An observational study in Delirium and Artificial Intelligence (AI), sponsored by Beijing Tiantan Hospital. Recruiting at 1 site in China. Open to participants aged 18 Years to 80 Years. Per ClinicalTrials.gov, last updated 2025-08-22.
Sponsored by Beijing Tiantan Hospital · Observational
This research project employs machine learning algorithms integrated with computer vision, image processing, and pattern recognition technologies to perform digital analysis of facial expression behaviors in neurocritical care patients with delirium. By constructing multidimensional high-level features of delirium, the investigators have established a classification model based on behavioral. The primary objective of this study is to address the critical challenge of achieving precise and efficient delirium diagnosis in neurologically critically ill patients through automated facial expression behavior recognition.
This study is a prospective cohort study approved by the Ethics Committee of Beijing Tiantan Hospital. It aims to support the accurate and efficient diagnosis of delirium in neurocritical patients through a facial expression recognition system. A mobile application was developed for this study, collaboratively designed by senior clinicians and engineers from the Institute of Computing Technology, Chinese Academy of Sciences. The application is based on a stimulus paradigm designed using CAM-ICU (Confusion Assessment Method for the Intensive Care Unit) questions to record dynamic facial videos of neurocritical patients following delirium evaluation based on the DSM-V criteria.
Patients were assessed for delirium and facial expression behavior data were collected twice daily during ICU admission, in two time slots: 8:00-10:00 AM and 8:00-10:00 PM, following the study's inclusion and exclusion criteria. A trained and experienced specialist used the gold standard DSM-V to diagnose delirium. Within five minutes after completing the assessment, dynamic facial behavior video data were collected to prepare images for subsequent model development.
Various image preprocessing and data augmentation techniques were employed to prepare the images for the VGG16 model. These techniques are standard for running convolutional neural network (CNN) models. Using the "preprocess_input"function from the Keras VGGFace module, the investigators standardized image color and size to ensure that each image met the expected input requirements for model training. For data augmentation, the investigators applied TensorFlow's "ImageDataGenerator" function to perform horizontal flipping, rotation, scaling, width and height shifting, and shearing. These augmentation techniques created a more diverse dataset, helping to prevent overfitting and improving the model's generalizability to new faces.
The investigators developed a binary classification model to identify delirium using a CNN with a pretrained backbone. The VGG16 model, based on deep learning, was adopted, leveraging transfer learning from VGGFace2, which possesses pre-existing facial feature recognition capabilities. Transfer learning allowed us to utilize prior knowledge to detect features more quickly, accurately, and with lower computational cost. The VGGFace2 model was employed for training.
Model performance was evaluated through internal validation at Beijing Tiantan Hospital and external validation at Guiyang Second People's Hospital, with metrics including accuracy, sensitivity, specificity, and F1 score. Additionally, to address the "black box" issue of machine learning, occlusion heatmap techniques were used to identify the most critical facial regions for delirium assessment, with the results visualized on a virtual face.
This model aims to support precise and efficient identification of delirium in neurocritical care units.
1,057 studies on the registry are indexed under Delirium; 238 are open to participants now.
This study's planned enrollment of 1,000 is above the median of 200 across 418 observational studies indexed under Delirium.
Browse Delirium studies →Beijing Tiantan Hospital is the lead sponsor of 465 studies on the registry; 282 are open to participants now.
Counted across the registry records on this site, refreshed daily.
This study selects neurocritical patients as the population and collects facial expression data from both delirium and non-delirium patients.
Exclusion Criteria:
For neurocritical non-delirium patients, the investigators record facial expression videos, which are used during model development to compare with the facial expressions of delirium patients.
The investigators record facial expression videos of neurocritical delirium patients and perform frame sampling on the videos to analyze and extract the facial expression features specific to delirium. Based on this analysis, the investigators develop a model for delirium recognition in neurocritical patients.
Accuracy of the delirium prediction model
The accuracy of the delirium prediction model will be calculated as the proportion of correct predictions among total predictions.
Time frame: Through study completion, an average of 1 year
Sensitivity of the delirium prediction model
Sensitivity (true positive rate) will be assessed as the proportion of actual delirium cases correctly identified by the model.
Time frame: Through study completion, an average of 1 year
Specificity of the delirium prediction model
Specificity (true negative rate) will be calculated as the proportion of non-delirium cases correctly identified by the model.
Time frame: Through study completion, an average of 1 year
F1 Score of the delirium prediction model
The F1 score, the harmonic mean of precision and recall, will be used to evaluate the balance between sensitivity and specificity.
Time frame: Through study completion, an average of 1 year
AUC of the facial feature curve for delirium patients
The area under the curve (AUC) of the receiver operating characteristic (ROC) curve derived from facial features will be used to assess the discriminatory performance of the model.
Time frame: Through study completion, an average of 1 year
Documents are hosted by the registry — open the source record to download them.
Plan to share: No — This study involves collecting facial information of patients, which pertains to their privacy. To protect participants' confidentiality, all data will be uniformly destroyed after the study is completed. The investigators will not share or disclose patients' information to other researchers.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Beijing Tiantan Hospital