Using Kernel Methods and Model Selection for Prediction of Preterm Birth

Ilia Vovsha, Ansaf Salleb-Aouissi, Anita Raja, Thomas Koch, Alex Rybchuk, Axinia Radeva, Ashwath Rajan, Yiwen Huang, Hatim Diab, Ashish Tomar, Ronald Wapner
Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:55-72, 2016.

Abstract

We describe an application of machine learning to the problem of predicting preterm birth. We conduct a secondary analysis on a clinical trial dataset collected by the National Institute of Child Health and Human Development (NICHD) while focusing our attention on predicting different classes of preterm birth. We compare three approaches for deriving predictive models: a support vector machine (SVM) approach with linear and non-linear kernels, logistic regression with different model selection along with a model based on decision rules prescribed by physician experts for prediction of preterm birth. Our approach highlights the pre-processing methods applied to handle the inherent dynamics, noise and gaps in the data and describe techniques used to handle skewed class distributions. Empirical experiments demonstrate significant improvement in predicting preterm birth compared to past work.

Cite this Paper


BibTeX
@InProceedings{pmlr-v56-Vovsha16, title = {Using Kernel Methods and Model Selection for Prediction of Preterm Birth}, author = {Vovsha, Ilia and Salleb-Aouissi, Ansaf and Raja, Anita and Koch, Thomas and Rybchuk, Alex and Radeva, Axinia and Rajan, Ashwath and Huang, Yiwen and Diab, Hatim and Tomar, Ashish and Wapner, Ronald}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {55--72}, year = {2016}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Wallace, Byron and Wiens, Jenna}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Vovsha16.pdf}, url = {https://proceedings.mlr.press/v56/Vovsha16.html}, abstract = {We describe an application of machine learning to the problem of predicting preterm birth. We conduct a secondary analysis on a clinical trial dataset collected by the National Institute of Child Health and Human Development (NICHD) while focusing our attention on predicting different classes of preterm birth. We compare three approaches for deriving predictive models: a support vector machine (SVM) approach with linear and non-linear kernels, logistic regression with different model selection along with a model based on decision rules prescribed by physician experts for prediction of preterm birth. Our approach highlights the pre-processing methods applied to handle the inherent dynamics, noise and gaps in the data and describe techniques used to handle skewed class distributions. Empirical experiments demonstrate significant improvement in predicting preterm birth compared to past work.} }
Endnote
%0 Conference Paper %T Using Kernel Methods and Model Selection for Prediction of Preterm Birth %A Ilia Vovsha %A Ansaf Salleb-Aouissi %A Anita Raja %A Thomas Koch %A Alex Rybchuk %A Axinia Radeva %A Ashwath Rajan %A Yiwen Huang %A Hatim Diab %A Ashish Tomar %A Ronald Wapner %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Vovsha16 %I PMLR %P 55--72 %U https://proceedings.mlr.press/v56/Vovsha16.html %V 56 %X We describe an application of machine learning to the problem of predicting preterm birth. We conduct a secondary analysis on a clinical trial dataset collected by the National Institute of Child Health and Human Development (NICHD) while focusing our attention on predicting different classes of preterm birth. We compare three approaches for deriving predictive models: a support vector machine (SVM) approach with linear and non-linear kernels, logistic regression with different model selection along with a model based on decision rules prescribed by physician experts for prediction of preterm birth. Our approach highlights the pre-processing methods applied to handle the inherent dynamics, noise and gaps in the data and describe techniques used to handle skewed class distributions. Empirical experiments demonstrate significant improvement in predicting preterm birth compared to past work.
RIS
TY - CPAPER TI - Using Kernel Methods and Model Selection for Prediction of Preterm Birth AU - Ilia Vovsha AU - Ansaf Salleb-Aouissi AU - Anita Raja AU - Thomas Koch AU - Alex Rybchuk AU - Axinia Radeva AU - Ashwath Rajan AU - Yiwen Huang AU - Hatim Diab AU - Ashish Tomar AU - Ronald Wapner BT - Proceedings of the 1st Machine Learning for Healthcare Conference DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Vovsha16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 56 SP - 55 EP - 72 L1 - http://proceedings.mlr.press/v56/Vovsha16.pdf UR - https://proceedings.mlr.press/v56/Vovsha16.html AB - We describe an application of machine learning to the problem of predicting preterm birth. We conduct a secondary analysis on a clinical trial dataset collected by the National Institute of Child Health and Human Development (NICHD) while focusing our attention on predicting different classes of preterm birth. We compare three approaches for deriving predictive models: a support vector machine (SVM) approach with linear and non-linear kernels, logistic regression with different model selection along with a model based on decision rules prescribed by physician experts for prediction of preterm birth. Our approach highlights the pre-processing methods applied to handle the inherent dynamics, noise and gaps in the data and describe techniques used to handle skewed class distributions. Empirical experiments demonstrate significant improvement in predicting preterm birth compared to past work. ER -
APA
Vovsha, I., Salleb-Aouissi, A., Raja, A., Koch, T., Rybchuk, A., Radeva, A., Rajan, A., Huang, Y., Diab, H., Tomar, A. & Wapner, R.. (2016). Using Kernel Methods and Model Selection for Prediction of Preterm Birth. Proceedings of the 1st Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 56:55-72 Available from https://proceedings.mlr.press/v56/Vovsha16.html.

Related Material