EP07.08: Markers and intelligent agent driven early fetal echocardiography in lieu of the conventional views‐focused scanning method
Bibliographic record
Abstract
To improve the congenital heart disease CHD screening process using dimensionality reduction in the identification of the 26 most common CHDs starting at 11-14week scan. Extracting features from a time-oriented, international registry of prenatal CHDs augmented with cases from the literature, we developed: 1) a database of the natural history of 26 types of CHDs with 112 possible morphologic and biometric markers 2) an Intelligent Agent using markers stratified by a) temporal natural history of the markers b) the strength of association (relevance) of each marker with any other marker across all the CHDs. The database was mostly focused on CHD identification in early gestation and data was obtained primarily by transvaginal sonography. A total of 56 markers fulfilled the diagnostic requirements for 26 CHDs and respectively 48 for 22 CHDs and 42 for 18 CHDs benefiting the most from intrauterine detection. When the first scan is performed by 14wks, the number of subsequent markers participating at the process at any GA was small thanks to constant agent weighing of requirements of markers to be evaluated by comparing strongly relevant features with weakly relevant but not redundant features versus weakly relevant and redundant features and irrelevant features. The result is a significantly reduced diagnostic requirement achievable by sonologists compared with the conventional views based effort. Markers and Intelligent Agent driven fetal cardiac screening allows focusing echocardiography on the most important combination of parameters targeting the earliest and most efficient diagnostic process of CHDs with the minimum effort. Conventional cardiac screening requires the sonologist to capture large amounts of information that may be irrelevant. Mathematically driven scanning includes dynamic instructions streamlining the acquisition of certain views when the yield is low. The use of TVS by 14 wks has the collateral benefit of a significantly reduced, targeted effort at the fetal echo at 18 to 20 wks.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.003 | 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".