The Construction of a Digital Intelligence Early Warning System for the Whole Process of Acute Lung Injury in Liver Surgery Based on Cardiopulmonary Interaction Characteristics
Status: Recruiting
Location: See all (4) locations...
Study Type: Observational
SUMMARY
This study aims to develop an explainable machine learning model that takes into account the characteristics of cardiopulmonary interactions. This model will enable early prediction of acute lung injury (ALI) in patients undergoing major liver surgery. The research will create a digital early-warning system for ALI, thereby supporting clinical diagnosis and treatment decisions. This, in turn, should help reduce the incidence and mortality rates associated with ALI.
Eligibility
Participation Requirements
Sex: All
Minimum Age: 18
Healthy Volunteers: f
View:
• Age ≥ 18 years
• Undergoing major liver surgery (including two-segment or more hepatectomy, liver transplantation, etc.)
• Voluntary participation with signed informed consent
Locations
Other Locations
China
Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine，Tsinghua University
RECRUITING
Beijing
Peking University International Hospital
RECRUITING
Beijing
Southwest Hospital, The First Affiliated Hospital of Army Medical University
RECRUITING
Chongqing
Huangdao District People's Hospital of Qingdao
RECRUITING
Qingdao
Contact Information
Primary
Gao Zhifeng, MD
btchgzf@hotmail.com
+8615801249466
Time Frame
Start Date: 2024-11-01
Estimated Completion Date: 2027-11-30
Participants
Target number of participants: 3000
Treatments
Multicentre External Validation Cohort
Consecutive eligible adults who underwent major hepatobiliary or pancreatic surgery or liver transplantation at three independent external centres: Peking University International Hospital (WYA), Southwest Hospital of Army Medical University (WYB), and Huangdao District People's Hospital of Qingdao (WYC). The frozen full perioperative M3 model developed at BTCH was applied using the same predictor definitions, imputation rules, model parameters, and classification threshold, without centre-specific model fitting or recalibration. Centre-specific and pooled validation analyses were performed. This was a retrospective observational cohort; no intervention was assigned and routine clinical care was not altered.
BTCH Development and Validation Cohort
Consecutive eligible adults who underwent major hepatobiliary or pancreatic surgery or liver transplantation at Beijing Tsinghua Changgung Hospital (BTCH) between October 16, 2015, and December 24, 2025. The earliest 70% formed the development cohort and the most recent 30% formed the temporal-validation cohort. Model development was confined to the development cohort, and the frozen models were evaluated in the temporal-validation cohort. This was a retrospective observational study; no intervention was assigned and routine clinical care was not altered.
Related Therapeutic Areas
Sponsors
Collaborators: Peking University International Hospital, The First Affiliated Hospital of Army Medical University (Southwest Hospital), Huangdao District People's Hospital of Qingdao
Leads: Beijing Tsinghua Chang Gung Hospital