CoChat
Sign Up
Cited by 1Maternal and fetal healthcareArtificial Intelligence in HealthcarePregnancy and preeclampsia studies

Development and validation of an interpretable machine learning model for predicting adverse clinical outcomes in placenta accreta spectrum: a multicenter study

Li, Hongliang, Zhang, Yueyue, Mei, Hangru, Yuan, Yangguang, Wang, Lei, Liu, Weihao, Zeng, Haoyang, Huang, Jinjie +3 more·2025·Academic Radiology
DOI 10.1016/j.acra.2025.08.011
Open this paper in CoChat — free account

Abstract

Rationale and objectives Placenta accreta spectrum (PAS) is a serious perinatal complication. Accurate preoperative identification of patients at high risk for adverse clinical outcomes is essential for developing personalized treatment strategies. This study aimed to develop and validate a high-performance, interpretable machine learning model that integrates MRI morphological indicators and clinical features to predict adverse outcomes in PAS, and to build an online prediction tool to enhance its clinical applicability.Materials and methods This retrospective study included 125 clinically confirmed PAS patients from two centers, categorized into high-risk (intraoperative blood loss over 1500 mL or requiring hysterectomy) and low-risk groups. Data from Center 1 were used for model development, and data from Center 2 served as the external validation set. Five MRI morphological indicators and six clinical features were extracted as model inputs. Three machine learning classifiers-AdaBoost, TabPFN, and CatBoost-were trained and evaluated on both internal testing and external validation cohorts. SHAP analysis was used to interpret model decision-making, and the optimal model was deployed via a Streamlit-based web platform.Results The CatBoost model achieved the best performance, with AUROCs of 0.90 (95% CI: 0.73-0.99) and 0.84 (95% CI: 0.70-0.97) in the internal testing and external validation sets, respectively. Calibration curves indicated strong agreement between predicted and actual risks. SHAP analysis revealed that "Cervical canal length" and "Gestational age" contributed negatively to high-risk predictions, while "Prior C-sections number", "Placental abnormal vasculature area", and Parturition were positively associated. The final online tool allows real-time risk prediction and visualization of individualized force plots and is freely accessible to clinicians and patients.Conclusions This study successfully developed an interpretable and practical machine learning model for predicting adverse clinical outcomes in PAS. The accompanying online tool may support clinical decision-making and improve individualized management for PAS patients.

Integrity signals

Registry

Crossref · 10.1016/j.acra.2025.08.011

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Li et al. developed an ML model using the CatBoost algorithm to predict adverse clinical outcomes in PAS, achieving AUCs of 0.90 (internal) and 0.84 (external), with implementation as an online prediction tool.

    “A study by Li et al. [32] developed an ML model using the CatBoost algorithm to predict adverse clinical outcomes in PAS, achieving AUCs of 0.90 (internal) and 0.84 (external), with implementation as an online prediction tool.”

    From Machine Learning in Maternity: Early Diagnosis of Placenta Accreta Spectrum (2026) · cites this paper as [32]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

  • Machine Learning in Maternity: Early Diagnosis of Placenta Accreta Spectrum

    Waszczuk, D., Manikandan, V., Wong, B. L., Martin, F., Bhargava, N., Mondal, A., Loy, M., Strnad, D., Panchatcharam, M., Sadanala, G., et al. (2026) · Cureus · doi:10.7759/cureus.106592

    “A study by Li et al. [32] developed an ML model using the CatBoost algorithm to predict adverse clinical outcomes in PAS, achieving AUCs of 0.90 (internal) and 0.84 (external), with implementation as an online prediction tool.”
    Influential

Related

Authors
Li, H., Zhang, Y., Mei, H., Yuan, Y., Wang, L., Liu, W., Zeng, H., Huang, J., Chai, X., Wu, K., & Liu, H.
Affiliations
  • Shenzhen University (CN)
  • Second Affiliated Hospital of Soochow University (CN)
  • Southern University of Science and Technology (CN)
  • Shantou University (CN)
Corresponding author
Liu, Hanlin
ORCID
Venue
Academic Radiology
Publisher
Elsevier BV
Published
2025-11
Volume
32
Issue
11
Pages
6707-6715
ISSN
1076-6332 (ISSN-L)
DOI
10.1016/j.acra.2025.08.011
OpenAlex
W4413441788
Cited by
1
References
31
Citations by year
2026: 1
FWCI
1.53
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • Academic Radiology (publishedVersion)
  • PubMed (publishedVersion)
Funders
Science and Technology Program of Suzhou (KJXW2023022)
Topics
  • Health Sciences › Medicine › Pediatrics, Perinatology and Child Health › Maternal and fetal healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Obstetrics and Gynecology › Pregnancy and preeclampsia studies
Keywords
placenta accreta spectrum, model interpretability, CatBoost, SHAP analysis, gestational age, previous cesarean section, perinatal complications, hysterectomy, intraoperative blood loss
MeSH terms
Machine Learning, Adult, Female, Humans, Magnetic Resonance Imaging, Placenta Accreta, Pregnancy, Retrospective Studies, Reproducibility of Results

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.

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