Sign in
Enrolling by invitationNo phase

Multimodal Deep Learning Based on Chest CT and Clinical Features for Predicting the Risk of Postoperative Pulmonary Complications: A Decision Curve Analysis

Key facts

Who runs it
General Hospital of Ningxia Medical University
Where
China1 site in 1 countryChoose a country to see its sites
Trial code
Status
Enrolling by invitation
People taking part
1,500 people, planned
Started
1 Aug 2026
Expected to end
30 Jun 2028
Type of study
Observational
Record updated
18 November 2026

Who can take part

Age
65 years and older
Sex
Women and men
Healthy volunteers
Cannot take part
Show the full registry criteria (2)Hide the full registry criteria

Who can take part

  • Aged ≥65 years; Histopathologically confirmed colorectal cancer undergoing radical resection (either open or laparoscopic surgery); A complete preoperative chest CT performed within four weeks before surgery, including thin-slice reconstruction (slice thickness ≤5 mm; ≤2 mm preferred); Elective surgery

Who cannot take part

  • Prior lobectomy or destroyed lung parenchyma; Severe motion artifacts on chest CT, or a field of view that does not cover the entire lungs; Concomitant thoracic surgery; Missing key clinical data or outcome records that preclude determination of PPCs; Concomitant primary malignancy at another site

Eligibility questionnaire

From the criteria published for this trial, to help you prepare for a talk with your doctor or the study team. We do not tell you a result. Only the study team can say whether you can take part.

  • Age
  • Postoperative pulmonary complications

Where is this trial?

It has sites in one country. Choose a country to see its sites.

About the trial

What the trial wants to find out

Background and Objective Postoperative pulmonary complications (PPCs) are common after elective colorectal surgery and are associated with prolonged hospitalization, increased morbidity, and delayed recovery. Existing PPC prediction tools were mainly developed in thoracic or mixed surgical populations and rely predominantly on clinical variables; preoperative chest CT information remains underused, and a population-specific tool for elderly colorectal cancer patients is still lacking. This study aims to develop and validate a multimodal deep learning model that integrates preoperative chest CT-derived features with multidimensional clinical variables to predict PPCs in patients aged ≥65 years undergoing elective radical colorectal cancer surgery, and to quantify its incremental value and clinical net benefit.

Read full original descriptionShow less

Methods This is a single-center retrospective cohort study. Eligible patients will be assigned to a development window (August 2020-August 2024), split chronologically at a 7∶1∶2 ratio into training, validation, and test sets with five-fold cross-validation, and a locked temporal external validation window (September 2024-September 2026), which will be used only after the final model is fixed. The primary outcome is 30-day composite PPCs defined according to the EPCO criteria; the Melbourne Group Scale will serve as a parallel sensitivity definition. Preoperative clinical variables and chest CT images obtained within four weeks before surgery will be collected. A convolutional neural network imaging branch-or 2D transfer learning based on RadImageNet if the sample size is insufficient-will extract CT deep features, which will be fused with clinical variables at the feature (intermediate) level. Six classifiers, including logistic regression, support vector machine, random forest, XGBoost, LightGBM, and multilayer perceptron, will be tuned within a unified search space. Discrimination (AUC with DeLong test and Bootstrap 95% CI), calibration (calibration curves, Brier score), incremental value (NRI, IDI), and clinical utility (decision curve analysis) will be evaluated against the ARISCAT and GSU-Pulmonary scores, a clinical-only model, and an imaging-only model. Grad-CAM and SHAP will be applied to interpret the model.

Expected Outcome The study is expected to provide an interpretable and deployable preoperative risk stratification tool for elderly patients undergoing colorectal surgery, clarify the incremental contribution of preoperative chest CT information, and define the threshold range in which the model yields net clinical benefit.

Next steps

For your doctor

Doctor ask sheet

A PDF for your doctor: what this trial tests, who can take part, and 2 eligibility questions with room for answers and notes.

Download the PDF

PDF, US Letter, 1 to 2 pages. A4 size

For the study team

Questions to ask the study team

  1. How often do I need to come in, and for how long each time?
  2. Are travel costs paid?
  3. Can I keep my own doctor?
  4. What happens if I want to stop?

Contact the study team: see the registry record → Contacts and Locations

Data and sources

Registry record
Listed on ClinicalTrials.gov.How to verify a trial in the registry
Official title
Development and Validation of a Multimodal Deep Learning Model Combining Preoperative Chest CT-Derived Features and Clinical Variables for Predicting Postoperative Pulmonary Complications in Elderly Patients Undergoing Elective Colorectal Cancer Surgery: A Decision Curve Analysis
Criteria questions
Built from NCT07946081, who can take part
Record updated
18 November 2026