Preterm Birth Prediction: Stable Selection of Interpretable Rules from High Dimensional Data

Truyen Tran, Wei Luo, Dinh Phung, Jonathan Morris, Kristen Rickard, Svetha Venkatesh
Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:164-177, 2016.

Abstract

Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2–24.2% at specificity of 28.6–33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.

Cite this Paper

BibTeX
@InProceedings{pmlr-v56-Tran16, title = {Preterm Birth Prediction: Stable Selection of Interpretable Rules from High Dimensional Data}, author = {Tran, Truyen and Luo, Wei and Phung, Dinh and Morris, Jonathan and Rickard, Kristen and Venkatesh, Svetha}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {164--177}, 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/Tran16.pdf}, url = {https://proceedings.mlr.press/v56/Tran16.html}, abstract = {Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2–24.2% at specificity of 28.6–33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.} }
Endnote
%0 Conference Paper %T Preterm Birth Prediction: Stable Selection of Interpretable Rules from High Dimensional Data %A Truyen Tran %A Wei Luo %A Dinh Phung %A Jonathan Morris %A Kristen Rickard %A Svetha Venkatesh %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-Tran16 %I PMLR %P 164--177 %U https://proceedings.mlr.press/v56/Tran16.html %V 56 %X Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2–24.2% at specificity of 28.6–33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.
RIS
TY - CPAPER TI - Preterm Birth Prediction: Stable Selection of Interpretable Rules from High Dimensional Data AU - Truyen Tran AU - Wei Luo AU - Dinh Phung AU - Jonathan Morris AU - Kristen Rickard AU - Svetha Venkatesh 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-Tran16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 56 SP - 164 EP - 177 L1 - http://proceedings.mlr.press/v56/Tran16.pdf UR - https://proceedings.mlr.press/v56/Tran16.html AB - Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2–24.2% at specificity of 28.6–33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%. ER -
APA
Tran, T., Luo, W., Phung, D., Morris, J., Rickard, K. & Venkatesh, S.. (2016). Preterm Birth Prediction: Stable Selection of Interpretable Rules from High Dimensional Data. Proceedings of the 1st Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 56:164-177 Available from https://proceedings.mlr.press/v56/Tran16.html.

Related Material