Skip to content
2000
image of Clinical Deployment of Interpretable AI: Bridging Routine Clinical Tests and Proteomic Signatures for Preeclampsia Risk Stratification

Abstract

Introduction

Preeclampsia (PE) is the second-leading global cause of maternal mortality, affecting 5% of primigravidas. Owing to the substantial heterogeneity of clinical manifestations in PE, an urgent need arises to quantitatively evaluate the efficacy of existing diagnostic methods based on positive proteinuria (PRO) and to develop novel biomarkers to enhance diagnostic accuracy.

Methods

We based 1,215 pregnant women obtained from who delivery at the hospital in January 2018 and April 2022 and involved predictors of 66 routine clinical laboratory tests (RCLTs). In addition, from 362 peripheral blood proteomic samples obtained from published datasets. Compared, evaluated, and explored the performances of 5 machine learning models to constructed prediction models.

Results

We pioneered the application of machine learning to assess the diagnostic efficiency of PRO quantitatively, AUROC of 0.771. Next, a more comprehensive assessment was discussed, including 66 RCTIs from blood and urine test items, the AUROC increased to 0.920. Furthermore, the feature selection strategy trained a superior routine clinical prediction model with 5 RCLTs (PRO, alkaline phosphatase (ALP), amylase (AMY), Uric Acid (UA), and Lactate Dehydrogenase (LDH)) for PE to ensure practicality and high performance. In addition, we constructed a protein prediction model for PE based on peripheral blood proteome. Subsequently, EphA1 has been identified as a protein candidate marker for PE, and is highly expressed in placentals. Finally, we established a user-friendly and interpretable PE risk prediction webserver (http://bioinfor.imu.edu.cn/lbppe/) to assist improve the PE diagnosis efficiency.

Discussion

he predictive platform developed in this study enhances PE early detection, addressing the clinical need for rapid screening tools. Future multi-center trials should validate the models' generalizability.

Conclusion

This study assessed the diagnostic efficiency of proteinuria quantitatively and constructed a cost-effective PE prediction system, which is crucial for improving the diagnostic accuracy of PE.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cdt/10.2174/0113894501401057250928032123
2025-10-06
2025-12-15

  • From This Site

    /content/journals/cdt/10.2174/0113894501401057250928032123
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Mol B.W.J. Roberts C.T. Thangaratinam S. Magee L.A. de Groot C.J.M. Hofmeyr G.J. Pre-eclampsia. Lancet 2016 387 10022 999 1011 10.1016/S0140‑6736(15)00070‑7 26342729
    [Google Scholar]
  2. Tranquilli A.L. Dekker G. Magee L. The classification, diagnosis and management of the hypertensive disorders of pregnancy: A revised statement from the ISSHP. Pregnancy Hypertens. 2014 4 2 97 104 10.1016/j.preghy.2014.02.001 26104417
    [Google Scholar]
  3. Obstetricians A. Hypertension in pregnancy. Report of the american college of obstetricians and gynecologists’ task force on hypertension in pregnancy. Obstet. Gynecol. 2013 122 5 1122 1131 24150027
    [Google Scholar]
  4. Magee L.A. Temporary removal: The hypertensive disorders of pregnancy: ISSHP classification, diagnosis and management recommendations for international practice. 2018 Amsterdam, Netherlands Elsevier 2018 10.1016/j.preghy.2018.01.005
    [Google Scholar]
  5. Obstetricians A.C. Gestational hypertension and preeclampsia. Obstet. Gynecol. 2020 135 6 e237 e260 10.1097/AOG.0000000000003891 32443079
    [Google Scholar]
  6. Fishel Bartal M. Lindheimer M.D. Sibai B.M. Proteinuria during pregnancy: Definition, pathophysiology, methodology, and clinical significance. Am. J. Obstet. Gynecol. 2022 226 2 S819 S834 10.1016/j.ajog.2020.08.108 32882208
    [Google Scholar]
  7. Chen X. Yuan L. Ji Z. Bian X. Hua S. Development and validation of the prediction models for preeclampsia: A retrospective, single-center, case-control study. Ann. Transl. Med. 2022 10 22 1221 10.21037/atm‑22‑4192 36544644
    [Google Scholar]
  8. Kim Y.R. Jung I. Heo S.J. Chang S.W. Cho H.Y. A preeclampsia risk prediction model based on maternal characteristics and serum markers in twin pregnancy. J. Matern. Fetal Neonatal Med. 2021 34 21 3623 3628 10.1080/14767058.2019.1686757 31739715
    [Google Scholar]
  9. Townsend R. Khalil A. Premakumar Y. Prediction of pre‐eclampsia: Review of reviews. Ultrasound Obstet. Gynecol. 2019 54 1 16 27 10.1002/uog.20117 30267475
    [Google Scholar]
  10. Li S. Wang Z. Vieira L.A. Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data. NPJ Digit. Med. 2022 5 1 68 10.1038/s41746‑022‑00612‑x 35668134
    [Google Scholar]
  11. Salazar MR Espeche WG Leiva sisnieguez CE Masked hypertension and neonatal outcome in high-risk pregnancies. J. Hum. Hypertens. 2023 37 1 36 41 10.1038/s41371‑021‑00649‑7 35034090
    [Google Scholar]
  12. Tang Z. Ji Y. Zhou S. Development and validation of multi-stage prediction models for pre-eclampsia: A retrospective cohort study on chinese women. Front. Public Health 2022 10 911975 10.3389/fpubh.2022.911975 35712289
    [Google Scholar]
  13. Stefańska K. Zieliński M. Zamkowska D. Comparisons of dipstick test, urine protein-to-creatine ratio, and total protein measurement for the diagnosis of preeclampsia. Int. J. Environ. Res. Public Health 2020 17 12 4195 10.3390/ijerph17124195 32545523
    [Google Scholar]
  14. Saleem F.R. Chandru S. Biswas M. Evaluation of total LDH and its isoenzymes as markers in preeclampsia. J. Med. Biochem. 2020 39 3 392 398 33269027
    [Google Scholar]
  15. Bainbridge S.A. Roberts J.M. Uric acid as a pathogenic factor in preeclampsia. Placenta 2008 29 Suppl. A 67 72 10.1016/j.placenta.2007.11.001 18093648
    [Google Scholar]
  16. Li Q. Wang H. Wang H. Association between serum alkaline phosphatase levels in late pregnancy and the incidence of venous thromboembolism postpartum: A retrospective cohort study. EClinicalMedicine 2023 62 102088 10.1016/j.eclinm.2023.102088 37533415
    [Google Scholar]
  17. Erez O. Romero R. Maymon E. The prediction of late-onset preeclampsia: Results from a longitudinal proteomics study. PLoS One 2017 12 7 0181468 10.1371/journal.pone.0181468 28738067
    [Google Scholar]
  18. Tarca A.L. Romero R. Benshalom-Tirosh N. The prediction of early preeclampsia: Results from a longitudinal proteomics study. PLoS One 2019 14 6 0217273 10.1371/journal.pone.0217273 31163045
    [Google Scholar]
  19. Moufarrej M.N. Vorperian S.K. Wong R.J. Early prediction of preeclampsia in pregnancy with cell-free RNA. Nature 2022 602 7898 689 694 10.1038/s41586‑022‑04410‑z 35140405
    [Google Scholar]
  20. Fang G. Liu W. Wang L. A machine learning approach to select features important to stroke prognosis. Comput. Biol. Chem. 2020 88 107316 10.1016/j.compbiolchem.2020.107316 32629359
    [Google Scholar]
  21. Diaz-Uriarte R. GeneSrF and varSelRF: A web-based tool and R package for gene selection and classification using random forest. BMC Bioinformatics 2007 8 1 328 10.1186/1471‑2105‑8‑328 17767709
    [Google Scholar]
  22. Stoltzfus J.C. Logistic regression: A brief primer. Acad. Emerg. Med. 2011 18 10 1099 1104 10.1111/j.1553‑2712.2011.01185.x 21996075
    [Google Scholar]
  23. Chen T. Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA: Association for Computing Machinery 2016 785 94
    [Google Scholar]
  24. Noble W.S. What is a support vector machine? Nat. Biotechnol. 2006 24 12 1565 1567 10.1038/nbt1206‑1565 17160063
    [Google Scholar]
  25. Greener J.G. Kandathil S.M. Moffat L. Jones D.T. A guide to machine learning for biologists. Nat. Rev. Mol. Cell Biol. 2022 23 1 40 55 10.1038/s41580‑021‑00407‑0 34518686
    [Google Scholar]
  26. Cover T. Hart P. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 1967 13 1 21 27 10.1109/TIT.1967.1053964
    [Google Scholar]
  27. Breiman L. Random forests. Mach. Learn. 2001 45 1 5 32 10.1023/A:1010933404324
    [Google Scholar]
  28. Wang C. Zhang Y. Improving scoring-docking-screening powers of protein-ligand scoring functions using random forest. J. Comput. Chem. 2017 38 3 169 177 10.1002/jcc.24667 27859414
    [Google Scholar]
  29. Pedregosa F. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011 12 2825 2830
    [Google Scholar]
  30. Tougui I. Jilbab A. Mhamdi J.E. Impact of the choice of cross-validation techniques on the results of machine learning-based diagnostic applications. Healthc. Inform. Res. 2021 27 3 189 199 10.4258/hir.2021.27.3.189 34384201
    [Google Scholar]
  31. Liberzon A. Birger C. Thorvaldsdóttir H. Ghandi M. Mesirov J.P. Tamayo P. The molecular signatures database (MSigDB) hallmark gene set collection. Cell Syst. 2015 1 6 417 425 10.1016/j.cels.2015.12.004 26771021
    [Google Scholar]
  32. Wang H. Zhang Z. Li H. A cost-effective machine learning-based method for preeclampsia risk assessment and driver genes discovery. Cell Biosci. 2023 13 1 41 10.1186/s13578‑023‑00991‑y 36849879
    [Google Scholar]
  33. Liu M. Zhou J. Xi Q. A computational framework of routine test data for the cost-effective chronic disease prediction. Brief. Bioinform. 2023 24 2 bbad054 10.1093/bib/bbad054 36772998
    [Google Scholar]
  34. Lundberg S.M. Lee S-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 2017 30 1 8
    [Google Scholar]
  35. Greene C.S. Krishnan A. Wong A.K. Understanding multicellular function and disease with human tissue-specific networks. Nat. Genet. 2015 47 6 569 576 10.1038/ng.3259 25915600
    [Google Scholar]
  36. Szklarczyk D. Gable A.L. Nastou K.C. The STRING database in 2021: Customizable protein–protein networks, and functional characterization of user-uploaded gene/measurement sets. Nucleic Acids Res. 2021 49 D1 D605 D612 10.1093/nar/gkaa1074 33237311
    [Google Scholar]
  37. Bian X. Biswas A. Huang X. Short-term prediction of adverse outcomes using the sFlt-1 (Soluble fms-Like Tyrosine Kinase 1)/PlGF (Placental Growth Factor) ratio in asian women with suspected preeclampsia. Hypertension 2019 74 1 164 172 10.1161/HYPERTENSIONAHA.119.12760 31188674
    [Google Scholar]
  38. Higby K. Suiter C.R. Phelps J.Y. Siler-Khodr T. Langer O. Normal values of urinary albumin and total protein excretion during pregnancy. Am. J. Obstet. Gynecol. 1994 171 4 984 989 10.1016/S0002‑9378(13)90019‑3 7943114
    [Google Scholar]
  39. Phillips J.K. McBride C.A. Hale S.A. Solomon R.J. Badger G.J. Bernstein I.M. Examination of prepregnancy and pregnancy urinary protein levels in healthy nulliparous women. Reprod. Sci. 2017 24 3 407 412 10.1177/1933719116657198 27460407
    [Google Scholar]
  40. Gestational hypertension and preeclampsia: ACOG practice bulletin summary, number 222. Obstet. Gynecol. 2020 135 6 1492 1495 10.1097/AOG.0000000000003892
    [Google Scholar]
  41. Makuyana D. Mahomed K. Shukusho F.D. Majoko F. Liver and kidney function tests in normal and pre-eclamptic gestation--a comparison with non-gestational reference values. Cent. Afr. J. Med. 2002 48 5-6 55 59 12971159
    [Google Scholar]
  42. Liu C.W. Ke S.R. Tseng G.S. Wu Y.W. Hwang J.J. Elevated serum uric acid is associated with incident hypertension in the health according to various contemporary blood pressure guidelines. Nutr. Metab. Cardiovasc. Dis. 2021 31 4 1209 1218 10.1016/j.numecd.2021.01.003 33618920
    [Google Scholar]
  43. Mulla M.J. Myrtolli K. Potter J. Uric acid induces trophoblast IL-1β production via the inflammasome: Implications for the pathogenesis of preeclampsia. Am. J. Reprod. Immunol. 2011 65 6 542 548 10.1111/j.1600‑0897.2010.00960.x 21352397
    [Google Scholar]
  44. Thangaratinam S. Ismail K.M.K. Sharp S. Coomarasamy A. Khan K.S. Accuracy of serum uric acid in predicting complications of pre‐eclampsia: A systematic review. BJOG 2006 113 4 369 378 10.1111/j.1471‑0528.2006.00908.x 16553648
    [Google Scholar]
  45. Afroz R. Akhter Q.S. Sadia H. Sultana S. Serum lactate dehydrogenase (LDH) level in severe preeclampsia. J Banglad Soc Phys 2016 10 2 71 75 10.3329/jbsp.v10i2.27168
    [Google Scholar]
  46. Khidri F.F. Role of Lactate Dehydrogenase in the Prediction of Severity in Pre- Eclampsia | Bentham Science. Curr. Hypertens. Rev. 2020 3 16
    [Google Scholar]
  47. Pandey U. LDH a prognostic marker for preeclampsia: An observational study. Indian J Obstet Gynecol 2016 4 2 141 144 10.21088/ijog.2321.1636.4216.15
    [Google Scholar]
  48. Mary V.P. Chellatamizh M. Padmanaban S. Role of serum LDH in preeclampsia as a prognostic factor – a cross sectional case control study in tertiary care hospital. Int. J. Reprod. Contracept. Obstet. Gynecol. 2017 6 2 595 10.18203/2320‑1770.ijrcog20170389
    [Google Scholar]
  49. Gareev I. Beylerli O. Ahmad A. Ilyasova T. Shi H. Chekhonin V. Comparative analysis of circular RNAS expression and function between aortic and intracranial aneurysms. Curr. Drug Targets 2024 25 13 866 884 10.2174/0113894501319306240819052840 39219419
    [Google Scholar]
  50. Hunter R.J. Pinkerton J.H. Johnston H. Serum placental alkaline phosphatase in normal pregnancy and preeclampsia. Obstet. Gynecol. 1970 36 4 536 546 5506461
    [Google Scholar]
  51. Chen Y. Ou W. Lin D. Increased uric acid, gamma-glutamyl transpeptidase and alkaline phosphatase in early-pregnancy associated with the development of gestational hypertension and preeclampsia. Front. Cardiovasc. Med. 2021 8 756140 10.3389/fcvm.2021.756140 34722684
    [Google Scholar]
  52. Ababio G. Effects of lactate dehydrogenase (LDH) in preeclampsia. Clin Med Biochem 2017 3 2
    [Google Scholar]
  53. Zheng R Zhang J Zhao Y Zheng N Low serum amylase is associated with gestational diabetes mellitus in chinese pregnant women. Clin Lab 2015 61 10/2015 1423 8 10.7754/Clin.Lab.2015.150129 26642703
    [Google Scholar]
  54. Martinez-Fierro M.L. Garza-Veloz I. Analysis of circulating microrna signatures and preeclampsia development. Cells 2021 10 5 1003 10.3390/cells10051003 33923172
    [Google Scholar]
  55. Zhu L. Lv R. Kong L. Cheng H. Lan F. Li X. Genome-wide mapping of 5mC and 5hmC identified differentially modified genomic regions in late-onset severe preeclampsia: A pilot study. PLoS One 2015 10 7 0134119 10.1371/journal.pone.0134119 26214307
    [Google Scholar]
  56. Matsukawa R. Hirooka Y. Ito K. Sunagawa K. Inhibition of neuregulin-1/ErbB signaling in the rostral ventrolateral medulla leads to hypertension through reduced nitric oxide synthesis. Am. J. Hypertens. 2013 26 1 51 57 10.1093/ajh/hps005 23382327
    [Google Scholar]
  57. Armant D.R. Kilburn B.A. Petkova A. Human trophoblast survival at low oxygen concentrations requires metalloproteinase-mediated shedding of heparin-binding EGF-like growth factor. Development 2006 133 4 751 759 10.1242/dev.02237 16407398
    [Google Scholar]
  58. Liu X. Luo Q. Zheng Y. NOTCH4 signaling controls EFNB2-induced endothelial progenitor cell dysfunction in preeclampsia. Reproduction 2016 152 1 47 55 10.1530/REP‑16‑0132 27069008
    [Google Scholar]
  59. Salvucci O. Tosato G. Essential roles of EphB receptors and EphrinB ligands in endothelial cell function and angiogenesis. Adv. Cancer Res. 2012 114 21 57 10.1016/B978‑0‑12‑386503‑8.00002‑8 22588055
    [Google Scholar]
  60. Hur J. Yoon C.H. Kim H.S. Characterization of two types of endothelial progenitor cells and their different contributions to neovasculogenesis. Arterioscler. Thromb. Vasc. Biol. 2004 24 2 288 293 10.1161/01.ATV.0000114236.77009.06 14699017
    [Google Scholar]
  61. Steinle J.J. Meininger C.J. Chowdhury U. Wu G. Granger H.J. Role of ephrin B2 in human retinal endothelial cell proliferation and migration. Cell. Signal. 2003 15 11 1011 1017 10.1016/S0898‑6568(03)00072‑X 14499344
    [Google Scholar]
  62. Hirai H. Maru Y. Hagiwara K. Nishida J. Takaku F. A novel putative tyrosine kinase receptor encoded by the eph gene. Science 1987 238 4834 1717 1720 10.1126/science.2825356 2825356
    [Google Scholar]
  63. Hafner C. Becker B. Landthaler M. Vogt T. Expression profile of Eph receptors and ephrin ligands in human skin and downregulation of EphA1 in nonmelanoma skin cancer. Mod. Pathol. 2006 19 10 1369 1377 10.1038/modpathol.3800660 16862074
    [Google Scholar]
  64. Peng L. Wang H. Dong Y. Increased expression of EphA1 protein in prostate cancers correlates with high Gleason score. Int. J. Clin. Exp. Pathol. 2013 6 9 1854 1860 24040450
    [Google Scholar]
/content/journals/cdt/10.2174/0113894501401057250928032123
Loading
Clinical Deployment of Interpretable AI: Bridging Routine Clinical Tests and Proteomic Signatures for Preeclampsia Risk Stratification
Bentham Science Publishers ; https://doi.org/10.2174/0113894501401057250928032123
/content/journals/cdt/10.2174/0113894501401057250928032123
/content/journals/cdt/10.2174/0113894501401057250928032123
Loading

Data & Media loading...

Supplements

Supplementary material is available on the publisher’s website along with the published article.

file format download Download

  • Article Type:     Research Article
Keywords: routine clinical laboratory tests ; proteinuria (PRO) ; Preeclampsia ; machine learning ; webserver ; prediction

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test