Incorporating axillary-lateral thoracic vessel juncture dosimetric variables improves model for predicting lymphedema in patients with breast cancer: A validation analysis
Bibliographic record
Abstract
Background A relationship between the axillary-lateral thoracic vessel juncture (ALTJ) dose and lymphedema rate has been reported in patients with breast cancer. The purpose of this study was to validate this relationship and explore whether incorporation of the ALTJ dose-distribution parameters improves the prediction model's accuracy. Methods A total of 1,449 women with breast cancer who were treated with multimodal therapies from two institutions were analyzed. We categorized regional nodal irradiation (RNI) as limited RNI, which excluded level I/II, vs extensive RNI, which included level I/II. The ALTJ was delineated retrospectively, and dosimetric and clinical parameters were analyzed to determine the accuracy of predicting the development of lymphedema. Decision tree and random forest algorithms were used to construct the prediction models of the obtained dataset. We used Harrell's C-index to assess discrimination. Results The median follow-up time was 77.3 months, and the 5-year lymphedema rate was 6.8 %. According to the decision tree analysis, the lowest lymphedema rate (5-year, 1.2 %) was observed in patients with ≤ six removed lymph nodes and ≤ 66 % ALTJ V 35Gy . The highest lymphedema rate was observed in patients with > 15 removed lymph nodes and an ALTJ maximum dose (D max ) of > 53 Gy (5-year, 71.4 %). Patients with > 15 removed lymph nodes and an ALTJ D max ≤ 53 Gy had the second highest rate (5-year, 21.5 %). All other patients had relatively minor differences, with a rate of 9.5 % at 5 years. Random forest analysis revealed that the model's C-index increased from 0.84 to 0.90 if dosimetric parameters were included instead of RNI ( P <.001). Conclusion The prognostic value of ALTJ for lymphedema was externally validated. The estimation of lymphedema risk based on individual dose-distribution parameters of the ALTJ seemed more reliable than that based on the conventional RNI field design.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".