Integrating Machine Learning for Prognostic Prediction in Stage I NSCLC by CT Images and Pathological Factors

NCT06737367 | Completed DMC

• 1 other identifier: 2023DZKY-089-01
• Study Type: observational
• Target: 800
• Locations: 1 country
• Sites: 1

Brief Summary

The investigators retrospectively collected the participants with stage I non-small cell lung cancer (NSCLC) patients resected between January 2010 to December 2020 for training and internal validation. The Clinical data, preoperative clinical information, laboratory results and CT images were collected. The investigators also collected the disease-free survival time. On the Deepwise multi-modal research platform, the images were semi-automatically segmented and expanded outward by 3mm to obtain the peritumor tissue. PyRadiomics was used to extract the radiomic features. LASSOcox and rsf were used to select the features. we developed a machine learning-based integrative prognostic model that utilizes radiomic and pathological variables as input using LOOCV framework. And it was further tested on the internal and external cohorts. Discrimination was assessed by using the C-index and area under the receiver operating characteristic curve (AUC), IBS, DCA.

Conditions

Lung Cancer - Non Small Cell

Keywords

NSCLC, ML, DFS

Outcome Measures

Primary Outcomes (1)

• DFS（Disease-free survival）

  DFS was defined as the duration from the date of primary surgery to the first occurrence of recurrence or death from any cause.

  Record from the date of surgery to the date of recurrence or death from any cause, whichever comes first, and assess up to a maximum of 5 years.

Study Arms (2)

training set

Other: CT radiomic analysis

external test set

Other: CT radiomic analysis

Interventions

CT radiomic analysis OTHER

Radiomic features of tumor and peritumor tissue

external test set; training set

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Jinling Hospital, China

You may qualify if:

• patients with stage I NSCLC (ninth AJCC edition) who underwent curative R0 resections between January 2010 and December 2020 -

You may not qualify if:

• absence of enhanced CT
• history of lung cancer or synchronous lung cancers
• follow-up records ≤3 Months
• carcinoma in situ (CIS) or minimally invasive NSCLC
• death within 30 days of surgery
• no pathological slides or reports

Sponsors & Collaborators

• Jinling Hospital, China: lead

Study Sites (1)

Jinling Hospital, China

Nanjing, China

Location

MeSH Terms

Conditions

Carcinoma, Non-Small-Cell Lung

Condition Hierarchy (Ancestors)

Carcinoma, Bronchogenic; Bronchial Neoplasms; Lung Neoplasms; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: December 11, 2024
• First Posted: December 17, 2024
• Study Start: September 1, 2023
• Primary Completion: September 20, 2024
• Study Completion: November 11, 2024
• Last Updated: December 19, 2024

Record last verified: 2024-12

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)