Bauer, Sebastian

Abstract Cancer outcomes vary widely between individual patients, each accumulating an irregular record of treatments, diagnoses, measurements, and complications. Current prognostic models reduce this complexity into a single snapshot, focus on narrow clinical settings, and rarely generalize across hospitals. Here we introduce Chronicle , an explainable transformer that learns from entire patient trajectories to predict diverse clinical outcomes throughout the disease course while capturing both short- and long-term temporal dependencies. Trained on 53.7 million longitudinal data points from 51,711 patients spanning 67 cancer types, Chronicle operates natively on irregular data without imputation and jointly predicts eight endpoints within a flexible framework adaptable to additional outcomes. Chronicle outperformed cross-sectional models for overall survival prediction (C-index 0.84 vs 0.76-0.79), stratified patients more accurately than established prognostic systems, including TNM stage, and predicted seven adverse event and transfusion endpoints (AUC 0.80-0.92). Applied without retraining to 69,341 patients in Germany, Switzerland, and the United States, Chronicle generalized across healthcare systems and improved further with local fine-tuning. Integrated explainability traced each risk update to patient-specific clinical factors, revealing distinct temporal persistence of prognostic information, with relevance half-lives ranging from weeks for therapies to nearly one year for baseline characteristics. These findings demonstrate that learning from hospital-wide patient trajectories enables interpretable and continuously updated predictions, providing a scalable framework to support individualized treatment decisions.

In the INTRIGUE phase III trial (ClinicalTrials.gov identifier: NCT03673501 ), adult patients with advanced gastrointestinal stromal tumor previously treated with imatinib were randomly assigned 1:1 to ripretinib 150 mg once daily or sunitinib 50 mg once daily (4 weeks on/2 weeks off). In the primary analysis, overall survival (OS) was immature. In this study, we report the final planned analysis of OS (key secondary end point), progression-free survival (PFS) on third-line therapy (second PFS; prespecified exploratory end point), and long-term safety. Final OS analysis was prespecified to occur with approximately 200 and ≥145 events in the overall and KIT exon 11 intention-to-treat (ITT) populations, respectively. As of March 15, 2023, there were 211 and 151 OS events in the overall ITT and KIT exon 11 ITT populations, respectively. Median OS was similar between second-line ripretinib and sunitinib in both populations (overall, 35.5 v 31.5 months; KIT exon 11, 35.5 v 32.8 months). Median second PFS (on third-line therapy) for the overall ITT population was similar between the ripretinib and sunitinib arms (7.7 v 7.4 months). Safety was consistent with the primary analysis. OS from this analysis was similar between arms, and second PFS suggests that receiving ripretinib did not adversely affect the PFS of third-line therapy.

PURPOSE Sunitinib, a multitargeted tyrosine kinase inhibitor (TKI), is approved for advanced gastrointestinal stromal tumor (GIST) after imatinib failure. Ripretinib is a switch-control TKI approved for advanced GIST after prior treatment with three or more TKIs, including imatinib. We compared efficacy and safety of ripretinib versus sunitinib in patients with advanced GIST who were previously treated with imatinib (INTRIGUE, ClinicalTrials.gov identifier: NCT03673501 ). PATIENTS AND METHODS Random assignment was 1:1 to once-daily ripretinib 150 mg or once-daily sunitinib 50 mg (4 weeks on/2 weeks off) and stratified by KIT/ platelet-derived growth factor α mutation and imatinib intolerance. The primary end point was progression-free survival (PFS) by independent radiologic review using modified Response Evaluation Criteria in Solid Tumors version 1.1. Secondary end points included objective response rate by independent radiologic review, safety, and patient-reported outcome measures. RESULTS Overall, 453 patients were randomly assigned to ripretinib (intention-to-treat [ITT], n = 226; KIT exon 11 ITT, n = 163) or sunitinib (ITT, n = 227; KIT exon 11 ITT, n = 164). Median PFS for ripretinib and sunitinib ( KIT exon 11 ITT) was 8.3 and 7.0 months, respectively (hazard ratio, 0.88; 95% CI, 0.66 to 1.16; P = .36); median PFS (ITT) was 8.0 and 8.3 months, respectively (hazard ratio, 1.05; 95% CI, 0.82 to 1.33; nominal P = .72). Neither was statistically significant. Objective response rate was higher for ripretinib versus sunitinib in the KIT exon 11 ITT population (23.9% v 14.6%, nominal P = .03). Ripretinib was associated with a more favorable safety profile, fewer grade 3/4 treatment-emergent adverse events (41.3% v 65.6%, nominal P < .0001), and better scores on patient-reported outcome measures of tolerability. CONCLUSION Ripretinib was not superior to sunitinib in terms of PFS. However, meaningful clinical activity, fewer grade 3/4 treatment-emergent adverse events, and improved tolerability were observed with ripretinib.

Abstract Purpose: Most patients with gastrointestinal stromal tumor (GIST) have activating mutations in KIT/PDGFRA and are initially responsive to tyrosine kinase inhibitors (TKI). The acquisition of secondary mutations leads to refractory/relapsed disease. This study reports the results of an analysis from the phase III INVICTUS study (NCT03353753) characterizing the genomic heterogeneity of tumors from patients with advanced GIST and evaluating ripretinib efficacy across KIT/PDGFRA mutation subgroups. Patients and Methods: Tumor tissue and liquid biopsy samples that captured circulating tumor DNA were collected prior to study enrollment and sequenced using next-generation sequencing. Subgroups were determined by KIT/PDGFRA mutations and correlation of clinical outcomes and KIT/PDGFRA mutational status was assessed. Results: Overall, 129 patients enrolled (ripretinib 150 mg once daily, n = 85; placebo, n = 44). The most common primary mutation subgroup detected by combined tissue and liquid biopsies were in KIT exon 11 (ripretinib, 61.2%; placebo, 77.3%) and KIT exon 9 (ripretinib, 18.8%; placebo, 15.9%). Patients receiving ripretinib demonstrated progression-free survival (PFS) benefit versus placebo regardless of mutation status (HR 0.16) and in all assessed subgroups in Kaplan–Meier PFS analysis (exon 11, P &lt; 0.0001; exon 9, P = 0.0023; exon 13, P &lt; 0.0001; exon 17, P &lt; 0.0001). Among patients with wild-type KIT/PDGFRA by tumor tissue, PFS ranged from 2 to 23 months for ripretinib versus 0.9 to 10.1 months for placebo. Conclusions: Ripretinib provided clinically meaningful activity across mutation subgroups in patients with advanced GIST, demonstrating that ripretinib inhibits a broad range of KIT/PDGFRA mutations in patients with advanced GIST who were previously treated with three or more TKIs.

Abstract Background Ripretinib 150 mg once daily (QD) is indicated for advanced gastrointestinal stromal tumors (GISTs) as at least fourth-line therapy. In INVICTUS, ripretinib intrapatient dose escalation (IPDE) to 150 mg b.i.d. was allowed after progressive disease (PD) on 150 mg QD by blinded independent central review using modified RECIST 1.1. We report the efficacy and safety of ripretinib IPDE to 150 mg b.i.d. after PD among patients randomized to ripretinib 150 mg QD in the INVICTUS study. Materials and Methods Tumor imaging was performed every 28-day cycle for the first four cycles in the ripretinib 150 mg QD period and then every other cycle, including the 150 mg b.i.d. period. Among the ripretinib IPDE patients, progression-free survival (PFS)1 was the time from randomization until PD; PFS2 was the time from the first dose of ripretinib 150 mg b.i.d. to PD or death. Results Among 43 ripretinib IPDE patients, median PFS1 was 4.6 months (95% confidence interval [CI], 2.7–6.4) and median PFS2 was 3.7 months (95% CI, 3.1–5.3). Median overall survival was 18.4 months (95% CI, 14.5–not estimable). Ripretinib 150 mg b.i.d. (median duration of treatment 3.7 months) was well tolerated with new or worsening grade 3–4 treatment-emergent adverse events (TEAEs) of anemia in six (14%) and abdominal pain in three (7%) patients. Ripretinib 150 mg b.i.d. was discontinued because of TEAEs in seven (16%) patients. Conclusion Ripretinib 150 mg b.i.d. after PD on 150 mg QD may provide additional clinically meaningful benefit with an acceptable safety profile in patients with at least fourth-line GISTs. Implications for Practice Of the 85 patients with advanced gastrointestinal stromal tumor having received at least three prior anticancer therapies randomized to ripretinib 150 mg once daily (QD) in the phase III INVICTUS study, 43 underwent ripretinib intrapatient dose escalation (IPDE) to 150 mg b.i.d. after progressive disease (PD). Median progression-free survival was 4.6 months before and 3.7 months after ripretinib IPDE. The safety profile of ripretinib 150 mg b.i.d. was acceptable. These findings indicate ripretinib IPDE to 150 mg b.i.d. may provide additional clinical benefit in patients with PD on ripretinib 150 mg QD, for whom limited treatment options exist.

BACKGROUNDLittle is known about the factors that predict for gastrointestinal stromal tumor (GIST) recurrence in patients treated with adjuvant imatinib.METHODSRisk factors for GIST recurrence were identified, and 2 risk stratification scores were developed using the database of the Scandinavian Sarcoma Group (SSG) XVIII trial, where 358 patients with high‐risk GIST with no overt metastases were randomly assigned to adjuvant imatinib 400 mg/day either for 12 or 36 months after surgery. The findings were validated in the imatinib arm of the American College of Surgeons Oncology Group Z9001 trial, where 359 patients with GIST were randomized to receive imatinib and 354 were to receive placebo for 12 months.RESULTSFive factors (high tumor mitotic count, nongastric location, large size, rupture, and adjuvant imatinib for 12 months) were independently associated with unfavorable recurrence‐free survival (RFS) in a multivariable analysis in the SSGXVIII cohort. A risk score based on these 5 factors had a concordance index with GIST recurrence of 78.9%. When a simpler score consisting of the 2 strongest predictive factors (mitotic count and tumor site) was devised, the groups with the lowest, intermediate high, and the highest risk had 5‐year RFS of 76.7%, 47.5%, and 8.4%, respectively. Both scores were strongly associated with RFS in the validation cohort (P < .001 for each comparison).CONCLUSIONSThe scores generated were effective in stratifying the risk of GIST recurrence in patient populations treated with adjuvant imatinib. Patients with nongastric GIST with a high mitotic count are at a particularly high risk for recurrence. Cancer 2014;120:2325–2333 © 2014 The Authors. Cancer published by Wiley Periodicals, Inc. on behalf of American Cancer Society.