Health Disparities through Generative AI Models: A Comparison Study Using A Domain Specific large language model
This work addresses health disparities by evaluating AI models for clinician-patient communication, but it is incremental as it focuses on a comparison study without major breakthroughs.
The study compared domain-specific (SciBERT) and general-purpose (BERT) large language models on health disparity queries, finding that SciBERT failed to differentiate between queries like 'race' alone and 'perpetuates health disparities' using cosine similarity, highlighting limitations in AI for health communication.
Health disparities are differences in health outcomes and access to healthcare between different groups, including racial and ethnic minorities, low-income people, and rural residents. An artificial intelligence (AI) program called large language models (LLMs) can understand and generate human language, improving health communication and reducing health disparities. There are many challenges in using LLMs in human-doctor interaction, including the need for diverse and representative data, privacy concerns, and collaboration between healthcare providers and technology experts. We introduce the comparative investigation of domain-specific large language models such as SciBERT with a multi-purpose LLMs BERT. We used cosine similarity to analyze text queries about health disparities in exam rooms when factors such as race are used alone. Using text queries, SciBERT fails when it doesn't differentiate between queries text: "race" alone and "perpetuates health disparities." We believe clinicians can use generative AI to create a draft response when communicating asynchronously with patients. However, careful attention must be paid to ensure they are developed and implemented ethically and equitably.