CoChat
Sign Up
Cited by 19Artificial Intelligence in Healthcare and EducationArtificial Intelligence in HealthcarePrenatal Screening and Diagnostics

Automated prediction of early spontaneous miscarriage based on the analyzing ultrasonographic gestational sac imaging by the convolutional neural network: a case-control and cohort study

Open access
Wang, Yu, Zhang, Qixin, Yin, Chenghuan, Chen, Lizhu, Yang, Zeyu, Jia, Shanshan, Sun, Xue, Bai, Yuzuo +2 more·2022·BMC Pregnancy and Childbirth
DOI 10.1186/s12884-022-04936-0PMC PMC9354356
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: It is challenging to predict the outcome of the pregnancy when fetal heart activity is detected in early pregnancy. However, an accurate prediction is of importance for obstetricians as it helps to provide appropriate consultancy and determine the frequency of ultrasound examinations. The purpose of this study was to investigate the role of the convolutional neural network (CNN) in the prediction of spontaneous miscarriage risk through the analysis of early ultrasound gestational sac images. Methods: A total of 2196 ultrasound images from 1098 women with early singleton pregnancies of gestational age between 6 and 8 weeks were used for training a CNN for the prediction of the miscarriage in the retrospective study. The patients who had positive fetal cardiac activity on their first ultrasound but then experienced a miscarriage were enrolled. The control group was randomly selected in the same database from the fetuses confirmed to be normal during follow-up. Diagnostic performance of the algorithm was validated and tested in two separate test sets of 136 patients with 272 images, respectively. Performance in prediction of the miscarriage was compared between the CNN and the manual measurement of ultrasound characteristics in the prospective study. Results: The accuracy of the predictive model was 80.32% and 78.1% in the retrospective and prospective study, respectively. The area under the receiver operating characteristic curve (AUC) for classification was 0.857 (95% confidence interval [CI], 0.793–0.922) in the retrospective study and 0.885 (95%CI, 0.846–0.925) in the prospective study, respectively. Correspondingly, the predictive power of the CNN was higher compared with manual ultrasound characteristics, for which the AUCs of the crown-rump length combined with fetal heart rate was 0.687 (95%CI, 0.587–0.775). Conclusions: The CNN model showed high accuracy for predicting miscarriage through the analysis of early pregnancy ultrasound images and achieved better performance than that of manual measurement.

AI snapshot

Written from the paper’s full text.

TL;DR

This study trained a VGG19 convolutional neural network on early gestational sac ultrasound images to predict spontaneous miscarriage in singleton pregnancies at 6–8 weeks with detectable fetal cardiac activity. The CNN achieved an AUC of 0.857 retrospectively and 0.885 prospectively, outperforming manual crown-rump length plus fetal heart rate measurement (AUC 0.687).

Key findings

  • In the retrospective study, the CNN’s overall accuracy was 80.32%, with sensitivity 80.73%, specificity 80.91%, PPV 81.18%, NPV 80.02%, and AUC 0.857 (95% CI 0.793–0.922).
  • In the prospective study, the CNN had accuracy 78.10%, sensitivity 80.39%, specificity 94.52%, PPV 94.89%, NPV 77.00%, and AUC 0.885 (95% CI 0.846–0.925).
  • Manual ultrasound characteristics performed worse: CRL plus heart rate had an AUC of 0.687 (95% CI 0.587–0.775), compared with the CNN’s prospective AUC of 0.885.
  • Gestational sac segmentation performed well, with average DICE 90.69%, recall 94.56%, and precision 87.86%; the sixth week showed the best retrospective classification among weeks, with AUC 0.904 (95% CI 0.781–0.950) for transverse plus sagittal planes.

Methods

  • Retrospective review from September 2013 to June 2019 at Shengjing Hospital of China Medical University: 71,372 early singleton pregnancies at 6–8 weeks with embryonic cardiac activity were analyzed; 721 miscarriage cases and 721 randomly selected normal controls were enrolled, with 72 excluded for measurement caliper overlays. A prospective study from January to June 2019 included 108 women with singleton pregnancies (6 miscarriages, 102 term), with 7 excluded for missed follow-up.
  • Ultrasound images were JPEG 768 × 1024 pixels, acquired transvaginally at 3–9 MHz. Gestational sac regions were segmented using a level set method, then a VGG19 CNN was trained with data augmentation; 10-fold cross-validation used 136 cases for testing, 136 for validation, and 1098 for training.
  • Diagnostic performance was assessed with sensitivity, specificity, accuracy, PPV, NPV, and ROC/AUC. Manual ultrasound characteristics were analyzed using fetal heart rate and crown-rump length thresholds based on DeVilbiss et al., and statistical comparisons used Mann-Whitney U or χ² tests.

Limitations

  • The paper states that CNN performance depends on input image quality; higher-resolution images from experienced sonographers may improve predictions, and retrospective images often had irremovable measurement marks that may have limited learning performance.
  • The paper states that the prospective sample was small and that future multicenter, large-scale prospective studies are needed; the model used only 2D ultrasound, and future work should analyze 3D gestational sac volume data combined with other ultrasound and biochemical markers.
  • Evident from the text: the prospective miscarriage group contained only 6 women, producing wide confidence intervals for manual ultrasound measures and limiting generalizability; the study was also single-center and used a case-control retrospective design with randomly selected controls, which may not reflect real-world prevalence.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s12884-022-04936-0

Cites

Statistics

Nothing to recompute.

Claims the paper makes

0 of 28 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    In the retrospective study, the CNN model predicted miscarriage with an overall sensitivity of 80.73%.

    “The overall accuracy was 80.32%, and the overall sensitivity, specificity, PPV, and NPV for prediction of miscarriage were 80.73, 80.91, 81.18, and 80.02%, respectively (Table 2).”
    Quote in the paperSubstantial claim
  • Findingown data

    The AUC of the crown-rump length combined with fetal heart rate for predicting miscarriage was 0.687 (95% CI 0.587-0.775).

    “Correspondingly, the predictive power of the CNN was higher compared with manual ultrasound characteristics, for which the AUCs of the crown-rump length combined with fetal heart rate was 0.687 (95%CI, 0.587–0.775).”
    Quote in the paperSubstantial claim
  • Findingown data

    In the prospective study, the accuracy of the predictive model was 78.1%.

    “The accuracy of the predictive model was 80.32% and 78.1% in the retrospective and prospective study, respectively.”
    Quote in the paperSubstantial claim
  • Findingown data

    In the retrospective study, the CNN model predicted miscarriage with an overall specificity of 80.91%.

    “The overall accuracy was 80.32%, and the overall sensitivity, specificity, PPV, and NPV for prediction of miscarriage were 80.73, 80.91, 81.18, and 80.02%, respectively (Table 2).”
    Quote in the paperSubstantial claim
  • Findingown data

    The automated segmentation of the gestational sac achieved a recall of 94.56%.

    “The average DICE index was 90.69%, the recall was 94.56%, and the precision was 87.86%, indicating that the gestational sac could be well segmented automatically.”
    Quote in the paperSubstantial claim
  • May combine two claims. 10
  • Classified as probably not a substantial claim. 22
  • The quote only partly states this claim. 1

  • May combine two claims.

    Findingown data

    In the retrospective study, the CNN model using sagittal combined with transverse planes had an AUC of 0.857 (95% CI 0.793-0.922), which was higher than sagittal alone (AUC 0.843, 95% CI 0.801-0.884) or transverse alone (AUC 0.834, 95% CI 0.776-0.893).

    “the AUC of the sagittal combined with transverse planes was 0.857 (95%CI, 0.793–0.922), which showed better diagnostic performance compared with the sagittal (AUC, 0.843 (95%CI, 0.801–0.884)) or transverse plane (AUC, 0.834 (95%CI, 0.776–0.893)) alone.”
    • Also stated in: § Classification · plain
      “Because the sagittal combined with transverse planes showed better diagnostic performance compared with the sagittal or transverse plane alone, we used the sagittal combined with transverse planes for analysis in the prospective study.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    In the retrospective study, the best-performing model on the test set had an AUC of 0.857, a sensitivity of 80.73%, and a specificity of 80.91%.

    “The best-performing model yielded satisfactory predictions on the test set, with an AUC of 0.857, a sensitivity of 80.73%, and a specificity of 80.91%.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    In the retrospective study, the CNN model's classification performance for gestational week 6 had an AUC of 0.904 (95% CI 0.781-0.950), which was higher than week 7 (AUC 0.832, 95% CI 0.702-0.865) and week 8 (AUC 0.858, 95% CI 0.729-0.829).

    “the sixth week had a better classification effect, as the AUC for the sixth week was 0.904 (95% confidence interval [CI], 0.781–0.950), which was higher than the other 2 groups (seventh week, 0.832 (95%CI, 0.702–0.865); eighth week, 0.858 (95%CI, 0.729–0.829)).”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    In the prospective study, the CNN model using sagittal combined with transverse planes had accuracy 78.10%, sensitivity 80.39%, specificity 94.52%, PPV 94.89%, NPV 77%, and AUC 0.885 (95% CI 0.846-0.925).

    “It had good predictive ability in predicting early pregnancy miscarriage, with the accuracy, sensitivity, specificity, PPV, and NPV of 78.10, 80.39, 94.52, 94.89, and 77%, respectively, and an AUC of 0.885(95%CI, 0.846–0.925) (Table 3).”
    • Also stated in: § Discussion · plain
      “For the prospective study, the sensitivity and specificity of the classification were 80.39 and 94.52%, respectively, and the AUC was 0.885.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Even after embryonic cardiac activity is detected, the subsequent rate of miscarriage remains 5.2 to 10.4%.

    “Even after the embryonic cardiac activity is detected, the subsequent rate of miscarriage remains 5.2 to 10.4% [4, 5].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [4] Stamatopoulos N, Lu C, Casikar I, Reid S, Mongelli M, Hardy N, et al. Prediction of subsequent miscarriage risk in women who present with a viable pregnancy at the first early pregnancy scan. Aust N Z J Obstet Gynaecol. 2015;55:464–72. source

      Not checked in the free run.

    • cites [5] DeVilbiss EA, Mumford SL, Sjaarda LA, Connell MT, Plowden TC, Andriessen VC, et al. Prediction of pregnancy loss by early first trimester ultrasound characteristics. Am J Obstet Gynecol. 2020;223:242 e241–22.

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Deep learning algorithms have been widely applied in the field of image diagnosis and prediction owing to their advantages of being fast, accurate, and reproducible.

    “Deep learning algorithms have been widely applied in the field of image diagnosis and prediction owing to their advantages of being fast, accurate, and reproducible [15].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [15] Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18:500–10. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    In fetal ultrasonography, CNNs have shown potential for standard plane recognition, detection, and localization.

    “In fetal ultrasonography (US), CNNs have shown potential for standard plane recognition, detection, and localization [19].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [19] Xie H, Wang N, He M, Zhang L, Cai H, Xian J, et al. Using deep learning algorithms to classify fetal brain ultrasound images as normal or abnormal. Ultrasound Obstet Gynecol. 2020. https://doi.org/10.1002/uog.21967. source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Deep CNNs can be successfully used to extract and analyze information obtained from medical images.

    “Recent research on medical data has shown that deep CNNs can be successfully used to extract and analyze information obtained from medical images [16–18].”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [16] Litjens G, Sanchez CI, Timofeeva N, Hermsen M, Nagtegaal I, Kovacs I, et al. Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci Rep. 2016;6:26286. source

      Not checked in the free run.

    • cites [17] Lee JH, Joo I, Kang TW, Paik YH, Sinn DH, Ha SY, et al. Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network. Eur Radiol. 2019. https://doi.org/10.1007/s00330-019-06407-1. source

      Not checked in the free run.

    • cites [18] Park SH. Artificial intelligence for ultrasonography: unique opportunities and challenges. Ultrasonography. 2021;40:3–6. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    The data augmentation strategy helps prevent network overfitting and memorization of the exact training image details.

    “The data augmentation strategy has proved to help prevent network overfitting and memorization of the exact training image details [21].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [21] Zhou LQ, Wu XL, Huang SY, Wu GG, Ye HR, Wei Q, et al. Lymph node metastasis prediction from primary breast Cancer US images using deep learning. Radiology. 2020;294:19–28. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Low fetal heart rate (≤122, 123, and 158 bpm for gestational weeks 6, 7, and 8, respectively) and small crown-rump length (≤6.0, 8.5, and 10.9 mm for gestational weeks 6, 7, and 8, respectively) are independent predictors of clinical pregnancy loss.

    “Low fetal heart rate (≤122, 123, and 158 bpm) and small crown-rump length (≤6.0, 8.5, and 10.9 mm) for gestational weeks 6, 7, and 8, respectively, were used as independent predictors of clinical pregnancy loss.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites DeVilbiss et al. [5] DeVilbiss EA, Mumford SL, Sjaarda LA, Connell MT, Plowden TC, Andriessen VC, et al. Prediction of pregnancy loss by early first trimester ultrasound characteristics. Am J Obstet Gynecol. 2020;223:242 e241–22.

      Not checked in the free run.

  • May combine two claims. The quote only partly states this claim.

    Interpretationown data

    The CNN method is fast, convenient, and provides more accurate results than manual ultrasound measurements.

    “The results suggest that our CNN method is fast, convenient, and provides more accurate results.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Study design and conductown data

    Normal controls were randomly selected from the same database.

    “Besides, 721 confirmed normal fetuses were randomly selected from the same database to serve as normal controls.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Measurement of crown-rump length in early pregnancy is affected by inter-observer variation.

    “This could be due to the fact that the measurement of the crown-rump length in early pregnancy is affected by inter-observer variation [29].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [29] Pexsters A, Luts J, Van Schoubroeck D, Bottomley C, Van Calster B, Van Huffel S, et al. Clinical implications of intra- and interobserver reproducibility of transvaginal sonographic measurement of gestational sac and crown-rump length at 6-9 weeks' gestation. Ultrasound Obstet Gynecol. 2011;38:510–5. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Pillai et al. reported that crown-rump length has a lower predictive value than fetal heart rate.

    “Pillai et al reported that the crown-rump length has a lower predictive value than the fetal heart rate [28].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [28] Pillai RN, Konje JC, Richardson M, Tincello DG, Potdar N. Prediction of miscarriage in women with viable intrauterine pregnancy-a systematic review and diagnostic accuracy meta-analysis. Eur J Obstet Gynecol Reprod Biol. 2018;220:122–31. source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Study design and conductown data

    The diagnostic performance of the algorithm was validated and tested in two separate test sets of 136 patients with 272 images each.

    “Diagnostic performance of the algorithm was validated and tested in two separate test sets of 136 patients with 272 images, respectively.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Abnormal yolk sac size and appearance are useful markers for miscarriage prediction before the demonstration of fetal viability.

    “Abnormal yolk sac size and appearance have been reported to be useful markers for miscarriage prediction before the demonstration of fetal viability [27].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [27] Suguna B, Sukanya K. Yolk sac size & shape as predictors of first trimester pregnancy outcome: a prospective observational study. J Gynecol Obstet Hum Reprod. 2019;48:159–64. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Some studies used 3D ultrasound to observe the volume of the gestational sac or trophoblast to predict early pregnancy miscarriage.

    “Some studies used 3D ultrasound to observe the volume of the gestational sac or trophoblast to predict early pregnancy miscarriage [30–32].”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [30] Odeh M, Ophir E, Grinin V, Tendler R, Kais M, Bornstein J. Prediction of abortion using three-dimensional ultrasound volumetry of the gestational sac and the amniotic sac in threatened abortion. J Clin Ultrasound. 2012;40:389–93. source

      Not checked in the free run.

    • cites [31] Reus AD, El-Harbachi H, Rousian M, Willemsen SP, Steegers-Theunissen RP, Steegers EA, et al. Early first-trimester trophoblast volume in pregnancies that result in live birth or miscarriage. Ultrasound Obstet Gynecol. 2013;42:577–84. source

      Not checked in the free run.

    • cites [32] Wie JH, Choe S, Kim SJ, Shin JC, Kwon JY, Park IY. Sonographic parameters for prediction of miscarriage: role of 3-dimensional volume measurement. J Ultrasound Med. 2015;34:1777–84. source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    The ultrasound images were acquired by an experienced sonographer according to a unified acquisition process.

    “In all the cases, the images were acquired by an experienced sonographer according to a unified acquisition process in the routine ultrasound examination.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductown data

    The model was evaluated using 10-fold cross-validation.

    “In the evaluation step, 10-fold cross-validation was used.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The presence of irremovable measurement marks may explain why the deep learning algorithm cannot achieve a better learning performance.

    “which may explain why the deep learning algorithm cannot achieve a better learning performance.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Study design and conductown data

    The segmentation accuracy was assessed against a gold standard of manual tracing by two experienced sonographers.

    “To quantitatively assess the accuracy of the segmentation, we defined the segmentation area as “S”, and two experienced sonographers were trained and asked to manually trace along the inner edges of the trophoblast together, which we used as the “gold standard” (GT).”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Interpretationreasoning

    The CNN method is more robust, has lower requirements on input prediction images, and is more suitable for clinical diagnosis.

    “But on the other hand, it also shows that our method is more robust, has lower requirements on input prediction images, and is more suitable for clinical diagnosis.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    DeVilbiss et al. found that low fetal heart rate and small crown-rump length were independent predictors of clinical pregnancy loss, with the greatest risks observed for pregnancies having both characteristics.

    “Recently, DeVilbiss et al. [5] found that low fetal heart rate and small crown-rump length were independent predictors of clinical pregnancy loss, with the greatest risks observed for pregnancies having both characteristics.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [5] DeVilbiss EA, Mumford SL, Sjaarda LA, Connell MT, Plowden TC, Andriessen VC, et al. Prediction of pregnancy loss by early first trimester ultrasound characteristics. Am J Obstet Gynecol. 2020;223:242 e241–22.

      Not checked in the free run.

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationnone given

    Post-processing of volume data is a lengthy process, which limits its clinical application.

    “However, the post-processing of volume data is a lengthy process, which limits its clinical application.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Interpretationreasoning

    Higher resolution ultrasound images performed by experienced sonographers will aid in improved predictions.

    “The higher resolution ultrasound images performed by experienced sonographers will aid in the improved predictions.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisereasoning

    Gestational age needs to be considered when using sonographic markers because they change with gestational age throughout the first trimester.

    “Gestational age also needs to be considered when using these sonographic markers, because they change with the gestational age throughout the first trimester.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Interpretationnone given

    Our research surpasses the limitations of manual measurement of clinical ultrasound image parameters and calculates the image features quantitatively and automatically.

    “Our research surpasses the limitations of manual measurement of clinical ultrasound image parameters and calculates the image features quantitatively and automatically.”
    Quote in the paperSubstantial claim
27 of 27

  • The paper relies on this without support.

    No reports to date on the prediction of miscarriage by deep learning.

    “However, to our knowledge, there have been no reports to date on the prediction of miscarriage by deep learning.”

  • The paper relies on this without support.

    This is the first study to analyze ultrasound image features using CNN to predict the subsequent risk of pregnancy loss during early pregnancy.

    “To our knowledge, this is the first study to analyze ultrasound image features using CNN to predict the subsequent risk of pregnancy loss during early pregnancy.”

  • The paper relies on this without support.

    Post-processing of volume data is a lengthy process, which limits its clinical application.

    “However, the post-processing of volume data is a lengthy process, which limits its clinical application.”

  • The paper relies on this without support.

    Gestational age needs to be considered when using sonographic markers because they change with gestational age throughout the first trimester.

    “Gestational age also needs to be considered when using these sonographic markers, because they change with the gestational age throughout the first trimester.”
4 of 4

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Prospective accuracy is below both sensitivity and specificity

    Major

    The prospective accuracy of 78.10% is below the reported sensitivity of 80.39% and specificity of 94.52%. Accuracy cannot be below both when these measures refer to the same test set.

  • Retrospective accuracy is below both sensitivity and specificity

    Major

    Overall accuracy must be a weighted average of sensitivity and specificity. The reported 80.32% is below both 80.73% and 80.91%, so these three values cannot describe the same classification results.

  • Combined manual-measurement accuracy does not match its sensitivity and specificity

    Minor

    Among 6 miscarriages, 50.00% sensitivity implies 3 correct predictions; among 95 live births, 87.37% specificity implies 83. That is 86 correct predictions out of 101, or 85.15% accuracy, rather than 83.17%.

  • Sagittal and transverse overall AUCs are reversed in the prose

    Minor

    The prose assigns AUC 0.843 to the sagittal plane and 0.834 to the transverse plane, whereas Table 2 assigns 0.843 to transverse and 0.834 to sagittal.

  • Eighth-week AUC lies outside its stated confidence interval

    Minor

    The reported AUC of 0.858 exceeds the upper bound, 0.829, of its stated 95% confidence interval.

5 of 5

The citation lists haven’t been fetched yet

References 36 · Cited by 19

Authors
Wang, Y., Zhang, Q., Yin, C., Chen, L., Yang, Z., Jia, S., Sun, X., Bai, Y., Han, F., & Yuan, Z.
Affiliations
  • Sheng Jing Hospital (CN)
  • Northeastern University (CN)
  • China Medical University (CN)
  • Guangdong Pharmaceutical University (CN)
Corresponding author
  • Han, Fangfang
  • Yuan, Zhengwei
ORCID
Venue
BMC Pregnancy and Childbirth
Publisher
Springer Science and Business Media LLC
Published
2022-08-05
Volume
22
Issue
1
Pages
621-621
ISSN
1471-2393 (ISSN-L)
DOI
10.1186/s12884-022-04936-0
PMC
PMC9354356
OpenAlex
W4289878564
Cited by
19
References
36
Citations by year
2026: 6 · 2025: 4 · 2024: 7 · 2023: 2
FWCI
0.98
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Pregnancy and Childbirth (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • 345 Talent Project (M0305)
  • National Natural Science Foundation of China (81871219)
  • LiaoNing Revitalization Talents Program (XLYC1902099)
  • National Key Research and Development Program of China (2021YFC2701003, 2021YFC2701104)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Pediatrics, Perinatology and Child Health › Prenatal Screening and Diagnostics
Keywords
miscarriage, first-trimester ultrasound, convolutional neural networks, fetal cardiac activity, crown-rump length, fetal heart rate
MeSH terms
Abortion, Spontaneous, Female, Humans, Infant, Pregnancy, Pregnancy Trimester, First, Prospective Studies, Retrospective Studies, Cohort Studies, Ultrasonography, Prenatal, Neural Networks, Computer, Gestational Sac

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-10.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-10.

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