Colorectal Cancer Treated With Adjuvant Regorafenib Versus Placebo After Curative Treatment of Liver Metastases in a Randomized, Double-blind, Placebo-Controlled Phase-III STudy

Model scores of the 29,894 trials active now.

Model score 17% for any early termination, 2% for termination due to slow enrollment. Past trials like this one (phase, sponsor type and disease area, started 2008–2016) ended terminated 16% of the time (927 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 2016-08-29. 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: randomizationstagesurgeryresectiongreater
  Phrases that lowered it: safety ofsubjects whoand safetyefficacy andcompare
• Accepts healthy volunteers: No (raises risk) · Who can join
• Phase: 3 (lowers risk) · Design
• Trials the sponsor started in the prior 2 years: 88 (lowers risk) · Sponsor's track record
• Sponsor's past termination rate: 6.6% (lowers risk) · Sponsor's track record
• Has a data monitoring committee: Yes (raises risk) · Design
• Design: parallel (raises risk) · Design
• Disease area, cancer: Yes (raises risk) · Disease area
• Sponsor type: industry (lowers risk) · Sponsor's track record
• Sponsor's past trials: 497 (lowers risk) · Sponsor's track record
• Minimum age: 18 (raises risk) · Who can join
• Primary purpose: treatment (raises risk) · Design
• Blinding: quadruple (lowers risk) · Design
• Number of arms: 2 (raises risk) · Design
• Drug's FAERS reports marked serious: 85.0% (raises risk) · Drug's FDA history
• Maximum age: not given (raises risk) · Who can join

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.

• FOLFOXIRI With or Without Cetuximab as First-line Treatment of Patients With Non-resectable Liver - Only Metastatic Colorectal Cancer NCT02063529 · started 2014 · scored riskier than 60% of active trials completed
• Efficacy of FOLFOX Alone, FOLFOX Plus Bevacizumab and FOLFOX Plus Panitumumab in Patients With Resectable Liver Metastases NCT01508000 · started 2013 · scored riskier than 70% of active trials terminated
• A Study of Perioperative Chemotherapy Plus Panitumumab in Patients With Colorectal Cancer Liver Metastases NCT01260415 · started 2010 · scored riskier than 79% of active trials completed
• Improving SUrgery of Liver Metastases: a Trial of the Arterial Chemotherapy Network NCT03164655 · started 2018 · scored riskier than 75% of active trials completed
• A Study Evaluating Regorafenib Following Completion of Standard Chemotherapy for Patients With Colon Cancer NCT02664077 · started 2016 · scored riskier than 99% of active trials terminated

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.