Machine learning models for identifying preterm infants at risk of cerebral hemorrhage


Autoři: Varvara Turova aff001;  Irina Sidorenko aff002;  Laura Eckardt aff003;  Esther Rieger-Fackeldey aff004;  Ursula Felderhoff-Müser aff003;  Ana Alves-Pinto aff001;  Renée Lampe aff001
Působiště autorů: Research Unit for Pediatric Neuroorthopedics and Cerebral Palsy of the Buhl-Strohmaier Foundation, Orthopedic Department, Klinikum Rechts der Isar, Technical University of Munich, München, Germany aff001;  Chair of Mathematical Modelling, Mathematical Faculty, Technical University of Munich, Garching bei München, Germany aff002;  Departments of Pediatrics and Neonatology, University Hospital Essen, University of Duisburg‐Essen, Essen, Germany aff003;  Department of Pediatrics, Neonatology, Klinikum Rechts der Isar, Technical University of Munich, München, Germany aff004
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: 10.1371/journal.pone.0227419

Souhrn

Intracerebral hemorrhage in preterm infants is a major cause of brain damage and cerebral palsy. The pathogenesis of cerebral hemorrhage is multifactorial. Among the risk factors are impaired cerebral autoregulation, infections, and coagulation disorders. Machine learning methods allow the identification of combinations of clinical factors to best differentiate preterm infants with intra-cerebral bleeding and the development of models for patients at risk of cerebral hemorrhage. In the current study, a Random Forest approach is applied to develop such models for extremely and very preterm infants (23–30 weeks gestation) based on data collected from a cohort of 229 individuals. The constructed models exhibit good prediction accuracy and might be used in clinical practice to reduce the risk of cerebral bleeding in prematurity.

Klíčová slova:

Birth weight – Blood vessels – Cerebral blood flow assay – Hemorrhage – Machine learning – Neonates – Oxygen – Ultrasound imaging


Zdroje

1. Ballabh P. Intraventricular hemorrhage in premature infants: mechanism of disease. Pediatr Res. 2010; 67(1): 1. doi: 10.1203/PDR.0b013e3181c1b176 19816235

2. Kaiser JR., Gauss CH, Williams DK. The effects of hypercapnia on cerebral autoregulation in ventilated very low birth weight infants. Pediatr Res. 2005; 58(5): 931. doi: 10.1203/01.pdr.0000182180.80645.0c 16257928

3. Soul JS, Hammer PE, Tsuji M, Saul JP, Bassan H, Limperopoulos C, et al. Fluctuating pressure-passivity is common in the cerebral circulation of sick premature infants. Pediatr Res. 2007;61(4): 467. doi: 10.1203/pdr.0b013e31803237f6 17515873

4. O'Leary H, Gregas MC, Limperopoulos C, Zaretskaya I, Bassan H, Soul JS, et al. Elevated cerebral pressure passivity is associated with prematurity-related intracranial hemorrhage. Pediatrics. 2009;124(1): 302–309. doi: 10.1542/peds.2008-2004 19564313

5. Poryo M, Boeckh JC, Gortner L, Zemlin M, Duppré P, Ebrahimi-Fakhari D, et al. Ante-, peri-and postnatal factors associated with intraventricular hemorrhage in very premature infants. Early Hum Dev. 2017;116: 1–8. doi: 10.1016/j.earlhumdev.2017.08.010 29091782

6. Duppré P, Sauer H, Giannopoulou EZ, Gortner L, Nunold H, Wagenpfeil S. Cellular and humoral coagulation profiles and occurrence of IVH in VLBW and ELWB infants. Early Hum Dev. 2015;91(12): 695–700. doi: 10.1016/j.earlhumdev.2015.09.008 26529174

7. Schmid MB, Reister F, Mayer B, Hopfner RJ, Fuchs H, Hummler HD. Prospective risk factor monitoring reduces intracranial hemorrhage rates in preterm infants. Deutsches Ärzteblatt International. 2013;10(29–30): 489.

8. Lampe R, Turova V, Botkin N, Eckardt L, Felderhoff-Müser U, Rieger-Fackeldey E, et al. Postnatal paraclinical parameters associated to occurrence of intracerebral hemorrhage in preterm infants. Neuropediatrics. 2019;50(02): 103–110.

9. Sidorenko I, Turova V, Botkin N, Eckardt L, Alves-Pinto A, Felderhoff-Müser U, et al. Modeling cerebral blood flow dependence on carbon dioxide and mean arterial blood pressure in the immature brain with accounting for the germinal matrix. Front Neurol. 2018; 9: 812. doi: 10.3389/fneur.2018.00812 30356709

10. Asadi H, Dowling R, Yan B, Mitchell P. Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy. PloS One 2014;9(2): e88225. doi: 10.1371/journal.pone.0088225 24520356

11. Podda M, Bacciu D, Micheli A, Bellù R, Placidi G, Gagliardi L. A machine learning approach to estimating preterm infants survival: development of the Preterm Infants Survival Assessment (PISA) predictor. Sci Rep. 2018; 8(1): 13743. doi: 10.1038/s41598-018-31920-6 30213963

12. Rittenhouse KJ, Vwalika B, Keil A, Winston J, Stoner M, Price JT, et al. Improving preterm newborn identification in low-resource settings with machine learning. PloS One. 2019;14(2): e0198919. doi: 10.1371/journal.pone.0198919 30811399

13. Guihard-Costa AM, Larroche JC. Differential growth between the fetal brain and its infratentorial part. Early Hum Dev. 1990;23: 27–40. doi: 10.1016/0378-3782(90)90126-4 2209474

14. Kinoshita Y, Okudera T, Tsuru E, Yokota A. Volumetric analysis of the germinal matrix and lateral ventricles performed using MR images of postmortem fetuses. AJNR Am J Neuroradiol. 2001;22(2): 382–388. 11156787

15. Wilson-Costello D, Friedman H, Minich N, Fanaroff AA, Hack M. Improved survival rates with increased neurodevelopmental disability for extremely low birth weight infants in the 1990s. Pediatrics. 2005;115: 997–1003. doi: 10.1542/peds.2004-0221 15805376

16. Christian EA, Jin DL, Attenello F, Wen T, Cen S, Mack WJ, et al. Trends in hospitalization of preterm infants with intraventricular hemorrhage and hydrocephalus in the United States, 2000–2010. J of Neurosurg Pediatr. 2016;17(3): 260–269.

17. Piechnik SK, Chiarelli PA, Jezzard P. Modelling vascular reactivity to investigate the basis of the relationship between cerebral blood volume and flow under CO2 manipulation. Neuroimage. 2008;39(1): 107–118. doi: 10.1016/j.neuroimage.2007.08.022 17920935

18. Browniee J. Machine learning mastery with R. 2014. Available from: http://machinelearningmastery.com/discover-feature-engineering-howtoengineer-features-and-how-to-getgood-at-it.

19. Lesmeister C. Mastering machine learning with R. Packt Publishing Ltd; 2015.

20. Couronné R, Probst P, Boulesteix A-L. Random forest versus logistic regression: a large-scale benchmark experiment. Technical Report Nr. 205. 2017. Department of Statistics, University of Munich.

21. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16: 321–357.

22. Rastogi S, Olmez I, Bhutada A, Rastogi D. NCI classification of thrombocytopenia in extremely preterm neonates and its association with mortality and morbidity. J Perinat Med. 2011;39(1): 65–69. doi: 10.1515/JPM.2010.122 20954853

23. Paul DA, Leef KH, Stefano JL. Increased leukocytes in infants with intraventricular hemorrhage. Pediatr Neurol. 2000;22(3): 194–199. doi: 10.1016/s0887-8994(99)00155-1 10734249

24. Jare K, Carli T, Lucovnik M, Premru-Srsen T, Cerar L, Derganc M. Maternal serum c-reactive protein and white blood cell count in the prediction of chorioamnionitis and fetal inflammatory response after preterm rupture of membranes. Gynaecologia et Perinatologia. 2013;22: 165–169.

25. Villamor-Martinez E, Fumagalli M, Mohammed RO, Passera S, Cavallaro G, Degraeuwe P, et al. Chorioamnionitis is a risk factor for intraventricular hemorrhage in preterm infants: a systematic reviewand meta-analysis. Front Physiol. 2018;11(09): 1253.

26. Poralla C, Hertfelder HJ, Oldenburg J, Müller A, Bartmann P, Heep A. Elevated interleukin-6 concentration and alterations of the coagulation system are associated with the development of intraventricular hemorrhage in extremely preterm infants. Neonatology. 2012;102(4): 270–275. doi: 10.1159/000341266 22906886

27. Dekom S, Vachhani A, Patel K, Barton L, Ramanathan R, Noori S. Initial hematocrit values after birth and peri/intraventricular hemorrhage in extremely low birth weight infants. J Perinatol. 2018;38: 1471. doi: 10.1038/s41372-018-0224-6 30206347

28. Levene MI, Fawer CL, Lamont RF. Risk factors in the development of intraventricular haemorrhage in the preterm neonate. Arch Dis Child. 1982;57(6): 410–417. doi: 10.1136/adc.57.6.410 7092304

29. Perlman JM, Goodman S, Kreusser KL, Volpe J J. Reduction in intraventricular hemorrhage by elimination of fluctuating cerebral blood-flow velocity in preterm infants with respiratory distress syndrome. N Engl J Med. 1985;312(21): 1353–1357. doi: 10.1056/NEJM198505233122104 3887165

30. Anand V. Neonatal seizures: predictors of adverse outcome. J Pediatr Neurosci. 2014;9(2): 97. doi: 10.4103/1817-1745.139261 25250059

31. Synnes AR, MacNab YC, Qiu Z, Ohlsson A, Gustafson P, Dean CB, et al. Neonatal intensive care unit characteristics affect the incidence of severe intraventricular hemorrhage. Med Care. 2006: 754–759. doi: 10.1097/01.mlr.0000218780.16064.df 16862037

32. Chiesa C, Natale F, Pascone R, Osborn J F, Pacifico L, Bonci E, et al (2011). C reactive protein and procalcitonin: reference intervals for preterm and term newborns during the early neonatal period. Clin Chim Acta. 2011;412(11–12): 1053–1059. doi: 10.1016/j.cca.2011.02.020 21338596

33. Askie LM, Darlow BA, Davis PG, Finer N, Stenson B, Vento M, et al. Effects of targeting lower versus higher arterial oxygen saturations on death or disability in preterm infants. Cochrane Database Syst Rev. 2017;4.

34. Steinhorn RH. Oxygen saturation limits for premature babies: the final word for now. NEJM Journal Watch. 2018;June 25.

35. Cuestas E, Bas J, Pautasso J. Sex differences in intraventricular hemorrhage rates among very low birth weight newborns. Gend Med. 2009;6(2): 376–382. doi: 10.1016/j.genm.2009.06.001 19682665

36. Mohamed MA, Aly H. Male gender is associated with intraventricular hemorrhage. Pediatrics. 2010:125(2): e333–e339. doi: 10.1542/peds.2008-3369 20083524


Článek vyšel v časopise

PLOS One


2020 Číslo 1