A subset of AI where systems analyze data, identify patterns, and improve performance over time without explicit programming. ML is commonly used in predictive analytics and automated diagnostic tools in mental health.

A specialized form of machine learning that uses artificial neural networks to model complex patterns in data. Deep learning is instrumental in processing large-scale datasets, such as neuroimaging or speech analysis, to identify markers of mental health conditions.

AI models trained on extensive text data to understand and generate human-like language. LLMs, such as ChatGPT, Google Gemini, and Med-PaLM, assist in drafting clinical notes, summarizing research, and providing patient education materials.

A field of AI focused on the interaction between computers and human language. In psychiatry, NLP can analyze clinical notes, patient interviews, and social media posts to detect signs of mental health issues.

A type of AI that can create new content, such as text, images, or music, based on its training data. In psychiatry, generative AI can develop therapeutic resources, simulate patient interactions for training, or create personalized patient materials.

Instances where AI models produce incorrect, misleading, or entirely fabricated information that appears plausible. In clinical settings, such inaccuracies can lead to misinformation and must be carefully managed.

Objective, quantifiable physiological and behavioral data collected through digital devices that can indicate health outcomes. In mental health, digital biomarkers might include speech patterns, sleep metrics, or social media usage, offering insights into a patient's psychological state.