in the United States. The rates of suicide have increased by 33% in the period 1999-2019. In 2019, suicide was responsible for one death every 11 minutes. Clinically, a previous history of suicide attempts is the main risk factor, as well as the presence of comorbid conditions like depression and anxiety. Accurate and real-time prediction of suicidal thoughts may lead to improved management of patients with depression. Prediction of suicidality is difficult due to its day-to-day variability in relation to mood and anxiety symptoms. This can be overcome with the advent of mobile health (mHealth) technology that can capture granular data scores at a higher frequency than conventional therapeutic visitations. Objective The aim of this study is to predict suicidal ideation using self-reported mood and anxiety in patients undergoing treatment for depression. Methods This study will use data from the DepWatch study, an mHealth study that uses the DepWatch app developed by our research group. The objective of this longitudinal study is to develop an mHealth-based, personalized diagnostic prediction system for patients undergoing treatment for depression. Patients are followed over 12 weeks using electronic assessments conducted via the DepWatch app installed on their smartphones. The electronic assessments include the Quick Inventory of Depression Symptomatology-Self Report (QIDS-SR), conducted on a weekly basis, and weekly medication adherence and medication safety and tolerability questionnaires. The assessments include brief mood and anxiety assessments conducted on a daily basis. Generalized estimating equation modeling for a binary outcome (the presence or absence of suicidal thought), clustered by individual subjects, will be used. The key explanatory variables are the daily mood and anxiety levels (time variant). The outcome variable is suicidal ideation as determined by the self-reported subject response to question 12 (about suicidality) on the QIDS-SR scale. Variables that show significance at P values <.1 are subsequently used in the multivariate model, in addition to mood and anxiety. Results A total of 34 subjects are in the interim analysis set. The median age is 26 years, 85.3% are female, and 64.7% are White. In addition, 38.2% either have a college degree or graduate education, while 23.5% are unemployed and 41.1% are full-time employed. About half of participants (52.9%) earn less than $50,000 annually and 61% have never smoked. Univariate analysis shows statistical significance of gender, race, aggregate anxiety, and employment status at .1 significance level. In the multivariate model, only gender and employment status are significant at .05. Race is marginally insignificant (P=.068). Conclusions Suicidality and completed suicides are significant public health problems, especially in patients with depression. The mHealth technology and statistical modelling that captures daily variability in anxiety leading up to suicidal ideation can help predict suicidality. Conflicts of Interest None declared.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".