EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development and validation of a lasso-logistic regression-based risk prediction model for retinopathy in patients with hypertensive disorders of pregnancy

Shuzhen Gan, Yuanyuan Liu, Caiping Lai, Qiong Li

Frontiers in Cardiovascular Medicine · 15.04.2026 · 13

DOI: 10.3389/fcvm.2026.1796366 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Cardiovascular Medicine, online erschienen am 15.04.2026. Verfasst von Shuzhen Gan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics, Ganzhou People's Hospital, Ganzhou, Jiangxi, China. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To identify risk factors for retinopathy in patients with hypertensive disorders of pregnancy (HDP) and develop a predictive nomogram model.

Methods

A total of 667 patients with PIH treated at our hospital between December 2020 and December 2025 were retrospectively enrolled based on M. Kendall sample size estimation. Patients were randomly assigned to a development cohort ( n = 400) and an internal validation cohort ( n = 267) in a 6:4 ratio. According to the occurrence of retinopathy, the modeling group was further divided into a retinopathy group ( n = 112) and a non-retinopathy group ( n = 288). Additionally, 200 PIH patients from Xunwu County People's Hospital (January 2021 to December 2024) were included as an external validation cohort. LASSO regression was used to screen potential predictors, followed by multivariate logistic regression to identify independent risk factors. A nomogram prediction model was constructed. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).

Results

Among the 400 patients in the modeling group, 112 developed retinopathy, with an incidence of 28.0%. Eight potential predictors were identified by LASSO regression. Multivariate analysis revealed that HDP onset <28 weeks (OR = 7.027), disease duration >3 weeks (OR = 11.548), proteinuria (+++) (OR = 14.535), hematocrit >0.35 (OR = 16.733), and systolic blood pressure (OR = 1.143) were independent risk factors (all P < 0.05). Pre-pregnancy BMI (OR = 0.308), albumin (OR = 0.654), and platelet count (OR = 0.961) were independent protective factors ( P < 0.05). The nomogram demonstrated good calibration in the training, internal validation, and external validation cohorts. The AUC values were 0.948 (95% CI: 0.925–0.970), 0.921 (95% CI: 0.881–0.962), and 0.907 (95% CI: 0.842–0.972), respectively. DCA showed favorable net clinical benefit across a wide range of threshold probabilities.

Conclusion

The nomogram based on clinical and laboratory indicators demonstrated good discrimination and calibration in internal and external validation of retinopathy risk in PIH patients, with good clinical applicability.

Schlagwörter

Stichwörter der Autor:innen

lasso-logistic regressionnomogrampregnancy induced hypertensionretinopathyrisk prediction model

Autor:innen und Institutionen

  • Department of Obstetrics, Ganzhou People's Hospital, Ganzhou, Jiangxi, China.
  • Department of Obstetrics, Xunwu County People's Hospital, Ganzhou, Jiangxi, China.

Zitieren

APA

Gan, S., Liu, Y., Lai, C., & Li, Q. (2026). Development and validation of a lasso-logistic regression-based risk prediction model for retinopathy in patients with hypertensive disorders of pregnancy. Frontiers in Cardiovascular Medicine, 13. https://doi.org/10.3389/fcvm.2026.1796366

Vancouver

Gan S, Liu Y, Lai C, Li Q. Development and validation of a lasso-logistic regression-based risk prediction model for retinopathy in patients with hypertensive disorders of pregnancy. Frontiers in Cardiovascular Medicine. 2026;13. doi:10.3389/fcvm.2026.1796366

BibTeX
@article{Gan2026,
  author = {Gan, Shuzhen and Liu, Yuanyuan and Lai, Caiping and Li, Qiong},
  title = {Development and validation of a lasso-logistic regression-based risk prediction model for retinopathy in patients with hypertensive disorders of pregnancy},
  journal = {Frontiers in Cardiovascular Medicine},
  year = {2026},
  volume = {13},
  doi = {10.3389/fcvm.2026.1796366}
}
Kostenlos starten →