A Phase III Randomized Trial of Metformin vs Placebo in Early Stage Breast Cancer

Model scores of the 29,894 trials active now.

Model score 14% for any early termination, 11% for termination due to slow enrollment. Past trials like this one (phase, sponsor type and disease area, started 2008–2016) ended terminated 20% of the time (607 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 2023-08-18. 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.

• Wording of the registration (title, summary, criteria) (raises risk) · Wording Phrases that raised it: cancersubjectpatientstagesubjects with
  Phrases that lowered it: breast cancerher2metformintrialinsulin
• Phase: 3 (lowers risk) · Design
• Accepts healthy volunteers: No (raises risk) · Who can join
• Sponsor's past termination rate: no earlier finished trials (lowers risk) · Sponsor's track record
• Collaborators: 3 (lowers risk) · Design
• Drug's FAERS reports marked serious: 56.4% (lowers risk) · Drug's FDA history
• Drug's FAERS reports with a death: 6.8% (lowers risk) · Drug's FDA history
• Sponsor type: academic or other (raises risk) · Sponsor's track record
• Disease area, cancer: Yes (raises risk) · Disease area
• Blinding: triple (raises risk) · Design
• Design: parallel (raises risk) · Design
• Has a data monitoring committee: Yes (raises risk) · Design
• Trials the sponsor started in the prior 2 years: 2 (raises risk) · Sponsor's track record
• Drug's FAERS reports before start: 38904 (lowers risk) · Drug's FDA history
• Maximum age: 74 (lowers risk) · Who can join
• Minimum age: 18 (raises risk) · Who can join
• Primary purpose: treatment (raises risk) · Design
• Disease area, dermatology: Yes (raises risk) · Disease area
• Drug's FAERS reports in the prior 12 months: 8435 (lowers risk) · Drug's FDA history
• Responsible party: sponsor (lowers risk) · Design

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.

• Circulating Tumor DNA Enriched, Genomically Directed Post-neoadjuvant Trial for Patients With Residual Triple Negative Breast Cancer NCT04849364 · started 2021 · scored riskier than 80% of active trials terminated
• Randomized Controlled Trial of Genomically Directed Therapy in Patients With Triple Negative Breast Cancer NCT02101385 · started 2014 · scored riskier than 48% of active trials completed
• Comparison of Neoadjuvant Chemotherapy With Weekly Paclitaxel or Eribulin Followed by A/C in Women With Locally Advanced HER2-Negative Breast Cancer NCT01705691 · started 2012 · scored riskier than 98% of active trials completed
• BETH Study: Treatment of HER2 Positive Breast Cancer With Chemotherapy Plus Trastuzumab vs Chemotherapy Plus Trastuzumab Plus Bevacizumab NCT00625898 · started 2008 · scored riskier than 45% of active trials terminated
• BYL719 and Letrozole in Post-Menopausal Patients With Hormone Receptor-Positive Metastatic Breast Cancer NCT01791478 · started 2013 · scored riskier than 98% 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.