Placenta-pulmonary coupling-guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy
Open accessThe DOI matches its Crossref record; 21 of the 24 references it cites were found in a registry or an index; 13 of the 28 sources its claims cite were checked for support.
Abstract
Background and aim: Deep learning has improved medical image analysis but often produces opaque decisions and correlation-driven predictions that may diverge from clinical reasoning. We hypothesize that a physiology-informed hybrid framework, which explicitly models placenta-pulmonary interactions and integrates multimodal data, could provide interpretable and reliable guidance for assessing fetal lung maturity (FLM) and optimizing antenatal glucocorticoids (GCs). Materials and methods: In a prospective cohort study involving 320 pregnancies-including 160 with hypertensive disorders of pregnancy (HDP)-each with weekly acquisitions from 28 to 36 weeks, we combined 2D/3D ultrasound, shear-wave elastography, Doppler, and maternal plasma metabolomics. A biophysical placenta-pulmonary coupling model used the umbilical artery pulsatility index (PI) and a metabolomic hypoxia-steroid score to represent placental reserve, while backscatter integrals and elastography were used to characterize fetal lung properties. Constrained by this model, a dual-branch network was developed: (i) a cross-modal attention Transformer with self-supervised contrastive learning to generate unsupervised FLM stages from fused representations and (ii) a spatiotemporal convolution-LSTM network to predict individualized GC dosing and the optimal administration window. A composite loss penalized both projected respiratory distress syndrome (RDS) risk and the biomarker-derived neurotoxicity index. Results: The cross-modal representations clustered into four distinct maturity stages matching biochemical benchmarks, with an inter-stage silhouette score of 0.72. A downstream classifier achieved 92.3% accuracy in discriminating early from late maturity. The dosing branch predicted the GC dose within ±0.5 mg of clinically prescribed regimens and reduced projected RDS risk by 27% compared to standard dosing, while maintaining the biomarker-derived neurotoxicity index below the prespecified threshold. Conclusion: A mechanism-guided, multimodal AI framework constrained by placenta-pulmonary physiology transforms imaging features into traceable decision pathways that align with clinical cognition. This interpretable framework may enable non-invasive FLM staging and individualized GC therapy, providing hypothesis-generating decision support that warrants external validation and prospective trials.
Overview
CoChat Summary
## TL;DR
This prospective cohort study developed a physiology-guided multimodal AI system that used ultrasound, Doppler, elastography, and maternal metabolomics to stage fetal lung maturity and recommend individualized antenatal glucocorticoid dosing. In 320 pregnancies, the model formed four maturity stages, reached 92.3% accuracy for early vs late maturity, and was associated with a 27% reduction in model-projected RDS risk versus standard dosing.
## Key findings
- In 320 singleton pregnancies with weekly scans from 28 to 36 weeks, multimodal self-supervised representations clustered into 4 maturity stages with an inter-stage silhouette score of 0.72 (95% CI 0.69–0.75).
- The downstream classifier achieved 92.3% accuracy (95% CI 89.5–94.6%) for distinguishing early (Stages 1–2) from late (Stages 3–4) maturity, with 91.7% sensitivity and 92.9% specificity.
- The dosing branch predicted glucocorticoid dose with MAE 0.31 ± 0.17 mg; 80% of predictions were within ±0.5 mg of prescribed doses, and predicted administration windows had a median deviation of 0.4 days.
- Model-guided dosing reduced projected RDS risk from 30.8% to 22.5% in the total cohort, a 27% relative reduction; the reduction was 33% in HDP pregnancies (41.2% to 27.6%) and 21% in normotensive pregnancies (20.5% to 16.2%).
## Methods
- Design/sample: Prospective cohort study of 320 singleton pregnancies enrolled at two tertiary perinatal centers from January 2021 to December 2022; 160 had hypertensive disorders of pregnancy and 160 were normotensive controls, with weekly data collected from 28+0 to 36+0 weeks.
- Data/modalities: 2D and 3D ultrasound, shear-wave elastography, umbilical artery Doppler, and maternal plasma metabolomics (a 45-metabolite panel) were collected longitudinally.
- Analysis/modeling: A biophysical placenta–pulmonary coupling model was combined with a dual-branch deep network: a Transformer-based cross-modal staging branch trained with contrastive learning and a spatiotemporal convolution–LSTM dosing branch; evaluation used patient-level splits, Gaussian mixture clustering, silhouette score, accuracy, MAE, and risk/safety comparisons.
## Limitations
- The paper states that external generalizability remains to be established and that performance may vary across vendors, transducers, acquisition settings, and clinical workflows; external multi-vendor validation is warranted.
- The neurotoxicity index is a surrogate biomarker and “not a validated proxy for long-term neurodevelopmental outcomes,” so safety conclusions are preliminary.
- Respiratory benefit was based on model-projected RDS risk rather than adjudicated neonatal RDS outcomes; the paper says prospective studies with neonatal endpoints are needed.
- The text also notes that higher-order nonlinearities (e.g., cytokine-mediated feedback) were not incorporated, which is a limitation evident from the model description.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
7 Valid · 4 Not valid · 12 Not checked · 68 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“placental elastography reveals correlations between tissue stiffness and lung delay (7).”
§ Placenta–pulmonary coupling–guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy > Introduction
What the sources say
- Partly supportedcites [7] Kilic, 2015, Shear wave elastography of placenta: in vivo quantitation of placental elasticity in preeclampsia, Diagn Interv Radiol sourceExperimental — accuracy not yet measured
Our copy does show placental shear wave elastography yielding correlations involving tissue stiffness: the Results (Table 3) report median elasticity of the central-fetal placental surface correlating moderately with uterine artery pulsatility indices (r = 0.512, 0.436) and weakly with resistivity indices (r = 0.295, 0.339), and the Discussion links higher stiffness to preeclampsia with associated low birth weight and low Apgar scores. However, no passage mentions lung maturation, respiratory distress, or any 'lung delay' variable, and the Statistical analysis section restricts correlations of SWE data to Doppler indices only. The Discussion even states that no relationship between placental elasticity and gestational age has been established and that further correlative studies are needed. So the correlation-with-lung-delay component of the claim is not supported by this source. (LLM, conf=0.65)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“GC optimization models are predominantly static; pharmacokinetic/pharmacodynamic (PK/PD) frameworks reduce the incidence of RDS by 19% but rely on invasive inputs and do not account for cumulative neurotoxicity risks (12).”
§ Placenta–pulmonary coupling–guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy > Introduction
What the sources say
- Could not verifycites [12] Della Torre, 2010, Betamethasone in pregnancy: influence of maternal body weight and multiple gestation on pharmacokinetics, Am J Obstet Gynecol sourceExperimental — accuracy not yet measured
The Methods describe one population pharmacokinetic model, and the Discussion describes a standard betamethasone dosing regimen. Neither section assesses glucocorticoid optimization models generally or says that they are predominantly static (searched: static optimization models, PK/PD frameworks, and fixed dosing regimens). (LLM, conf=0.72)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“multimodal data fusion—essential for integrating ultrasound, elastography, Doppler imaging, and metabolomics—is often superficial.”
§ Placenta–pulmonary coupling–guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy > Introduction
What the sources say
- Partly supportedcites [11] Baltrusaitis, 2019, Multimodal machine learning: a survey and taxonomy, IEEE Trans Pattern Anal Mach Intell sourceExperimental — accuracy not yet measured
Section 6.1 (p. 12) says early fusion often simply concatenates features and late fusion ignores low-level interactions between modalities. Those limitations support the concern behind “superficial,” but the survey does not characterize multimodal fusion generally as often superficial, nor does it assess fusion of the specific medical modalities listed. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Variability in placental enzyme activity (e.g., 11β-HSD2 activity fluctuations causing 230% differences in GC exposure) further complicates dosing (13).”
§ Placenta–pulmonary coupling–guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy > Introduction
What the sources say
- Partly supportedcites [13] Jahnke, 2021, Maternal stress, placental 11β-HSD2 methylation and expression, and infant cortisol reactivity, Placenta sourceExperimental — accuracy not yet measured
The Introduction says placental HSD11B2 buffers fetal glucocorticoid exposure, and the Results (Placental HSD11B2 characteristics) document variation in methylation and gene expression. The paper does not report 230% differences in exposure or assess whether enzyme variability complicates dosing; its measurements of expression should not be treated as measurements of enzyme activity. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The umbilical artery pulsatility index (PI), a key indicator of placental perfusion, was 25.5% higher in the HDP cohort (1.83 ± 0.32 vs. 1.46 ± 0.23, p < 0.001).”
§ Placenta–pulmonary coupling–guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy > Results > Study population characteristics
plainstates an associationn = 320 ·- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
31 more claims
Create a free account to see all 91 claims and every source verdict.
- Probably not a substantial claim. 21
- It may state two separate claims as one. 44
Citations
Cites
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
Trends in Care Practices, Morbidity, and Mortality of Extremely Preterm Neonates, 1993-2012
Stoll, B. J., Hansen, N. I., Bell, E. F., Walsh, M. C., Carlo, W. A., Shankaran, S., Laptook, A. R., Sánchez, P. J., Van Meurs, K. P., Wyckoff, M., et al. (2015) · JAMA · doi:10.1001/jama.2015.10244 · Cited by 2,791
Liggins, G. C., & Howie, R. N. (1972) · Pediatrics · doi:10.1542/peds.50.4.515 · Cited by 2,544
The New BPD: An Arrest of Lung Development
Jobe, A. J. (1999) · Pediatric Research · doi:10.1203/00006450-199912000-00007 · Cited by 1,013
Antenatal corticosteroids for accelerating fetal lung maturation for women at risk of preterm birth
McGoldrick, E., Stewart, F., Parker, R., & Dalziel, S. R. (2020) · Cochrane Database of Systematic Reviews · doi:10.1002/14651858.cd004454.pub4 · Cited by 614
Committee Opinion No. 713: Antenatal Corticosteroid Therapy for Fetal Maturation
(2017) · Obstetrics & Gynecology · doi:10.1097/aog.0000000000002237 · Cited by 561
Placental 11β‐hydroxysteroid dehydrogenase: a key regulator of fetal glucocorticoid exposure
Benediktsson, R., Calder, A. A., Edwards, C. R. W., & Seckl, J. R. (1997) · Clinical Endocrinology · doi:10.1046/j.1365-2265.1997.1230939.x · Cited by 536
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound
Baumgartner, C. F., Kamnitsas, K., Matthew, J., Fletcher, T. P., Smith, S., Koch, L. M., Kainz, B., & Rueckert, D. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2712367 · Cited by 416
Placental Pathology in Early-Onset and Late-Onset Fetal Growth Restriction
Mifsud, W., & Sebire, N. J. (2014) · Fetal Diagnosis and Therapy · doi:10.1159/000359969 · Cited by 328
The Human Placenta Project: Placental structure, development, and function in real time
Guttmacher, A. E., Maddox, Y. T., & Spong, C. Y. (2014) · Placenta · doi:10.1016/j.placenta.2014.02.012 · Cited by 271 · cited 1×
“First, assessments remain organ-specific, neglecting the dynamic interplay between placental perfusion and pulmonary surfactant synthesis (9).”
Research works printed but not linked: 3
- Vaswani, 2017, Advances in Neural Information Processing Systems 30 (NeurIPS 2017), 5998
- Grill, 2020, NeurIPS, 21271
- Grill, 2020, Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 21271
Metadata
- Authors
- Ma, B., Ran, J., Pan, T., Yan, F., Yue, Z., Yao, Y., Li, Y., & Nie, F.
- Affiliations
- Gansu Provincial Maternal and Child Health Hospital (CN)
- Lanzhou University Second Hospital (CN)
- Corresponding author
- Nie, Fang
- Venue
- Frontiers in Medicine
- Publisher
- Frontiers Media SA
- Published
- 2026-03-12
- Volume
- 13
- Pages
- 1791481-1791481
- ISSN
- 2296-858X (ISSN-L)
- PMC
- PMC13018156
- OpenAlex
- W7135129954
- Cited by
- 0
- References
- 20
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Gansu Province Clinical Research Center for Ultrasonography (2020-0411-SFC-0021)
- The Gansu Provincial Natural Science Foundation (23JRRA1383)
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Neonatal Respiratory Health Research
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- fetal lung maturity, antenatal glucocorticoids, hypertensive disorders of pregnancy, respiratory distress syndrome, shear wave elastography, umbilical artery pulsatility index, fetal lung ultrasound, plasma metabolomics, explainable AI, decision support
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Placenta-pulmonary coupling-guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy. https://app.cochat.ai/papers/10.3389/fmed.2026.1791481
- The paper
- Ma, B., Ran, J., Pan, T., Yan, F., Yue, Z., Yao, Y., Li, Y., & Nie, F. (2026). Placenta-pulmonary coupling-guided multimodal AI for fetal lung maturity staging and individualized glucocorticoid therapy. Frontiers in Medicine. https://doi.org/10.3389/fmed.2026.1791481
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.