Heinemann, Volker

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.

PURPOSE Colorectal cancer (CRC) incidence and mortality have decreased since the 1970s, but the incidence in young adults (<50 years, named early-onset CRC [eoCRC]) has been increasing. PATIENTS AND METHODS Individual patient data on 13,365 patients with metastatic CRC enrolled between 2000 and 2012 in 17 first-line randomized trials in the Aide et Recherche en Cancérologie Digestive database were pooled. The distribution of demographics, clinicopathologic features, biomarkers, and outcome data were summarized and compared by age groups. Progression-free survival (PFS) and overall survival (OS) were assessed by Kaplan-Meier curves and Cox models stratified by treatment arms within studies, adjusting for potential confounders. Predictive value of age group on clinical outcomes was evaluated by testing interaction effect between treatment and age variables. RESULTS Overall, 2,045 patients with eoCRC (median age, 42.5) and 11,320 patients with average-onset CRC (aoCRC; median age, 63.8) were included in this analysis. Within the eoCRC population, treatment with bevacizumab in addition to chemotherapy improved PFS (9.9 v 6.8 months; hazard ratio [HR], 0.66 [95% CI, 0.54 to 0.80]; P < .0001), which was similar to the findings in aoCRC population (9.4 v 7.3 months; HR, 0.73 [95% CI, 0.67 to 0.80]; P < .001; interaction P = .5415). However, epithelial growth factor receptor inhibitor (EGFRi) did not improve PFS in RAS wild-type (WT) patients with eoCRC who had left-sided primary tumors (8.3 v 8.9 months; HR, 1.20 [95% CI, 0.81 to 1.77]; P = .36), whereas EGFRi significantly improved PFS in the aoCRC population (9.9 v 8.5 months; HR, 0.74 [95% CI, 0.64 to 0.86]; P < .0001; interaction P = .083). CONCLUSION Treatment-naïve patients with metastatic eoCRC appear to derive similar benefit from bevacizumab as patients with aoCRC. However, patients with eoCRC with left-sided RAS/RAF WT tumors did not appear to derive benefit from first-line EGFRi.

3588 Background: Although anti-EGFR antibody plus doublet chemotherapy has become the standard of first-line treatment for RAS wild-type (wt), left sided metastatic colorectal cancer (mCRC), the optimal molecular-targeted therapy for RAS wt, right-sided mCRC is not clear. Methods: To evaluate the efficacy between anti-EGFR antibody vs. bevacizumab combination therapy, from 40,889 Individual patient (pt) data from 59 studies in ARCAD mCRC database, 723 pts with RAS wt, right-sided mCRC who received a first-line molecular-targeted therapy with backbone chemotherapy (FOLFOX/FOLFIRI when anti-EGFR antibody combination, and FOLFOX/FOLFIRI/CAPOX/FOLFOXIRI when bevacizumab combination) were selected from 10 randomized studies (FIRE-3, CALGB80495, CRYSTAL, PRIME, CAIRO2, OPUS, TRIBE, TRIBE2, ATOM, and CCOG1201). Primary objective was overall survival (OS), and secondary objectives were progression-free survival (PFS) and overall response rate (ORR); Hazard ratio (HR) and Odds ratio (OR) were adjusted for ECOG-PS, age, and gender. Propensity score matching (PSM) and inverse probability treatment weighting (IPTW) as sensitivity analysis were also performed. Secondary analyses were limited to BRAF wt pts. Results: Anti-EGFR antibody and bevacizumab were administrated in 329 and 394 pts, respectively, of whom 162 and 151 pts were BRAF wt, respectively. Baseline characteristics were as follows (anti-EGFR antibody/bevacizumab): median age, 63.0 years both; female, 47.1/46.4%; and ECOG-PS 0, 53.2/65.2%. The OS and PFS were significantly prolonged in pts receiving bevacizumab combination therapy compared to those receiving anti-EGFR antibody combination therapy (Table). These trends were more pronounced when limited to BRAF wt pts (Table). There were no significant differences in ORR for both overall and BRAF wt pts. These results were similar in the sensitivity analysis (Table). Conclusions: For patients with RAS wt or RAS/ BRAF wt, right-sided mCRC, bevacizumab combination therapy is preferred first-line treatment. [Table: see text]

3554 Background: Approximately 30% of patients (pts) diagnosed with colorectal cancer (CRC) develop liver metastases (LM). Liver is the most common organ of metastasis of CRC. The ARCAD database contains individual patient data of randomized trials that included CRC pts with initially unresectable metastases treated with systemic therapy. The aim of this study was to assess the response and survival outcomes in non-LM (NLM) vs LM across different lines of treatment. Methods: We analyzed survival outcomes of mCRC pts with either single site (SS) or multiple sites (MS) according to LM status in the following treatment groups: A: chemotherapy (CT) alone, B: CT + VEGF-antibodies, C: CT + EGFR-antibodies in KRAS wild-type tumors, within first-line (1L) and second line (2L) of therapy and D: pts enrolled on third line (≥3L) trials treated with trifluridine/tipiracil or regorafenib and placebo. The primary and secondary endpoints were overall survival (OS) and progression-free survival (PFS) which were assessed using Kaplan-Meier estimates and adjusted Cox models on ECOG PS, age, and gender. Results: We included 26 trials with 17924 pts. 14066 pts had LM. Pts with LM had a higher rate of colon vs rectum as primary tumor (72 vs 62%; P < .001) and less SS (31 vs 47%; P < .001) than those with NLM. OS and PFS results in subgroups are reported in the table. In groups A and B, we found better OS and PFS outcomes in NLM pts as either SS or MS in 1L and 2L. In group C from 1L, we found better survival outcomes in pts with SS LM. In pts with MS, NLM superiority was observed in OS but not in PFS. However, these results were influenced by primary tumor sidedness. In group D, better OS and PFS was observed in pts without LM than those with LM whether in pts with SS or MS. Response rates were higher in LM than in NLM in most 1L and 2L subgroups. Conclusions: LM is a poor prognostic factor for mCRC increasing from the 1L to ≥3L. Survival with CT alone and CT + anti-VEGF according to LM and NLM differs significantly in 1L and 2L but not with CT + anti-EGFR. This data justifies using LM as a stratification factor at least in ≥3L trials. [Table: see text]

TPS3631 Background: The current standard of care (SOC) for the treatment of metastatic colorectal cancer (mCRC) is multi-agent chemotherapy, with or without a VEGF or EGFR inhibitor. Human epidermal growth factor receptor-2 (HER2) is a validated clinical target in breast and gastric cancers. HER2 amplification occurs in 3%–5% of patients with mCRC; the rate of HER2 amplification can increase to approximately 10% in patients with RAS/BRAF wild-type mCRC tumors. Tucatinib (TUC)—a highly selective, HER2-directed tyrosine kinase inhibitor—is approved in multiple regions for HER2-positive (HER2+) metastatic breast cancer, approved in the US for HER2+ metastatic colorectal cancer, and under investigation in gastrointestinal cancers. MOUNTAINEER (NCT03043313) evaluated the safety and efficacy of TUC and trastuzumab (Tras) in patients with treatment-refractory RAS wild-type, HER2+ mCRC. Results from the primary endpoint analysis showed clinically meaningful activity, with a confirmed objective response rate (ORR) per blinded independent central review (BICR) of 38.1% (95% confidence interval [CI] 27.7, 49.3) and median duration of response per BICR of 12.4 months (95% CI 8.5, 20.5). Results also demonstrated TUC + Tras was well tolerated, with a low discontinuation rate (5.8%) and no deaths due to adverse events. MOUNTAINEER-03 will further investigate TUC in combination with modified FOLFOX (mFOLFOX) and Tras in patients with RAS wild-type HER2+ mCRC. Methods: MOUNTAINEER-03 (NCT05253651) is a global, open-label, randomized, phase III study for first-line treatment of HER2+ and RAS wild-type mCRC. Approximately 400 patients will be randomized 1:1 to the TUC experimental arm (TUC [300 mg orally twice daily] + Tras + mFOLFOX) or the SOC arm (mFOLFOX alone or in combination with either bevacizumab or cetuximab). HER2 status is determined centrally with tissue-based HER2 immunohistochemistry and in situ hybridization assays. Eligible patients must not have received prior treatment in the metastatic setting but may have received adjuvant treatment if completed > 6 months prior to enrollment. Patients must be ≥18 years old with an Eastern Cooperative Oncology Group Performance Status of ≤1 and RAS wild-type mCRC. Patients with treated stable central nervous system metastases are eligible. Randomization is stratified by primary tumor location (left-sided vs other) and liver metastases (presence/absence). The primary endpoint is progression-free survival per RECIST v1.1 assessed by BICR. Key secondary endpoints are overall survival and confirmed ORR per RECIST v1.1 assessed by BICR. Enrollment is ongoing in North America, Asia, Australia, and Europe. Clinical trial information: NCT05253651 .

TPS261 Background: Current standard of care (SOC) for treatment (tx) of metastatic colorectal cancer (mCRC) is multi-agent chemotherapy, w/ or w/o a VEGF- or EGFR-inhibitor. HER2 is a validated clinical target in breast and gastric cancers. HER2 amplification occurs in 3%-5% of patients (pts) w/ mCRC; the rate of HER2 amplification can increase to ~10% in pts w/ RAS/BRAF wild-type mCRC tumors. Tucatinib (TUC), a highly selective, HER2-directed tyrosine kinase inhibitor, is approved in multiple regions for HER2+ metastatic breast cancer and is being investigated in gastrointestinal cancers. MOUNTAINEER (NCT03043313) evaluated the safety and efficacy of TUC and trastuzumab (Tras) in pts w/ tx refractory RAS wild-type, HER2+ mCRC. Results from the primary endpoint analysis showed clinically meaningful activity (confirmed ORR of 38.1% and median DOR of 12.4 months) and demonstrated TUC + Tras was well tolerated with a low discontinuation rate (5.8%) and no deaths due to AEs. MOUNTAINEER-03 will further investigate TUC in combo w/ mFOLFOX and Tras in pts w/ RAS wild-type, HER2+ mCRC. Methods: MOUNTAINEER-03 (NCT05253651) is a global, open label, randomized, phase 3 study for 1L tx of HER2+ and RAS wild-type mCRC. Approximately 400 pts will be randomized 1:1 to the TUC experimental arm (TUC [300 mg PO BID] + Tras + mFOLFOX) or the SOC arm (mFOLFOX alone or in combo w/ either bevacizumab or cetuximab). HER2 status is determined centrally w/ tissue based HER2 immunohistochemistry and in situ hybridization assays. Eligible pts must not have received prior tx in the metastatic setting but may have received adjuvant tx if completed > 6 months prior to enrollment. Pts must be ≥18 years of age w/ an ECOG performance status of ≤1 and RAS wild-type mCRC. Pts w/ treated stable central nervous system metastases are eligible. Randomization is stratified by primary tumor location (left-sided vs other) and liver metastases (presence/absence). Primary endpoint is progression-free survival per RECIST v1.1, assessed by blinded independent central review (BICR). Key secondary endpoints are overall survival and confirmed objective response rate per RECIST v1.1 assessed by BICR. Enrollment is ongoing in the US, w/ global sites planned. Clinical trial information: NCT05253651 .

PURPOSE This randomized, open-label trial compared the efficacy and safety of adjuvant nab-paclitaxel + gemcitabine with those of gemcitabine for resected pancreatic ductal adenocarcinoma (ClinicalTrials.gov identifier: NCT01964430 ). METHODS We assigned 866 treatment-naive patients with pancreatic ductal adenocarcinoma to nab-paclitaxel (125 mg/m 2 ) + gemcitabine (1,000 mg/m 2 ) or gemcitabine alone to one 30-40 infusion on days 1, 8, and 15 of six 28-day cycles. The primary end point was independently assessed disease-free survival (DFS). Additional end points included investigator-assessed DFS, overall survival (OS), and safety. RESULTS Two hundred eighty-seven of 432 patients and 310 of 434 patients completed nab-paclitaxel + gemcitabine and gemcitabine treatment, respectively. At primary data cutoff (December 31, 2018; median follow-up, 38.5 [interquartile range [IQR], 33.8-43 months), the median independently assessed DFS was 19.4 ( nab-paclitaxel + gemcitabine) versus 18.8 months (gemcitabine; hazard ratio [HR], 0.88; 95% CI, 0.729 to 1.063; P = .18). The median investigator-assessed DFS was 16.6 (IQR, 8.4-47.0) and 13.7 (IQR, 8.3-44.1) months, respectively (HR, 0.82; 95% CI, 0.694 to 0.965; P = .02). The median OS (427 events; 68% mature) was 40.5 (IQR, 20.7 to not reached) and 36.2 (IQR, 17.7-53.3) months, respectively (HR, 0.82; 95% CI, 0.680 to 0.996; P = .045). At a 16-month follow-up (cutoff, April 3, 2020; median follow-up, 51.4 months [IQR, 47.0-57.0]), the median OS (511 events; 81% mature) was 41.8 ( nab-paclitaxel + gemcitabine) versus 37.7 months (gemcitabine; HR, 0.82; 95% CI, 0.687 to 0.973; P = .0232). At the 5-year follow-up (cutoff, April 9, 2021; median follow-up, 63.2 months [IQR, 60.1-68.7]), the median OS (555 events; 88% mature) was 41.8 versus 37.7 months, respectively (HR, 0.80; 95% CI, 0.678 to 0.947; P = .0091). Eighty-six percent ( nab-paclitaxel + gemcitabine) and 68% (gemcitabine) of patients experienced grade ≥ 3 treatment-emergent adverse events. Two patients per study arm died of treatment-emergent adverse events. CONCLUSION The primary end point (independently assessed DFS) was not met despite favorable OS seen with nab-paclitaxel + gemcitabine.

3572 Background: Early onset colorectal cancer (eoCRC: disease diagnosed < 50) has been increasing over the past 2 decades. Currently, standard treatment recommendations for eoCRC patients (pts) with metastatic disease does not differ from late-onset CRC (loCRC) pts although outcomes data in eoCRC pts is limited. Methods: Individual patient data on 5,761 treatment-naive metastatic eoCRC pts was pooled from 8 phase II and III randomized EGFRi studies (2000 - 2012) from the ARCAD mCRC database. The distribution of demographics, clinicopathological features, and biomarkers were summarized by age groups. Progression-free survival (PFS) was compared between age groups by stratified Cox models, adjusting for potential confounders. Predictive value of age group was evaluated by testing interaction effect between treatment and age variables based on a subset of trials with concurrent randomizations between regimens with and without EGFRi Results: eoCRC (n=756) were more evenly distributed between gender, had improved performance status (PS), increased likelihood of metastatic resection, and distant lymph node metastasis, but were less likely to have lung metastasis or KRAS mutation compared to loCRC (n=5,005, table 1). eoCRC and loCRC patients had similar distribution of primary tumor sidedness, primary resection, liver and/or peritoneal involvement, number of metastatic sites involved, and BRAF mutations (MT). No difference in PFS for eoCRC versus loCRC pts was noted (7.8 vs. 7.9 months [M], adjusted hazard ratio [HRadj], 1.02, 95% confidence interval [CI], 0.93-1.11). Among pts with KRAS wild type (WT) and left sided primary tumors, univariable analysis of EGFRi demonstrated improved mPFS in loCRC (9.9 vs 8.5M, HR = 0.74, p<0.001), but this benefit was not seen in eoCRC (8.3 vs 8.9 months, HR 1.20, p=0.36). The same pattern was observed upon multivariable analysis (Table). Conclusions: In our pooled analysis, EGFRi + chemotherapy significantly improved PFS in treatment-naïve loCRC patients but not in left sided, KRAS WT, eoCRC patients. Further validation in an independent cohort is warranted. [Table: see text]

Abstract Background We evaluated the time to progression (TTP) and survival outcomes of second-line therapy for metastatic colorectal cancer among adults aged 70 years and older compared with younger adults following progression on first-line clinical trials. Methods Associations between clinical and disease characteristics, time to initial progression, and rate of receipt of second-line therapy were evaluated. TTP and overall survival (OS) were compared between older and younger adults in first- and second-line trials by Cox regression, adjusting for age, sex, Eastern Cooperative Oncology Group Performance Status, number of metastatic sites and presence of metastasis in the lung, liver, or peritoneum. All statistical tests were 2-sided. Results Older adults comprised 16.4% of patients on first-line trials (870 total older adults aged &gt;70 years; 4419 total younger adults aged ≤70 years, on first-line trials). Older adults and those with Eastern Cooperative Oncology Group Performance Status &gt;0 were less likely to receive second-line therapy than younger adults. Odds of receiving second-line therapy decreased by 11% for each additional decade of life in multivariable analysis (odds ratio = 1.11, 95% confidence interval = 1.02 to 1.21, P = .01). Older and younger adults enrolled in second-line trials experienced similar median TTP and median OS (median TTP = 5.1 vs 5.2 months, respectively; median OS = 11.6 vs 12.4 months, respectively). Conclusions Older adults were less likely to receive second-line therapy for metastatic colorectal cancer, though we did not observe a statistical difference in survival outcomes vs younger adults following second-line therapy. Further study should examine factors affecting decisions to treat older adults with second-line therapy. Inclusion of geriatric assessment may provide better criteria regarding the risks and benefits of second-line therapy.