Clinical analysis of EV‐Fingerprint to predict grade group 3 and above prostate cancer and avoid prostate biopsy
Bibliographic record
Abstract
BACKGROUND: There is an unmet clinical need for minimally invasive diagnostic tests to improve the detection of grade group (GG) ≥3 prostate cancer relative to prostate antigen-specific risk calculators. We determined the accuracy of the blood-based extracellular vesicle (EV) biomarker assay (EV Fingerprint test) at the point of a prostate biopsy decision to predict GG ≥3 from GG ≤2 and avoid unnecessary biopsies. METHODS: This study analyzed 415 men referred to urology clinics and scheduled for a prostate biopsy, were recruited to the APCaRI 01 prospective cohort study. The EV machine learning analysis platform was used to generate predictive EV models from microflow data. Logistic regression was then used to analyze the combined EV models and patient clinical data and generate the patients' risk score for GG ≥3 prostate cancer. RESULTS: The EV-Fingerprint test was evaluated using the area under the curve (AUC) in discrimination of GG ≥3 from GG ≤2 and benign disease on initial biopsy. EV-Fingerprint identified GG ≥3 cancer patients with high accuracy (0.81 AUC) at 95% sensitivity and 97% negative predictive value. Using a 7.85% probability cutoff, 95% of men with GG ≥3 would have been recommended a biopsy while avoiding 144 unnecessary biopsies (35%) and missing four GG ≥3 cancers (5%). Conversely, a 5% cutoff would have avoided 31 unnecessary biopsies (7%), missing no GG ≥3 cancers (0%). CONCLUSIONS: EV-Fingerprint accurately predicted GG ≥3 prostate cancer and would have significantly reduced unnecessary prostate biopsies.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| 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".