Validation of the Black-&-White sign to predict intracerebral hematoma expansion in the multi-center PREDICT study cohort
Bibliographic record
Abstract
BACKGROUND: Hematoma expansion (HE) occurs in one-fourth to one-third of patients with acute intracerebral hemorrhage (ICH) and is associated with worse outcomes. The co-localization of non-contrast computed tomography (NCCT) hypodensity and computed tomography angiography (CTA) spot sign, the so-called Black-&-White (B&W) sign, has been shown to have high predictive accuracy for HE in a single-center cohort. In this analysis, we aimed to validate the predictive accuracy of the B&W sign for HE in a multicenter cohort. METHODS: Acute ICH patients from the multicenter, observational PREDICT study (Predicting Hematoma Growth and Outcome in Intracerebral Hemorrhage Using Contrast Bolus CT) were included. Outcomes included HE (⩾6 mL or ⩾33%) and severe HE (⩾12.5 mL or >66%). The association between B&W sign and outcomes was assessed with multivariable regression analyses adjusted for baseline factors. RESULTS: Three hundred four patients were included, with 106 (34.9%) showing HE. The spot sign was present in 76 (25%) patients, the hypodensity sign in 119 (39.1%), and the B&W sign in 29 (9.5%). In the stratum with positive spot signs, patients with B&W signs experienced more frequent HE (79.3% vs 46.8%, p = 0.008), hematoma absolute growth (19.1 mL (interquartile range (IQR) = 6.4-40) vs 3.2 mL (IQR= 0-23.3), p = 0.018), and hematoma relative growth (92% (IQR = 16-151%) vs 24% (IQR= 0-69%), p = 0.038). There was a strong association between B&W sign and HE (adjusted odds ratio (OR) = 7.83 (95% confidence interval (CI) = 2.93-20.91)) and severe HE (adjusted OR = 5.67 (95% CI = 2.41-13.36)). The B&W sign yielded a positive predictive value of 79.3% (IQR = 61.7-90.1) for HE. Inter-rater agreement was moderate (k = 0.54). CONCLUSION: The B&W sign is associated with an increased likelihood of HE and severe HE by approximately eightfold and fivefold, respectively.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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) | 0.001 | 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".