Influenza Screening via Deep Learning Using a Combination of Epidemiological and Patient-Generated Health Data: Development and Validation Study

Abstract

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.

Diagnosing Influenza Infection from Pharyngeal Images using Deep Learning: Machine Learning Approach

“…These studies were also limited because performance outside the health care system of the University of Pittsburgh was unknown. More recently, a Korean study reported an influenza screening system based on deep learning using a combination of epidemiological and patient-generated health data from a mobile health app [22]. However, the gold standard in the study was the clinical diagnosis of influenza at a clinic reported by app users instead of laboratory-based confirmed influenza.…”

“…Recently, several AI-assisted diagnostic prediction models have been proposed for influenza diagnosis [19][20][21][22]. A single-center study from Japan reported a machine learning-based infection screening system incorporating a random tree algorithm that used vital signs [19].…”

“…However, the gold standard in the study was the clinical diagnosis of influenza at a clinic reported by app users instead of laboratorybased confirmed influenza. Notably, none of the previous studies included an assessment of pharyngeal images in their diagnostic prediction models [19][20][21][22]. The novelty of our study is that we have developed the first AI-assisted diagnosis camera for influenza and prospectively validated its performance through a Good Clinical Practice-based clinical trial process.…”

“…However, there may be other useful variables for the prediction of true influenza diagnosis that were not collected in our study. For example, some studies have suggested that the population level trend of influenza outbreaks in an area is useful for predicting an individual patient's influenza infection [22]. Further improvement of the AI-assisted diagnosis camera by including additional variables, in addition to an improvement of the AI models to analyze pharyngeal images, are justified.…”

Relationship Between Medical Questionnaire and Influenza Rapid Test Positivity: Subjective Pretest Probability, “I Think I Have Influenza,” Contributes to the Positivity Rate

“…Xia et al reported an AI-based classifier distinguishing influenza from COVID-19 using chest X-ray images and clinical features with an AUC of 0.9 [ 17 ]. Choo et al reported the usefulness of the patient-generated health data obtained from a mobile health application to develop an AI-based screening tool for influenza [ 18 ]. However, Japan has lagged behind other countries in introducing such mobile health applications based on smartphones or smartwatches [ 19 ].…”