Systems and methods for generating a patient-specific clinical assessment are disclosed. A processor receives patient health data corresponding to a patient. The patient health data is analyzed using a trained large language model (LLM) configured to process the patient health data. Clinical insights are determined based on the analysis of the patient health data using the trained LLM. A set of interactive prompts is generated for a patient interface based on the identified clinical insights. The set of interactive prompts may obtain additional information associated with the patient. A set of patient responses responsive to the generated set of interactive prompts are received. The clinical insights and the set of patient responses are displayed on a clinician interface.