Machine Learning Approaches to Personalized Therapy for Advanced Non-small Cell Lung Cancer With Real-World Data

Recruiting

• Conditions: Non-small Cell Lung Cancer

• Registration Number: NCT06934343
• Lead Sponsor: University of Utah

Brief Summary

This research will leverage machine learning (ML) and causal inference techniques applied to real-world data (RWD) to generate evidence that personalizes treatment strategies for patients with advanced non-small cell lung cancer (aNSCLC). Rather than influencing regulatory decisions or clinical guidelines, the goal of this trial is to refine treatment selection among existing therapeutic options, ensuring that care is tailored to individual patient characteristics. Additionally, by generating real-world evidence, these findings will inform the design and implementation of future clinical trials. Importantly, the methodological advancements will establish a pipeline that extends beyond aNSCLC, facilitating the identification of optimal dynamic treatment regimes (DTRs) for other complex diseases.

Detailed Description

The proposed research will enhance patient-centered outcomes research (PCOR) and comparative effectiveness research (CER) methodologies by addressing two key challenges: (1) appropriate handling of missing EHR data and (2) rigorous causal inference techniques for sequential treatment strategies. By focusing on treatment strategies tailored to individual patients and incorporating patient-reported outcomes (PROs), this study is fundamentally patient-centered. Furthermore, the research is guided by practicing physicians, a patient advocate, and a former patient caregiver, ensuring that it remains aligned with the needs and priorities of those directly affected by aNSCLC.

This study will develop novel reinforcement learning algorithms by integrating multiply robust matching-based approaches. This study will tailor each component of DTR to optimize treatment sequences for aNSCLC patients, leveraging two large-scale, high-quality nationwide real-world electronic health record (EHR) databases: the Flatiron aNSCLC database and the CancerLinQ lung cancer database. These databases provide comprehensive clinicodemographic and longitudinal patient data.

Additionally, incorporating PRO data from two National Cancer Institute (NCI)-designated Comprehensive Cancer Centers -Huntsman Cancer Institute (HCI) and Moffitt Cancer Center (MCC) - will enable this trial to capture the patient perspective when personalizing aNSCLC care recommendations. Key outcomes will include overall survival, quality-adjusted life years (QALYs), time to second progression or death (PFS2), and time to worsening of selected PROs, all framed as time-to-event outcomes.

These methodological innovations will establish a reproducible pipeline for translating real-world evidence from large-scale EHR data into personalized DTR recommendations for aNSCLC patients and other complex disease populations.

Study Timeline

• Study Start: 2024-09-01
• Study First Submitted: 2025-02-28
• Status Verified: 2025-04
• Study First Submitted QC: 2025-04-10
• Last Update Submitted: 2025-04-10
• Study First Posted: 2025-04-18
• Last Update Posted: 2025-04-18
• Primary Completion: 2026-03
• Study Completion: 2026-03

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 144400

Inclusion Criteria

Not provided

Exclusion Criteria

Not provided

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Overall Survival (OS)	From the initiation of first-line therapy to death or the last follow-up, whichever occurs first, up to 10 years.	Mortality is the primary concern in aNSCLC care. This study will track survival from the initiation of first-line therapy to death or the last follow-up, whichever occurs first.; OS will be censored at the last recorded date in the electronic health records.

Secondary Outcome Measures

Name	Time	Method
Quality-Adjusted Life Years (QALYs)	From the initiation of first-line therapy to death or the last follow-up, whichever occurs first, up to 2 years.	Assessed within two years after treatment initiation.
Time to second progression or death (PFS2)	From the initiation of first-line therapy to second disease progression, death, or the last follow-up, whichever occurs first, up to 10 years.	Time from treatment initiation to second disease progression or death, whichever occurs first.
National Cancer Institute (NCI) Patient-Reported Outcomes Measurement Information System-Cancer (PROMIS-Ca)	From the initiation of first-line therapy to worsening or the last follow-up, whichever occurs first, up to 10 years.	PROs were collected using the NCI PROMIS-Ca Bank at the Huntsman Cancer Institute. Six PROMIS-Ca scales were utilized: the 17-item Fatigue scale (Fatigue-17), the 7-item PROMIS Fatigue scale (Fatigue-7), the 10-item Pain Interference scale (PainInt-10), the 10-item Physical Function scale (PhysFunc-10), the 9-item Anxiety scale (Anxiety-9), and the 10-item Depression scale (Depression-10).; Each item was rated on a 5-point ordinal scale, with all PROMIS-Ca scales scored so that higher scores indicate greater levels of the respective concept (e.g., a higher Fatigue-7 score reflects greater fatigue, while a higher PhysFunc-10 score denotes better physical functioning).; Raw scores were calculated as the prorated sum of item responses when at least 50% of the items on a scale were completed. T-scores were derived using a reference population with a mean of 50 and a standard deviation of 10. This outcome measure will report each T-score (range: 0-100).
Edmonton Symptom Assessment System (ESAS) Outcomes	From the initiation of first-line therapy to worsening or the last follow-up, whichever occurs first, up to 10 years.	The Edmonton Symptom Assessment System (ESAS) was used to evaluate 9 common symptoms: pain, tiredness, drowsiness, nausea, lack of appetite, shortness of breath, depression, anxiety, and overall well-being. Symptoms were rated on an 11-point scale ranging from 0 (no symptom burden) to 10 (worst symptom burden). Moffitt employs a modified version of the ESAS that includes two additional symptoms: constipation and sleep disturbance.; ESAS will be analyzed using a time-to-worsening framework, with a worsening benchmark of ≥2 points for ESAS-both representing approximately twice the minimally important difference.

Trial Locations

Locations (1)

Huntsman Cancer Institute at the University of Utah; 🇺🇸 Salt Lake City, Utah, United States