Using Machine Learning to Predict Remission in Patients With Major Depressive Disorder Treated With Desvenlafaxine
Bibliographic record
Abstract
Background Major depressive disorder (MDD) is a common and burdensome condition that has low rates of treatment success for each individual treatment. This means that many patients require several medication switches to achieve remission; selecting an effective antidepressant is typically a sequential trial-and-error process. Machine learning techniques may be able to learn models that can predict whether a specific patient will respond to a given treatment, before it is administered. This study uses baseline clinical data to create a machine-learned model that accurately predicts remission status for a patient after desvenlafaxine (DVS) treatment. Methods We applied machine learning algorithms to data from 3,399 MDD patients (90% of the 3,776 subjects in 11 phase-III/IV clinical trials, each described using 92 features), to produce a model that uses 26 of these features to predict symptom remission, defined as an 8-week Hamilton Depression Rating Scale score of 7 or below. We evaluated that learned model on the remaining held-out 10% of the data ( n = 377). Results Our resulting classifier, a trained linear support vector machine, had a holdout set accuracy of 69.0%, significantly greater than the probability of classifying a patient correctly by chance. We demonstrate that this learning process is stable by repeatedly sampling part of the training dataset and running the learner on this sample, then evaluating the learned model on the held-out instances of the training set; these runs had an average accuracy of 67.0% ± 1.8%. Conclusions Our model, based on 26 clinical features, proved sufficient to predict DVS remission significantly better than chance. This may allow more accurate use of DVS without waiting 8 weeks to determine treatment outcome, and may serve as a first step toward changing psychiatric care by incorporating clinical assistive technologies using machine-learned models.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".