Lorlatinib Exposure-Response Analyses for Safety and Efficacy in a Phase I/II Trial to Support Benefit-Risk Assessment in Non-Small Cell Lung Cancer

Abstract

Lorlatinib is a small molecule inhibitor of anaplastic lymphoma kinase (ALK) and c-ROS oncogene 1 (ROS1) tyrosine kinases and is approved for the treatment of patients with ALK-positive advanced non-small cell lung cancer (NSCLC). In the phase I/II study (NCT01970865), potential exposure-response (E-R) relationships between lorlatinib and selected safety and efficacy end points were evaluated in patients with NSCLC. E-R relationships were assessed for safety end points with incidence > 10% in all treated patients (n = 328). In total, 4 safety end points were assessed: hypercholesterolemia grade ≥ 3, hypertriglyceridemia grade ≥ 3, weight gain grade ≥ 2, and treatment-emergent adverse events (TEAEs) grade ≥ 3. Using logistic regression, significant relationships were identified between lorlatinib plasma exposure and risk of hypercholesterolemia grade ≥ 3 (odds ratio (OR) 5.256) and risk of TEAE grade ≥ 3 (OR 3.214). The covariates baseline cholesterol and time on study prior to the event (TE) were associated with the probability of hypercholesterolemia grade ≥ 3. Baseline cholesterol and TE were found to have a statistically significant correlation with TEAE grade ≥ 3. Exposure-efficacy relationships were assessed for objective response rate (ORR; n = 197) and intracranial objective response rate (IC-ORR; n = 132). Lorlatinib plasma exposure was not identified as a statistically significant factor related to either efficacy end point. The only significant E-R relationships identified for efficacy were between baseline alkaline phosphatase and baseline amylase with IC-ORR (ORs 0.363 and 1.015, respectively). These findings support the lorlatinib indicated dose and dose modification guidelines regarding the management of lorlatinib-related AEs.

Figure 1

Predicted probability of hypercholesterolemia grade ≥ 3 vs. C_max prior to the AE. The dashed lines represent the 10th, 50th, and 90th percentiles of C_{max event} for patients in the safety analysis population dosed at 100 mg q.d. The black line is the median predicted probability and the gray ribbon is the 95% confidence interval of the predicted probability. Note that C_{max event} is presented instead of log(C_{max event}) for ease of interpretation. Time on study prior to the event was fixed to the analysis population median of 41 days and baseline cholesterol was fixed to the analysis population median of 193 mg/day. AE, adverse event; C_{max event}, maximum observed concentration prior to the adverse event; q.d., once daily.

Figure 2

Predicted probability of TEAE grade ≥ 3 vs. C_{trough ss}. The dashed lines represent the 10th, 50th, and 90th percentiles of C_{trough ss} for patients in the safety analysis population dosed at 100 mg q.d. The black line is the median predicted probability and the gray ribbon is the 95% prediction interval of the predicted probability. Note that C_{trough ss} is presented instead of log(C_{trough ss}) for ease of interpretation. Time on study prior to the event was fixed to the analysis population median of 38.75 days and age fixed to the analysis population median of 193 mg/dL. C_{trough ss}, trough concentration at steady‐state; q.d., once daily; TEAE, treatment‐emergent adverse event.