Artificial Intelligence in Depression – Medication Enhancement (AID-ME): A Cluster Randomized Trial of a Deep Learning Enabled Clinical Decision Support System for Personalized Depression Treatment Selection and Management
Bibliographic record
Abstract
Abstract Background There has been increasing interest in the use of Artificial Intelligence (AI)-enabled clinical decision support systems (CDSS) for the personalization of major depressive disorder (MDD) treatment selection and management, but clinical studies are lacking. We tested whether a CDSS that combines an AI which predicts remission probabilities for individual antidepressants and a clinical algorithm based on treatment can improve MDD outcomes. Methods This was a multicenter, cluster randomized, patient-and-rater blinded and clinician-partially-blinded, active-controlled trial that recruited outpatient adults with moderate or greater severity MDD. All patients had access to a patient portal to complete questionnaires. Clinicians in the active group had access to the CDSS; clinicians in the active-control group received patient questionnaires; both groups received guideline training. Primary outcome was remission (<11 points on the Montgomery Asberg Depression Rating Scale (MADRS)) at study exit. Results 47 clinicians were recruited at 9 sites. Of 74 eligible patients, 61 patients completed a post-baseline MADRS and were analyzed. There were no differences in baseline MADRS (p = 0.153). There were more remitters in the active (n= 12, 28.6%) than in the active-control (0%) group (p = 0.012, Fisher’s exact). Of three serious adverse events, none were caused by the CDSS. Speed of improvement was higher in the Active than the Control group (1.26 vs. 0.37, p = 0.03). Conclusions While limited by sample size and the lack of primary care clinicians, these results demonstrate preliminary evidence that longitudinal use of an AI-CDSS can improve outcomes in moderate and greater severity MDD.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".