Use of prenatal ultrasound findings to predict postnatal outcome in fetuses with lower urinary tract obstruction
Bibliographic record
Abstract
OBJECTIVE: Lower urinary tract obstruction (LUTO) is a chronic condition with a spectrum of outcomes. It is usually suspected prenatally based on ultrasound features (USFs). Given the unknown postnatal trajectory and the potential for significant morbidity and mortality, many families choose termination of pregnancy (TOP), often based on USFs alone. Herein, we sought to develop a tool that can be used to predict postnatal outcome based on combinations of USFs, which can aid prenatal counseling and parental decision-making. METHODS: This was a retrospective study of cases with suspected fetal LUTO that were seen at a high-risk fetal center and a tertiary pediatric center in Canada. Data were collected on USFs, prenatal/postnatal death and postnatal need for transplantation and/or dialysis. USFs from pregnancies with a gestational age of 13-26 weeks on initial ultrasound at the high-risk fetal center that underwent TOP were collected and matched to fetuses with comparable prenatal USFs that were not terminated, which had a known postnatal outcome, to build a random forest model. The random forest model was fitted for each outcome (death, dialysis or transplantation) and tested for accuracy using leave-one-out cross-validation. Each predictor was assessed independently with combined importance when accounting for other predictors. The model was used to predict the most likely postnatal outcomes for cases of TOP had the pregnancy been continued. RESULTS: USF data from 85 cases of TOP and 125 cases of expectantly managed pregnancy with prenatally suspected LUTO were retrieved. For expectantly managed cases, there was a median follow-up duration of 5.7 (interquartile range, 0.2-14.5) years among the liveborn infants. There were 14 prenatal and 22 postnatal deaths in the expectantly managed cohort. The random forest model demonstrated the highest predictive accuracy for transplantation (77% accuracy, 50% sensitivity, 80% specificity), followed by death (72% accuracy, 83% sensitivity, 67% specificity) and dialysis (71% accuracy, 70% sensitivity, 71% specificity). For the TOP cohort, had the pregnancies been continued, the model predicted transplantation and dialysis in 21/85 (25%) and 37/85 (44%) cases, respectively; pre- or postnatal death was predicted in 69/85 (81%) cases. CONCLUSIONS: Our data suggest that it is possible to predict death and postnatal transplantation and/or dialysis from USFs in fetuses with suspected LUTO with acceptable accuracy. Predictive accuracy will improve with continued follow-up of more patients, enabling more personalized prenatal counseling and more informed decision-making for families. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.
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 | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.001 | 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".