Dianbo Liu

TL;DR: In a study of 105 patients with cancer and 536 without, all with confirmed COVID-19, cancer was predictive of more severe disease, with stage IV cancer, hematologic cancer, and lung cancer being associated with worse outcomes.

TL;DR: Examination of province-level variability of the basic reproductive numbers of COVID-19 across China finds that changes in weather alone will not necessarily lead to declines in CO VID-19 case counts without the implementation of extensive public health interventions.

TL;DR: A community-based federated machine learning (CBFL) algorithm was introduced and evaluated on non-IID ICU EMRs and results show that CBFL outperformed the baseline federatedMachine learning algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area under the Precision-Recall Curve (PR AUC) and communication cost between hospitals and the server.

TL;DR: The results indicate that patients with cancer appear more vulnerable to SARS-CoV-2 outbreak, and it is extremely important that this study be disseminated widely to alert clinicians and patients.

TL;DR: In this article, a community-based federated machine learning (CBFL) algorithm was proposed for predicting disease incidence, patient response to treatment, and other healthcare events in non-IID ICU EMRs.