Radiation Therapy for Locally Advanced Prostate Cancer: How Do We Treat Patients with cN1 Disease?

Radiotherapy (RT) for high-risk localized prostate cancer (HRLPC) can be controversial in the context of increasing detection of suspicious lymph nodes via advanced imaging techniques. The EORTC 22683 trial initially established RT with androgen deprivation therapy (ADT) as the standard of care for HRLPC, but many patients remain uncured. GETUG-AFU-12 showed that addition of docetaxel and estramustine to ADT improved relapse-free survival but not overall survival. STAMPEDE later demonstrated that abiraterone acetate with ADT and RT significantly improved failure-free survival and overall survival. Ongoing trials such as ENZARAD, ATLAS, DASL-HiCap, and GETUG-P17 ALADDIN are investigating the efficacy of new androgen receptor pathway inhibitors combined with RT and ADT. These studies aim to refine treatment strategies for HRLPC, particularly in the context of advanced imaging and patient upstaging. PATIENT SUMMARY: Addition of newer medications to standard radiation therapy has shown promise in improving survival for men with high-risk prostate cancer. Ongoing studies are testing these options to find the best combination. The aim is to increase the chances of curing prostate cancer, especially as advanced scan techniques are detecting more cases.

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy.

BACKGROUND AND PURPOSE: Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap. METHODS AND MATERIALS: A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended. RESULTS: The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated. CONCLUSION: A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Artificial intelligence in radiotherapy: Current applications and future trends.

Radiation therapy has dramatically changed with the advent of computed tomography and intensity modulation. This added complexity to the workflow but allowed for more precise and reproducible treatment. As a result, these advances required the accurate delineation of many more volumes, raising questions about how to delineate them, in a uniform manner across centers. Then, as computing power improved, reverse planning became possible and three-dimensional dose distributions could be generated. Artificial intelligence offers the opportunity to make such workflow more efficient while increasing practice homogeneity. Many artificial intelligence-based tools are being implemented in routine practice to increase efficiency, reduce workload and improve homogeneity of treatments. Data retrieved from this workflow could be combined with clinical data and omic data to develop predictive tools to support clinical decision-making process. Such predictive tools are at the stage of proof-of-concept and need to be explainatory, prospectively validated, and based on large and multicenter cohorts. Nevertheless, they could bridge the gap to personalized radiation oncology, by personalizing oncologic strategies, dose prescriptions to tumor volumes and dose constraints to organs at risk.

Assessment of bias in scoring of AI-based radiotherapy segmentation and planning studies using modified TRIPOD and PROBAST guidelines as an example.

BACKGROUND AND PURPOSE: Studies investigating the application of Artificial Intelligence (AI) in the field of radiotherapy exhibit substantial variations in terms of quality. The goal of this study was to assess the amount of transparency and bias in scoring articles with a specific focus on AI based segmentation and treatment planning, using modified PROBAST and TRIPOD checklists, in order to provide recommendations for future guideline developers and reviewers. MATERIALS AND METHODS: The TRIPOD and PROBAST checklist items were discussed and modified using a Delphi process. After consensus was reached, 2 groups of 3 co-authors scored 2 articles to evaluate usability and further optimize the adapted checklists. Finally, 10 articles were scored by all co-authors. Fleiss' kappa was calculated to assess the reliability of agreement between observers. RESULTS: Three of the 37 TRIPOD items and 5 of the 32 PROBAST items were deemed irrelevant. General terminology in the items (e.g., multivariable prediction model, predictors) was modified to align with AI-specific terms. After the first scoring round, further improvements of the items were formulated, e.g., by preventing the use of sub-questions or subjective words and adding clarifications on how to score an item. Using the final consensus list to score the 10 articles, only 2 out of the 61 items resulted in a statistically significant kappa of 0.4 or more demonstrating substantial agreement. For 41 items no statistically significant kappa was obtained indicating that the level of agreement among multiple observers is due to chance alone. CONCLUSION: Our study showed low reliability scores with the adapted TRIPOD and PROBAST checklists. Although such checklists have shown great value during development and reporting, this raises concerns about the applicability of such checklists to objectively score scientific articles for AI applications. When developing or revising guidelines, it is essential to consider their applicability to score articles without introducing bias.

Deep learning for automated segmentation in radiotherapy: a narrative review.

The segmentation of organs and structures is a critical component of radiation therapy planning, with manual segmentation being a laborious and time-consuming task. Interobserver variability can also impact the outcomes of radiation therapy. Deep neural networks have recently gained attention for their ability to automate segmentation tasks, with convolutional neural networks (CNNs) being a popular approach. This article provides a descriptive review of the literature on deep learning (DL) techniques for segmentation in radiation therapy planning. This review focuses on five clinical sub-sites and finds that U-net is the most commonly used CNN architecture. The studies using DL for image segmentation were included in brain, head and neck, lung, abdominal, and pelvic cancers. The majority of DL segmentation articles in radiation therapy planning have concentrated on normal tissue structures. N-fold cross-validation was commonly employed, without external validation. This research area is expanding quickly, and standardization of metrics and independent validation are critical to benchmarking and comparing proposed methods.

Pilot applications of GPT-4 in radiation oncology: Summarizing patient symptom intake and targeted chatbot applications.

This study explores using GPT-4 for radiation toxicity monitoring in prostate cancer treatments. Two methods were tested: a summarization method and a chatbot interface. Surveyed radiation oncologists preferred the summarization method for its accuracy and potential for adoption (median rating 8 vs 4, p =.002). Both methods saved time.

A Radiomics Approach to Identify Immunologically Active Tumor in Patients with Head and Neck Squamous Cell Carcinomas.

BACKGROUND: We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC. METHOD: We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitié-Salpêtrière (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort. RESULTS: A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset. CONCLUSIONS AND RELEVANCE: We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.

[Nephron sparing in the management of localized solid renal mass]. / Épargne néphronique dans la prise en charge des tumeurs rénales malignes solides localisées.

Managing a malignant renal tumor requires, first of all, a reflection on the necessity of its treatment. It must consider the renal function, altered at the time of diagnosis in 50% of cases. The treatment method chosen depends on many factors, in particular, the predicted residual renal function, the risk of chronic kidney disease, the need for temporary or long-term dialysis, and overall long-term survival. Other factors include the size, position, and number of tumors and a hereditary tumor background. When a renal-sparing management alternative is available, total nephrectomy should no longer be performed in patients with small malignant renal masses (cT1a). This may consist of surgery (partial nephrectomy or lumpectomy), percutaneous thermo-ablation (by radiofrequency, microwave, or cryotherapy). In patients with limited life expectancy, imaging-based surveillance may be proposed to suggest treatment in case of local progression. Good coordination between urologist, radiologist, nephrologist, and sometimes radiotherapist should allow optimal management of patients with a malignant renal tumor with or without underlying renal failure.

Salvage stereotactic reirradiation for intraprostatic cancer recurrence: A large retrospective study.

INTRODUCTION: Prostate cancer is the most common cancer in men. Thirty to forty-seven percent of patients treated with exclusive radiotherapy for prostate cancer will experience intraprostate recurrence. The use of radiotherapy in stereotactic conditions allows millimetric accuracy in irradiation to the target zone that minimizes the dose to organs at risk. In this study, we evaluated the clinical outcome of prostatic reirradiation with stereotactic body radiation therapy (SBRT) in patients with intraprostatic recurrence initially treated by radiotherapy. METHOD: This single-center retrospective study included 41 patients diagnosed with exclusive local recurrence of prostate cancer after radiotherapy and treatedby stereotactic Cyberknife irradiation. The objective of this study was to assess the efficacy and the safety of stereotactic reirradiation for patients with intraprostatic recurrence initially treated with radiotherapy. RESULTS: Median follow-up was 35 months. The 2-year biochemical relapse-free survival was 72.89%, the 2-year local recurrence free survival was 93.59%, the 2-year local regional recurrence-free survival was 85.24%, and the 2-year metastasis-free survival was to 91.49%. The analysis of toxicities showed a good tolerance of stereotactic irradiation. Urinary and gastro-intestinal adverse events was mostly of grades 1-2 (CTCAEv4). Grade 3 toxicity occurred in one to two patients. CONCLUSION: Stereotactic reirradiation appears effective and well-tolerated for local recurrence of prostate cancer and might allow to delay the introduction of hormonal therapy and its side effects.

Ethical Aspects of Artificial Intelligence in Radiation Oncology.

Radiation oncology is a field that heavily relies on new technology. Data science and artificial intelligence will have an important role in the entire radiotherapy workflow. A new paradigm of routine healthcare data reuse to automate treatments and provide decision support is emerging. This review will discuss the ethical aspects of the use of artificial intelligence (AI) in radiation oncology. More specifically, the review will discuss the evolution of work through the ages, as well as the impact AI will have on it. We will then explain why AI opens a new technical era for the field and we will conclude on the challenges in the years to come.

Stereotactic Body Radiation Therapy for the Management of Hepatocellular Carcinoma: Efficacy and Safety.

This study aimed to describe patient characteristics, treatment efficacy, and safety in patients with hepatocellular carcinoma (HCC) undergoing stereotactic body radiation therapy (SBRT). We retrospectively analyzed data of 318 patients with 375 HCC treated between June 2007 and December 2018. Efficacy (overall survival [OS], relapse-free survival, and local control) and acute and late toxicities were described. The median follow-up period was 70.2 months. Most patients were treated with 45 Gy in three fractions. The median (range) PTV volume was 90.7 (2.6-1067.6) cc. The local control rate at 24 and 60 months was 94% (91-97%) and 94% (91-97%), respectively. Relapse-free survival at 12, 24, and 60 months was 62% (55-67%), 29% (23-36%), and 13% (8-19%), respectively. OS at 12, 24, and 60 months was 72% (95%CI 67-77%), 44% (38-50%), and 11% (7-15%), respectively. Approximately 51% and 38% experienced acute and late toxicity, respectively. Child-Pugh score B-C, high BCLC score, portal thrombosis, high GTV volume, and higher PTV volume reported on total hepatic volume ratio were significantly associated with OS. SBRT is efficient for the management of HCC with a favorable toxicity profile. The outcome is highly related to the natural evolution of the underlying cirrhosis.

Bladder preservation in older adults with muscle-invasive bladder cancer: A retrospective study with concurrent chemotherapy and twice-daily hypofractionated radiotherapy schedule.

INTRODUCTION: Bladder cancer occurs mainly in older adults and surgery is not always possible when there are geriatric conditions and comorbidities. Trimodal treatment (TMT) combining trans-urethral resection of bladder tumour (TURBT) followed by concurrent chemoradiation (CRT) would be a curative alternative in such patients. MATERIALS AND METHODS: All consecutive patients 75 years of age and older with non-metastatic muscle-invasive bladder cancer (MIBC) treated with TMT by Georges Pompidou European Hospital team were retrospectively analysed. Induction CRT combined hypofractionated twice-daily radiotherapy targeting bladder and pelvis to a total dose of 24 Gy (Gy) with concurrent platinum salt and 5-fluorouracil. Consolidation CRT to a total dose of 44 Gy was proposed to patients with biopsy-proven complete response after induction phase and those with persistent tumour underwent salvage cystectomy. We assessed using Kaplan-Meier method overall survival (OS), cancer specific survival (CSS), invasive recurrence-free survival (IRFS), metastasis-free survival (MFS), survival with bladder preserved (SBP), and toxicities. With a Cox model for OS and the Fine Gray method of competing risk for secondary endpoints, we analysed in univariate (u) and multivariate (m) analysis the impact of tumour characteristics and patient profiles: gender, age, age-adjusted Charlson comorbidity index, polypharmacy, and malnutrition. RESULTS: From 1988 to 2017, 85 patients were included. After induction, complete response rate was 83.5%. With a median follow-up of 63 months, 5 year-OS, CSS, IRFS, MFS and SBP were 61.0%, 77.6%, 71%, 82.9%, and 70.2% respectively. A persistent tumour after induction impacted SBP (SHRm 3.61; p = 0.004), CSS (SHRm 3.27; p = 0.023), and MFS (SHRm 3.68; p = 0.018). Late grade 3 urinary and gastrointestinal toxicities were 3.5% and 1.2%. DISCUSSION: We report here the largest series of bladder preservation over 75 years in a curative intent. Outcomes and tolerance in selected older adults compared favourably with surgical series and with CRT studies using classical fractionation.

Development and Validation of an Interpretable Artificial Intelligence Model to Predict 10-Year Prostate Cancer Mortality.

Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.

The Role of Radiomics in Lung Cancer: From Screening to Treatment and Follow-Up.

PURPOSE: Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients' care. METHODS: A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020. RESULTS: We identified several studies at each point of patient's care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications. CONCLUSION: Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.

Outcomes of endoscopic submucosal dissection for early esophageal and gastric cardia adenocarcinomas.

OBJECTIVES: Adenocarcinomas of the esophagus and of the gastric cardia are regarded as a same clinical entity in oncology. For endoscopic resection however, endoscopic mucosal resection is recommended for esophageal adenocarcinoma, while endoscopic submucosal dissection (ESD) is advocated for gastric adenocarcinomas. Our aim was to compare the outcomes of ESD in both types of esophagogastric junction adenocarcinomas. METHODS: Between March 2015 and December 2019, we included all patients who underwent an ESD for early adenocarcinoma of the esophagogastric junction at a French tertiary referral center. Esophageal and gastric cardia adenocarcinomas were compared in terms of clinical, procedural and histological outcomes. RESULTS: 57 esophageal and 19 gastric cardia adenocarcinomas were included in the analysis, for a total of 76 patients. The median (IQR) size of the resections was 40 (40-57.5) and 50 (35-55)mm, p=0.96, respectively. En bloc resection was achieved in 100% and 89% for adenocarcinomas of the esophagus and the gastric cardia, p=0.06. Late adverse events occurred in 14% and 5.3%, respectively, p=0.44, with no severe adverse event. Curative resection rates were 67% and 63% for adenocarcinomas of the esophagus and the gastric cardia, respectively, p=0.89. CONCLUSION: ESD is a safe treatment for T1 adenocarcinomas of the esophagogastric junction, curative in two thirds of the patients, in tumors arising from the esophagus or from the stomach. ESD should be considered for the routine resection of esophageal adenocarcinomas.

Long-term outcomes after bladder-preserving tri-modality therapy for patients with muscle-invasive bladder cancer.

PURPOSE: To evaluate trimodal conservative treatment as an alternative to radical surgery for urothelial muscle-invasive bladder cancer (MIBC). PATIENTS AND METHODS: This retrospective study reported the carcinologic and functional results of patients (pts) presenting a cT2/T3 N0M0 operable MIBC and fit for surgery, treated by a conservative strategy. Treatment consisted of a transurethral resection (TURB) followed by concomitant bi-fractionated split-course radiochemotherapy (RCT) with 5FU-Cisplatine. A control cystoscopy was performed six weeks after the induction RCT (eq45Gy) with systematic biopsies. Patients with complete histologic response achieved RCT protocol. Salvage surgery was proposed to pts with persistent tumor. RESULTS: 313 pts (83% cT2 and 17% cT3) treated between 1988 and 2013 were included, with a median follow-up of 59 months and 67-year mean age. After the induction RCT, the histologic response rate was 83%. After five years, overall, disease-free, and functional bladder-intact survival rates were respectively 69%, 61%, and 69%, significantly better for pts in complete response after induction RCT. Late urinary and digestive toxicities were limited, with respective rates of 4% and 1.5% of grade 3 toxicity. CONCLUSION: Trimodal strategy with RCT after TURB showed interesting functional and oncologic results and should be considered as an alternative to surgery in well-selected pts.

Automated contour propagation of the prostate from pCT to CBCT images via deep unsupervised learning.

PURPOSE: To develop and evaluate a deep unsupervised learning (DUL) framework based on a regional deformable model for automated prostate contour propagation from planning computed tomography (pCT) to cone-beam CT (CBCT). METHODS: We introduce a DUL model to map the prostate contour from pCT to on-treatment CBCT. The DUL framework used a regional deformable model via narrow-band mapping to augment the conventional strategy. Two hundred and fifty-one anonymized CBCT images from prostate cancer patients were retrospectively selected and divided into three sets: 180 were used for training, 12 for validation, and 59 for testing. The testing dataset was divided into two groups. Group 1 contained 50 CBCT volumes, with one physician-generated prostate contour on CBCT image. Group 2 contained nine CBCT images, each including prostate contours delineated by four independent physicians and a consensus contour generated using the STAPLE method. Results were compared between the proposed DUL and physician-generated contours through the Dice similarity coefficients (DSCs), the Hausdorff distances, and the distances of the center-of-mass. RESULTS: The average DSCs between DUL-based prostate contours and reference contours for test data in group 1 and group 2 consensus were 0.83 ± 0.04, and 0.85 ± 0.04, respectively. Correspondingly, the mean center-of-mass distances were 3.52 mm ± 1.15 mm, and 2.98 mm ± 1.42 mm, respectively. CONCLUSIONS: This novel DUL technique can automatically propagate the contour of the prostate from pCT to CBCT. The proposed method shows that highly accurate contour propagation for CBCT-guided adaptive radiotherapy is achievable via the deep learning technique.

Alexithymia and professional quality of life in radiation oncology: The moderator effect of the professional profile.

BACKGROUND AND PURPOSE: Cancer care can be taxing. Alexithymia, a personality construct characterized by difficulties in identifying and describing feeling and emotions, an externally-oriented thinking style and scarcity of imagination and fantasy, is significantly correlated with higher levels of both secondary traumatic stress (STS) and burnout and lower levels of compassion satisfaction in medical professionals in radiation oncology. In this study, we aimed to assess the difference in professional quality of life (QoL) and the association with alexithymia in this multidisciplinary field depending on the specific profession (radiation/clinical oncologist, RO; medical physicist, MP; radiation therapist, RTT). MATERIAL AND METHODS: The study was conducted via an online questionnaire, receiving 1500 submissions between May and October 2018. Alexithymia was assessed via the Toronto Alexithymia Scale (TAS-20) and professional QoL was evaluated using the Professional Quality of Life Scale (ProQoL) version 5. Comparisons between the RO, RTT, and MP groups were performed by ANOVA or MANOVA, followed by Bonferroni corrected ANOVAs for continuous variables, and Pearson's chi-square test for categorical variables. The effect size was determined by calculating partial eta-squared (η2). RESULTS: Profession had a moderator role on the correlation between alexithymia and STS, with RO being at a higher risk than MP and RTT. Further, the results of this study demonstrate the relevant point prevalence of decreased well-being at work even for professional categories such as MP despite the more technical profile and reduced interaction with patients. CONCLUSIONS: This study demonstrates the importance of alexithymia as a factor contributing to decreased professional QoL amongst radiation oncology professionals. Alexithymic ROs are impacted to a higher extent compared to MPs and RTTs by the indirect exposure to patients suffering. It is worth addressing these observations in professional education, aiming to improve QoL for healthcare personnel.

Enhance the Immune Checkpoint Inhibitors Efficacy with Radiotherapy Induced Immunogenic Cell Death: A Comprehensive Review and Latest Developments.

The immunogenic cell death (ICD) is defined as a regulated cell death able to induce an adaptive immunity. It depends on different parameters including sufficient antigenicity, adjuvanticity and favorable microenvironment conditions. Radiation therapy (RT), a pillar of modern cancer treatment, is being used in many tumor types in curative, (neo) adjuvant, as well as metastatic settings. The anti-tumor effects of RT have been traditionally attributed to the mitotic cell death resulting from the DNA damages triggered by the release of reactive oxygen species. Recent evidence suggests that RT may also exert its anti-tumor effect by recruiting tumor-specific immunity. RT is able to induce the release of tumor antigens, to act as an immune adjuvant and thus to synergize with the anti-tumor immunity. The advent of new efficient immunotherapeutic agents, such as immune checkpoint inhibitors (ICI), in multiple tumor types sheds new light on the opportunity of combining RT and ICI. Here, we will describe the biological and radiobiological rationale of the RT-induced ICD. We will then focus on the interest to combine RT and ICI, from bench to bedside, and summarize the clinical data existing with this combination. Finally, RT technical adaptations to optimize the ICD induction will be discussed.

Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine.

OBJECTIVE: The success of treatment planning relies critically on our ability to predict the potential benefit of a therapy. In colorectal cancer (CRC), several nomograms are available to predict different outcomes based on the use of tumour specific features. Our objective is to provide an accurate and explainable prediction of the risk to die within 10 years after CRC diagnosis, by incorporating the tumour features and the patient medical and demographic information. DESIGN: In the prostate, lung, colorectal and ovarian cancer screening (PLCO) Trial, participants (n=154 900) were randomised to screening with flexible sigmoidoscopy, with a repeat screening at 3 or 5 years, or to usual care. We selected patients who were diagnosed with CRC during the follow-up to train a gradient-boosted model to predict the risk to die within 10 years after CRC diagnosis. Using Shapley values, we determined the 20 most relevant features and provided explanation to prediction. RESULTS: During the follow-up, 2359 patients were diagnosed with CRC. Median follow-up was 16.8 years (14.4-18.9) for mortality. In total, 686 patients (29%) died from CRC during the follow-up. The dataset was randomly split into a training (n=1887) and a testing (n=472) dataset. The area under the receiver operating characteristic was 0.84 (±0.04) and accuracy was 0.83 (±0.04) with a 0.5 classification threshold. The model is available online for research use. CONCLUSIONS: We trained and validated a model with prospective data from a large multicentre cohort of patients. The model has high predictive performances at the individual scale. It could be used to discuss treatment strategies.