Identifying high risk individuals for targeted lung cancer screening: Independent validation of the PLCO<sub>m2012</sub> risk prediction tool
Bibliographic record
Abstract
Lung cancer screening with computerised tomography holds promise, but optimising the balance of benefits and harms via selection of a high risk population is critical. PLCO m2012 is a logistic regression model based on U.S. data, incorporating sociodemographic and health factors, which predicts 6‐year lung cancer risk among ever‐smokers, and thus may better predict those who might benefit from screening than criteria based solely on age and smoking history. We aimed to validate the performance of PLCO m2012 in predicting lung cancer outcomes in a cohort of Australian smokers. Predicted risk of lung cancer was calculated using PLCO m2012 applied to baseline data from 95,882 ever‐smokers aged ≥45 years in the 45 and Up Study (2006–2009). Predictions were compared to lung cancer outcomes captured to June 2014 via linkage to population‐wide health databases; a total of 1,035 subsequent lung cancer diagnoses were identified. PLCO m2012 had good discrimination (area under the receiver‐operating‐characteristic‐curve; AUC 0.80, 95%CI 0.78–0.81) and excellent calibration (mean and 90th percentiles of absolute risk difference between observed and predicted outcomes: 0.006 and 0.016, respectively). Sensitivity (69.4%, 95%CI, 65.6–73.0%) of the PLCO m2012 criteria in the 55–74 year age group for predicting lung cancers was greater than that using criteria based on ≥30 pack‐years smoking and ≤15 years quit (57.3%, 53.3‐61.3%; p < 0.0001), but specificity was lower (72.0%, 71.7–72.4% versus 75.2%, 74.8–75.6%, respectively; p < 0.0001). Targeting high risk people for lung cancer screening using PLCO m2012 might improve the balance of benefits versus harms, and cost‐effectiveness of lung cancer screening.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".