Background Screening for influenza in primary care is challenging due to the low sensitivity of rapid antigen tests and the lack of proper screening tests. Objective The aim of this study was to develop a machine learning–based screening tool using patient-generated health data (PGHD) obtained from a mobile health (mHealth) app. Methods We trained a deep learning model based on a gated recurrent unit to screen influenza using PGHD, including each patient’s fever pattern and drug administration records. We used meteorological data and app-based surveillance of the weekly number of patients with influenza. We defined a single episode as the set of consecutive days, including the day the user was diagnosed with influenza or another disease. Any record a user entered 24 hours after his or her last record was considered to be the start of a new episode. Each episode contained data on the user’s age, gender, weight, and at least one body temperature record. The total number of episodes was 6657. Of these, there were 3326 episodes within which influenza was diagnosed. We divided these episodes into 80% training sets (2664/3330) and 20% test sets (666/3330). A 5-fold cross-validation was used on the training set. Results We achieved reliable performance with an accuracy of 82%, a sensitivity of 84%, and a specificity of 80% in the test set. After the effect of each input variable was evaluated, app-based surveillance was observed to be the most influential variable. The correlation between the duration of input data and performance was not statistically significant (P=.09). Conclusions These findings suggest that PGHD from an mHealth app could be a complementary tool for influenza screening. In addition, PGHD, along with traditional clinical data, could be used to improve health conditions.

No abstract

As the number of cases for COVID-19 continues to grow unprecedentedly, COVID-19 screening is becoming more important. In this study, we trained machine learning models from the Israel COVID-19 dataset and compared models that used surveillance indices of COVID-19 and those that did not. The AUC scores were 0.8478±0.0037 and 0.8062±0.005 with and without surveillance information, respectively, and there was significant improvement when the surveillance information was used.

BACKGROUND Screening for influenza in primary care is challenging due to the low sensitivity of rapid antigen tests and a lack of proper screening tests. OBJECTIVE We developed a machine learning-based screening tool using patient-generated health data (PGHD) obtained from a mobile application (mHealth app). METHODS We trained a deep learning model based on GRU to identify influenza based on the PGHD, using each patient’s fever pattern, drug administration records, app-based surveillance calculated from the number of weekly influenza users reported through the app, and meteorological data. We defined a single episode as the set of consecutive days containing the day the user was diagnosed with influenza or other diseases. Any record a user entered after 24 hours from his or her last record was considered as belong to a new episode. Each episode must contain user’s age, gender, weight, and at least one body temperature records. The total number of our dataset was 6,657, of which 3,189 were diagnosed with influenza. RESULTS We achieved reliable performance with an accuracy of 82%, sensitivity of 84%, and specificity of 80% in test set. To evaluate the effect of each input variable, we conducted two experiments. One is removing a variable one by one and observe the change of performance, Another is adding the variable one by one to the base features and observe the change of performance. As a result, app-based surveillance turned out to be most influential variable. We also looked at the correlation between the duration of input data and performance. The Spearman’s rank correlation coefficient was 0.09162, which means the association was not significant. CONCLUSIONS These findings suggest that PGHD from a mHealth app could be a complementary tool for influenza screening. Especially, it could be good screening method for infectious disease. In addition, PGHD, along with traditional clinical data, could be used to help improve health conditions.

It is very important to ensure reliable performance of deep learning model for future dataset for healthcare. This is more pronounced in the case of patient generated health data such as patient reported symptoms, which are not collected in a controlled environment. Since there has been a big difference in influenza incidence since the COVID-19 pandemic, we evaluated whether the deep learning model can maintain sufficiently robust performance against these changes. We have collected 226,655 episodes from 110,893 users since June 2020 and tested the influenza screening model, our model showed 87.02% sensitivity and 0.8670 of AUROC. The results of COVID-19 pandemic are comparable to that of before COVID-19 pandemic.