Nelson, Garth D.

PURPOSE Social determinants of health (SDOH) shape cancer treatment access, adherence, and outcomes, yet their collection and use within National Clinical Trials Network (NCTN) studies remain poorly defined. This study examined how demographic and SDOH-related variables were historically collected and published to identify gaps that constrain the study of social context within NCTN trials. METHODS Participant-level data from completed phase III trials for gastrointestinal (GI) cancers conducted by the Alliance for Clinical Trials in Oncology (Alliance) or its legacy groups from 1999 to 2018 were pooled. Thirteen measures were assessed: four demographic and nine SDOH-related. The proportion of individual participants with data collected for each measure was evaluated. Data utilization was evaluated for all primary articles and via targeted review of related publications using the number either reporting subgroups or publishing analyses for each measure. RESULTS A total of 12,701 participants across 11 trials were included. All trials collected demographic measures (<2% of patients missing), insurance status (1% missing), and ZIP code (3% missing). Education level was collected in two trials (28% missing) with marital and employment status collected in one trial (41% missing for both). No trials collected data on other SDOH-related measures. Education level was the only SDOH-related measure reported in primary articles, and none reported analysis of SDOH-related measures. Of the 149 related publications, <2% reported or analyzed any SDOH-related measure. CONCLUSION Across Alliance and NCTN legacy group phase III trials for GI cancers, demographic variables have been consistently collected and frequently reported or analyzed, whereas SDOH-related measures are inconsistently collected and rarely published in the literature. These findings demonstrate a historical absence of routine SDOH data capture and utilization within NCTN trials.

9503 Background: Neoadjuvant ± adjuvant immunotherapy improves event-free survival relative to adjuvant immunotherapy alone for patients with high-risk resectable stage III melanoma. However, the optimal regimen balancing efficacy and tolerability is not known. T-cell immunoglobulin and ITIM domain (TIGIT) is a promising immune checkpoint but its therapeutic potential in stage III melanoma is underexplored. Methods: In this phase II trial, patients with resectable, macroscopic stage III melanoma received four 21-day neoadjuvant cycles of 1200mg IV atezolizumab (atezo, anti-PD-L1) + 600mg IV tiragolumab (tira, anti-TIGIT), followed by therapeutic lymph node dissection (TLND) and eight 21-day adjuvant cycles of 1200mg IV atezo. Primary endpoints were pathologic response (of all patients initiating neoadjuvant therapy) and recurrence-free survival (RFS) from the time of TLND in patients who were operated on per protocol and received adjuvant therapy. Secondary endpoint was adverse events (AEs); exploratory endpoints included event-free survival (EFS) and distant metastasis-free survival (DMFS). Results: Thirty-four patients, median age 59 years, were accrued and initiated neoadjuvant atezo/tira. 76.5% had >1 metastatic lymph node involved at baseline and 73.5% presented with Stage IIIC disease. All 34 patients were evaluable for AEs, pathologic response and EFS. Four patients were diagnosed with metastatic disease during neoadjuvant treatment, while 30 had TLND per protocol and 28 received adjuvant treatment and were evaluable for RFS and DMFS. Major pathologic responses (MPR, ≤10% viable tumor) were observed in 16/34 patients (47.1%, Table). With 19.9 months median follow-up from registration, 12-month EFS was 72.0% (95% CI 57.9 to 89.5%). With 16 months median follow-up from operation, 12-month RFS was 73.3% (n=28, 95% CI 56.9 to 94.5%), while 12-month DMFS was 86.0% (n=28, 95% CI 72.2 to 100%). In the 16 patients with an MPR, 2 did not receive adjuvant treatment and were followed for 33.3 and 10.8 months without recurrence/death. In the remaining 14 patients, 12-month RFS and 12-month DMFS were both 91.7% (95% CI 77.3 to 100%). 5 patients (14.7%) experienced any grade 3+ AE with 2 (5.9%) at least possibly related to the neoadjuvant regimen. Conclusions: Among patients with high-risk resectable stage III melanoma, neoadjuvant atezo/tira was a promising regimen with a favorable safety profile and warrants further study. Identification of predictive biomarkers will allow for optimization of neoadjuvant therapy for individual patients. Clinical trial information: NCT03554083 . Pathologic response. N=34 Major Pathologic Response 16 (47.1%) Pathologic complete response (no viable tumor) 13 (38.2%) Near-pathologic complete response (0.1−10% viable tumor) 3 (8.8%) Pathologic partial response (>10.0−50% viable tumor) 2 (5.9%) Pathologic non-response (>50% viable tumor) 12 (35.3%) No per protocol operation 4 (11.8%)

Background Neoadjuvant treatment has become standard for patients with high-risk operable stage III melanoma, but the optimal regimen is unknown. Targeted therapy approaches yield high pathological response rates, while immunotherapy regimens show favorable recurrence-free survival (RFS). NeoACTIVATE was designed to address whether a neoadjuvant combination of both targeted therapy and immunotherapy might leverage the benefits of each. Methods We tested neoadjuvant treatment with 12 weeks of vemurafenib, cobimetinib, and atezolizumab for patients with BRAF-mutated (BRAFm) melanoma (cohort A) and cobimetinib and atezolizumab for patients with BRAF-wild-type (BRAFwt) melanoma (cohort B), regimens which we have shown generate a substantial major pathological response. After therapeutic lymph node dissection, patients received 24 weeks of adjuvant atezolizumab. Here, we report survival outcomes and their association with biomarkers assayed among the gut microbiome and peripheral blood immune subsets. Results With 49 months median follow-up, the median RFS was not reached for cohort A and was 40.8 months for cohort B. At 24 months after operation, 2 of 14 cohort A patients and 4 of 13 cohort B patients had experienced distant relapse. Key findings from correlative analyses included diversity, taxonomic and functional metagenomic gut microbiome signals associated with distant metastasis-free survival at 2 years. Notably, we observed a strong correlation between low microbial arginine biosynthesis (required for T-cell activation and effector function) and early distant recurrence (p=0.0005), which correlated with taxonomic differential abundance findings. Peripheral blood immune monitoring revealed increased double-positive (CD4+CD8+) T cells in patients with early recurrence. Conclusions Neoadjuvant treatment with cobimetinib and atezolizumab±vemurafenib was associated with a low rate of distant metastasis in patients with high-risk stage III melanoma. Freedom from early distant metastasis was highly associated with taxonomic differences in gut microbiome structure and with functional pathway alterations known to modulate T cell immunity. Identification of predictive biomarkers will permit optimization of neoadjuvant therapy regimens for individual patients. Trial registration number NCT03554083.

Importance Outcomes for patients with unresectable stage III non–small cell lung cancer (NSCLC) treated with chemoradiation therapy (CRT) have improved with adjuvant immune checkpoint inhibitors, with a reported 5-year overall survival benefit of approximately 10% for adjuvant durvalumab vs placebo after completion of CRT without progression and with preserved performance status. Starting atezolizumab prior to CRT may allow more patients to benefit from immunotherapy. Objective To evaluate clinical outcomes of patients treated with atezolizumab before and after CRT for unresectable stage III NSCLC. Design, Setting, and Participants This single-cohort, phase II, nonrandomized controlled trial was conducted at 11 US sites. Patients with pathologically confirmed, unresectable stage III NSCLC who were treatment naive and had good performance status were enrolled between January 3, 2018, and July 24, 2019. Data were locked on March 21, 2023. Interventions Patients received four 21-day cycles of atezolizumab, 1200 mg intravenously, with therapy administered on day 1 of each cycle. Patients not experiencing tumor progression continued to CRT (60 Gy to involved fields) concurrent with weekly carboplatin area under the curve of 2 and paclitaxel, 50 mg/m 2 , followed by planned consolidation carboplatin area under the curve of 6 and paclitaxel, 200 mg/m 2 , for two 21-day cycles. Patients not experiencing progression continued atezolizumab, 1200 mg, every 21 days to complete 1 year of therapy. Main Outcomes and Measures The primary end point was the disease control rate at 12 weeks. Secondary end points were progression-free survival, overall survival, overall response rate, safety, and translational science end points. Results A total of 62 patients (median [range] age, 63.9 [38.1-86.5] years; 32 female [51.6%]) were enrolled and received at least 1 dose of atezolizumab. The disease control rate at 12 weeks was 74.2% (80% CI, 65.7%-81.4%). Median progression-free survival was 30.0 months (95% CI, 15.8 to not evaluable), and the median overall survival was not reached. The overall survival rate at 24 months was 73.7% (95% CI, 63.4%-85.7%), and the overall response rate was 66.2%. Seventeen patients (27.4%) experienced grade 3 or higher immune-related adverse events, including 1 with grade 5 pneumonitis and 1 with grade 4 Guillain-Barré syndrome. Thirty patients (48.4%) experienced grade 3 or higher treatment-related adverse events. Conclusions and Relevance These findings suggest that neoadjuvant atezolizumab merits further study based on safety and encouraging outcomes. Trial Registration ClinicalTrials.gov Identifier: NCT03102242

TPS8123 Background: A minority of patients with unresectable stage III non-small cell lung cancer (NSCLC) may be cured by chemoradiotherapy (CRT). Adjuvant checkpoint inhibition through PD-L1 blockade after CRT improved survival compared to placebo in the PACIFIC trial (median progression-free survival (mPFS) 16.9 vs 5.6 months (mo), median overall survival (mOS) 47.5 vs 29.1 mo), but overall survival at 5 years remains below 50% (Spigel D, et al J Clin Oncol 2022, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9015199/ . Only patients completing CRT without progression and with good performance status were eligible for this approach. Neoadjuvant checkpoint inhibition would allow more patients the opportunity to benefit from immunotherapy and may attenuate tumor-related immunosuppression via depletion of regulatory T cells and clonal expansion of effector T cells, thereby improving tumor immunogenicity. Neoadjuvant atezolizumab had favorable outcomes compared to historic PACIFIC data in the phase II single arm trial, AFT-16 (mPFS 30 mo and mOS not reached). Whether combination immunotherapy therapy before CRT will improve outcomes in this setting is the question posed in the AFT-57 trial. Methods: This phase II randomized Alliance Foundation Trials study (AFT-57) will evaluate safety and efficacy of atezolizumab with or without the anti-TIGIT monoclonal antibody, tiragolumab, before and after definitive CRT with concurrent atezolizumab. The primary endpoint is PFS in the two experimental arms with a goal to select the most promising regimen for further study. AFT-57 will randomly assign 158 patients with stage III NSCLC (AJCC v8), Eastern Cooperative Oncology Group performance status 0-1, no active autoimmune disease and no underlying organ dysfunction to 2 cycles of neoadjuvant atezolizumab (1200 mg intravenously [IV] every 21 days) with or without tiragolumab (600 mg IV). Non-progressing patients will receive carboplatin and paclitaxel weekly with atezolizumab 1200 mg IV every 21 days concurrent with 60 Gray involved field thoracic radiation in 30 daily fractions (Monday - Friday) followed by atezolizumab with or without tiragolumab on the same schedule as the neoadjuvant doses, with a plan to complete one year of therapy. A pilot cohort of 20 patients for whom tiragolumab will be combined with atezolizumab during chemoradiotherapy is planned toward the end of accrual. Correlative science includes tissue and blood-based immune-related biomarkers at baseline and during therapy. This trial utilizes the Alliance Participant Engagement Portal, a patient-facing site designed to provide information and resources to Alliance clinical trial participants. The trial was activated on 12/7/23 with the first patient screened 1/19/24. Clinical trial information: NCT05798663 .

Abstract Deep learning may detect biologically important signals embedded in tumor morphologic features that confer distinct prognoses. Tumor morphologic features were quantified to enhance patient risk stratification within DNA mismatch repair (MMR) groups using deep learning. Using a quantitative segmentation algorithm (QuantCRC) that identifies 15 distinct morphologic features, we analyzed 402 resected stage III colon carcinomas [191 deficient (d)-MMR; 189 proficient (p)-MMR] from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy. Results were validated in an independent cohort (176 d-MMR; 1,094 p-MMR). Association of morphologic features with clinicopathologic variables, MMR, KRAS, BRAFV600E, and time-to-recurrence (TTR) was determined. Multivariable Cox proportional hazards models were developed to predict TTR. Tumor morphologic features differed significantly by MMR status. Cancers with p-MMR had more immature desmoplastic stroma. Tumors with d-MMR had increased inflammatory stroma, epithelial tumor-infiltrating lymphocytes (TIL), high-grade histology, mucin, and signet ring cells. Stromal subtype did not differ by BRAFV600E or KRAS status. In p-MMR tumors, multivariable analysis identified tumor-stroma ratio (TSR) as the strongest feature associated with TTR [HRadj 2.02; 95% confidence interval (CI), 1.14–3.57; P = 0.018; 3-year recurrence: 40.2% vs. 20.4%; Q1 vs. Q2–4]. Among d-MMR tumors, extent of inflammatory stroma (continuous HRadj 0.98; 95% CI, 0.96–0.99; P = 0.028; 3-year recurrence: 13.3% vs. 33.4%, Q4 vs. Q1) and N stage were the most robust prognostically. Association of TSR with TTR was independently validated. In conclusion, QuantCRC can quantify morphologic differences within MMR groups in routine tumor sections to determine their relative contributions to patient prognosis, and may elucidate relevant pathophysiologic mechanisms driving prognosis. Significance: A deep learning algorithm can quantify tumor morphologic features that may reflect underlying mechanisms driving prognosis within MMR groups. TSR was the most robust morphologic feature associated with TTR in p-MMR colon cancers. Extent of inflammatory stroma and N stage were the strongest prognostic features in d-MMR tumors. TIL density was not independently prognostic in either MMR group.

Abstract Background: The prognosis of patients with MM with CNS mets is poor. E6201 is an intravenous (IV) MEK inhibitor with activity against BRAF V600-mutated MM cell lines, including MAPK resistance alteration. A previous phase I trial demonstrated activity of E6201 in BRAF V600E mutated MM with a Maximal Tolerated Dose of 320mg/m2 given IV once a week x 3 weeks q 28 days. 2/23 (8.7%) of patients had a PR, 8/23 (34.8%) had SD. Two patients with MM and brain mets achieved near-CR which led to preclinical studies that demonstrated E6201 is unaffected by P-gp and BCRP transport and achieved higher brain to blood concentration (266%).In this trial, patients with BRAF mutation + MM with brain mets, single agent E6201 given at 320mg/m2 twice weekly x 3 weeks q 28 days was determined to be safe. One patient had CNS SD and a PR in lung mets, and a second patient achieved CNS stable disease and CR in a leg melanotic lesion. The drug was well-tolerated with one reversible AE thrombocytopenia (Gr 2). The final review showed intracranial response of SD in 2/4 (50%) patients and systemic SD in 3/4 (75%) patients. Methods: We are currently accruing to the dose escalation cohort of E6201 with dabrafenib 150 mg twice daily orally (n=up to 22 evaluable patients). E6201 is administered IV at 320mg/m2 twice weekly for 3 weeks every 28 days. Patients must have stage IV melanoma with BRAF mutation with at least one active lesion in the brain. Prior local therapy is allowed if done at least 3 weeks prior to cycle 1. Participants must be on a stable dose of steroids for at least 7 days and have an ECOG &lt;!–=2. The study allows one prior BRAF/MEK inhibitor therapy. The primary objectives are to determine the MTD of E6201 when combined with dabrafenib and the response rate of brain mets. The secondary objectives include duration of response, extracranial response, progression free survival, overall survival, and impact of BRAF mutation subtype and safety of the combination. Clinicaltrials.gov: NCT05388877 References:1.Gampa G, et al. Brain distribution of a novel MEK inhibitor E6201: implications in the treatment of melanoma brain metastases. 2018. Drug Metab Dispos.2.Tibes R et al. Safety, pharmacokinetics, and preliminary efficacy of E6201 in patients with advanced solid tumors, including melanoma: results of a phase I study. 2018. Brit J of Cancer. 3.Babiker Gm et al, E6201, an intravenous MEK1 inhibitor, achieves an exceptional response in BRAF V600E mutated metastatic malignant melanoma with brain metastases. 2018. Inv New Drugs4.Gampa G, Kim M, Cook-Rostie N, Laramy JK, Sarkaria JN, Paradiso L, DePalatis L, Elmquist WF. Brain distribution of a novel MEK inhibitor E6201: Implications in the treatment of melanoma brain metastases. 2018. Drug Met Disp.–&gt; Citation Format: Mahesh Seetharam, Roxana Dronca, Arkadiusz Z. Dudek, Garth Nelson, Matthew Block, Skylar Starling, Amber Baskin, Renee Bradshaw, Courtney Nelson, Kylee Andrews, Alisha Birgin, Cristina Watson, Yiyi Yan, Daruka Mahadevan, Svetomir Markovic, Tom Myers, Linda Paradiso, Hani Babiker. Phase 1 trial of MEK1 inhibitor E6201 plus dabrafenib in patients (pts) with BRAF V600-mutated metastatic melanoma (MM) with central nervous system (CNS) metastases (mets) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr CT157.

TPS3640 Background: Recent data have demonstrated that in locally advanced rectal cancer (LARC), a total neoadjuvant therapy (TNT) approach improves compliance with chemotherapy and increases rates of tumor response compared to neoadjuvant chemoradiation (CRT) alone. They further indicate that the optimal sequencing of TNT involves consolidation (rather than induction) chemotherapy to optimize complete response rates. Data, largely from retrospective studies, have also shown that patients (pts) with clinical complete response (cCR) after neoadjuvant therapy may be managed safely with the watch and wait approach (WW) instead of preemptive total mesorectal resection (TME). However, the optimal consolidation chemotherapy regimen to achieve cCR has not been established, and a randomized clinical trial has not robustly evaluated it as a primary endpoint. Collaborating with a multidisciplinary oncology team and pt groups, we designed this NCI-sponsored study of chemotherapy intensification to address these issues and to drive up cCR rates, to provide opportunity for organ preservation and improve quality of life for pts. Methods: In this Alliance for Clinical Trials in Oncology randomized phase II trial (1:1), up to 312 pts with microsatellite stable LARC, clinical stage T4N0, any T, N+ or T3N0 requiring abdominoperineal resection or coloanal anastomosis and distal margin within 12 cm of anal verge will be enrolled. Stratification factors include tumor stage (T4 vs T1-3), nodal stage (N+ vs N0) and distance from anal verge (0-4; 4-8; 8-12 cm). Pts will be randomized to receive neoadjuvant long course CRT (LCRT) followed by consolidation doublet (mFOLFOX6 or CAPOX) or triplet chemotherapy (mFOLFIRINOX) for 4 months. LCRT in both arms involves 4500 cGy in 25 fractions over 5 weeks (w) + 900 cGy boost in 5 fractions with a fluoropyrimidine (capecitabine preferred). Pts will undergo assessment 8-12 w post-TNT completion for the primary endpoint of cCR per previously validated criteria and recommended WW and surveillance if cCR is achieved or TME if an incomplete response is noted. Secondary objectives include time-to event outcomes (disease-free and overall survival, organ preservation time and time to distant metastasis) and adverse effects. Statistical power, based on cCR, incorporates a one-sided alpha = 0.048 and power = 90% yielding 312 patients (156 per arm). Biospecimens including archival tumor tissue, matched / normal blood samples and serial rectal MRI will be collected for exploratory correlative research. This study, activated in late 2022, is open across the NCTN and is actively recruiting. Support: U10CA180821, U10CA180882, U24 CA196171; https://acknowledgments.alliancefound.org . U10CA180868 (NRG); U10CA180888 (SWOG); Clinicaltrials.gov ID: NCT05610163 Clinical trial information: NCT05610163 .

3542 Background: Solid tumors can be characterized by distinct immune phenotypes based on the level of T cell infiltration in the tumor microenvironment (TME) which may provide prognostic information and also inform strategies to restore the anti-tumor immune response. Immune phenotypes were determined using an artificial intelligence (AI) algorithm in digitized whole-slide images (WSI) of tumors with deficient (d) mismatch repair (MMR) vs proficient (p) MMR. Methods: Stage III colon carcinomas (N = 401; 393 met QC) from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy were analyzed including all available tumors with dMMR (n = 196) and a randomly selected cohort of pMMR tumors (n = 195). Using an AI algorithm (Lunit SCOPE) previously trained on solid tumors, digitized tumors were categorized into three immune phenotypes based on epithelial and stromal TIL data-driven cutpoints in dMMR and pMMR (inflamed: TIL high in epithelium (> upper 25%); excluded: TIL high in stroma (>lower 25%), low in epithelium; and desert: TIL low in epithelium and stroma). Phenotypes were then examined in relationship to disease-free survival (DFS) using Kaplan-Meier methodology. Results: Of the 3 immune phenotypes in dMMR tumors, 25% were inflamed, 50% were immune-excluded, and 25% were immune-desert. Based on univariate results, multivariable modeling was performed incorporating immune phenotype in addition to age, histological grade, N stage, T stage, performance status, treatment arm, BRAF and KRAS status and identified immune phenotypes and N stage to be significantly associated with DFS. Among dMMR tumors, immune desert phenotype was associated with the poorest DFS (Desert: HR adj 1.95, 95%CI (1.01, 3.80); Excluded: HR adj 0.89, 95%CI (0.47, 1.69); Inflamed: ref; p:0.01). When compared to immune desert tumors, immune-excluded tumors had significantly better DFS (HR adj 0.49, 95%CI (0.27, 0.88), p:0.01). At a median follow-up of 60 months, 3-year DFS of patients with dMMR was 71.2% with Immune inflamed, 78.5% with Excluded, and 54.5% with Desert phenotypes. In contrast to dMMR, univariate analyses of data-driven cutpoints in pMMR tumors was not prognostic. Using a different data-driven cutpoint (15%), the revised immune phenotypes remained non-significant for DFS within pMMR tumors. Conclusions: Distinct AI-derived immune phenotypes in the TME were identified that were significantly prognostic in patients with dMMR, but not pMMR colon cancers. A data-driven immune-desert phenotype was identified in dMMR tumors that was associated with significantly poorer survival. Further investigation of the potential predictive utility of these phenotypes for immunotherapy are planned. Support: https://acknowledgments.alliancefound.org . ClinicalTrials.gov Identifier: NCT00079274 .

3527 Background: Advances in deep learning may improve the ability to evaluate and quantify pathological features in solid tumors to improve prediction of patient disease-free survival (DFS). We used an artificial intelligence (AI) algorithm to quantify morphological features in the tumor microenvironment of stage III colon cancers. Methods: We analyzed digitized stage III colon carcinomas (N = 402; 382 met QC) from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy that included all available tumors with dMMR and a randomly selected cohort of pMMR tumors (median follow-up 60 months) [NCCTG N0147; Alliance for Clinical Trials in Oncology]. Fifteen morphological features were extracted using the QuantCRC algorithm that segments images into carcinoma (low-grade, high-grade, signet ring cell), stroma (immature, mature, and inflammatory), mucin, tumor/stroma ratio, tumor budding/poorly differentiated clusters (TB/PDC), necrosis, smooth muscle, fat, and tumor-infiltrating lymphocytes (TILs) and tumor area (mucin, epithelium and TB/PDC). Analysis of AI-derived features with clinical variables, molecular alterations ( BRAF/KRAS), and DFS were examined using Kaplan-Meier methodology and multivariable Cox regression. Results: Among the 15 AI-derived morphological features, the following differed significantly between dMMR (n = 191) and pMMR (n = 189) whereby dMMR tumors had lower mature stroma, but higher inflammatory stroma and tumor, higher tumor grade and increased mucin, TB/PDCs, signet ring cells, and TILs (all p< 0.05). Among dMMR tumors, multivariable analysis revealed that tumor area [mucin, epithelium and TB/PDC] (HR adj 0.45, 95%CI (0.24, 0.84), p:0.01, [Q2/3 vs Q1]) and N stage were the only significant and independent prognostic variables. Among pMMR tumors, multivariable analysis identified that tumor budding/poorly differentiated clusters (TB/PDCs) (HR adj 0.20, 95%CI (0.06, 0.61), p:0.01, [Q1 vs Q4]) was the strongest prognostic variable and the only morphological feature that was significantly associated with DFS along with age, N stage and T stage. Conclusions: Using AI, we can extract and quantify distinct morphological features in tumor sections that differ between dMMR and pMMR and multivariately, can significantly and robustly enhance prognostication within each MMR group. Among pMMR tumors, tumor budding/poorly differentiated clusters was the strongest predictor of DFS. Support: NIH U10CA180821, U10CA180882, U24CA196171, R01 CA210509 (to FAS). Study NCCTG N0147 received funds from Sanofi https://acknowledgments.alliancefound.org . ClinicalTrials.gov Identifier: NCT00079274 Key words Artificial Intelligence; Tumor Microenvironment; Colonic Neoplasms; Disease-free survival.