Clinical and Imaging Factors for Predicting Lung Micropapillary Adenocarcinoma

Linhui Yang's dataset supports the development of a preoperative predictive model for micropapillary adenocarcinoma (MPA), a high-risk subtype of lung adenocarcinoma. The dataset contains clinical, pathological, and imaging data from patients classified into MPA and non-MPA groups, with disease-free survival as the primary outcome. A nomogram built from the data achieved an area under the ROC curve (AUC) of 0.923, identifying independent risk factors including smoking history, CT-diameter, nodule type, and volume doubling time.

Use Cases

• Developing a preoperative nomogram for MPA risk based on clinical and CT imaging features.
• Identifying independent risk factors (e.g., smoking history, spiculation) associated with poor prognosis in lung adenocarcinoma.
• Validating imaging biomarkers like volume doubling time (VDT) and nodule type (PSN/SN) for cancer subtyping.
• Stratifying patients for clinical management based on predicted disease-free survival (DFS).

Strengths

• The derived predictive nomogram demonstrated high discriminative performance with an AUC of 0.923.
• Dataset is openly licensed under CC-BY-4.0, facilitating reuse and validation.
• Analysis identified specific, quantifiable risk factor thresholds (e.g., CT-diameter ≥22.5 mm, VDT ≤310 days).

Limitations

• Key metadata is missing, including the exact row count and the complete set of column names.
• The dataset's temporal and geographical coverage for the patient cohort is not specified.
• File formats include TIF and DOCX, suggesting possible supplementary documents, but the core data structure is unclear.

Provenance

Source

Linhui Yang

Collection Method

Clinical, pathological, and imaging data were collected from patients diagnosed with lung adenocarcinoma, with follow-up via outpatient visits or telephone interviews.

Freshness

Last updated on 2026-03-23.