0
0
Disclaimer: This article is for informational purposes only and does not constitute medical, financial, or legal advice. The views expressed are those of the researchers and do not necessarily reflect the positions of any institutions or regulatory bodies.
In an era where telehealth is revolutionizing patient care, the challenge of billing remains a pressing issue. The current time-based billing model often undervalues experienced medical professionals while rewarding inefficiency. Addressing this, researchers at the University of Cincinnati are leveraging artificial intelligence (AI) and electronic health records to create a more equitable billing system.
Dr. Dong-Gil Ko, an associate professor at the Carl H. Lindner College of Business, has been at the forefront of this research. His work, recently published in the Journal of the American Medical Informatics Association, highlights how the current billing model fails to account for medical expertise and clinical judgment.
The Problem with Time-Based Billing
Ohio, like the rest of the United States, uses a time-based metric for telehealth billing. Under this system, medical professionals are compensated based on the duration of their responses to patient inquiries. If a response takes less than five minutes, it is not billable. Longer interactions, however, are compensated at increasing rates.
This model presents a fundamental problem: experienced doctors, who can diagnose and respond quickly due to years of training, may earn less than newly trained residents who take longer to answer the same question. “This creates a systemic issue,” Ko stated. “Medical expertise should not be undervalued simply because an experienced doctor is efficient.”
AI as a Solution
To address these disparities, Ko is collaborating with Dr. Umberto Tachinardi, UC Health’s chief health digital officer, and Dr. Eric J. Warm, an internal medicine physician and researcher at UC’s College of Medicine. Together, they aim to integrate AI into the billing model to consider both response time and medical expertise.
“Doctors undergo years of rigorous medical training to develop specialized knowledge,” Ko explained. “Let’s acknowledge and recognize that by incorporating expertise as a key factor in telehealth billing.”
Using AI-driven machine learning models, Ko’s research has demonstrated promising results in quantifying clinical judgment. The AI system can analyze a doctor’s behavior and decision-making patterns to measure their expertise more accurately, allowing for fairer compensation.
Challenges and Future Prospects
While AI can enhance telehealth efficiency, it also introduces new challenges. Doctors must validate AI-generated responses, requiring additional time and oversight. Without proper compensation, this could lead to increased burnout among healthcare providers.
“At the early stages, validating AI-assisted responses will be critical,” Ko emphasized.
His team is working on developing predictive models that determine whether a patient will be billed before submitting a question. This innovation could improve transparency and patient trust, ensuring that medical consultations remain accessible.
Looking ahead, Ko envisions piloting the AI-driven billing system in health institutions by 2025. His research not only has the potential to transform telehealth billing but also to enhance patient care by fostering a sustainable, fair compensation model for medical professionals.
As telehealth continues to evolve, AI-based innovations like Ko’s work may pave the way for a more balanced and efficient healthcare system—one that values both time and expertise in delivering quality patient care.
