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.

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.

Clarification of Definitions of Hyperprogressive Disease During Immunotherapy for Non-Small Cell Lung Cancer.

Importance: Hyperprogressive disease (HPD) is an aggressive pattern of progression reported for patients treated with programmed cell death 1 (PD-1)/programmed cell death 1 ligand (PD-L1) inhibitors as a single agent in several studies. However, the use of different definitions of HPD introduces the risk of describing different tumoral behaviors. Objective: To assess the accuracy of each HPD definition to identify the frequency of HPD and the association with poorer outcomes of immune-checkpoint inhibitor (ICI) treatment in patients with advanced non-small cell lung cancer (NSCLC) and to provide an optimized and homogenized definition based on all previous criteria for identifying HPD. Design, Setting, and Participants: This retrospective cohort study included 406 patients with advanced NSCLC treated with PD-1/PD-L1 inhibitors from November 1, 2012, to April 5, 2017, in 8 French institutions. Measurable lesions were defined using the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 criteria on at least 2 computed tomographic scans before the initiation of ICI therapy and 1 computed tomographic scan during treatment. Data were analyzed from November 1, 2012, to August 1, 2019. Exposures: Advanced NSCLC and treatment with PD-1/PD-L1 inhibitors. Main Outcomes and Measures: Association of the definition with the related incidence and the HPD subset constitution and the association between each HPD definition and overall survival. All dynamic indexes used in the previous proposed definitions, such as the tumor growth rate (TGR) or tumor growth kinetics (TGK), were calculated before and during treatment. Results: Among the 406 patients with NSCLC included in the analysis (259 male [63.8%]; median age at start of ICI treatment, 64 [range, 30-91] years), the different definitions resulted in incidences of the HPD phenomenon varying from 5.4% (n = 22; definition based on a progression pace >2-fold and a time to treatment failure of <2 months) to 18.5% (n = 75; definition based on the TGR ratio). The concordance between these different definitions (using the Jaccard similarity index) varied from 33.3% to 69.3%. For every definition, HPD was associated with poorer survival (range of median overall survival, 3.4 [95% CI, 1.9-8.4] to 6.0 [95% CI, 3.7-9.4] months). The difference between TGR before and during therapy (ΔTGR) was the most correlated with poor overall survival with an initial plateau for a larger number of patients and a slower increase, and it had the highest ability to distinguish patients with HPD from those with progressive disease not classified as HPD. In addition, an optimal threshold of ΔTGR of greater than 100 was identified for this distinction. Conclusions and Relevance: The findings of this retrospective cohort study of patients with NSCLC suggest that the previous 5 definitions of HPD were not associated with the same tumor behavior. A new definition, based on ΔTGR of greater than 100, appeared to be associated with the characteristics expected with HPD (increase of the tumor kinetics and poor survival). Additional studies on larger groups of patients are necessary to confirm the accuracy and validate this proposed definition.