JMIR Publications

ABSTRACT

Background:

Asynchronous telemedicine has emerged as a crucial component of multi-channel healthcare delivery, where effective physician-patient communication is known to drive satisfaction. However, the effectiveness of communication features remains poorly understood. Prior research has relied heavily on subjective surveys or small-scale simulations, failing to link communication features to objective outcomes. Elucidating the distinct utility of these modalities is critical for optimizing physician engagement tactics and establishing evidence-based quality indicators to enhance the patient experience.

Objective:

This study aimed to bridge this gap by leveraging a large scale, real-world dataset to quantify the impact of physicians’ communication features, including response modalities, length, and sequence on patient repurchase behavior and review scores within a high autonomy healthcare setting.

Methods:

This retrospective cross-sectional study analyzed 304,337 paid, patient-initiated virtual visits from a Chinese academic medical center (2021-2023), which included 823,135 physician responses. The sample was selected after excluding free consultations, team-based response and outlier data. The key exposure was the modality of physician responses, response length, and response sequence. Outcomes included patient loyalty and satisfaction. Loyalty was operationalized as follow-up visits within 6-month, with a 30-day exclusion period applied to same-physician (fv1) and same-department (fv2) revisits to filter out clinical necessity, but not to hospital-wide revisits (fv3). Satisfaction was measured by the review scores. We used probit and ordinary least squares (OLS) regressions to assess the impact of communication features.

Results:

Among all asynchronous visits, regarding patient loyalty, audio-only visits were associated with the lowest fv1, with an average marginal effect (AME) of -0.030 (95% CI -0.043 to -0.016, P<.001), which translated to 30.9% (0.030/0.097) reduction compared to text-only visits. Regarding patient satisfaction, audio messages were associated with significantly increased likelihood of patients providing reviews, with AME of 0.041 (95% CI 0.006-0.076, P=.02), but they did not affect review scores after adjusting for inverse Mills ratios. An increase in the number of text and audio replies was associated with improved fv1, with AMEs of 0.009 (95% CI 0.006-0.011, P<.001) and 0.007 (95% CI -0.000 to 0.016, P=.06), respectively. Visits that began with a sub-5-second audio response and ended with text had significantly higher fv1 than text-only visits, with AME of 0.069 (95% CI 0.018-0.120, P=.008). The same patterns hold for fv2 and fv3. Coefficients with P value smaller than α=0.05 are regarded as significant.

Conclusions:

Physicians’ communication practices in asynchronous telemedicine significantly influence patient loyalty and satisfaction. Different from prior survey-based research, this study is the first to leverage large-scale real-world data to systematically examine physician communication features within a clinical setting. Our work identifies an optimal hybrid strategy that balances human connection with the clarity of text. These findings provide data-driven evidence to guide clinicians and policymakers in designing high-quality digital health services.