Predicting preterm birth using electronic medical records from multiple prenatal visits
Abstract This study aimed to predict preterm birth in nulliparous women using machine learning and easily accessible variables from prenatal visits. Elastic net regularized logistic regression models were developed and evaluated using 5-fold cross-validation on data from 8,830 women in the Nulliparo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-12-01
|
| Series: | BMC Pregnancy and Childbirth |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12884-024-07049-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112071455866880 |
|---|---|
| author | Chenyan Huang Xi Long Myrthe van der Ven Maurits Kaptein S. Guid Oei Edwin van den Heuvel |
| author_facet | Chenyan Huang Xi Long Myrthe van der Ven Maurits Kaptein S. Guid Oei Edwin van den Heuvel |
| author_sort | Chenyan Huang |
| collection | DOAJ |
| description | Abstract This study aimed to predict preterm birth in nulliparous women using machine learning and easily accessible variables from prenatal visits. Elastic net regularized logistic regression models were developed and evaluated using 5-fold cross-validation on data from 8,830 women in the Nulliparous Pregnancy Outcomes Study: New Mothers-to-Be (nuMoM2b) dataset at three prenatal visits: $$6^0$$ 6 0 - $$13^6$$ 13 6 , $$16^0$$ 16 0 - $$21^6$$ 21 6 , and $$22^0$$ 22 0 - $$29^6$$ 29 6 weeks of gestational age (GA). The models’ performance, assessed using Area Under the Curve (AUC), sensitivity, specificity, and accuracy, consistently improved with the incorporation of data from later prenatal visits. AUC scores increased from 0.6161 in the first visit to 0.7087 in the third visit, while sensitivity and specificity also showed notable improvements. The addition of ultrasound measurements, such as cervical length and Pulsatility Index, substantially enhanced the models’ predictive ability. Notably, the model achieved a sensitivity of 0.8254 and 0.9295 for predicting very preterm and extreme preterm births, respectively, at the third prenatal visit. These findings highlight the importance of ultrasound measurements and suggest that incorporating machine learning-based risk assessment and routine late-pregnancy ultrasounds into prenatal care could improve maternal and neonatal outcomes by enabling timely interventions for high-risk women. |
| format | Article |
| id | doaj-art-bf83a99a3ee04c87a32b9e9047df02a4 |
| institution | Kabale University |
| issn | 1471-2393 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pregnancy and Childbirth |
| spelling | doaj-art-bf83a99a3ee04c87a32b9e9047df02a42024-12-22T12:54:01ZengBMCBMC Pregnancy and Childbirth1471-23932024-12-0124112510.1186/s12884-024-07049-yPredicting preterm birth using electronic medical records from multiple prenatal visitsChenyan Huang0Xi Long1Myrthe van der Ven2Maurits Kaptein3S. Guid Oei4Edwin van den Heuvel5Department of Mathematics and Computer Science, Eindhoven University of TechnologyDepartment of Electrical Engineering, Eindhoven University of TechnologyDepartment of Biomedical Engineering, Eindhoven University of TechnologyDepartment of Mathematics and Computer Science, Eindhoven University of TechnologyDepartment of Electrical Engineering, Eindhoven University of TechnologyDepartment of Mathematics and Computer Science, Eindhoven University of TechnologyAbstract This study aimed to predict preterm birth in nulliparous women using machine learning and easily accessible variables from prenatal visits. Elastic net regularized logistic regression models were developed and evaluated using 5-fold cross-validation on data from 8,830 women in the Nulliparous Pregnancy Outcomes Study: New Mothers-to-Be (nuMoM2b) dataset at three prenatal visits: $$6^0$$ 6 0 - $$13^6$$ 13 6 , $$16^0$$ 16 0 - $$21^6$$ 21 6 , and $$22^0$$ 22 0 - $$29^6$$ 29 6 weeks of gestational age (GA). The models’ performance, assessed using Area Under the Curve (AUC), sensitivity, specificity, and accuracy, consistently improved with the incorporation of data from later prenatal visits. AUC scores increased from 0.6161 in the first visit to 0.7087 in the third visit, while sensitivity and specificity also showed notable improvements. The addition of ultrasound measurements, such as cervical length and Pulsatility Index, substantially enhanced the models’ predictive ability. Notably, the model achieved a sensitivity of 0.8254 and 0.9295 for predicting very preterm and extreme preterm births, respectively, at the third prenatal visit. These findings highlight the importance of ultrasound measurements and suggest that incorporating machine learning-based risk assessment and routine late-pregnancy ultrasounds into prenatal care could improve maternal and neonatal outcomes by enabling timely interventions for high-risk women.https://doi.org/10.1186/s12884-024-07049-yPreterm birthPredictionMachine learningLogistics regression |
| spellingShingle | Chenyan Huang Xi Long Myrthe van der Ven Maurits Kaptein S. Guid Oei Edwin van den Heuvel Predicting preterm birth using electronic medical records from multiple prenatal visits BMC Pregnancy and Childbirth Preterm birth Prediction Machine learning Logistics regression |
| title | Predicting preterm birth using electronic medical records from multiple prenatal visits |
| title_full | Predicting preterm birth using electronic medical records from multiple prenatal visits |
| title_fullStr | Predicting preterm birth using electronic medical records from multiple prenatal visits |
| title_full_unstemmed | Predicting preterm birth using electronic medical records from multiple prenatal visits |
| title_short | Predicting preterm birth using electronic medical records from multiple prenatal visits |
| title_sort | predicting preterm birth using electronic medical records from multiple prenatal visits |
| topic | Preterm birth Prediction Machine learning Logistics regression |
| url | https://doi.org/10.1186/s12884-024-07049-y |
| work_keys_str_mv | AT chenyanhuang predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits AT xilong predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits AT myrthevanderven predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits AT mauritskaptein predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits AT sguidoei predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits AT edwinvandenheuvel predictingpretermbirthusingelectronicmedicalrecordsfrommultipleprenatalvisits |