Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance

Background: Hypertensive disorders of pregnancy (HDP) are significant drivers of maternal and neonatal morbidity and mortality. Current management strategies include early identification and initiation of risk mitigating interventions facilitated by a rules-based checklist. Advanced analytic techniq...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonathan S. Schor, PhD, Adesh Kadambi, BEng, Isabel Fulcher, PhD, Kartik K. Venkatesh, MD, PhD, Mark A. Clapp, MD, MPH, Senan Ebrahim, MD, PhD, Ali Ebrahim, PhD, Timothy Wen, MD, MPH
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:AJOG Global Reports
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666577824000807
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122073526632448
author Jonathan S. Schor, PhD
Adesh Kadambi, BEng
Isabel Fulcher, PhD
Kartik K. Venkatesh, MD, PhD
Mark A. Clapp, MD, MPH
Senan Ebrahim, MD, PhD
Ali Ebrahim, PhD
Timothy Wen, MD, MPH
author_facet Jonathan S. Schor, PhD
Adesh Kadambi, BEng
Isabel Fulcher, PhD
Kartik K. Venkatesh, MD, PhD
Mark A. Clapp, MD, MPH
Senan Ebrahim, MD, PhD
Ali Ebrahim, PhD
Timothy Wen, MD, MPH
author_sort Jonathan S. Schor, PhD
collection DOAJ
description Background: Hypertensive disorders of pregnancy (HDP) are significant drivers of maternal and neonatal morbidity and mortality. Current management strategies include early identification and initiation of risk mitigating interventions facilitated by a rules-based checklist. Advanced analytic techniques, such as machine learning, can potentially offer improved and refined predictive capabilities. Objective: To develop and internally validate a machine learning prediction model for hypertensive disorders of pregnancy (HDP) when initiating prenatal care. Study Design: We developed a prediction model using data from the prospective multisite cohort Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) among low-risk individuals without a prior history of aspirin utilization for preeclampsia prevention. The primary outcome was the development of HDP. Random forest modeling was utilized to develop predictive models. Recursive feature elimination (RFE) was employed to create a reduced model for each outcome. Area under the curve (AUC), 95% confidence intervals (CI), and calibration curves were utilized to assess discrimination and accuracy. Sensitivity analyses were conducted to compare the sensitivity and specificity of the reduced model compared to existing risk factor-based algorithms. Results: Of 9,124 assessed low risk nulliparous individuals, 21% (n=1,927) developed HDP. The prediction model for HDP had satisfactory discrimination with an AUC of 0.73 (95% CI: 0.70, 0.75). After RFE, a parsimonious reduced model with 30 features was created with an AUC of 0.71 (95% CI: 0.68, 0.74). Variables included in the model after RFE included body mass index at the first study visit, pre-pregnancy weight, first trimester complete blood count results, and maximum systolic blood pressure at the first visit. Calibration curves for all models revealed relatively stable agreement between predicted and observed probabilities. Sensitivity analysis noted superior sensitivity (AUC 0.80 vs 0.65) and specificity (0.65 vs 0.53) of the model compared to traditional risk factor-based algorithms. Conclusion: In cohort of low-risk nulliparous pregnant individuals, a prediction model may accurately predict HDP diagnosis at the time of initiating prenatal care and aid employment of close interval monitoring and prophylactic measures earlier in pregnancy.
format Article
id doaj-art-b9c9fbd9e0294937bacd1c5dea807909
institution Kabale University
issn 2666-5778
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series AJOG Global Reports
spelling doaj-art-b9c9fbd9e0294937bacd1c5dea8079092024-12-15T06:17:11ZengElsevierAJOG Global Reports2666-57782024-11-0144100386Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a GlanceJonathan S. Schor, PhD0Adesh Kadambi, BEng1Isabel Fulcher, PhD2Kartik K. Venkatesh, MD, PhD3Mark A. Clapp, MD, MPH4Senan Ebrahim, MD, PhD5Ali Ebrahim, PhD6Timothy Wen, MD, MPH7Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen); University of California, San Francisco (UCSF) Medical Scientist Training Program, San Francisco, CA, USA (Schor)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen); Department of Biomedical Engineering, University of Toronto, Toronto, Canada (Kadambi)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen); Department of Global Health and Social Medicine, Harvard Medical School, Boston, Massachusetts, USA (Fulcher)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen); Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Ohio State University Medical Center, Columbus, OH, USA (Venkatesh)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen)Delfina Care Inc, San Francisco, CA, USA (Schor, Kadambi, Fulcher, Venkatesh, Clapp, Ebrahim, Ebrahim and Wen); Division of Maternal Fetal Medicine, Department of Obstetrics, Gynecology, and Reproductive Sciences, University of California, San Francisco (UCSF), San Francisco, CA USA (Wen); Corresponding author: Timothy Wen, MD, MPH.Background: Hypertensive disorders of pregnancy (HDP) are significant drivers of maternal and neonatal morbidity and mortality. Current management strategies include early identification and initiation of risk mitigating interventions facilitated by a rules-based checklist. Advanced analytic techniques, such as machine learning, can potentially offer improved and refined predictive capabilities. Objective: To develop and internally validate a machine learning prediction model for hypertensive disorders of pregnancy (HDP) when initiating prenatal care. Study Design: We developed a prediction model using data from the prospective multisite cohort Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) among low-risk individuals without a prior history of aspirin utilization for preeclampsia prevention. The primary outcome was the development of HDP. Random forest modeling was utilized to develop predictive models. Recursive feature elimination (RFE) was employed to create a reduced model for each outcome. Area under the curve (AUC), 95% confidence intervals (CI), and calibration curves were utilized to assess discrimination and accuracy. Sensitivity analyses were conducted to compare the sensitivity and specificity of the reduced model compared to existing risk factor-based algorithms. Results: Of 9,124 assessed low risk nulliparous individuals, 21% (n=1,927) developed HDP. The prediction model for HDP had satisfactory discrimination with an AUC of 0.73 (95% CI: 0.70, 0.75). After RFE, a parsimonious reduced model with 30 features was created with an AUC of 0.71 (95% CI: 0.68, 0.74). Variables included in the model after RFE included body mass index at the first study visit, pre-pregnancy weight, first trimester complete blood count results, and maximum systolic blood pressure at the first visit. Calibration curves for all models revealed relatively stable agreement between predicted and observed probabilities. Sensitivity analysis noted superior sensitivity (AUC 0.80 vs 0.65) and specificity (0.65 vs 0.53) of the model compared to traditional risk factor-based algorithms. Conclusion: In cohort of low-risk nulliparous pregnant individuals, a prediction model may accurately predict HDP diagnosis at the time of initiating prenatal care and aid employment of close interval monitoring and prophylactic measures earlier in pregnancy.http://www.sciencedirect.com/science/article/pii/S2666577824000807Hypertensive disorders of pregnancyMachine learningRisk prediction
spellingShingle Jonathan S. Schor, PhD
Adesh Kadambi, BEng
Isabel Fulcher, PhD
Kartik K. Venkatesh, MD, PhD
Mark A. Clapp, MD, MPH
Senan Ebrahim, MD, PhD
Ali Ebrahim, PhD
Timothy Wen, MD, MPH
Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
AJOG Global Reports
Hypertensive disorders of pregnancy
Machine learning
Risk prediction
title Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
title_full Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
title_fullStr Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
title_full_unstemmed Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
title_short Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance
title_sort using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortajog global reports at a glance
topic Hypertensive disorders of pregnancy
Machine learning
Risk prediction
url http://www.sciencedirect.com/science/article/pii/S2666577824000807
work_keys_str_mv AT jonathansschorphd usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT adeshkadambibeng usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT isabelfulcherphd usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT kartikkvenkateshmdphd usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT markaclappmdmph usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT senanebrahimmdphd usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT aliebrahimphd usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance
AT timothywenmdmph usingmachinelearningtopredicttheriskofdevelopinghypertensivedisordersofpregnancyusingacontemporarynulliparouscohortajogglobalreportsataglance