Due to the characteristics of COVID-19, the epidemic develops rapidly and overwhelms health service systems worldwide. Many patients suffer from life-threatening systemic problems and need to be carefully monitored in ICUs. An intelligent prognosis can assist physicians to take an early intervention, prevent adverse outcomes, and optimize the medical resource allocation, thus it is urgently needed especially in this ongoing global pandemic crisis. However, in the early stage of the epidemic outbreak, the data available for analysis is limited due to the lack of effective diagnostic mechanisms, the rarity of the cases, and privacy concerns. In this paper, we propose a distilled transfer learning framework, DistCare, which leverages the existing publicly available online electronic medical records to enhance the prognosis for inpatients with emerging infectious diseases. It learns to embed the COVID-19-related medical features based on massive existing EMR data. The transferred parameters are further trained to imitate the teacher models representation behavior based on distillation, which em-beds the health status comprehensively in the source dataset. We conduct the length-of-stay prediction experiments for patients in ICUs on a real-world COVID-19 dataset. The experiment results indicate that our proposed model consistently outperforms competitive baseline methods, especially when the data is insufficient. In order to further verify the scalability of DistCare to deal with different clinical tasks on different EMR datasets, we conduct an additional mortality prediction experiment on multiple end-stage renal disease datasets. The extensive experiments demonstrate that DistCare can significantly benefit the prognosis for emerging pandemics and other diseases with limited EMR. As a proof-of-concept to demonstrate that DistCare can assist the prognosis, we also implement DistCare as a real-world AI-Doctor interaction system that can reveal the patient’s health trajectory for the prognosis. We release our code and the AI-Doctor interaction system anonymously at GitHub https://github.com/anonymous201902/DistCare.

The Web Conference is announcing latest news and developments biweekly or on a monthly basis. We respect The General Data Protection Regulation 2016/679.