A New Predictive Scoring System Based on Clinical Data and Computed Tomography Features for Diagnosing EGFR-mutated Lung Adenocarcinoma
Bibliographic record
Abstract
Background: We aimed to develop a new EGFR mutation–predictive scoring system to use in screening for EGFR-mutated lung adenocarcinomas (LACS). Methods: The study enrolled 279 patients with LAC, including 121 patients with EGFR wild-type tumours and 158 with EGFR-mutated tumours. The Student t-test, chi-square test, or Fisher exact test was applied to discriminate clinical and computed tomography (CT) features between the two groups. Using a principal component analysis (PCA) model, we derived predictive coefficients for the presence of EGFR mutation in LAC. Results: The EGFR mutation–predictive score includes sex, smoking history, homogeneity, ground-glass opacity (GGO) on imaging, and the presence of pericardial effusion. The PCA predictive model took this form: sex × 16 + smoking history × 15 + GGO × 12 + pericardial effusion × 10 + emphysema × 11. Model scores ranged from 79 to 147. The area under the receiver operating characteristic curve was 0.752 [95% confidence interval (ci): 0.697 to 0.801] in the LAC population at the optimal cut-off value of 109, and the sensitivity and specificity were 68.4% (95% CI: 60.5% to 75.5%) and 74.4% (95% CI: 65.6% to 81.9%) respectively. Conclusions: The EGFR mutation risk scoring system based on clinical data and CT features is noninvasive and user-friendly. The model appears to frame a positive predictive value and was able to determine the value of repeating a biopsy if tissue is limited.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".