TY - JOUR
T1 - Prediction of Preeclampsia and Intrauterine Growth Restriction
T2 - Development of Machine Learning Models on a Prospective Cohort
AU - Sufriyana, Herdiantri
AU - Wu, Yu-Wei
AU - Su, Emily Chia-Yu
N1 - Funding Information:
Tanja Premru-Srsen from the Department of Perinatology, Division of Obstetrics and Gynecology, University Medical Centre Ljubljana, Slovenia, provided the dataset in this study through the Mendeley Data repository. She also provided a reprint of the full text that initially reported this dataset. This study was funded by the Ministry of Science and Technology (MOST) in Taiwan (grant numbers MOST107-2221-E-038-016 and MOST108-2221-E-038-018) and the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan (grant numbers DP2-107-21121-01-A-01 and DP2-108-21121-01-A-01-04), with funding awarded to Emily Chia-Yu Su. The sponsors had no role in the research design or contents of the manuscript for publication.
Publisher Copyright:
© 2020 Herdiantri Sufriyana, Yu-Wei Wu, Emily Chia-Yu Su.
PY - 2020/5/18
Y1 - 2020/5/18
N2 - BACKGROUND: Preeclampsia and intrauterine growth restriction are placental dysfunction-related disorders (PDDs) that require a referral decision be made within a certain time period. An appropriate prediction model should be developed for these diseases. However, previous models did not demonstrate robust performances and/or they were developed from datasets with highly imbalanced classes. OBJECTIVE: In this study, we developed a predictive model of PDDs by machine learning that uses features at 24-37 weeks' gestation, including maternal characteristics, uterine artery (UtA) Doppler measures, soluble fms-like tyrosine kinase receptor-1 (sFlt-1), and placental growth factor (PlGF). METHODS: A public dataset was taken from a prospective cohort study that included pregnant women with PDDs (66/95, 69%) and a control group (29/95, 31%). Preliminary selection of features was based on a statistical analysis using SAS 9.4 (SAS Institute). We used Weka (Waikato Environment for Knowledge Analysis) 3.8.3 (The University of Waikato, Hamilton, NZ) to automatically select the best model using its optimization algorithm. We also manually selected the best of 23 white-box models. Models, including those from recent studies, were also compared by interval estimation of evaluation metrics. We used the Matthew correlation coefficient (MCC) as the main metric. It is not overoptimistic to evaluate the performance of a prediction model developed from a dataset with a class imbalance. Repeated 10-fold cross-validation was applied. RESULTS: The classification via regression model was chosen as the best model. Our model had a robust MCC (.93, 95% CI .87-1.00, vs .64, 95% CI .57-.71) and specificity (100%, 95% CI 100-100, vs 90%, 95% CI 90-90) compared to each metric of the best models from recent studies. The sensitivity of this model was not inferior (95%, 95% CI 91-100, vs 100%, 95% CI 92-100). The area under the receiver operating characteristic curve was also competitive (0.970, 95% CI 0.966-0.974, vs 0.987, 95% CI 0.980-0.994). Features in the best model were maternal weight, BMI, pulsatility index of the UtA, sFlt-1, and PlGF. The most important feature was the sFlt-1/PlGF ratio. This model used an M5P algorithm consisting of a decision tree and four linear models with different thresholds. Our study was also better than the best ones among recent studies in terms of the class balance and the size of the case class (66/95, 69%, vs 27/239, 11.3%). CONCLUSIONS: Our model had a robust predictive performance. It was also developed to deal with the problem of a class imbalance. In the context of clinical management, this model may improve maternal mortality and neonatal morbidity and reduce health care costs.
AB - BACKGROUND: Preeclampsia and intrauterine growth restriction are placental dysfunction-related disorders (PDDs) that require a referral decision be made within a certain time period. An appropriate prediction model should be developed for these diseases. However, previous models did not demonstrate robust performances and/or they were developed from datasets with highly imbalanced classes. OBJECTIVE: In this study, we developed a predictive model of PDDs by machine learning that uses features at 24-37 weeks' gestation, including maternal characteristics, uterine artery (UtA) Doppler measures, soluble fms-like tyrosine kinase receptor-1 (sFlt-1), and placental growth factor (PlGF). METHODS: A public dataset was taken from a prospective cohort study that included pregnant women with PDDs (66/95, 69%) and a control group (29/95, 31%). Preliminary selection of features was based on a statistical analysis using SAS 9.4 (SAS Institute). We used Weka (Waikato Environment for Knowledge Analysis) 3.8.3 (The University of Waikato, Hamilton, NZ) to automatically select the best model using its optimization algorithm. We also manually selected the best of 23 white-box models. Models, including those from recent studies, were also compared by interval estimation of evaluation metrics. We used the Matthew correlation coefficient (MCC) as the main metric. It is not overoptimistic to evaluate the performance of a prediction model developed from a dataset with a class imbalance. Repeated 10-fold cross-validation was applied. RESULTS: The classification via regression model was chosen as the best model. Our model had a robust MCC (.93, 95% CI .87-1.00, vs .64, 95% CI .57-.71) and specificity (100%, 95% CI 100-100, vs 90%, 95% CI 90-90) compared to each metric of the best models from recent studies. The sensitivity of this model was not inferior (95%, 95% CI 91-100, vs 100%, 95% CI 92-100). The area under the receiver operating characteristic curve was also competitive (0.970, 95% CI 0.966-0.974, vs 0.987, 95% CI 0.980-0.994). Features in the best model were maternal weight, BMI, pulsatility index of the UtA, sFlt-1, and PlGF. The most important feature was the sFlt-1/PlGF ratio. This model used an M5P algorithm consisting of a decision tree and four linear models with different thresholds. Our study was also better than the best ones among recent studies in terms of the class balance and the size of the case class (66/95, 69%, vs 27/239, 11.3%). CONCLUSIONS: Our model had a robust predictive performance. It was also developed to deal with the problem of a class imbalance. In the context of clinical management, this model may improve maternal mortality and neonatal morbidity and reduce health care costs.
KW - Intrauterine growth restriction
KW - Machine learning
KW - Preeclampsia
KW - SFlt-1/PlGF ratio
KW - Uterine artery Doppler
UR - http://www.scopus.com/inward/record.url?scp=85093890653&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093890653&partnerID=8YFLogxK
U2 - 10.2196/15411
DO - 10.2196/15411
M3 - Article
C2 - 32348266
SN - 2291-9694
VL - 8
SP - e15411
JO - JMIR medical informatics
JF - JMIR medical informatics
IS - 5
M1 - e15411
ER -