Screening for bipolar disorder in a tertiary mental health centre using EarlyDetect: A machine learning-based pilot study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
: Bipolar disorder (BD) is a prevalent mental health illness with a direct impact on patient's well-being. Self-report-based BD screening questionnaires such as the Mood Disorder Questionnaire (MDQ) is economical and clinically validated. We use a machine-learning approach to test whether utilizing our composite screening application - EarlyDetect (ED), designed for assessing an array of mental health illness, can enhance bipolar disorder screening over MDQ. : This was a retrospective, naturalistic study at a tertiary mental health centre in western Canada. Participants (n = 955; 56.4% female; mean age 35.4; 18.7% BD) completed ED and underwent a clinical interview with a blinded psychiatrist for diagnostic accuracy. Elastic net and leave-one-out cross-validation was used to make more confident predictions at an individual level. : Using composite scoring, the balanced accuracy of our tool was 80.6%, with a sensitivity of 73.7% and a specificity of 87.5%. Compared with the MDQ original scoring method, the fully composite ED model improved balanced accuracy by 6.9%, sensitivity by 14.5%, while maintaining specificity. : Patients were assessed using clinical psychiatric evaluations, which are subjective. There is also the potential for self-reporting bias. BD subtypes were not differentiated. The cross-sectional design of this study rules out conclusions of causality. : Our results show improved BD detection accuracy using composite measures.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it