There are three efforts we are working on.

The first effort is to continuously profile the patients screened for SARS-CoV-2 in our health system. Using anonymized data, we watch trends in presenting symptoms of patients, test positivity rates, the age distribution of positive cases and hospitalization rates as well as monitor length of stay. This work as yielded a few insights already such as:

1. An EHR derived summary of presenting symptoms of patients screened for SARS-CoV-2, data at http://tinyurl.com/symptom-profile
2. High co-infection rates in COVID-19, in JAMA
3. Counts of hospitalized patients are a better metric for health system capacity planning for a reopening, in JAMIA
4. Persistent detection of SARS-CoV-2 RNA in patients and healthcare workers with COVID-19, in the Journal of Clinical Virology
5. Occurrence and timing of subsequent SARS-CoV-2 RT-PCR positivity among initially negative patients in Clinical Infectious Diseases
6. Estimating the feasibility of symptom based screening of COVID19, in npj Digital Medicine
7. A predictive tool for identification of SARS-CoV-2 PCR-negative patients using routine test results, in the Journal of Clinical Virology
8. Defining the Features and Duration of Antibody Responses to SARS-CoV- 2 Infection ... Science Immunology

The second effort is to help others in creating better models of the COVID-19 pandemic. Existing predictions of the pandemic are highly uncertain due to lack of accurate input data. We are trying to help in the efforts of multiple scientists to obtain more accurate estimates of the parameters that feed into computer models of the COVID-19 pandemic.

1. There are enough models, we need accurate inputs
2. Estimation of SARS-CoV-2 Infection Prevalence in Santa Clara County
3. A model to forecast regional demand for COVID-19 related hospital beds
4. Poor state reporting hampers pandemic fight, in The Hill
5. How data science can ease the COVID-19 pandemic, in the Brookings Institute's TechStream

The third effort is about answering specific questions by participating in network studies on COVID-19 in the OHDSI collaborative.

1. Deep phenotyping of 34,128 adult patients hospitalised with COVID-19 in an international network study, Protocol and, Shiny App
2. Characterizing Health Associated Risks, and Your Baseline Disease In SARS-COV-2 (CHARYBDIS). Study Package and, Shiny App
3. A networked study investigating the association of ACEis and ARBSs on COVID-19 incidence and complications. Protcol

5 min clip on how we need to improve the quality of the inputs to our COVID-19 models.

A talk about Stanford's data science efforts at COVID-19 and AI: A Virtual Conference by Stanford HAI.