Literature DB >> 32168227

Machine Learning and Statistical Models to Predict Postpartum Hemorrhage.

Kartik K Venkatesh1, Robert A Strauss, Chad A Grotegut, R Philip Heine, Nancy C Chescheir, Jeffrey S A Stringer, David M Stamilio, Katherine M Menard, J Eric Jelovsek.   

Abstract

OBJECTIVE: To predict a woman's risk of postpartum hemorrhage at labor admission using machine learning and statistical models.
METHODS: Predictive models were constructed and compared using data from 10 of 12 sites in the U.S. Consortium for Safe Labor Study (2002-2008) that consistently reported estimated blood loss at delivery. The outcome was postpartum hemorrhage, defined as an estimated blood loss at least 1,000 mL. Fifty-five candidate risk factors routinely available on labor admission were considered. We used logistic regression with and without lasso regularization (lasso regression) as the two statistical models, and random forest and extreme gradient boosting as the two machine learning models to predict postpartum hemorrhage. Model performance was measured by C statistics (ie, concordance index), calibration, and decision curves. Models were constructed from the first phase (2002-2006) and externally validated (ie, temporally) in the second phase (2007-2008). Further validation was performed combining both temporal and site-specific validation.
RESULTS: Of the 152,279 assessed births, 7,279 (4.8%, 95% CI 4.7-4.9) had postpartum hemorrhage. All models had good-to-excellent discrimination. The extreme gradient boosting model had the best discriminative ability to predict postpartum hemorrhage (C statistic: 0.93; 95% CI 0.92-0.93), followed by random forest (C statistic: 0.92; 95% CI 0.91-0.92). The lasso regression model (C statistic: 0.87; 95% CI 0.86-0.88) and logistic regression (C statistic: 0.87; 95% CI 0.86-0.87) had lower-but-good discriminative ability. The above results held with validation across both time and sites. Decision curve analysis demonstrated that, although all models provided superior net benefit when clinical decision thresholds were between 0% and 80% predicted risk, the extreme gradient boosting model provided the greatest net benefit.
CONCLUSION: Postpartum hemorrhage on labor admission can be predicted with excellent discriminative ability using machine learning and statistical models. Further clinical application is needed, which may assist health care providers to be prepared and triage at-risk women.

Entities:  

Mesh:

Year:  2020        PMID: 32168227      PMCID: PMC7236480          DOI: 10.1097/AOG.0000000000003759

Source DB:  PubMed          Journal:  Obstet Gynecol        ISSN: 0029-7844            Impact factor:   7.623


  44 in total

1.  Incidence, risk factors, and temporal trends in severe postpartum hemorrhage.

Authors:  Michael S Kramer; Cynthia Berg; Haim Abenhaim; Mourad Dahhou; Jocelyn Rouleau; Azar Mehrabadi; K S Joseph
Journal:  Am J Obstet Gynecol       Date:  2013-07-16       Impact factor: 8.661

2.  Decision curve analysis.

Authors:  Mark Fitzgerald; Benjamin R Saville; Roger J Lewis
Journal:  JAMA       Date:  2015-01-27       Impact factor: 56.272

3.  Obstetric Care Consensus #9: Levels of Maternal Care: (Replaces Obstetric Care Consensus Number 2, February 2015).

Authors:  Sarah J Kilpatrick; M Kathryn Menard; Christopher M Zahn; William M Callaghan
Journal:  Am J Obstet Gynecol       Date:  2019-07-25       Impact factor: 8.661

4.  Executive summary of the reVITALize initiative: standardizing obstetric data definitions.

Authors:  M Kathryn Menard; Elliott K Main; Sean M Currigan
Journal:  Obstet Gynecol       Date:  2014-07       Impact factor: 7.661

5.  What is Machine Learning? A Primer for the Epidemiologist.

Authors:  Qifang Bi; Katherine E Goodman; Joshua Kaminsky; Justin Lessler
Journal:  Am J Epidemiol       Date:  2019-12-31       Impact factor: 4.897

6.  Predictive Model for Failed Induction of Labor Among Obese Women.

Authors:  Robert M Rossi; Erin W Requarth; Carri R Warshak; Kevin Dufendach; Eric S Hall; Emily A DeFranco
Journal:  Obstet Gynecol       Date:  2019-09       Impact factor: 7.661

7.  Assessing clinical heterogeneity in sepsis through treatment patterns and machine learning.

Authors:  Alison E Fohner; John D Greene; Brian L Lawson; Jonathan H Chen; Patricia Kipnis; Gabriel J Escobar; Vincent X Liu
Journal:  J Am Med Inform Assoc       Date:  2019-12-01       Impact factor: 4.497

8.  Predicting Risk of Urinary Incontinence and Adverse Events After Midurethral Sling Surgery in Women.

Authors:  J Eric Jelovsek; Audra Jolyn Hill; Kevin M Chagin; Michael W Kattan; Matthew D Barber
Journal:  Obstet Gynecol       Date:  2016-02       Impact factor: 7.661

Review 9.  Global causes of maternal death: a WHO systematic analysis.

Authors:  Lale Say; Doris Chou; Alison Gemmill; Özge Tunçalp; Ann-Beth Moller; Jane Daniels; A Metin Gülmezoglu; Marleen Temmerman; Leontine Alkema
Journal:  Lancet Glob Health       Date:  2014-05-05       Impact factor: 26.763

10.  Postpartum haemorrhage: Case definition and guidelines for data collection, analysis, and presentation of immunization safety data.

Authors:  Robbie Kerr; Linda O Eckert; Beverly Winikoff; Jill Durocher; Shireen Meher; Sue Fawcus; Shuchita Mundle; Ben Mol; Sabaratnam Arulkumaran; Khalid Khan; Julius Wandwabwa; Sonali Kochhar; Andrew Weeks
Journal:  Vaccine       Date:  2016-07-16       Impact factor: 3.641

View more
  14 in total

1.  Risk Factors for Atonic Postpartum Hemorrhage: A Systematic Review and Meta-analysis.

Authors:  Holly B Ende; M James Lozada; David H Chestnut; Sarah S Osmundson; Rachel L Walden; Matthew S Shotwell; Jeanette R Bauchat
Journal:  Obstet Gynecol       Date:  2021-02-01       Impact factor: 7.661

2.  A novel oppositional binary crow search algorithm with optimal machine learning based postpartum hemorrhage prediction model.

Authors:  Sujatha Krishnamoorthy; Yihang Liu; Kun Liu
Journal:  BMC Pregnancy Childbirth       Date:  2022-07-13       Impact factor: 3.105

3.  Improving postpartum hemorrhage risk prediction using longitudinal electronic medical records.

Authors:  Amanda B Zheutlin; Luciana Vieira; Ryan A Shewcraft; Shilong Li; Zichen Wang; Emilio Schadt; Susan Gross; Siobhan M Dolan; Joanne Stone; Eric Schadt; Li Li
Journal:  J Am Med Inform Assoc       Date:  2022-01-12       Impact factor: 7.942

4.  A comprehensive digital phenotype for postpartum hemorrhage.

Authors:  Amanda B Zheutlin; Luciana Vieira; Ryan A Shewcraft; Shilong Li; Zichen Wang; Emilio Schadt; Yu-Han Kao; Susan Gross; Siobhan M Dolan; Joanne Stone; Eric Schadt; Li Li
Journal:  J Am Med Inform Assoc       Date:  2022-01-12       Impact factor: 4.497

5.  Machine learning approach for the prediction of postpartum hemorrhage in vaginal birth.

Authors:  Munetoshi Akazawa; Kazunori Hashimoto; Noda Katsuhiko; Yoshida Kaname
Journal:  Sci Rep       Date:  2021-11-19       Impact factor: 4.379

6.  Integration and Validation of a Natural Language Processing Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in the Emergency Department.

Authors:  Joshua Cohen; Jennifer Wright-Berryman; Lesley Rohlfs; Douglas Trocinski; LaMonica Daniel; Thomas W Klatt
Journal:  Front Digit Health       Date:  2022-02-02

Review 7.  Intelligent systems in obstetrics and midwifery: Applications of machine learning.

Authors:  Stavroula Barbounaki; Victoria G Vivilaki
Journal:  Eur J Midwifery       Date:  2021-12-20

8.  Artificial intelligence in obstetrics.

Authors:  Ki Hoon Ahn; Kwang-Sig Lee
Journal:  Obstet Gynecol Sci       Date:  2021-12-15

9.  Clinical Effects of Form-Based Management of Forceps Delivery under Intelligent Medical Model.

Authors:  Siming Xin; Zhizhong Wang; Hua Lai; Lingzhi Liu; Ting Shen; Fangping Xu; Xiaoming Zeng; Jiusheng Zheng
Journal:  J Healthc Eng       Date:  2021-05-31       Impact factor: 2.682

10.  Prediction of preterm birth in nulliparous women using logistic regression and machine learning.

Authors:  Reza Arabi Belaghi; Joseph Beyene; Sarah D McDonald
Journal:  PLoS One       Date:  2021-06-30       Impact factor: 3.240

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.