A novel tool to predict lymph node metastasis in patients with prostate cancer based on clinical and 68Ga-PSMA PET/CT parameters
Bibliographic record
Abstract
Introduction: We sought to develop a model that predicts lymph node invasion (LNI) in patients with intermediate- and high-risk prostate cancer incorporating preoperative clinical and 68Ga-prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) parameters. Methods: A cohort of 413 consecutive patients diagnosed with prostate cancer who underwent 68Ga-PSMA PET/CT prior to radical prostatectomy from 2015–2020 was used to develop and validate the model. The cohort was split into a learning (70%) and a validation group (30%). The former was used to identify clinical and 68Ga-PSMA PET/CT parameters (number and diameter of PET-positive lymph nodes) for prediction of pathologic LNI by applying multivariable logistic regression analyses. The discrimination ability of the model was evaluated using the area under the receiver operating characteristic (ROC) curve and internal validation was performed using the validation cohort. Results: One-hundred sixty-three men (39%) were categorized as high-risk, 168 (41%) as unfavorable-intermediate-risk, and 82 (20%) as favorable-intermediate-risk. Thirty-one patients (7.5%) had LNI on final pathology. All underwent extended lymph node dissection. Clinical stage, the presence of PET-positive lymph nodes, and diameter of the largest PET-positive node were included in the final predictive model. Four different categories were defined for estimating the risk for LNI. Internal validation was completed after applying the four-tire classification on both the learning and validation groups and achieving similar results. The sensitivity, specificity, positive predictive value, and negative predictive value of the model were 97%, 54%, 15%, and 99%, respectively, and area under the ROC curve was 0.906 (95% confidence interval 0.83–0.95, p<0.001). Using a 5% cutoff as a threshold for performing lymph node dissection, only one patient with LNI on final pathology would have been classified erroneously as node negative, while 206 (50%) men would have been spared an unwarranted lymph node dissection. Conclusions: We present a novel prediction model for LNI that incorporates clinical staging and molecular imaging data. Pending further validation, this model may improve the risk stratification and patient selection for lymph node dissection at time of radical prostatectomy.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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) | 0.002 | 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".