MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis.

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar-Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89-0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7-58.7%) and the consensus of all five radiologists (59.3%, P < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.

Comparison of Different Methods for Defining Hyperprogressive Disease in NSCLC.

INTRODUCTION: Hyperprogressive disease (HPD) as a consequence of immune checkpoint inhibitors in NSCLC has been reported in multiple studies. However, inconsistent results in incidence and survival outcomes within studies, together with different assessment methods, have led to increasing controversy regarding the concept of HPD. METHODS: Consecutive patients treated with nivolumab (N = 42) or docetaxel (N = 37) were evaluated. HPD was quantified by applying three different methods (tumor growth rate [TGR], tumor growth kinetics [TGK], and Response Evaluation Criteria in Solid Tumors version 1.1 [RECIST 1.1]). HPD rates were compared between and within both cohorts using the different methods. RESULTS: Using TGR, TGK, and RECIST 1.1, we identified seven (16.7%), seven (16.7%), and six (14.3%) patients with HPD in the nivolumab cohort and three (8.1%), four (10.8%), and five (13.6%) in the docetaxel cohort, respectively. We observed a higher concordance between TGR and TGK (90.1%) compared with RECIST 1.1 (31.3% and 37.5% with TGR and TGK, respectively). We found no significant differences in the overall survival between patients with progressive disease and HPD in either cohort. CONCLUSIONS: TGR and TGK revealed high concordance rates for identifying patients with HPD in NSCLC. The incidence of HPD was numerically higher in patients treated with immune checkpoint inhibitors. Standardization of methods for measuring HPD and its exploration in larger studies are needed to establish its clinical meaning in NSCLC.