In the paper, “The Interplay Between Online Reviews and Physician Demand: An Empirical Investigation,” NYU Stern Vice Dean of Faculty Mor Armony and Professor Anindya Ghose and co-author Yuqian Xu (Stern PhD ’17; University of Illinois at Urbana-Champaign) used text-mining and choice-modeling techniques and found that bedside manner, accuracy of diagnosis, waiting time and service time disproportionately affect demand for patient care.

Key takeaways include:

• Patients rely on text reviews of physician service to make their choices
• The paper identified the seven most frequently mentioned service features of physicians and doctors, among patients through text mining, among which (1) bedside manner, (2) accuracy of diagnosis, (3) waiting time, and (4) service time had a statistically significant relationship with patient choices
• Improving predictive models of patient choices can help doctors more efficiently manage the operational aspects of their practice (e.g., service time, waiting time, etc.)
• Using text-mining of online reviews to understand which features affect patient satisfaction can help promote better long-term relationships between patients and healthcare providers

On a broader scale, the co-authors anticipate that this type of predictive modeling of patient choice will play an increasingly important role in the healthcare industry: “With the uptick in tele-health due to Covid-19, individuals are using digital platforms to choose doctors and healthcare providers more than ever before. Understanding the role that those reviews play in patient choice will be critical for doctors who want to thrive in today’s rapidly changing healthcare landscape.”

This research is forthcoming in Management Science.