Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning

Paola, Ayala-Ramírez; Daniela, Mennickent; Carlos, Farkas; Enrique, Guzmán-Gutiérrez; Eduardo, Retamal-Fredes; Nancy, Segura-Guzmán; Diego, Roca; Manuel, Venegas; Matias, Carrillo-Muñoz; Yanitza, Gutierrez-Monsalve; Doris, Sanabria; Catalina, Ospina; Jaime, Silva; Mercedes, Olaya-C.; Reggie, García-Robles

doi:10.3390/biomedicines13081958

Open AccessArticle

Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning

by

Ayala-Ramírez Paola

^1,2,*,†

,

Mennickent Daniela

^3,4,*,†

,

Farkas Carlos

³

,

Guzmán-Gutiérrez Enrique

^2,4,5

,

Retamal-Fredes Eduardo

⁶,

Segura-Guzmán Nancy

⁷,

Roca Diego

⁸,

Venegas Manuel

⁷,

Carrillo-Muñoz Matias

⁷

,

Gutierrez-Monsalve Yanitza

⁷,

Sanabria Doris

⁹,

Ospina Catalina

¹⁰,

Silva Jaime

¹⁰,

Olaya-C. Mercedes

¹¹

and

García-Robles Reggie

^1,2,12

¹

Human Genetics Institute, Faculty of Medicine, Pontificia Universidad Javeriana, Bogotá 110231, Colombia

²

Red Iberoamericana de Alteraciones Vasculares en Trastornos del Embarazo (RIVATREM), Chillán 3780000, Chile

³

Departamento de Ciencias Básicas y Morfología, Facultad de Medicina, Universidad Católica de la Santísima Concepción, Concepción 4090541, Chile

⁴

Grupo Inicial de Investigación en Tecnología e Innovación en Salud para el Bienestar de las Personas (VITALIS), Universidad Católica de la Santísima Concepción, Concepción 4090541, Chile

⁵

Departamento de Bioquímica Clínica e Inmunología, Facultad de Farmacia, Universidad de Concepción, Concepción 4070386, Chile

⁶

Tecnología Médica con Mención en Imagenología y Física Médica, Facultad de Medicina, Universidad Católica de la Santísima Concepción, Concepción 4090541, Chile

⁷

Magíster en Ciencias Biomédicas, Facultad de Medicina, Universidad Católica de la Santísima Concepción, Concepción 4090541, Chile

⁸

Nutrición y Dietética, Facultad de Medicina, Universidad Católica de la Santísima Concepción, Concepción 4090541, Chile

⁹

Research Seedbed in Perinatal Medicine, Faculty of Medicine, Pontificia Universidad Javeriana, Hospital Universitario San Ignacio, Bogotá 110231, Colombia

¹⁰

Department of Obstetrics and Gynecology, Faculty of Medicine, Pontificia Universidad Javeriana, Hospital Universitario San Ignacio, Bogotá 110231, Colombia

¹¹

Department of Pathology, Faculty of Medicine, Pontificia Universidad Javeriana, Hospital Universitario San Ignacio, Bogotá 110231, Colombia

¹²

Department of Physiological Sciences, Faculty of Medicine, Pontificia Universidad Javeriana, Bogotá 110231, Colombia

Show full affiliation list

Hide full affiliation list

^*

Authors to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Biomedicines 2025, 13(8), 1958; https://doi.org/10.3390/biomedicines13081958

Submission received: 29 May 2025 / Revised: 25 July 2025 / Accepted: 30 July 2025 / Published: 12 August 2025

(This article belongs to the Special Issue Pathogenesis, Diagnostics and Therapeutics in Obsterics and Gynaecology)

Download

Browse Figures

Review Reports Versions Notes

Abstract

Background/Objectives: Preeclampsia (PE) is a major cause of maternal and perinatal morbidity and mortality, particularly in low- and middle-income countries. Early-onset PE (EOP) and late-onset PE (LOP) are distinct clinical entities with differing pathophysiological mechanisms and prognoses. However, few studies have explored differential risk factors for EOP and LOP in Latin American populations. This study aimed to identify and assess clinical risk factors for predicting EOP and LOP in a cohort of pregnant women from Bogotá, Colombia, using traditional statistics and machine learning (ML). Methods: A cross-sectional observational study was conducted on 190 pregnant women diagnosed with PE (EOP = 80, LOP = 110) at a tertiary hospital in Bogotá between 2017 and 2018. Risk factors and perinatal outcomes were collected via structured interviews and clinical records. Traditional statistical analyses were performed to compare the study groups and identify associations between risk factors and outcomes. Eleven ML techniques were used to train and externally validate predictive models for PE subtype and secondary outcomes, incorporating permutation-based feature importance to enhance interpretability. Results: EOP was significantly associated with higher maternal education and history of hypertension, while LOP was linked to a higher prevalence of allergic history. The best-performing ML model for predicting PE subtype was linear discriminant analysis (recall = 0.71), with top predictors including education level, family history of perinatal death, number of sexual partners, primipaternity, and family history of hypertension. Conclusions: EOP and LOP exhibit distinct clinical profiles in this cohort. The combination of traditional statistics with ML may improve early risk stratification and support context-specific prenatal care strategies in similar settings.

Keywords: late-onset preeclampsia; early-onset preeclampsia; hypertension in pregnancy; Latin America; risk factors; traditional statistics; machine learning; artificial intelligence

Share and Cite

MDPI and ACS Style

Paola, A.-R.; Daniela, M.; Carlos, F.; Enrique, G.-G.; Eduardo, R.-F.; Nancy, S.-G.; Diego, R.; Manuel, V.; Matias, C.-M.; Yanitza, G.-M.; et al. Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning. Biomedicines 2025, 13, 1958. https://doi.org/10.3390/biomedicines13081958

AMA Style

Paola A-R, Daniela M, Carlos F, Enrique G-G, Eduardo R-F, Nancy S-G, Diego R, Manuel V, Matias C-M, Yanitza G-M, et al. Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning. Biomedicines. 2025; 13(8):1958. https://doi.org/10.3390/biomedicines13081958

Chicago/Turabian Style

Paola, Ayala-Ramírez, Mennickent Daniela, Farkas Carlos, Guzmán-Gutiérrez Enrique, Retamal-Fredes Eduardo, Segura-Guzmán Nancy, Roca Diego, Venegas Manuel, Carrillo-Muñoz Matias, Gutierrez-Monsalve Yanitza, and et al. 2025. "Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning" Biomedicines 13, no. 8: 1958. https://doi.org/10.3390/biomedicines13081958

APA Style

Paola, A.-R., Daniela, M., Carlos, F., Enrique, G.-G., Eduardo, R.-F., Nancy, S.-G., Diego, R., Manuel, V., Matias, C.-M., Yanitza, G.-M., Doris, S., Catalina, O., Jaime, S., Mercedes, O.-C., & Reggie, G.-R. (2025). Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning. Biomedicines, 13(8), 1958. https://doi.org/10.3390/biomedicines13081958

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI