Abstract

AI virtual assistants have significant potential to alleviate the pressure on overly burdened healthcare systems by enabling patients to self-assess their symptoms and to seek further care when appropriate. For these systems to make a meaningful contribution to healthcare globally, they must be trusted by patients and healthcare professionals alike, and service the needs of patients in diverse regions and segments of the population. We developed an AI virtual assistant which provides patients with triage and diagnostic information. Crucially, the system is based on a generative model, which allows for relatively straightforward re-parameterization to reflect local disease and risk factor burden in diverse regions and population segments. This is an appealing property, particularly when considering the potential of AI systems to improve the provision of healthcare on a global scale in many regions and for both developing and developed countries. We performed a prospective validation study of the accuracy and safety of the AI system and human doctors. Importantly, we assessed the accuracy and safety of both the AI and human doctors independently against identical clinical cases and, unlike previous studies, also accounted for the information gathering process of both agents. Overall, we found that the AI system is able to provide patients with triage and diagnostic information with a level of clinical accuracy and safety comparable to that of human doctors. Through this approach and study, we hope to start building trust in AI-powered systems by directly comparing their performance to human doctors, who do not always agree with each other on the cause of patients’ symptoms or the most appropriate triage recommendation.

Highlights

  • AI virtual assistants are a convenient and valuable resource for users to better understand the underlying cause(s) of their symptoms and to receive advice on the most appropriate point of care (Millenson et al, 2018; Rowland et al, 2020)

  • A comprehensive description of the system that powers the Babylon Triage and Diagnostic System is outside of the scope of this paper, we provide a brief summary of this system by way of background

  • We found that the Babylon Triage and Diagnostic System provided a safer triage recommendation than doctors on average (97.0% vs. 93.1%), at the expense of a marginally lower appropriateness (90.0% vs. 90.5%; see Table 2)

Read more

Summary

Introduction

AI virtual assistants (symptom checkers) are a convenient and valuable resource for users to better understand the underlying cause(s) of their symptoms and to receive advice on the most appropriate point of care (Millenson et al, 2018; Rowland et al, 2020). A patient may want to know whether their symptoms require treatment or further investigation; this is medical triage and involves directing patients to the most suitable location within an appropriate time frame. The appropriate action depends on the nature and urgency of the symptoms or their underlying cause, which might require further investigation. Patients may want to understand the conditions that might be responsible for their symptoms. This corresponds to diagnosis or “differential diagnosis” and is typically performed by an experienced medical practitioner

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call