Abstract WP199: Profiles of Cortical White Matter Hyperintensity Burden Measured using the SPOTTY Tool Align with Fazekas Scores in ICH Patients.
Bibliographic record
Abstract
Introduction: White matter hyperintensity (WMH) burden is associated with poor cognitive and functional outcomes after intracerebral hemorrhage (ICH). Grading WMH burden is commonly performed using morphometric scales like Fazeka’s scores, which require training and may be prone to subjectivity. Deep-learning models provide a potential alternative to quantify WMH burden. We compare WMH volumes calculated using the SPOTTY tool with categorical Fazekas scores. Methods: An analytical group of adult (>18) ICH patients was created by randomly sampling from the Registry for Neurological Endpoint Assessment among patients with Ischemic and Hemorrhagic Stroke (REINAH) database, which includes Fazeka’s scores for ICH patients with available MRIs. Total Fazekas scores (Periventricular + Deep) were determined and patients were randomly selected at each level. T2 FLAIR images used for initial Fazekas scoring were retrieved and the previously trained SPOTTY tool was used mask WMH lesions and calculate total lesion volume in cm 3 . Calculated WMH volumes are reported as medians and interquartile ranges, with statistical differences assessed across Total Fazekas score (0-6), severe WMH burden in the periventricular (PV) (Fazeka’s score =3) and deep (Fazeka’s score ≥ 2) white matter, and in-hospital mortality using Mann Whitney Rank Sum and Kruskal Wallis tests of hypothesis. Results: The final cohort included 476 total patients admitted between May 2016 and August 2024. Patients had a median age of 68 [55-77] years and included 236 (49.5%) female and 86 (18.0%) Hispanic patients, with a racial distribution of 289 (60.6%) White, 131 (27.5%) Black, 43 (9.0%) Asian/Native Hawaiian or Pacific Islander, and 14 (2.9%). 147 (30.9%) had severe PV WMH, 251 (52.7%) showed severe deep WMH, and 72 (15.1%) died in-hospital. Significant differences were found between SPOTTY-calculated volumes for non-severe and severe PV WMH (4.40 [1.47-10.15] vs 24.01 [14.99-35.69] p<0.001), non-severe and severe deep WMH (2.51 [0.98-5.72] vs 18.45 [9.47-31.06]; p<0.001) (Figure 1), and across Total Fazekas Score (Figure 2; p<0.001). Patients who died in-hospital similarly had higher SPOTTY WMH volumes than those who did not (12.51 [3.84-24.43] vs 7.85 [2.31-19.29]; p=0.032). Discussion: The SPOTTY tool provides an avenue for automatic assessment of WMH burden in ICH patients.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".