Abstract P4-09-02: Validation of iPrevent using the prospective family study cohort (ProF-SC)
Bibliographic record
Abstract
Abstract Background: iPrevent (https://www.petermac.org/iprevent) provides women with highly-tailored risk management information after first estimating their breast cancer (BC) risk using the established risk prediction models, IBIS and BOADICEA. iPrevent has an internal switching algorithm that governs which model is used for each woman, depending on her risk factor data (i.e. LCIS/atypical hyperplasia status, BRCA status, and cancer family history). This study assessed the calibration and discriminatory accuracy of the 10-year BC risk estimates provided by iPrevent. Methods: Subjects were 16,574 women in the ProF-SC, aged 18-70 years and without BC or bilateral mastectomy at recruitment. After 10 years follow-up, 655 women (4%) were diagnosed with invasive BC. A “batch mode” for iPrevent is not available, so the iPrevent-assigned cumulative 10-year invasive BC risks were calculated by entering self-reported risk factors at cohort entry into either the IBIS (10,169 women) or BOADICEA (6,405 women) software packages (according to the iPrevent switching algorithm). To assess calibration, the mean iPrevent-assigned risk was compared with the mean 10-year observed invasive BC incidence, using a chi-squared goodness-of-fit statistic for the whole cohort, and by quartiles of risk. To evaluate discriminatory accuracy, the overall area under the receiver operating characteristic curve (AUC) for the development of invasive BC within 10 years was computed. Data were censored at date of invasive or in situ BC diagnosis, bilateral mastectomy, death, loss to follow-up, or at 10 years of follow-up. Results: For the whole cohort, iPrevent assigned risk was well-calibrated – 690 expected BCs (E) 655 observed (O) (E/O=1.05, 95% CI: 0.98-1.14), although for women in the highest risk quartile, i.e. >6% 10-year risk, E/O=1.19, 95% CI: 1.07-1.32. The AUC was 0.70, 95% CI: 0.68-0.72. Conclusions: iPrevent is well calibrated overall and has good discriminatory accuracy for predicting 10-year BC risk, thus justifying its clinical use. Citation Format: Phillips K-A, Liao Y, Collins IM, Buchsbaum R, Weideman P, Bickerstaffe A, MacInnis RJ, kConFab Investigators, Cuzick J, Antoniou A, Andrulis IL, John EM, Daly MB, Buys SS, Hopper JL, Terry MB. Validation of iPrevent using the prospective family study cohort (ProF-SC) [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P4-09-02.
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 | 0.026 | 0.058 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".