Feature importance analysis using a Random Forest classifier estimated five symptoms associated with Cluster 4, which showed a trend toward symptom worsening during the post‐dosing follow‐up period, and revealed that insomnia‐related HAM‐D17 items were the primary drivers of cluster separation.
← all excerpts
Analysis of depressive symptom trajectory patterns with zuranolone: Time-series clustering of Japanese Phase 2 and Phase 3 trial data.
1
—
—