Bibliographic record
Abstract
Back to table of contents Previous article Next article Clinical and Research NewsFull AccessResearch Using Machine Learning in Psychiatry Expands RapidlyMark MoranMark MoranSearch for more papers by this authorPublished Online:2 Oct 2018https://doi.org/10.1176/appi.pn.2018.10a52AbstractInterest in the application of machine learning to psychiatry is growing exponentially, as reflected in the increasing number of publications on the subject. Here is a small sample of seminal papers on machine learning:“Reevaluating the Efficacy and Predictability of Antidepressant Treatments: A Symptom Clustering Approach.” Chekroud and colleagues used machine learning to analyze the predictive value of 20 depressive symptoms on choice of antidepressant medication using data on more than 7,000 patients from nine antidepressant clinical trials. They found three “symptom clusters”—sleep/insomnia symptoms, core emotional symptoms (such as sad mood and feelings of worthlessness), and atypical symptoms (such as psychomotor agitation or suicidal ideation)—that were associated with response to different medications. For instance, high-dose duloxetine outperformed escitalopram in treating core emotional symptoms. Moreover, the predictive power of the symptom clusters was greater than the difference between any one medication and placebo.“Multisite Prediction of 4-Week and 52-Week Treatment Outcomes in Patients With First-Episode Psychosis: A Machine Learning Approach.” Koutsouleris and colleagues applied machine learning to data from 334 patients in the European First-Episode Schizophrenia Trial to predict poor versus good treatment outcomes after four weeks and 52 weeks of treatment. Unemployment, poor education, functional deficits, and unmet psychosocial needs predicted both endpoints at four weeks and 52 weeks, whereas previous depressive episodes, male sex, and suicidality additionally predicted poor one-year outcomes. Predictions at 52 weeks identified patients at risk for symptom persistence, nonadherence to treatment, readmission to hospital, and poor quality of life. Among these patients, amisulpride and olanzapine showed superior efficacy over haloperidol, quetiapine, and ziprasidone.“Predicting Response to Repetitive Transcranial Magnetic Stimulation in Patients With Schizophrenia Using Structural Magnetic Resonance Imaging: A Multisite Machine Learning Analysis.” Koutsouleris and colleagues applied machine learning to MRI data on 92 patients with schizophrenia enrolled in the multisite RESIS trial to predict response to transcranial magnetic stimulation.“Treatment Response Prediction and Individualized Identification of First-Episode Drug-Naïve Schizophrenia Using Brain Functional Connectivity.” Bo Cao, M.D., of the University of Alberta and colleagues applied machine learning to MRI data. By measuring the connections of the superior temporal cortex to other regions of the brain, the algorithm successfully identified patients with schizophrenia with 78 percent accuracy. It also predicted with 82 percent accuracy whether a patient would respond to risperidone. ■See related article: Artificial Intelligence, Big Data Merge to Solve Problems in Psychiatry. ISSUES NewArchived
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 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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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; both teacher heads agree on what is shown here.
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".