MétaCan
Menu
Back to cohort
Record W4399611640 · doi:10.1101/2024.06.13.24308884

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

2024· preprint· en· W4399611640 on OpenAlexaff
David Benrimoh, Kate Whitmore, Maud Richard, Grace Golden, Kelly Perlman, Sara Jalali, Timothy L. Friesen, Youcef Barkat, Joseph Mehltretter, Robert Fratila, Caitrin Armstrong, Sonia Israel, Christina Popescu, Jordan F. Karp, Sagar V. Parikh, Shirin Golchi, Erica E. M. Moodie, Junwei Shen, Anthony J. Gifuni, Manuela Ferrari, Mamta Sapra, Stefan Kloiber, G Pinard, Boadie W. Dunlop, Karl Looper, Mohini Ranganathan, Martin Enault, Serge Beaulieu, Soham Rej, Fanny Hersson-Edery, Warren Steiner, Alexandra Anacleto, Sabrina Qassim, Rebecca McGuire-Snieckus, Howard C. Margolese

Bibliographic record

VenuemedRxiv · 2024
Typepreprint
Languageen
FieldMedicine
TopicTreatment of Major Depression
Canadian institutionsJewish General HospitalInstitut Universitaire en Santé Mentale de QuébecUniversity of TorontoUniversity of WaterlooMcGill University Health CentreCentre for Addiction and Mental HealthWestern UniversityMcGill UniversityDouglas Mental Health University Institute
Fundersnot available
KeywordsDepression (economics)Randomized controlled trialSelection (genetic algorithm)Cluster (spacecraft)Personalized medicinePsychologyArtificial intelligenceClinical psychologyMedicinePsychiatryComputer scienceBioinformaticsInternal medicine

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.004
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.000

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.

Opus teacher head0.036
GPT teacher head0.367
Teacher spread0.331 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designRandomized trial
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuemedRxivSame topicTreatment of Major DepressionFrench-language works237,207