Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care for Depression

Model scores of the 29,894 trials active now.

Model score 8% for any early termination, 4% for termination due to slow enrollment. Past trials like this one (phase, sponsor type and disease area, started 2008–2016) ended terminated 11% of the time (407 trials).

Finished trial that started 2008–2014: scored by a model trained without any trial from its start year, so its own outcome was never used.

Cumulative chance of ending terminated (red) or completed (green) by each year from its start; it actually ended on 2016-04-30. The rest of the way to 100% is still running.

From the competing-risks survival model (termination vs completion, still-running trials censored), fit to trials that started 2008–2014 and recalibrated to termination rates over 2022–2024, since termination has become more common. Checked on past years, it still ran a little low when the rise continued.

• Accepts healthy volunteers: Yes (lowers risk) · Who can join
• Primary purpose: other (lowers risk) · Design
• Sponsor's past termination rate: 14.1% (raises risk) · Sponsor's track record
• Disease area, psychiatry: Yes (raises risk) · Disease area
• Blinding: quadruple (lowers risk) · Design
• Phase: 2 (raises risk) · Design
• Sponsor type: academic or other (raises risk) · Sponsor's track record
• Trials the sponsor started in the prior 2 years: 47 (lowers risk) · Sponsor's track record
• Has a data monitoring committee: Yes (raises risk) · Design
• Drug's FAERS reports with a death: 10.0% (lowers risk) · Drug's FDA history
• Disease area, cancer: No (lowers risk) · Disease area
• Number of arms: 3 (lowers risk) · Design
• Minimum age: 18 (raises risk) · Who can join
• Design: sequential (lowers risk) · Design
• Drug's FAERS reports before start: 31474 (raises risk) · Drug's FDA history
• Wording of the registration (title, summary, criteria) (lowers risk) · Wording Phrases that raised it: patientstherapyadequatediagnosisreceiving
  Phrases that lowered it: participantssmokingindexmedicationmultiple
• Sponsor's past trials: 78 (lowers risk) · Sponsor's track record
• Collaborators: 0 (raises risk) · Design
• Responsible party: principal investigator (lowers risk) · Design
• Drug's FAERS reports in the prior 12 months: 7721 (raises risk) · Drug's FDA history
• Drug's FAERS reports marked serious: 75.8% (lowers risk) · Drug's FDA history
• Disease area, neurology: No (lowers risk) · Disease area

Every input that moved this score, largest first: SHAP contributions in log-odds, red raising risk and green lowering it. They describe the model, not causes of termination. Phrases are traced from the text features back to this registration's words, approximately.

• A Study to Evaluate the Efficacy and Safety of JNJ-42847922 as Adjunctive Therapy to Antidepressants in Adult Participants With Major Depressive Disorder Who Have Responded Inadequately to Antidepressant Therapy NCT03227224 · started 2017 · scored riskier than 62% of active trials completed
• A Study of Aticaprant as Adjunctive Therapy in Adult Participants With Major Depressive Disorder (MDD) With Moderate-to-severe Anhedonia and Inadequate Response to Current Antidepressant Therapy NCT05455684 · started 2022 · scored riskier than 69% of active trials completed
• A Paroxetine- and Placebo-Controlled Study of 50 mg/Day and 100 mg/Day of EB-1010 Among Outpatients With Major Depressive Disorder Who Have Responded Inadequately to Prior Selective Serotonin Reuptake Inhibitors (SSRIs) and Serotonin Norepinephrine Reuptake Inhibitors (SNRIs) NCT01318434 · started 2011 · scored riskier than 72% of active trials completed
• A Study to Evaluate the Efficacy, Pharmacokinetics, Safety and Tolerability of Flexible Doses of Intranasal Esketamine Plus an Oral Antidepressant in Adult Participants With Treatment-resistant Depression NCT03434041 · started 2018 · scored riskier than 30% of active trials completed
• A Study of JNJ-61393215 in the Treatment of Depression NCT04080752 · started 2019 · scored riskier than 59% of active trials completed

Closest by meaning of the registration text (PubMedBERT embeddings), among finished trials. How they ended is context, not an input to this trial's score.