Multimodal Artificial Intelligence for Detecting the Psychological State of Cancer Patients

Artificial intelligence (AI) technology is expected to assist clinical doctors in promptly identifying cancer patients at risk of developing psychological issues and to develop preemptive management plans, thereby enhancing their quality of life. Computer vision technology can directly capture and extract subtle changes in skin color from facial images in videos, assess heart rate using signal processing algorithms, and also extract facial expressions to evaluate psychological conditions through facial expression change signal processing algorithms. The accuracy rate can exceed 88%. By leveraging the capabilities of computer vision technology, it can accurately capture subtle movements and expressions of the human body, thereby understanding the internal psychological state and obtaining relevant psychological information

Enrolling by Invitation

Interested in participating?

Request Info

Key information

Conditions

Neoplasm Neoplasms

Age range

18 year and older

Sex eligibility

All sexes

Study type

Observational

Primary location

Chinese PLA Hospital

Beijing, China

Who can participate

Healthy volunteers accepted: No

Only the study team can determine whether someone qualifies for participation.

nclusion criteria: 1. Age ≥18 years old; 2. Patients with tumors diagnosed by magnetic resonance imaging or contrast-enhanced ultrasound; 3. The patient has self-awareness and is able to cooperate with the research. 4. Patients who voluntarily undergo psychological assessment tests Exclusion criteria: 1. Age ≤18 years old; 2. Not diagnosed as a tumor patient; 3. Lack of autonomy and inability to conduct cooperative research.

Treatment and study plan

Primary outcomes

Area Under the Receiver Operating Characteristic Curve (AUC) of the Multimodal Machine Learning Model for Anxiety and Depression Screening

Time frame: Data collected at two time points: 1 day pre-operatively and at ≤7 days post-operatively or at discharge, whichever came first

The AUC quantifies the overall discriminative ability of the final multimodal machine learning model to distinguish between patients with positive vs. negative anxiety/depression status. The AUC will be calculated on an independent test set that is strictly separated from the training and validation sets and will not be used in any model training or hyperparameter tuning.

Sponsors and collaborators

Lead sponsor

Chinese PLA General Hospital

Other

Registry information

Acronym: AIPSY

Important dates

Study start: 2021
Primary completion: 2028
Study completion: 2028
First posted: Aug 7, 2026
Registry last updated: Aug 7, 2026

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Published trials that share one or more normalized conditions with this study.

Enrolling by Invitation