Display options
Cite
Li T, Gao C, Yan C, et al. Predicting Neonatal Encephalopathy From Maternal Data in Electronic Medical Records. AMIA Jt Summits Transl Sci Proc. 2018;2017:359-368
Li, T., Gao, C., Yan, C., Osmundson, S., Malin, B. A., & Chen, Y. (2018). Predicting Neonatal Encephalopathy From Maternal Data in Electronic Medical Records. AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science, 2017359-368.
Li, Thomas, et al. "Predicting Neonatal Encephalopathy From Maternal Data in Electronic Medical Records." AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science vol. 2017 (2018): 359-368.
Li T, Gao C, Yan C, Osmundson S, Malin BA, Chen Y. Predicting Neonatal Encephalopathy From Maternal Data in Electronic Medical Records. AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:359-368. eCollection 2018. PMID: 29888094; PMCID: PMC5961831.
Copy Download .nbib Format: NLM
Share it on

AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:359-368. eCollection 2018.

Predicting Neonatal Encephalopathy From Maternal Data in Electronic Medical Records.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science

Thomas Li, Cheng Gao, Chao Yan, Sarah Osmundson, Bradley A Malin, You Chen

Affiliations

  1. Duke University, Durham, NC.
  2. Vanderbilt University, Nashville, TN.

PMID: 29888094 PMCID: PMC5961831

Abstract

Neonatal encephalopathy (NE) is a leading cause of neonatal mortality and lifetime neurological disability. The earlier the risk of NE can be assessed, the more effective interventions can be in preventing adverse outcomes. Existing studies that focus on intrapartum risk factors do not provide the early prognostic forecasting necessary to prepare healthcare professionals to intervene early in a high-risk NE case. This work used maternal data in a supervised machine learning framework to predict NE events. Specifically, we 1) collected the electronic medical records (EMRs) for 104 NE newborns and 31,054 non-NE newborns and their mothers, 2) trained and tested a regularized logistic regression on imbalanced and high-dimensional EMR data, and 3) discerned important features that could be possible risk factors. The learned model offers prenatal predictions of NE cases with an average area under the receiving operator characteristic curve (AUC) of 87% and identified the most important predictors.

References

  1. AMIA Annu Symp Proc. 2003;:1065 - PubMed
  2. Br J Obstet Gynaecol. 1990 Oct;97(10):883-92 - PubMed
  3. J Matern Fetal Neonatal Med. 2018 Jun;31(12 ):1595-1601 - PubMed
  4. Ann Nutr Metab. 2015;66 Suppl 2:14-20 - PubMed
  5. J Stat Softw. 2010;33(1):1-22 - PubMed
  6. BMJ. 1998 Dec 5;317(7172):1549-53 - PubMed
  7. Obstet Gynecol. 2007 Oct;110(4):801-7 - PubMed
  8. Dev Med Child Neurol. 2008 Jan;50(1):9 - PubMed
  9. Arch Pediatr Adolesc Med. 2007 Jul;161(7):663-8 - PubMed
  10. East Afr Med J. 2003 Mar;80(3):140-3 - PubMed
  11. N Engl J Med. 2004 Dec 16;351(25):2581-9 - PubMed
  12. Arch Gynecol Obstet. 2017 Sep;296(3):503-512 - PubMed
  13. J Perinatol. 2005 Jul;25(7):447-52 - PubMed
  14. Pediatrics. 2013 Oct;132(4):e952-9 - PubMed
  15. J Matern Fetal Neonatal Med. 2018 Mar;31(6):791-796 - PubMed
  16. Early Hum Dev. 2010 Jun;86(6):329-38 - PubMed

Publication Types

Grant support