Longitudinal adverse event assessment in oncology clinical trials: the Toxicity over Time (ToxT) analysis of Alliance trials NCCTG N9741 and 979254

Abstract

Background: Traditional methods of reporting adverse events in clinical trials are inadequate for modern cancer treatments with chronic administration. Conventional analysis and display of maximum grade adverse events do not capture toxicity profiles that evolve over time or longer lasting, lower grade toxic effects; we aimed to address this shortcoming in this study.

Methods: We developed an analytic approach and standardised, comprehensive format, the Toxicity over Time (ToxT) approach, which combines graphs and adverse event tabular displays with multiple longitudinal statistical techniques into a readily applicable method to study toxic effects. Plots visualising summary statistics or individual patient data over discrete timepoints were combined with statistical methods including the following longitudinal techniques: repeated measures models that describe the changes in adverse events across all cycles of treatment; time-to-event analyses of first and worst grade toxicity; and area under the curve (AUC) analyses summarising adverse event profiles over the entire course of a study, including chronic low-grade events. We applied ToxT analysis to adverse event data from two completed North Central Cancer Treatment Group (NCCTG/Alliance) trials: N9741 (NCT00003594), in which different combinations of oxaliplatin, 5-fluorouracil, and irinotecan were investigated for metastatic colorectal cancer, and 979254, in which survivors of breast cancer were given venlafaxine or placebo for control of hot flashes.

Findings: In trial NCCTG 979254 there was a higher incidence of late-occurring dry mouth in patients who were given venlafaxine than in those given placebo (week 1 [baseline]: 13% [six incidence in 48 patients, SD 5] vs 22% [11/49, SD 6]; p=0·20; week 5: 49% [24/49, 7] vs 2% [1/46, 2]; p<0·0001). In trial NCCTG N9741 there was an increased incidence of early nausea for patients given irinotecan plus oxaliplatin (IROX) compared with those given 5-fluorouracil plus oxaliplatin (FOLFOX; cycle 1 mean grade nausea 1·1 [SD 1·0] vs 0·6 [0·7]; p<0·0001). Event charts showed earlier occurrences of higher grades of diarrhoea for patients given IROX compared with those given FOLFOX, and the AUC analysis shows a higher magnitude of diarrhoea consistently over time throughout the study in patients given IROX versus those given FOLFOX (mean AUC 4·2 [SD 5·2] vs 2·9 [4·2]; p<0·0001).

Interpretation: The ToxT analytical approach incorporates the dimension of time into adverse event assessment and offers a more comprehensive depiction of toxic effects than present methods. With new, continuously administered targeted agents, immunotherapy, and maintenance regimens, these improved longitudinal analyses are directly relevant to patients and are crucial in cancer clinical trials.

Funding: National Cancer Institute of the National Institutes of Health and the Mayo Comprehensive Cancer Center.

Figure 1. Diarrhea Incidence of FOLFOX versus IROX By Cycle and Grade

Output 1 demonstrates individual AEs at a given time point between different study arms. The bar chart of diarrhea on FOLFOX and IROX by cycle and grade demonstrates the most substantial difference in diarrhea incidence between the two arms at cycle 1, with consistently less diarrhea on FOLFOX than IROX over time.

Figure 2. AE Trajectory Over Time–Stream Plots

Output 2 highlights AE trajectory over time. Stream plot 2a shows several treatment-related AEs on a single study arm over time (cycles, in this study), and illustsrates the higher grade of gastrointestinal AEs compared to others early in FOLFOX treatment. The butterfly plot (2b) employs a shared y-axis to facilitate comparison of multiple AEs between two different treatment arms (FOLFOX versus IROX) over time. Stream plot 2c demonstrates comparison of a single AE of interest between two study arms to readily display the delayed time profile of dry mouth on venlafaxine versus placebo. Figure 2a. Multiple Toxicities of FOLFOX By Cycle - Stream Plot Figure 2b. Multiple Toxicities of FOLFOX and IROX By Cycle - Butterfly Plot Figure 2c. Dry Mouth on Venlafaxine versus Placebo By Cycle

Figure 2. AE Trajectory Over Time–Stream Plots

Output 2 highlights AE trajectory over time. Stream plot 2a shows several treatment-related AEs on a single study arm over time (cycles, in this study), and illustsrates the higher grade of gastrointestinal AEs compared to others early in FOLFOX treatment. The butterfly plot (2b) employs a shared y-axis to facilitate comparison of multiple AEs between two different treatment arms (FOLFOX versus IROX) over time. Stream plot 2c demonstrates comparison of a single AE of interest between two study arms to readily display the delayed time profile of dry mouth on venlafaxine versus placebo. Figure 2a. Multiple Toxicities of FOLFOX By Cycle - Stream Plot Figure 2b. Multiple Toxicities of FOLFOX and IROX By Cycle - Butterfly Plot Figure 2c. Dry Mouth on Venlafaxine versus Placebo By Cycle

Figure 3. Nausea on FOLFOX versus IROX By Cycle with Repeated Measures

Output 3, repeated measures analysis, assesses the trajectory (slope) of an AE over time between arms. The p-value of 0.18 affirms no difference in th trajectory of nausea grades over time between FOLFOX and IROX.

Figure 4. Time-to-Event Analyses for Onset of AEs

Time-to-event analyses from Output 4 display information about the onset of AEs. The time to occurrence of a single AE between arms is highlighted in the Kaplan-Meier curve (Figure 4a), which depicts earlier time to Grade 2+ diarrhea on IROX. Figure 4b demonstrates time to first occurrence and worst grade of multiple AEs in a single arm, IROX. In this plot, the more gradual onset of neuropathy compared to other AEs in oxaliplatin-based chemotherapy is seen. Figure 4a. Time to Grade 2+ Diarrhea on FOLFOX versus IROX Figure 4b. Median Time to First Occurrence and Worst Grade Toxicity on IROX

Figure 4. Time-to-Event Analyses for Onset of AEs

Time-to-event analyses from Output 4 display information about the onset of AEs. The time to occurrence of a single AE between arms is highlighted in the Kaplan-Meier curve (Figure 4a), which depicts earlier time to Grade 2+ diarrhea on IROX. Figure 4b demonstrates time to first occurrence and worst grade of multiple AEs in a single arm, IROX. In this plot, the more gradual onset of neuropathy compared to other AEs in oxaliplatin-based chemotherapy is seen. Figure 4a. Time to Grade 2+ Diarrhea on FOLFOX versus IROX Figure 4b. Median Time to First Occurrence and Worst Grade Toxicity on IROX

Figure 5. Event Charts for Severity and Timing of AEs on an Individual Patient Level

The event charts produced in Output 5 display overall patterns of AE data for gross comparison between two cohorts. Graduated colors indicate the AE grade (white is no diarrhea, black is grade 4 or 5) and readily display higher grade diarrhea earlier on in IROX (5b) than FOLFOX (5a). As each horitontal line indicates a single patient’s experience with an AE over interest over time, event charts offer resolution down to the level of an individual study participant. Figure 5a. Diarrhea on FOLFOX–Event Chart Figure 5b. Diarrhea on IROX–Event Chart

Figure 6. Area Under the Curve (AUC) Analysis to Compare AEs over Time

AUC analysis from Output 6 quantifies numerous pieces of AE data over time and accounts for low grade, longer lasting toxicity in a single number. In Figure 6a, patient A lacks any high grade event, but demonstrates chronic grade 2 toxicity that produces a higher AUC than Patient B, who has a single high grade event. The AUC captures the substantial toxicity experience of low grade, longer lasting AEs. AUC analysis can be applied to entire cohorts on study (Figure 6b), in this case readily revealing a consistently higher grade diarrhea experience over time on IROX compared to FOLFOX. Figure 6a. Conceptual Example of Area-Under-Curve Analysis Figure 6b. Area Under Curve Analysis Applied–Diarrhea Grade Over Time on FOLFOX versus IROX

Figure 6. Area Under the Curve (AUC) Analysis to Compare AEs over Time

AUC analysis from Output 6 quantifies numerous pieces of AE data over time and accounts for low grade, longer lasting toxicity in a single number. In Figure 6a, patient A lacks any high grade event, but demonstrates chronic grade 2 toxicity that produces a higher AUC than Patient B, who has a single high grade event. The AUC captures the substantial toxicity experience of low grade, longer lasting AEs. AUC analysis can be applied to entire cohorts on study (Figure 6b), in this case readily revealing a consistently higher grade diarrhea experience over time on IROX compared to FOLFOX. Figure 6a. Conceptual Example of Area-Under-Curve Analysis Figure 6b. Area Under Curve Analysis Applied–Diarrhea Grade Over Time on FOLFOX versus IROX