JMIR Publications

ABSTRACT

Background:

COVID-19 has become an urgent and serious global public health crisis. Community engagement is the first line of defense in the fight against infectious diseases and general practitioners (GPs) play an important role in it. Disasters and pandemics pose unique challenges for them to deliver health care, including infected risk, shortage of medical resources and a rush of worried or infected people, and et al. However, there is still no suitable mobile management system, which can help GPs collect data, dynamic assess risks, and effective triage or follow-up patients of COVID-19.

Objective:

We designed and developed a dynamic risk assessment decision support system for COVID-19 (DDC19) to assist GPs in collecting data, assessing risk, triaging, managing, and follow-up during the COVID-19 outbreak.

Methods:

Based on the actual scenes and process of patients using health care, we analyzed the key issues that need to be solved and designed the main business flowchart of DDC19. Then, we constructed a COVID-19 dynamic risk stratification model with high recall and clinical interpretability, which was based on multi-class logistic regression algorithm and integrated the patient's retrospective clinical data analysis results, doctors’ experience, and clinical guidelines.

Results:

The DDC19 we developed is composed of three parts: Two main mobile terminal applications (patient end & GP end), database system with its related components and underlying related support model. All mobile terminal devices connected to the back-end data center wirelessly to achieve request sending and data transmission. When we use the three categories of low risk, moderate risk and high risk as labels, and adopt a 10-fold cross-validation method to evaluate and test the COVID-19 dynamic risk stratification model in different scenarios (different dimensions of personal clinical data accessible at the early stage). The data set dimensions are (2243, 15) when only using the data of patients’ demographic information, clinical symptoms and contact history, (2243, 35) when the results of blood tests are added, (2243, 36) after obtaining the CT imaging results of the patient. The average value of the three classification results of Macro-AUC is all above 0.71 in any scenario.

Conclusions:

DCC19 is a mobile decision support system designed and developed to assist GPs in providing dynamic risk assessments for potential patients during the COVID-19 outbreak and the model in it has a good ability to predict risk levels in any scenario it covered.