JMIR Publications

ABSTRACT

Background:

With the advent of electronic storage of medical records and the Internet, patients can access online medical records. This has facilitated doctor–patient communication and built trust between them.

Objective:

Based on demographic and individual behavioral characteristics, this study explores the predictors of and the reasons for online medical record nonuse.

Methods:

Data were collected from the National Cancer Institute’s 2019–2020 Health Information National Trends Survey. First, based on the data-rich environment, the chi-square test (categorical variable) and two-tailed t-tests (continuous variable) were performed on the response variables and the variables in the questionnaire. According to the test results, the variables were initially screened and those that passed the test were selected. Second, the samples with missing values in the initially screened variables were deleted. Finally, the data obtained were modeled using five machine learning algorithms, namely logistic regression, automatic generalized linear model, automatic random forests, automatic deep neural networks, and automatic gradient boosting machine, to identify and investigate factors affecting online medical record nonuse.

Results:

Automatic machine learning methods have a high prediction accuracy. Based on the validation dataset fitting performance, the optimal model was auto-random forests with an AUC value of 88.90%. Using the five models, 28 variables were identified as crucial predictors of nonuse of online medical records. They consisted of six sociodemographic variables and 22 variables related to individual lifestyles and behavioral habits.

Conclusions:

When monitoring online medical record usage trends, research should focus on social factors such as age, education, BMI, marital status, as well as personal lifestyle and behavioral habits, including smoking, use of electronic devices and Internet, patients’ personal health status, and their level of health concern wait. The use of electronic medical records can be promoted to specific groups of people in a targeted manner, so that the usefulness of medical records can be promoted in more groups of people.