NCT06067347

A Global Study of the PETAL Consortium

Integration of Machine Learning and Genomics to Predict Outcomes for Newly Diagnosed, Relapsed and Refractory Mature T-cell and NK/T-cell Lymphomas: a Global Study of the PETAL Consortium

• Status: Recruiting
• Phase: —
• Study type: Observational
• Enrollment: 1,200 (estimated)
• Sponsor: Massachusetts General Hospital · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Accepted

Summary

The goal of this observational study is to correlate molecular alterations with outcomes including overall survival (OS), progression-free survival (PFS), response rates for patients with a new diagnosis, primary refractory or relapse, of mature T-cell and NK-cell neoplasms (TNKL). We hypothesize that machine learning can be leveraged to uncover distinct genetic vulnerabilities that underlie treatment response and resistance for patients with TNKL, thus moving towards personalized treatment solutions.

Detailed description

This study is a prospective, longitudinal observational study of patients with newly diagnosed or relapsed/refractory T-cell and NK-cell neoplasms, conducted across multiple participating institutions globally. Patients will be enrolled during their initial visit as new patients and will be followed for up to four years through the course of their clinical management. Data for routine demographics, baseline clinical features, including pathology, molecular information related to the tumor, radiology, treatment characteristics and quality of life (QoL) associated with their lymphoma care will be collected over the course of 4 years by clinical research teams at every participating institution. The de-identified data will be securely shared through a password protected REDCap with other participating institutions under data usage agreements of the consortium. Next generation sequencing (NGS) including but not limited to whole exome sequencing and bulk RNA-sequencing will be performed on archived lymphoma specimens, mononuclear cells, cfDNA and saliva (when feasible) for a comprehensive molecular characterization of the tumor. Molecular data will be analyzed in correlation with patient outcomes. Advanced deep learning algorithms will be applied to predict responses and survival across lymphoma subtypes, heterogeneous clinical scenarios and various potential therapeutic approaches that the patient has not been exposed to.

Conditions

• T-Cell and NK-Cell Neoplasm

Timeline

• Start date: 2024-01-05
• Primary completion: 2028-01-01
• Completion: 2028-01-01
• First posted: 2023-10-04
• Last updated: 2026-04-09

Locations

14 sites across 4 countries: United States, Australia, Japan, South Africa