An artificial intelligence model predicts the survival of solid tumour patients from imaging and clinical data.

BACKGROUND: The need for developing new biomarkers is increasing with the emergence of many targeted therapies. Artificial Intelligence (AI) algorithms have shown great promise in the medical imaging field to build predictive models. We developed a prognostic model for solid tumour patients using AI on multimodal data. PATIENTS AND METHODS: Our retrospective study included examinations of patients with seven different cancer types performed between 2003 and 2017 in 17 different hospitals. Radiologists annotated all metastases on baseline computed tomography (CT) and ultrasound (US) images. Imaging features were extracted using AI models and used along with the patients' and treatments' metadata. A Cox regression was fitted to predict prognosis. Performance was assessed on a left-out test set with 1000 bootstraps. RESULTS: The model was built on 436 patients and tested on 196 patients (mean age 59, IQR: 51-6, 411 men out of 616 patients). On the whole, 1147 US images were annotated with lesions delineation, and 632 thorax-abdomen-pelvis CTs (total of 301,975 slices) were fully annotated with a total of 9516 lesions. The developed model reaches an average concordance index of 0.71 (0.67-0.76, 95% CI). Using the median predicted risk as a threshold value, the model is able to significantly (log-rank test P value < 0.001) isolate high-risk patients from low-risk patients (respective median OS of 11 and 31 months) with a hazard ratio of 3.5 (2.4-5.2, 95% CI). CONCLUSION: AI was able to extract prognostic features from imaging data, and along with clinical data, allows an accurate stratification of patients' prognoses.

Natural Language Processing for Patient Selection in Phase I or II Oncology Clinical Trials.

PURPOSE: Early discontinuation affects more than one third of patients enrolled in early-phase oncology clinical trials. Early discontinuation is deleterious both for the patient and for the study, by inflating its duration and associated costs. We aimed at predicting the successful screening and dose-limiting toxicity period completion (SSD) from automatic analysis of consultation reports. MATERIALS AND METHODS: We retrieved the consultation reports of patients included in phase I and/or phase II oncology trials for any tumor type at Gustave Roussy, France. We designed a preprocessing pipeline that transformed free text into numerical vectors and gathered them into semantic clusters. These document-based semantic vectors were then fed into a machine learning model that we trained to output a binary prediction of SSD status. RESULTS: Between September 2012 and July 2020, 56,924 consultation reports were used to build the dictionary and 1,858 phase I or II inclusion reports were used to train (72%), validate (14%), and test (14%) a random forest model. Preprocessing could efficiently cluster words with semantic proximity. On the unseen test cohort of 264 consultation reports, the performances of the model reached: F1 score 0.80, recall 0.81, and area under the curve 0.88. Using this model, we could have reduced the screen fail rate (including dose-limiting toxicity period) from 39.8% to 12.8% (relative risk, 0.322; 95% CI, 0.209 to 0.498; P < .0001) within the test cohort. Most important semantic clusters for predictions comprised words related to hematologic malignancies, anatomopathologic features, and laboratory and imaging interpretation. CONCLUSION: Machine learning with semantic conservation is a promising tool to assist physicians in selecting patients prone to achieve SSD in early-phase oncology clinical trials.

Intercontinental Multidisciplinary Oncology Videoconferencing for Rare and Complex Cancer: An Alternative to Systematic Transfer.

PURPOSE: To report our experience of intercontinental multidisciplinary oncology videoconferencing between the French mainland and South Pacific to discuss rare and/or complex cancer cases. METHODS: On the first and third Friday of each month, all participants connected between 6:30 am and 8:00 am GMT to discuss using a web conference service. RESULTS: Between November 2019 and April 2020, 99 cases concerning 78 patients were discussed. Oncology subspecialties required were sarcoma (n = 36), digestive (n = 29), dermatology (n = 5), gynecology (n = 5), breast (n = 5), urology (n = 5), hematology (n = 5), ENT (n = 3), thoracic (n = 3), thyroid (n = 2), and pediatric (n = 1). Median patient age was 58 years, 41 were female (53%), 37 were male (47%), and 43 had a metastatic disease (55%). Following discussion, 16 patients (21%) were transferred to the French mainland. Reasons for transfer were requirement for complex surgery (n = 11) and need for specialized diagnostic biopsy (n = 5). Fifty-six patients were treated locally, with systemic chemotherapy (n = 36), surveillance (n = 8), surgery (n = 8), radiotherapy (n = 3), or endoscopy (n = 1). Direct benefits for patients treated in their local facility included strategy changes (surveillance or surgery contraindication, n = 9), targeted therapy decision (n = 14), immunotherapy decision (n = 9), and diagnostic or metastatic status corrections (n = 4). Six patients are still awaiting decision. CONCLUSION: Using real-time intercontinental multidisciplinary oncology videoconferencing to discuss complex or rare cancer cases is reliable and effective for decision making. This concept helped to limit to 21% the need for transfers to the mainland.

Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients.

The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach.