JMIR Publications

ABSTRACT

Background:

Artificially Intelligent (AI) Chatbots that deploy natural language processing (NLP) and machine learning (ML) are becoming more common in healthcare to facilitate patient education and outreach, but generative chatbots such as Chat GPT face challenges because they can misinform and hallucinate. Healthcare systems are increasingly interested in using these tools for patient education, access to care and self-management, but need reassurances that AI systems can be secure and credible.

Objective:

To build a secure system that people can use to send messages via SMS with questions about substance use, and where they can screen for substance use disorder. The system will rely on data transfer via third party vendors and will thus require reliable and trustworthy encryption of protected health information (PHI).

Methods:

We describe the process and specifications for building an AI chatbot that users can access to gain information about and screen for substance use disorder (SUD) from Be Well Texas, a clinical provider affiliated with the University of Texas Health Sciences at San Antonio.

Results:

The AI chatbot system utilizes NLP and ML to classify expert curated content related to SUD illustrates how we can comply with best practices in HIPAA compliance in data encryption for data transfer and data at rest while still offering a state-of-the-art system that utilizes dynamic user driven conversation to dialogue about SUD, screen for SUD and access SUD treatment services.

Conclusions:

Recent calls for attention to user friendly design that attend to user rights that honor digital rights and regulations for digital substance use offerings suggests this work is timely and appropriate while still advancing the field of AI. Clinical Trial: Not applicable, this is not a clinical trial.