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.
Study Type
OBSERVATIONAL
Enrollment
795
Number of participants with delirium as assessed by DSM-5
Zero is equivalent to no delirium and a high score means a higher occurrence of delirium
Time frame: 7th day after ICU admission
Accuracy
Zero is equivalent to the minimum accuracy, while a value of 1 represents perfect accuracy
Time frame: 7th day after ICU admission
Precision
The proportion of truly positive samples among those predicted as positive; the closer the score is to 1, the higher the precision
Time frame: 7th day after ICU admission
Recall
The proportion of truly positive samples that are correctly predicted; the closer the score is to 1, the higher the diagnostic sensitivity
Time frame: 7th day after ICU admission
F1-score
The harmonic mean of precision and recall; the higher the score, the better the diagnostic performance of the model
Time frame: 7th day after ICU admission
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.