MétaCan
Menu
Back to cohort
Record W2894641362 · doi:10.1176/appi.pn.2018.10a52

Research Using Machine Learning in Psychiatry Expands Rapidly

2018· article· en· W2894641362 on OpenAlexaboutno aff
Mark Moran

Bibliographic record

VenuePsychiatric News · 2018
Typearticle
Languageen
FieldPsychology
TopicMental Health Research Topics
Canadian institutionsnot available
Fundersnot available
KeywordsPsychiatryMoodMedicinePsychoeducationPsychosocialPsychologyClinical psychologyMachine learningPsychological intervention

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.609
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.003
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0050.002

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.

Opus teacher head0.152
GPT teacher head0.501
Teacher spread0.349 · 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; both teacher heads agree on what is shown here.

Study designObservational
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

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same venuePsychiatric NewsSame topicMental Health Research TopicsFrench-language works237,207