Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage III colon cancer outcomes in PETACC08 study.

OBJECTIVE: Diagnostic tests, such as Immunoscore, predict prognosis in patients with colon cancer. However, additional prognostic markers could be detected on pathological slides using artificial intelligence tools. DESIGN: We have developed a software to detect colon tumour, healthy mucosa, stroma and immune cells on CD3 and CD8 stained slides. The lymphocyte density and surface area were quantified automatically in the tumour core (TC) and invasive margin (IM). Using a LASSO algorithm, DGMate (DiGital tuMor pArameTErs), we detected digital parameters within the tumour cells related to patient outcomes. RESULTS: Within the dataset of 1018 patients, we observed that a poorer relapse-free survival (RFS) was associated with high IM stromal area (HR 5.65; 95% CI 2.34 to 13.67; p<0.0001) and high DGMate (HR 2.72; 95% CI 1.92 to 3.85; p<0.001). Higher CD3+ TC, CD3+ IM and CD8+ TC densities were significantly associated with a longer RFS. Analysis of variance showed that CD3+ TC yielded a similar prognostic value to the classical CD3/CD8 Immunoscore (p=0.44). A combination of the IM stromal area, DGMate and CD3, designated 'DGMuneS', outperformed Immunoscore when used in estimating patients' prognosis (C-index=0.601 vs 0.578, p=0.04) and was independently associated with patient outcomes following Cox multivariate analysis. A predictive nomogram based on DGMuneS and clinical variables identified a group of patients with less than 10% relapse risk and another group with a 50% relapse risk. CONCLUSION: These findings suggest that artificial intelligence can potentially improve patient care by assisting pathologists in better defining stage III colon cancer patients' prognosis.

Dynamic evaluation of circulating tumour cells in patients with advanced gastric and oesogastric junction adenocarcinoma: Prognostic value and early assessment of therapeutic effects.

BACKGROUND: The identification of dynamic biomarkers in advanced gastric and oesogastric junction adenocarcinoma (GOA) could help to tailor strategies for each patient. Enumeration of circulating tumour cells (CTCs) is approved by the US Food and Drug Administration in breast, colon and prostate cancer but is not in advanced GOA. Our study aims to establish the optimal threshold and the clinical significance of CTC count in advanced GOA before and during treatment. METHODS: One hundred six patients with untreated advanced GOA were included in the ancillary study of the PRODIGE 17-ACCORD 20 trial. CTCs were detected in the peripheral blood using the CellSearch system on day 0 (D0) and day 28 (D28). The prognostic value of CTCs at D0 and D28 was analysed by testing several thresholds. RESULTS: At baseline, median CTC count was 1 (range, 0-415). While CTCs ≥1, 2 or 3 at D0 were all significantly associated with worse overall survival (OS) and progression-free survival (PFS), CTCs ≥2 were the optimal threshold, on D0 or D28. CTCs ≥2 at D28 were also predictive of disease control. Taking into account both D0 and D28 CTC count defined 3 groups (low/low, high/low and low-high/high) with significantly different PFS (p = 0.0002) and OS (p = 0.003). CONCLUSION: Quantification of CTCs at baseline and during treatment may be a useful prognostic tool in advanced GOA, as it is associated with worse PFS and OS. A threshold ≥2 CTCs seems to have the best discriminant value. Change in CTC count between baseline and D28 could help to tailor treatment to each individual patient.

Prognostic value of health-related quality of life in patients with metastatic pancreatic adenocarcinoma: a random forest methodology.

PURPOSE: Eastern Cooperative Oncology Group Performance Status (ECOG-PS) is currently an important parameter in the choice of treatment strategy for metastatic pancreatic adenocarcinoma (mPA) patients. However, previous research has shown that patients' self-reported health-related quality of life (HRQOL) scales provided additional prognostic information in homogeneous groups of patients with respect to ECOG-PS. The aim of this study was to identify HRQOL scales with independent prognostic value in mPA and to propose prognostic groups for these patients. METHODS: We analysed data from 98 chemotherapy-naive patients with histologically proven mPA recruited from 2007 to 2011 in the FIRGEM phase II study which aimed to compare the effectiveness of two chemotherapy regimen. HRQOL data were assessed with the European Organization for Research and Treatment of Cancer QLQ-C30 questionnaire. A random survival forest methodology was used to impute missing data and to identify major prognostic factors for overall survival. RESULTS: Baseline HRQOL assessment was completed by 60 % of patients (59/98). Twelve prognostic variables were identified. The three most important prognostic variables were fatigue, appetite loss, and role functioning, followed by three laboratory variables. The model's discriminative power assessed by Harrell's C statistic was 0.65. Fatigue score explained almost all the survival variability. CONCLUSION: HRQOL scores have prognostic value for mPA patients with good ECOG-PS. Moreover, the patient's fatigue, appetite loss, and self-perception of daily activities were more reliable prognostic indicators than clinical and laboratory variables. These HRQOL scores, especially the fatigue symptom, should be urgently included for prognostic assessment of mPA patients (with good ECOG-PS).

Guidelines for time-to-event end-point definitions in trials for pancreatic cancer. Results of the DATECAN initiative (Definition for the Assessment of Time-to-event End-points in CANcer trials).

BACKGROUND: Using potential surrogate end-points for overall survival (OS) such as Disease-Free- (DFS) or Progression-Free Survival (PFS) is increasingly common in randomised controlled trials (RCTs). However, end-points are too often imprecisely defined which largely contributes to a lack of homogeneity across trials, hampering comparison between them. The aim of the DATECAN (Definition for the Assessment of Time-to-event End-points in CANcer trials)-Pancreas project is to provide guidelines for standardised definition of time-to-event end-points in RCTs for pancreatic cancer. METHODS: Time-to-event end-points currently used were identified from a literature review of pancreatic RCT trials (2006-2009). Academic research groups were contacted for participation in order to select clinicians and methodologists to participate in the pilot and scoring groups (>30 experts). A consensus was built after 2 rounds of the modified Delphi formal consensus approach with the Rand scoring methodology (range: 1-9). RESULTS: For pancreatic cancer, 14 time to event end-points and 25 distinct event types applied to two settings (detectable disease and/or no detectable disease) were considered relevant and included in the questionnaire sent to 52 selected experts. Thirty experts answered both scoring rounds. A total of 204 events distributed over the 14 end-points were scored. After the first round, consensus was reached for 25 items; after the second consensus was reached for 156 items; and after the face-to-face meeting for 203 items. CONCLUSION: The formal consensus approach reached the elaboration of guidelines for standardised definitions of time-to-event end-points allowing cross-comparison of RCTs in pancreatic cancer.

Cost-effectiveness modeling of colorectal cancer: computed tomography colonography vs colonoscopy or fecal occult blood tests.

OBJECTIVES: To assess the cost-effectiveness of three colorectal-cancer (CRC) screening strategies in France: fecal-occult-blood tests (FOBT), computed-tomography-colonography (CTC) and optical-colonoscopy (OC). METHODS: Ten-year simulation modeling was used to assess a virtual asymptomatic, average-risk population 50-74 years old. Negative OC was repeated 10 years later, and OC positive for advanced or non-advanced adenoma 3 or 5 years later, respectively. FOBT was repeated biennially. Negative CTC was repeated 5 years later. Positive CTC and FOBT led to triennial OC. Total cost and CRC rate after 10 years for each screening strategy and 0-100% adherence rates with 10% increments were computed. Transition probabilities were programmed using distribution ranges to account for uncertainty parameters. Direct medical costs were estimated using the French national health insurance prices. Probabilistic sensitivity analyses used 5000 Monte Carlo simulations generating model outcomes and standard deviations. RESULTS: For a given adherence rate, CTC screening was always the most effective but not the most cost-effective. FOBT was the least effective but most cost-effective strategy. OC was of intermediate efficacy and the least cost-effective strategy. Without screening, treatment of 123 CRC per 10,000 individuals would cost €3,444,000. For 60% adherence, the respective costs of preventing and treating, respectively 49 and 74 FOBT-detected, 73 and 50 CTC-detected and 63 and 60 OC-detected CRC would be €2,810,000, €6,450,000 and €9,340,000. CONCLUSION: Simulation modeling helped to identify what would be the most effective (CTC) and cost-effective screening (FOBT) strategy in the setting of mass CRC screening in France.