Amplitude and frequency modulation of EEG predicts Intraventricular hemorrhage in preterm infants

• Autorzy: Arasteh Emad , Tataranno Maria Luisa , De Vos Maarten , Wang Xiaowan , Benders Manon J.N.L. , Dudink Jeroen , Alderliesten Thomas

Identyfikatory

DOI

10.1016/j.bbe.2024.08.012

• Języki publikacji: EN

Abstrakty

EN

Background: Intraventricular hemorrhage (IVH) is a common and significant complication in premature infants. While cranial ultrasound is the golden standard for IVH detection, it may not identify lesions until hours or days after occurring, which limits early intervention. Predicting IVH in premature infants would be highly advantageous. Recent studies have shown that EEG data’s amplitude and frequency modulation features could offer predictive insights for neurological diseases in adults. Methods: To investigate the association between IVH and EEG monitoring, a retrospective case-control study was conducted in preterm infants. All infants underwent amplitude integrated EEG monitoring for at least 3 days after birth. The study included 20 cases who had an IVH diagnosed on cranial ultrasound and had a negative ultrasound 24 h earlier, and 20 matched controls without IVH. Amplitude and frequency modulation features were extracted from single-channel EEG data, and various machine learning algorithms were evaluated to create a predictive model. Results: Cases had an average gestational age and birth weight of 26.4 weeks and 965 g, respectively. The best-performing algorithm was adaptive boosting. EEG data from 24 h before IVH detection proved predictive with an area under the receiver operating characteristic curve of 93 %, an accuracy of 91 %, and a Kappa value of 0.85. The most informative features were the slow varying instantaneous frequency and amplitude in the Delta frequency band. Conclusion: Amplitude and frequency modulation features obtained from single-channel EEG signals in extremely preterm infants show promise for predicting IVH occurrence within 24 h before detection on cranial ultrasound.

Słowa kluczowe

EN

prematurity; brain injury; EEG data; machine learning

PL

wcześniactwo; uraz mózgu; dane EEG; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 3
• Strony: 708--715
• Opis fizyczny: Bibliogr. 58 poz., rys., tab., wykr.

Twórcy

autor

Arasteh Emad

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands
• Department of Electrical Engineering (ESAT), Division SCD, KU Leuven, Belgium

autor

Tataranno Maria Luisa

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands

autor

De Vos Maarten

• Department of Electrical Engineering (ESAT), Division SCD, KU Leuven, Belgium
• Department of Development and Regeneration, KU Leuven, Belgium

autor

Wang Xiaowan

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands

autor

Benders Manon J.N.L.

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands

autor

Dudink Jeroen

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands

autor

Alderliesten Thomas

• Department of Neonatology, Wilhelmina Children’s Hospital/University Medical Center Utrecht, The Netherlands

Bibliografia

• [1] S.A. Back, A. Riddle, M.M. McClure Maturation-dependent vulnerability of perinatal white matter in premature birth Stroke, 38 (2) (2007), pp. 724-730.
• [2] V. Gilard, et al. Intraventricular hemorrhage in very preterm infants: a comprehensive review J Clin Med, 9 (8) (2020), p. 2447.
• [3] A. Parodi, et al. Cranial ultrasound findings in preterm germinal matrix haemorrhage, sequelae and outcome Pediatr Res, 87 (Suppl 1) (2020), pp. 13-24.
• [4] L.R. Ment, et al. Intraventricular hemorrhage in the preterm neonate: timing and cerebral blood flow changes J Pediatr, 104 (3) (1984), pp. 419-425.
• [5] P. Ballabh Pathogenesis and prevention of intraventricular hemorrhage Clin Perinatol, 41 (1) (2014), pp. 47-67.
• [6] H.S. Bada, et al. Noninvasive diagnosis of neonatal asphyxia and intraventricular hemorrhage by Doppler ultrasound J Pediatr, 95 (5) (1979), pp. 775-779.
• [7] R.L. Triplett, C.D. Smyser Neuroimaging of structural and functional connectivity in preterm infants with intraventricular hemorrhage Seminars in Perinatology, Elsevier (2022).
• [8] P. Ballabh, L.S. de Vries White matter injury in infants with intraventricular haemorrhage: mechanisms and therapies Nat Rev Neurol, 17 (4) (2021), pp. 199-214.
• [9] M.S. Scher Automated EEG-sleep analyses and neonatal neurointensive care Sleep Med, 5 (6) (2004), pp. 533-540.
• [10] N. Koolen, et al. Automated classification of neonatal sleep states using EEG Clin Neurophysiol, 128 (6) (2017), pp. 1100-1108.
• [11] A. Temko, et al. EEG-based neonatal seizure detection with support vector machines Clin Neurophysiol, 122 (3) (2011), pp. 464-473.
• [12] M. Mirbabaie, S. Stieglitz, N.R. Frick Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction Heal Technol, 11 (4) (2021), pp. 693-731.
• [13] R.M. McAdams, et al. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review J Perinatol (2022), pp. 1-15.
• [14] C. Mangold, et al. Machine learning models for predicting neonatal mortality: a systematic review Neonatology, 118 (4) (2021), pp. 394-405.
• [15] Raurale, S.A., et al. Suitability of an inter-burst detection method for grading hypoxic-ischemic encephalopathy in newborn EEG. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2019. IEEE.
• [16] Raurale, S.A., et al. Grading the severity of hypoxic-ischemic encephalopathy in newborn EEG using a convolutional neural network. in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2020. IEEE.
• [17] H. Abbasi, C.P. Unsworth Applications of advanced signal processing and machine learning in the neonatal hypoxic-ischemic electroencephalography Neural Regen Res, 15 (2) (2020), p. 222.
• [18] K. Watanabe, et al. Electroencephalographic study of intraventricular hemorrhage in the preterm newborn Neuropediatrics, 14 (04) (1983), pp. 225-230.
• [19] V. Soubasi, et al. Early abnormal amplitude-integrated electroencephalography (aEEG) is associated with adverse short-term outcome in premature infants Eur J Paediatr Neurol, 16 (6) (2012), pp. 625-630.
• [20] R.R. Clancy, B.R. Tharp Positive rolandic sharp waves in the electroencephalograms of premature neonates with intraventricular hemorrhage Electroencephalogr Clin Neurophysiol, 57 (5) (1984), pp. 395-404.
• [21] Ú. Guillén, et al. Relationship between attrition and neurodevelopmental impairment rates in extremely preterm infants at 18 to 24 months: a systematic review Arch Pediatr Adolesc Med, 166 (2) (2012), pp. 178-184.
• [22] K. El-Atawi, et al. Risk factors, diagnosis, and current practices in the management of intraventricular hemorrhage in preterm infants: a review System, 16 (2016), p. 17.
• [23] K.K. Iyer, et al. Early detection of preterm intraventricular hemorrhage from clinical electroencephalography Crit Care Med, 43 (10) (2015), pp. 2219-2227.
• [24] K. Watanabe, F. Hayakawa, A. Okumura Neonatal EEG: a powerful tool in the assessment of brain damage in preterm infants Brain and Development, 21 (6) (1999), pp. 361-372.
• [25] A.H. Kong, et al. Background EEG features and prediction of cognitive outcomes in very preterm infants: a systematic review Early Hum Dev, 127 (2018), pp. 74-84.
• [26] L. Hellström-Westas, I. Rosén Electroencephalography and brain damage in preterm infants Early Hum Dev, 81 (3) (2005), pp. 255-261.
• [27] C.P. Loizou, et al. Multiscale amplitude-modulation frequency-modulation (AM–FM) texture analysis of multiple sclerosis in brain MRI images IEEE Trans Inf Technol Biomed, 15 (1) (2010), pp. 119-129.
• [28] P.F. Pai, A.N. Palazotto Detection and identification of nonlinearities by amplitude and frequency modulation analysis Mech Syst Sig Process, 22 (5) (2008), pp. 1107-1132.
• [29] F.J. Fraga, et al. Characterizing Alzheimer’s disease severity via resting-awake EEG amplitude modulation analysis PLoS One, 8 (8) (2013), p. e72240.
• [30] A. Averna, et al. Amplitude and frequency modulation of subthalamic beta oscillations jointly encode the dopaminergic state in Parkinson’s disease npj Parkinson's Dis, 8 (1) (2022), p. 131.
• [31] J.J. Volpe Brain injury in premature infants: a complex amalgam of destructive and developmental disturbances The Lancet Neurology, 8 (1) (2009), pp. 110-124.
• [32] J. Tao, A. Mathur Using amplitude-integrated EEG in neonatal intensive care J Perinatol, 30 (1) (2010), pp. S73-S81.
• [33] J.M. Perlman Neurobehavioral deficits in premature graduates of intensive care - potential medical and neonatal environmental risk factors Pediatrics, 108 (6) (2001), pp. 1339-1348.
• [34] J.Y. Lee, et al. Risk factors for periventricular-intraventricular hemorrhage in premature infants J Korean Med Sci, 25 (3) (2010), pp. 418-424.
• [35] A. Ansari, et al. Brain age as an estimator of neurodevelopmental outcome: A deep learning approach for neonatal cot-side monitoring bioRxiv (2023) p. 2023.01. 24.525361.
• [36] A. Temko, et al. Performance assessment for EEG-based neonatal seizure detectors Clin Neurophysiol, 122 (3) (2011), pp. 474-482.
• [37] J. Altenburg, et al. Seizure detection in the neonatal EEG with synchronization likelihood Clin Neurophysiol, 114 (1) (2003), pp. 50-55.
• [38] N. Stevenson, et al. An automated system for grading EEG abnormality in term neonates with hypoxic-ischaemic encephalopathy Ann Biomed Eng, 41 (2013), pp. 775-785.
• [39] T. Li, C. Zhang, M. Ogihara A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression Bioinformatics, 20 (15) (2004), pp. 2429-2437.
• [40] T.-T. Wong Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation Pattern Recogn, 48 (9) (2015), pp. 2839-2846.
• [41] C. Magri, et al. A toolbox for the fast information analysis of multiple-site LFP, EEG and spike train recordings BMC Neurosci, 10 (2009), pp. 1-24.
• [42] Guizzo, E.M., The essential message: Claude Shannon and the making of information theory. 2003, Massachusetts Institute of Technology.
• [43] A. Scaglione, et al. Trial-to-trial variability in the responses of neurons carries information about stimulus location in the rat whisker thalamus Proc Natl Acad Sci, 108 (36) (2011), pp. 14956-14961.
• [44] S. Wikström, et al. Early single-channel aEEG/EEG predicts outcome in very preterm infants Acta Paediatr, 101 (7) (2012), pp. 719-726.
• [45] K. Whitehead, R. Pressler, L. Fabrizi Characteristics and clinical significance of delta brushes in the EEG of premature infants Clin Neurophysiol Pract, 2 (2017), pp. 12-18.
• [46] M. El-Dib, et al. Amplitude-integrated electroencephalography in neonates Pediatr Neurol, 41 (5) (2009), pp. 315-326.
• [47] M. Olischar, et al. Background patterns and sleep-wake cycles on amplitude-integrated electroencephalography in preterms younger than 30 weeks gestational age with peri-/intraventricular haemorrhage Acta Paediatr, 96 (12) (2007), pp. 1743-1750,
• [48] A. Okumura, et al. Developmental outcome and types of chronic-stage EEG abnormalities in preterm infants Dev Med Child Neurol, 44 (11) (2002), pp. 729-734.
• [49] L.F. Chalak, et al. Low-voltage aEEG as predictor of intracranial hemorrhage in preterm infants Pediatr Neurol, 44 (5) (2011), pp. 364-369.
• [50] K. de Bijl-Marcus, et al. Neonatal care bundles are associated with a reduction in the incidence of intraventricular haemorrhage in preterm infants: a multicentre cohort study Arch Dis Child Fetal Neonatal Ed, 105 (4) (2020), pp. 419-424.
• [51] M.B. Schmid, et al. Prospective risk factor monitoring reduces intracranial hemorrhage rates in preterm infants Dtsch Arztebl Int, 110 (29-30) (2013), p. 489.
• [52] D.G. Jenkins, P.F. Quintana-Ascencio A solution to minimum sample size for regressions PLoS One, 15 (2) (2020), p. e0229345.
• [53] D. Woo, et al. Risk factors associated with mortality and neurologic disability after intracerebral hemorrhage in a racially and ethnically diverse cohort JAMA Netw Open, 5 (3) (2022), p. e221103.
• [54] E. Pavlidis, R.O. Lloyd, G.B. Boylan EEG-a valuable biomarker of brain injury in preterm infants Dev Neurosci, 39 (1-4) (2017), pp. 23-35.
• [55] S. Abirami, et al. “A comparative study on EEG features for neonatal seizure detection.” Biomedical Signals Based Computer-Aided Diagnosis for Neurological Disorders Springer International Publishing, Cham (2022), pp. 43-64.
• [56] C. Conde, R. José, et al. Assessment of neonatal EEG background and neurodevelopment in full-term small for their gestational age infants Pediatr Res, 88 (1) (2020), pp. 91-99.
• [57] O. Jr, D. William, et al. The risk of exposure to diagnostic ultrasound in postnatal subjects: thermal effects J Ultrasound Med, 27 (4) (2008), pp. 517-535.
• [58] G. ter Haar Ultrasonic imaging: safety considerations Interface focus, 1 (4) (2011), pp. 686-697.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).