AI predicts patient payments following online doctor visits
When it comes to getting paid patients’ portions for online medical consultations, physicians do better to engage patients attentively and provide high-quality service during the virtual visits than to rely on their standing reputations.
So found researchers who mined data from nearly 1.6 million online medical consultations and used machine learning to predict patients’ subsequent payment behaviors.
Jinglu Jiang, PhD, of Binghamton University in New York and colleagues published their research online Feb. 20 in JMIR Medical Informatics.
“Online healthcare consultation has become increasingly popular and is considered a potential solution to healthcare resource shortages and inefficient resource distribution,” the authors write to introduce their report. “However, many online medical consultation platforms are struggling to attract and retain patients who are willing to pay, and healthcare providers on the platform have the additional challenge of standing out in a crowd of physicians who can provide comparable services.”
Jiang and colleagues used data from the largest online medical consultation platform in China, zeroing in on 1,582,564 consultation records between patient-physician pairs from 2009 to 2018.
Applying several machine learning techniques with four classifiers—logistic regression, decision tree (DT), random forest and gradient boost—they identified key features that best help predict payment.
“[C]ompared with features related to physician reputation, service-related features, such as service delivery quality (eg, consultation dialog intensity and physician response rate), patient source (eg, online vs offline returning patients), and patient involvement (eg, provide social returns and reveal previous treatment), appear to contribute more to the patient’s payment decision,” the authors conclude. “Promoting multiple timely responses in patient-provider interactions is essential to encourage payment.”
Jiang et al. acknowledge their reliance on Chinese data and healthcare economics as limitations in their study design.
“Considering the cultural differences and healthcare regulations, our results may have limited generalizability to other contexts,” they write. “However, the mechanisms and types of interactions that have been found are generic enough to be promoted and managed in different online medical consultation platforms and in different countries. Furthermore, the Chinese context itself is quite large and should be of interest on its own.”
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.