Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data
Abstract Preeclampsia is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to reduce the risk of adverse outcomes. We assessed whether information routinely co...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00612-x |
| _version_ | 1797422267759591424 |
|---|---|
| author | Shilong Li Zichen Wang Luciana A. Vieira Amanda B. Zheutlin Boshu Ru Emilio Schadt Pei Wang Alan B. Copperman Joanne L. Stone Susan J. Gross Yu-Han Kao Yan Kwan Lau Siobhan M. Dolan Eric E. Schadt Li Li |
| author_facet | Shilong Li Zichen Wang Luciana A. Vieira Amanda B. Zheutlin Boshu Ru Emilio Schadt Pei Wang Alan B. Copperman Joanne L. Stone Susan J. Gross Yu-Han Kao Yan Kwan Lau Siobhan M. Dolan Eric E. Schadt Li Li |
| author_sort | Shilong Li |
| collection | DOAJ |
| description | Abstract Preeclampsia is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to reduce the risk of adverse outcomes. We assessed whether information routinely collected in electronic medical records (EMR) could enhance the prediction of preeclampsia risk beyond what is achieved in standard of care assessments. We developed a digital phenotyping algorithm to curate 108,557 pregnancies from EMRs across the Mount Sinai Health System, accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset (N = 60,879) to construct predictive models of preeclampsia across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted preeclampsia with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.82, and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts. While our machine learning approach identified known risk factors of preeclampsia (such as blood pressure, weight, and maternal age), it also identified other potential risk factors, such as complete blood count related characteristics for the antepartum period. Our model not only has utility for earlier identification of patients at risk for preeclampsia, but given the prediction accuracy exceeds what is currently achieved in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk. |
| first_indexed | 2024-03-09T07:29:45Z |
| format | Article |
| id | doaj.art-f7dd65b8756b4da2b60e0a23520b716d |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T07:29:45Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-f7dd65b8756b4da2b60e0a23520b716d2023-12-03T06:36:29ZengNature Portfolionpj Digital Medicine2398-63522022-06-015111610.1038/s41746-022-00612-xImproving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record dataShilong Li0Zichen Wang1Luciana A. Vieira2Amanda B. Zheutlin3Boshu Ru4Emilio Schadt5Pei Wang6Alan B. Copperman7Joanne L. Stone8Susan J. Gross9Yu-Han Kao10Yan Kwan Lau11Siobhan M. Dolan12Eric E. Schadt13Li Li14Sema4Sema4Department of Obstetrics, Gynecology, and Reproductive Science, Icahn School of Medicine at Mount SinaiSema4Sema4Sema4Department of Genetics and Genomic Sciences, The Icahn Institute for Genomics and Multiscale Biology, Icahn School of Medicine at Mount SinaiSema4Department of Obstetrics, Gynecology, and Reproductive Science, Icahn School of Medicine at Mount SinaiSema4Sema4Sema4Department of Obstetrics, Gynecology, and Reproductive Science, Icahn School of Medicine at Mount SinaiSema4Sema4Abstract Preeclampsia is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to reduce the risk of adverse outcomes. We assessed whether information routinely collected in electronic medical records (EMR) could enhance the prediction of preeclampsia risk beyond what is achieved in standard of care assessments. We developed a digital phenotyping algorithm to curate 108,557 pregnancies from EMRs across the Mount Sinai Health System, accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset (N = 60,879) to construct predictive models of preeclampsia across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted preeclampsia with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.82, and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts. While our machine learning approach identified known risk factors of preeclampsia (such as blood pressure, weight, and maternal age), it also identified other potential risk factors, such as complete blood count related characteristics for the antepartum period. Our model not only has utility for earlier identification of patients at risk for preeclampsia, but given the prediction accuracy exceeds what is currently achieved in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk.https://doi.org/10.1038/s41746-022-00612-x |
| spellingShingle | Shilong Li Zichen Wang Luciana A. Vieira Amanda B. Zheutlin Boshu Ru Emilio Schadt Pei Wang Alan B. Copperman Joanne L. Stone Susan J. Gross Yu-Han Kao Yan Kwan Lau Siobhan M. Dolan Eric E. Schadt Li Li Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data npj Digital Medicine |
| title | Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| title_full | Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| title_fullStr | Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| title_full_unstemmed | Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| title_short | Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| title_sort | improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data |
| url | https://doi.org/10.1038/s41746-022-00612-x |
| work_keys_str_mv | AT shilongli improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT zichenwang improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT lucianaavieira improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT amandabzheutlin improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT boshuru improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT emilioschadt improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT peiwang improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT alanbcopperman improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT joannelstone improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT susanjgross improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT yuhankao improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT yankwanlau improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT siobhanmdolan improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT ericeschadt improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata AT lili improvingpreeclampsiariskpredictionbymodelingpregnancytrajectoriesfromroutinelycollectedelectronicmedicalrecorddata |