Delirium has a high incidence rate and significantly affects patient prognosis. Diagnosis often relies on manual assessment, which is subject to strong subjectivity, high rates of missed diagnosis, and poor stability. This study employs non-contact identification technology based on machine vision analysis to quantitatively analyze characteristic biological feature data such as micro-expressions. It then investigates the correlation between these features and delirium subtypes. By integrating clinical phenotypic data and using machine learning algorithms, a multi-modal early prediction model for delirium is constructed to meet the clinical need for early warning of delirium subtypes and enhance the efficacy of delirium identification.

Inclusion Criteria:

• Age ≥ 18 years, expected ICU stay ≥ 24 hours, and informed consent to participate in this study;

Exclusion Criteria:

• Patients with severe facial trauma/deformities that prevent complete expression acquisition, and patients with a history of emotional problems (such as anxiety, depression, etc.).

Adult patients (≥18 years old) admitted to the ICU of Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, including elderly patients, those post-surgery, with sepsis, and trauma, which are common high-risk populations for delirium.