Mhgpt: Advancing Mental Health Ai With A Lightweight, Expert Knowledge-infused Transformer For Low-resource Environments

A.I. has shown great potential in the field of mental health, with models like mhGPT and MentalBERT being developed to detect symptoms and evaluate depression from clinical texts. However, creating these models requires substantial computational power and regulations such as HIPAA and GDPR further complicate their use. Researchers have introduced mhGPT, a lightweight generative model trained on mental health-related social media and PubMed articles, which outperformed larger models despite using just 5% of the dataset. This shows that smaller, expert knowledge-infused models can match or exceed the performance of state-of-the-art models in mental health tasks, even with limited computational resources.