1
|
Lacan L, Betrouni N, Chaton L, Lamblin MD, Flamein F, Riadh Boukhris M, Derambure P, Nguyen The Tich S. Early automated classification of neonatal hypoxic-ischemic encephalopathy - An aid to the decision to use therapeutic hypothermia. Clin Neurophysiol 2024; 166:108-116. [PMID: 39153459 DOI: 10.1016/j.clinph.2024.07.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Revised: 07/18/2024] [Accepted: 07/27/2024] [Indexed: 08/19/2024]
Abstract
OBJECTIVE The study aimed to address the challenge of early assessment of neonatal hypoxic-ischemic encephalopathy (HIE) severity to identify candidates for therapeutic hypothermia (TH). The objective was to develop an automated classification model for neonatal EEGs, enabling accurate HIE severity assessment 24/7. METHODS EEGs recorded within 6 h of life after perinatal anoxia were visually graded into 3 severity groups (HIE French Classification) and quantified using 6 qEEG markers measuring amplitude, continuity and frequency content. Machine learning models were developed on a dataset of 90 EEGs and validated on an independent dataset of 60 EEGs. RESULTS The selected model achieved an overall accuracy of 80.6% in the development phase and 80% in the validation phase. Notably, the model accurately identified 28 out of 30 children for whom TH was indicated after visual EEG analysis, with only 2 cases (moderate EEG abnormalities) not recommended for cooling. CONCLUSIONS The combination of clinically relevant qEEG markers led to the development of an effective automated EEG classification model, particularly suited for the post-anoxic latency phase. This model successfully discriminated neonates requiring TH. SIGNIFICANCE The proposed model has potential as a bedside clinical decision support tool for TH.
Collapse
Affiliation(s)
- Laure Lacan
- ULR 2694 - METRICS, University of Lille, Faculty of Medicine, Avenue Eugène Avinée, Lille F-59000, France; Department of Pediatric Neurology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| | - Nacim Betrouni
- INSERM U 1172, F-59000, University of Lille, Faculty of Medicine, 2 Avenue Eugène Avinée, Lille F-59000, France; Department of Clinical Neurophysiology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| | - Laurence Chaton
- INSERM U 1172, F-59000, University of Lille, Faculty of Medicine, 2 Avenue Eugène Avinée, Lille F-59000, France; Department of Clinical Neurophysiology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| | - Marie-Dominique Lamblin
- Department of Clinical Neurophysiology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| | - Florence Flamein
- Department of Neonatology, CHU Lille, Hôpital Jeanne de Flandre, Avenue Eugène Avinée, Lille F-59000, France.
| | - Mohamed Riadh Boukhris
- Department of Neonatology, CHU Lille, Hôpital Jeanne de Flandre, Avenue Eugène Avinée, Lille F-59000, France.
| | - Philippe Derambure
- INSERM U 1172, F-59000, University of Lille, Faculty of Medicine, 2 Avenue Eugène Avinée, Lille F-59000, France; Department of Clinical Neurophysiology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| | - Sylvie Nguyen The Tich
- ULR 2694 - METRICS, University of Lille, Faculty of Medicine, Avenue Eugène Avinée, Lille F-59000, France; Department of Pediatric Neurology, CHU Lille, Hôpital Roger Salengro, Rue Emile Laine, Lille F-59000, France.
| |
Collapse
|
2
|
Proietti J, O'Toole JM, Murray DM, Boylan GB. Advances in Electroencephalographic Biomarkers of Neonatal Hypoxic Ischemic Encephalopathy. Clin Perinatol 2024; 51:649-663. [PMID: 39095102 DOI: 10.1016/j.clp.2024.04.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/04/2024]
Abstract
Electroencephalography (EEG) is a key objective biomarker of newborn brain function, delivering critical, cotside insights to aid the management of encephalopathy. Access to continuous EEG is limited, forcing reliance on subjective clinical assessments. In hypoxia ischaemia, the primary cause of encephalopathy, alterations in EEG patterns correlate with. injury severity and evolution. As HIE evolves, causing secondary neuronal death, EEG can track injury progression, informing neuroprotective strategies, seizure management and prognosis. Despite its value, challenges with interpretation and lack of on site expertise has limited its broader adoption. Technological advances, particularly in digital EEG and machine learning, are enhancing real-time analysis. This will allow EEG to expand its role in HIE diagnosis, management and outcome prediction.
Collapse
Affiliation(s)
- Jacopo Proietti
- Department of Engineering for Innovation Medicine, University of Verona, Strada le Grazie, Verona 37134, Italy; INFANT Research Centre, University College Cork, Cork, Ireland
| | - John M O'Toole
- INFANT Research Centre, University College Cork, Cork, Ireland; Cergenx Ltd., Dublin, Ireland
| | - Deirdre M Murray
- INFANT Research Centre, University College Cork, Cork, Ireland; Department of Paediatrics & Child Health, University College Cork, Paediatric Academic Unit, Cork University Hospital, Wilton, Cork, T12 DC4A, Ireland
| | - Geraldine B Boylan
- INFANT Research Centre, University College Cork, Cork, Ireland; Department of Paediatrics & Child Health, University College Cork, Paediatric Academic Unit, Cork University Hospital, Wilton, Cork, T12 DC4A, Ireland.
| |
Collapse
|
3
|
Dilena R, Cilio MR. Free access via computational cloud to deep learning-based EEG assessment in neonatal hypoxic-ischemic encephalopathy: revolutionary opportunities to overcome health disparities. Pediatr Res 2024:10.1038/s41390-024-03427-6. [PMID: 39107521 DOI: 10.1038/s41390-024-03427-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/13/2024] [Accepted: 06/21/2024] [Indexed: 09/04/2024]
Abstract
In this issue of Pediatric Research, Kota et al. evaluate a novel monitoring visual trend using deep-learning - Brain State of the Newborn (BSN)- based EEG as a bedside marker for severity of the encephalopathy in 46 neonates with hypoxic-ischemic encephalopathy (HIE) compared with healthy infants. Early BSN distinguished between normal and abnormal outcome, and correlated with the Total Sarnat Score.
Collapse
Affiliation(s)
- Robertino Dilena
- Clinical Neurophysiology Unit, Department of Neuroscience, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy
| | - Maria Roberta Cilio
- Division of Pediatric Neurology, Department of Pediatrics, Saint-Luc University Hospital, and Institute of Neuroscience, Catholic University of Louvain, Brussels, Belgium.
| |
Collapse
|
4
|
Roychaudhuri S, Hannon K, Sunwoo J, Garvey AA, El-Dib M. Quantitative EEG and prediction of outcome in neonatal encephalopathy: a review. Pediatr Res 2024; 96:73-80. [PMID: 38503980 DOI: 10.1038/s41390-024-03138-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Revised: 02/18/2024] [Accepted: 03/01/2024] [Indexed: 03/21/2024]
Abstract
Electroencephalogram (EEG) is an important biomarker for neonatal encephalopathy (NE) and has significant predictive value for brain injury and neurodevelopmental outcomes. Quantitative analysis of EEG involves the representation of complex EEG data in an objective, reproducible and scalable manner. Quantitative EEG (qEEG) can be derived from both a limited channel EEG (as available during amplitude integrated EEG) and multi-channel conventional EEG. It has the potential to enable bedside clinicians to monitor and evaluate details of cortical function without the necessity of continuous expert input. This is particularly useful in NE, a dynamic and evolving condition. In these infants, continuous, detailed evaluation of cortical function at the bedside is a valuable aide to management especially in the current era of therapeutic hypothermia and possible upcoming neuroprotective therapies. This review discusses the role of qEEG in newborns with NE and its use in informing monitoring and therapy, along with its ability to predict imaging changes and short and long-term neurodevelopmental outcomes. IMPACT: Quantitative representation of EEG data brings the evaluation of continuous brain function, from the neurophysiology lab to the NICU bedside and has a potential role as a biomarker for neonatal encephalopathy. Clinical and research applications of quantitative EEG in the newborn are rapidly evolving and a wider understanding of its utility is valuable. This overview summarizes the role of quantitative EEG at different timepoints, its relevance to management and its predictive value for short- and long-term outcomes in neonatal encephalopathy.
Collapse
Affiliation(s)
- Sriya Roychaudhuri
- Division of Newborn Medicine, Department of Pediatrics, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Katie Hannon
- Division of Newborn Medicine, Department of Pediatrics, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - John Sunwoo
- Harvard Medical School, Boston, MA, USA
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, USA
| | - Aisling A Garvey
- Division of Newborn Medicine, Department of Pediatrics, Brigham and Women's Hospital, Boston, MA, USA
- INFANT Research Centre, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
- Department of Neonatology, Cork University Maternity Hospital, Cork, Ireland
| | - Mohamed El-Dib
- Division of Newborn Medicine, Department of Pediatrics, Brigham and Women's Hospital, Boston, MA, USA.
- Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
5
|
Montazeri S, Nevalainen P, Metsäranta M, Stevenson NJ, Vanhatalo S. Clinical outcome prediction with an automated EEG trend, Brain State of the Newborn, after perinatal asphyxia. Clin Neurophysiol 2024; 162:68-76. [PMID: 38583406 DOI: 10.1016/j.clinph.2024.03.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Revised: 02/13/2024] [Accepted: 03/11/2024] [Indexed: 04/09/2024]
Abstract
OBJECTIVE To evaluate the utility of a fully automated deep learning -based quantitative measure of EEG background, Brain State of the Newborn (BSN), for early prediction of clinical outcome at four years of age. METHODS The EEG monitoring data from eighty consecutive newborns was analyzed using the automatically computed BSN trend. BSN levels during the first days of life (a of total 5427 hours) were compared to four clinical outcome categories: favorable, cerebral palsy (CP), CP with epilepsy, and death. The time dependent changes in BSN-based prediction for different outcomes were assessed by positive/negative predictive value (PPV/NPV) and by estimating the area under the receiver operating characteristic curve (AUC). RESULTS The BSN values were closely aligned with four visually determined EEG categories (p < 0·001), as well as with respect to clinical milestones of EEG recovery in perinatal Hypoxic Ischemic Encephalopathy (HIE; p < 0·003). Favorable outcome was related to a rapid recovery of the BSN trend, while worse outcomes related to a slow BSN recovery. Outcome predictions with BSN were accurate from 6 to 48 hours of age: For the favorable outcome, the AUC ranged from 95 to 99% (peak at 12 hours), and for the poor outcome the AUC ranged from 96 to 99% (peak at 12 hours). The optimal BSN levels for each PPV/NPV estimate changed substantially during the first 48 hours, ranging from 20 to 80. CONCLUSIONS We show that the BSN provides an automated, objective, and continuous measure of brain activity in newborns. SIGNIFICANCE The BSN trend discloses the dynamic nature that exists in both cerebral recovery and outcome prediction, supports individualized patient care, rapid stratification and early prognosis.
Collapse
Affiliation(s)
- Saeed Montazeri
- BABA Center, Pediatric Research Center, Children's Hospital, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Physiology, University of Helsinki, Helsinki, Finland.
| | - Päivi Nevalainen
- BABA Center, Pediatric Research Center, Children's Hospital, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Clinical Neurophysiology, Epilepsia Helsinki, Full Member of ERN Epicare, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Marjo Metsäranta
- Department of Pediatrics, Children's Hospital, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Nathan J Stevenson
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia
| | - Sampsa Vanhatalo
- BABA Center, Pediatric Research Center, Children's Hospital, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Physiology, University of Helsinki, Helsinki, Finland; Department of Clinical Neurophysiology, Epilepsia Helsinki, Full Member of ERN Epicare, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| |
Collapse
|
6
|
Abbasi H, Davidson JO, Dhillon SK, Zhou KQ, Wassink G, Gunn AJ, Bennet L. Deep Learning for Generalized EEG Seizure Detection after Hypoxia-Ischemia-Preclinical Validation. Bioengineering (Basel) 2024; 11:217. [PMID: 38534490 DOI: 10.3390/bioengineering11030217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 02/12/2024] [Accepted: 02/23/2024] [Indexed: 03/28/2024] Open
Abstract
Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia-ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI-normothermia term (n = 7), HI-hypothermia term (n = 14), sham-normothermia term (n = 5), and HI-normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI-normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI-normothermia preterm data were used in training, the performance on HI-normothermia term and HI-hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI-normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.
Collapse
Affiliation(s)
- Hamid Abbasi
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
- Auckland Bioengineering Institute (ABI), University of Auckland, Auckland 1010, New Zealand
| | - Joanne O Davidson
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| | - Simerdeep K Dhillon
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| | - Kelly Q Zhou
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| | - Guido Wassink
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| | - Alistair J Gunn
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| | - Laura Bennet
- Department of Physiology, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
| |
Collapse
|
7
|
Sullivan BA, Beam K, Vesoulis ZA, Aziz KB, Husain AN, Knake LA, Moreira AG, Hooven TA, Weiss EM, Carr NR, El-Ferzli GT, Patel RM, Simek KA, Hernandez AJ, Barry JS, McAdams RM. Transforming neonatal care with artificial intelligence: challenges, ethical consideration, and opportunities. J Perinatol 2024; 44:1-11. [PMID: 38097685 PMCID: PMC10872325 DOI: 10.1038/s41372-023-01848-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 11/21/2023] [Accepted: 11/30/2023] [Indexed: 12/17/2023]
Abstract
Artificial intelligence (AI) offers tremendous potential to transform neonatology through improved diagnostics, personalized treatments, and earlier prevention of complications. However, there are many challenges to address before AI is ready for clinical practice. This review defines key AI concepts and discusses ethical considerations and implicit biases associated with AI. Next we will review literature examples of AI already being explored in neonatology research and we will suggest future potentials for AI work. Examples discussed in this article include predicting outcomes such as sepsis, optimizing oxygen therapy, and image analysis to detect brain injury and retinopathy of prematurity. Realizing AI's potential necessitates collaboration between diverse stakeholders across the entire process of incorporating AI tools in the NICU to address testability, usability, bias, and transparency. With multi-center and multi-disciplinary collaboration, AI holds tremendous potential to transform the future of neonatology.
Collapse
Affiliation(s)
- Brynne A Sullivan
- Division of Neonatology, Department of Pediatrics, University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Kristyn Beam
- Department of Neonatology, Beth Israel Deaconess Medical Center, Boston, MA, USA
| | - Zachary A Vesoulis
- Division of Newborn Medicine, Department of Pediatrics, Washington University in St. Louis, St. Louis, MO, USA
| | - Khyzer B Aziz
- Division of Neonatology, Department of Pediatrics, Johns Hopkins University, Baltimore, MD, USA
| | - Ameena N Husain
- Division of Neonatology, Department of Pediatrics, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Lindsey A Knake
- Division of Neonatology, Department of Pediatrics, University of Iowa, Iowa City, IA, USA
| | - Alvaro G Moreira
- Division of Neonatology, Department of Pediatrics, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA
| | - Thomas A Hooven
- Division of Newborn Medicine, Department of Pediatrics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Elliott M Weiss
- Department of Pediatrics, University of Washington School of Medicine, Seattle, WA, USA
- Treuman Katz Center for Pediatric Bioethics and Palliative Care, Seattle Children's Research Institute, Seattle, WA, USA
| | - Nicholas R Carr
- Division of Neonatology, Department of Pediatrics, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - George T El-Ferzli
- Division of Neonatology, Department of Pediatrics, Ohio State University, Nationwide Children's Hospital, Columbus, OH, USA
| | - Ravi M Patel
- Division of Neonatology, Department of Pediatrics, Emory University School of Medicine and Children's Healthcare of Atlanta, Atlanta, GA, USA
| | - Kelsey A Simek
- Division of Neonatology, Department of Pediatrics, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Antonio J Hernandez
- Division of Neonatology, Department of Pediatrics, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA
| | - James S Barry
- Division of Neonatology, Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO, USA
| | - Ryan M McAdams
- Department of Pediatrics, University of Wisconsin School of Medicine and Public Health, Madison, WI, USA.
| |
Collapse
|
8
|
Park J, Park SH, Kim C, Yoon SJ, Lim JH, Han JH, Shin JE, Eun HS, Park MS, Lee SM. Growth and developmental outcomes of infants with hypoxic ischemic encephalopathy. Sci Rep 2023; 13:23100. [PMID: 38155236 PMCID: PMC10754824 DOI: 10.1038/s41598-023-50187-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2023] [Accepted: 12/16/2023] [Indexed: 12/30/2023] Open
Abstract
Despite advances in obstetric care, hypoxic ischemic encephalopathy (HIE) remains a significant disease burden. We determined the national trends of HIE prevalence, therapeutic hypothermia (TH) use, mortality, and outcomes from 2012 to 2019. This study included term infants diagnosed with HIE between 2012 and 2019 from the National Health Insurance Service database. The prevalence of HIE was 2.4 per 1000 births without significant change during the period. TH was performed in approximately 6.7% of infants with HIE, and the annual variation ranged from 2.4 to 12.5%. The mortality among all term infants with HIE was 4.6%. The mortality rate among infants with HIE and TH significantly declined from 40 to 16.9% during the eight years. Infants with TH had higher mortality, increased use of inhaled nitric oxide, and more invasive ventilator use, indicating greater disease severity in the TH group. Infants with TH also showed significantly poorer outcomes, including delayed development, cerebral palsy, sensorineural hearing loss, and seizure, compared to infants without TH (p < 0.0001). With the increasing application of TH, mortality and developmental outcomes among infants with HIE have been improving in the past eight years in Korea. Further efforts to improve outcomes should be needed.
Collapse
Affiliation(s)
- Joonsik Park
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Sook Hyun Park
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Chloe Kim
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - So Jin Yoon
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Joo Hee Lim
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Jung Ho Han
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Jeong Eun Shin
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Ho Seon Eun
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Min Soo Park
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea
| | - Soon Min Lee
- Department of Pediatrics, Yonsei University College of Medicine, 211 Eonjuro Gangnam-gu, Seoul, 06273, Republic of Korea.
| |
Collapse
|
9
|
Catenaccio E, Smith RJ, Chavez-Valdez R, Burton VJ, Graham E, Parkinson C, Vaidya D, Tekes A, Northington FJ, Everett AD, Stafstrom CE, Ritzl EK. Evaluating Injury Severity in Neonatal Encephalopathy Using Automated Quantitative Electroencephalography Analysis: A Pilot Study. Dev Neurosci 2023; 46:136-144. [PMID: 37467736 PMCID: PMC11181340 DOI: 10.1159/000530299] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2022] [Accepted: 03/03/2023] [Indexed: 07/21/2023] Open
Abstract
Quantitative analysis of electroencephalography (qEEG) is a potential source of biomarkers for neonatal encephalopathy (NE). However, prior studies using qEEG in NE were limited in their generalizability due to individualized techniques for calculating qEEG features or labor-intensive pre-selection of EEG data. We piloted a fully automated method using commercially available software to calculate the suppression ratio (SR), absolute delta power, and relative delta, theta, alpha, and beta power from EEG of neonates undergoing 72 h of therapeutic hypothermia (TH) for NE between April 20, 2018, and November 4, 2019. We investigated the association of qEEG with degree of encephalopathy (modified Sarnat score), severity of neuroimaging abnormalities following TH (National Institutes of Child Health and Development Neonatal Research Network [NICHD-NRN] score), and presence of seizures. Thirty out of 38 patients met inclusion criteria. A more severe modified Sarnat score was associated with higher SR during all phases of TH, lower absolute delta power during all phases except rewarming, and lower relative delta power during the last 24 h of TH. In 21 patients with neuroimaging data, a worse NICHD-NRN score was associated with higher SR, lower absolute delta power, and higher relative beta power during all phases. QEEG features were not significantly associated with the presence of seizures after correction for multiple comparisons. Our results are consistent with those of prior studies using qEEG in NE and support automated qEEG analysis as an accessible, generalizable method for generating biomarkers of NE and response to TH. Additionally, we found evidence of an immature relative frequency composition in neonates with more severe brain injury, suggesting that automated qEEG analysis may have a use in the assessment of brain maturity.
Collapse
Affiliation(s)
- Eva Catenaccio
- Division of Pediatric Neurology, Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Rachel J. Smith
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Raul Chavez-Valdez
- Division of Neonatology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Vera J. Burton
- Division of Pediatric Neurology, Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Department of Neurology and Developmental Medicine, Kennedy Krieger Institute, Baltimore, MD, USA
| | - Ernest Graham
- Department of Obstetrics and Gynecology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Charlamaine Parkinson
- Division of Neonatology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Dhananjay Vaidya
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Aylin Tekes
- Department of Radiology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Frances J. Northington
- Division of Neonatology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Allen D. Everett
- Division of Pediatric Cardiology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Carl E. Stafstrom
- Division of Pediatric Neurology, Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Eva K. Ritzl
- Departments of Neurology and Anesthesia and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
10
|
O'Toole JM, Mathieson SR, Raurale SA, Magarelli F, Marnane WP, Lightbody G, Boylan GB. Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy. Sci Data 2023; 10:129. [PMID: 36899033 PMCID: PMC10006081 DOI: 10.1038/s41597-023-02002-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Accepted: 02/03/2023] [Indexed: 03/12/2023] Open
Abstract
This report describes a set of neonatal electroencephalogram (EEG) recordings graded according to the severity of abnormalities in the background pattern. The dataset consists of 169 hours of multichannel EEG from 53 neonates recorded in a neonatal intensive care unit. All neonates received a diagnosis of hypoxic-ischaemic encephalopathy (HIE), the most common cause of brain injury in full term infants. For each neonate, multiple 1-hour epochs of good quality EEG were selected and then graded for background abnormalities. The grading system assesses EEG attributes such as amplitude, continuity, sleep-wake cycling, symmetry and synchrony, and abnormal waveforms. Background severity was then categorised into 4 grades: normal or mildly abnormal EEG, moderately abnormal EEG, majorly abnormal EEG, and inactive EEG. The data can be used as a reference set of multi-channel EEG for neonates with HIE, for EEG training purposes, or for developing and evaluating automated grading algorithms.
Collapse
Affiliation(s)
- John M O'Toole
- INFANT Research Centre, University College Cork, Cork, Ireland.
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland.
| | - Sean R Mathieson
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - Sumit A Raurale
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - Fabio Magarelli
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - William P Marnane
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electronic and Electrical Engineering, University College Cork, Cork, Ireland
| | - Gordon Lightbody
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electronic and Electrical Engineering, University College Cork, Cork, Ireland
| | - Geraldine B Boylan
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| |
Collapse
|
11
|
Chioma R, Sbordone A, Patti ML, Perri A, Vento G, Nobile S. Applications of Artificial Intelligence in Neonatology. APPLIED SCIENCES 2023; 13:3211. [DOI: 10.3390/app13053211] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/17/2023]
Abstract
The development of artificial intelligence methods has impacted therapeutics, personalized diagnostics, drug discovery, and medical imaging. Although, in many situations, AI clinical decision-support tools may seem superior to rule-based tools, their use may result in additional challenges. Examples include the paucity of large datasets and the presence of unbalanced data (i.e., due to the low occurrence of adverse outcomes), as often seen in neonatal medicine. The most recent and impactful applications of AI in neonatal medicine are discussed in this review, highlighting future research directions relating to the neonatal population. Current AI applications tested in neonatology include tools for vital signs monitoring, disease prediction (respiratory distress syndrome, bronchopulmonary dysplasia, apnea of prematurity) and risk stratification (retinopathy of prematurity, intestinal perforation, jaundice), neurological diagnostic and prognostic support (electroencephalograms, sleep stage classification, neuroimaging), and novel image recognition technologies, which are particularly useful for prompt recognition of infections. To have these kinds of tools helping neonatologists in daily clinical practice could be something extremely revolutionary in the next future. On the other hand, it is important to recognize the limitations of AI to ensure the proper use of this technology.
Collapse
Affiliation(s)
- Roberto Chioma
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Annamaria Sbordone
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Maria Letizia Patti
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Alessandro Perri
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Giovanni Vento
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| | - Stefano Nobile
- Department of Life Sciences and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy
| |
Collapse
|
12
|
Moghadam SM, Airaksinen M, Nevalainen P, Marchi V, Hellström-Westas L, Stevenson NJ, Vanhatalo S. An automated bedside measure for monitoring neonatal cortical activity: a supervised deep learning-based electroencephalogram classifier with external cohort validation. Lancet Digit Health 2022; 4:e884-e892. [PMID: 36427950 DOI: 10.1016/s2589-7500(22)00196-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Accepted: 10/06/2022] [Indexed: 11/24/2022]
Abstract
BACKGROUND Electroencephalogram (EEG) monitoring is recommended as routine in newborn neurocritical care to facilitate early therapeutic decisions and outcome predictions. EEG's larger-scale implementation is, however, hindered by the shortage of expertise needed for the interpretation of spontaneous cortical activity, the EEG background. We developed an automated algorithm that transforms EEG recordings to quantified interpretations of EEG background and provides simple intuitive visualisations in patient monitors. METHODS In this method-development and proof-of-concept study, we collected visually classified EEGs from infants recovering from birth asphyxia or stroke. We used unsupervised learning methods to explore latent EEG characteristics, which guided the supervised training of a deep learning-based classifier. We assessed the classifier performance using cross-validation and an external validation dataset. We constructed a novel measure of cortical function, brain state of the newborn (BSN), from the novel EEG background classifier and a previously published sleep-state classifier. We estimated clinical utility of the BSN by identification of two key items in newborn brain monitoring, the onset of continuous cortical activity and sleep-wake cycling, compared with the visual interpretation of the raw EEG signal and the amplitude-integrated (aEEG) trend. FINDINGS We collected 2561 h of EEG from 39 infants (gestational age 35·0-42·1 weeks; postnatal age 0-7 days). The external validation dataset included 105 h of EEG from 31 full-term infants. The overall accuracy of the EEG background classifier was 92% in the whole cohort (95% CI 91-96; range 85-100 for individual infants). BSN trend values were closely related to the onset of continuous EEG activity or sleep-wake cycling, and BSN levels showed robust difference between aEEG categories. The temporal evolution of the BSN trends showed early diverging trajectories in infants with severely abnormal outcomes. INTERPRETATION The BSN trend can be implemented in bedside patient monitors as an EEG interpretation that is intuitive, transparent, and clinically explainable. A quantitative trend measure of brain function might harmonise practices across medical centres, enable wider use of brain monitoring in neurocritical care, and might facilitate clinical intervention trials. FUNDING European Training Networks Funding Scheme, the Academy of Finland, Finnish Pediatric Foundation (Lastentautiensäätiö), Aivosäätiö, Sigrid Juselius Foundation, HUS Children's Hospital, HUS Diagnostic Center, National Health and Medical Research Council of Australia.
Collapse
Affiliation(s)
- Saeed Montazeri Moghadam
- BABA Center, Pediatric Research Center, Department of Clinical Neurophysiology, Children's Hospital, HUS imaging, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Physiology, University of Helsinki, Helsinki, Finland.
| | - Manu Airaksinen
- BABA Center, Pediatric Research Center, Department of Clinical Neurophysiology, Children's Hospital, HUS imaging, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Physiology, University of Helsinki, Helsinki, Finland
| | - Päivi Nevalainen
- BABA Center, Pediatric Research Center, Department of Clinical Neurophysiology, Children's Hospital, HUS imaging, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Viviana Marchi
- Department of Developmental Neuroscience, Stella Maris Scientific Institute, IRCCS Fondazione Stella Maris Foundation, Pisa, Italy
| | | | - Nathan J Stevenson
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia
| | - Sampsa Vanhatalo
- BABA Center, Pediatric Research Center, Department of Clinical Neurophysiology, Children's Hospital, HUS imaging, HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Department of Physiology, University of Helsinki, Helsinki, Finland
| |
Collapse
|
13
|
Abstract
Clinical Decision Support (CDS) tools help the healthcare team diagnose, monitor, and treat patients more efficiently and consistently by executing clinical practice guidelines and recommendations. As a result, CDS has a direct impact on the delivery and healthcare outcomes. This review covers the fundamental concepts, as well as the infrastructure needed to create a CDS tool and examples of its use in the neonatal setting. This article also serves as a primer on what to think about when proposing the development of a new CDS tool, or when upgrading an existing one. We also highlight important elements that influence CDS development, such as informatics methodologies, data and device interoperability, and regulation.
Collapse
Affiliation(s)
- Anoop Rao
- Stanford University School of Medicine, Center for Academic Medicine, # 434A, 453 Quarry Rd, Palo Alto, CA, 94304, USA.
| | - Jonathan Palma
- Orlando Health Winnie Palmer Hospital for Women and Babies, 83 W Miller St, Orlando, FL, 32806, USA.
| |
Collapse
|
14
|
Abstract
Neonatal care is becoming increasingly complex with large amounts of rich, routinely recorded physiological, diagnostic and outcome data. Artificial intelligence (AI) has the potential to harness this vast quantity and range of information and become a powerful tool to support clinical decision making, personalised care, precise prognostics, and enhance patient safety. Current AI approaches in neonatal medicine include tools for disease prediction and risk stratification, neurological diagnostic support and novel image recognition technologies. Key to the integration of AI in neonatal medicine is the understanding of its limitations and a standardised critical appraisal of AI tools. Barriers and challenges to this include the quality of datasets used, performance assessment, and appropriate external validation and clinical impact studies. Improving digital literacy amongst healthcare professionals and cross-disciplinary collaborations are needed to harness the full potential of AI to help take the next significant steps in improving neonatal outcomes for high-risk infants.
Collapse
|
15
|
Ray J, Wijesekera L, Cirstea S. Machine learning and clinical neurophysiology. J Neurol 2022; 269:6678-6684. [PMID: 35907045 DOI: 10.1007/s00415-022-11283-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Revised: 07/05/2022] [Accepted: 07/09/2022] [Indexed: 11/29/2022]
Abstract
Clinical neurophysiology constructs a wealth of dynamic information pertaining to the integrity and function of both central and peripheral nervous systems. As with many technological fields, there has been an explosion of data in neurophysiology over recent years, and this requires considerable analysis by experts. Computational algorithms and especially advances in machine learning (ML) have the ability to assist with this task and potentially reveal hidden insights. In this update article, we will provide a brief overview where such technology is being applied in clinical neurophysiology and possible future directions.
Collapse
Affiliation(s)
- Julian Ray
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK.
| | - Lokesh Wijesekera
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK
| | - Silvia Cirstea
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK
| |
Collapse
|
16
|
Baser O, Yavuz M, Ugurlu K, Onat F, Demirel BU. Automatic detection of the spike-and-wave discharges in absence epilepsy for humans and rats using deep learning. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103726] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
|
17
|
Zhang Y, Xi Z, Zheng J, Shi H, Jiao Z. GWLS: A Novel Model for Predicting Cognitive Function Scores in Patients With End-Stage Renal Disease. Front Aging Neurosci 2022; 14:834331. [PMID: 35185530 PMCID: PMC8850953 DOI: 10.3389/fnagi.2022.834331] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Accepted: 01/05/2022] [Indexed: 01/03/2023] Open
Abstract
The scores of the cognitive function of patients with end-stage renal disease (ESRD) are highly subjective, which tend to affect the results of clinical diagnosis. To overcome this issue, we proposed a novel model to explore the relationship between functional magnetic resonance imaging (fMRI) data and clinical scores, thereby predicting cognitive function scores of patients with ESRD. The model incorporated three parts, namely, graph theoretic algorithm (GTA), whale optimization algorithm (WOA), and least squares support vector regression machine (LSSVRM). It was called GTA-WOA-LSSVRM or GWLS for short. GTA was adopted to calculate the area under the curve (AUC) of topological parameters, which were extracted as the features from the functional networks of the brain. Then, the statistical method and Pearson correlation analysis were used to select the features. Finally, the LSSVRM was built according to the selected features to predict the cognitive function scores of patients with ESRD. Besides, WOA was introduced to optimize the parameters in the LSSVRM kernel function to improve the prediction accuracy. The results validated that the prediction accuracy obtained by GTA-WOA-LSSVRM was higher than several comparable models, such as GTA-SVRM, GTA-LSSVRM, and GTA-WOA-SVRM. In particular, the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) between the predicted scores and the actual scores of patients with ESRD were 0.92, 0.88, and 4.14%, respectively. The proposed method can more accurately predict the cognitive function scores of ESRD patients and thus helps to understand the pathophysiological mechanism of cognitive dysfunction associated with ESRD.
Collapse
Affiliation(s)
- Yutao Zhang
- School of Microelectronics and Control Engineering, Changzhou University, Changzhou, China
| | - Zhengtao Xi
- School of Microelectronics and Control Engineering, Changzhou University, Changzhou, China
| | - Jiahui Zheng
- Department of Radiology, Changzhou Second People’s Hospital Affiliated to Nanjing Medical University, Changzhou, China
| | - Haifeng Shi
- Department of Radiology, Changzhou Second People’s Hospital Affiliated to Nanjing Medical University, Changzhou, China
- *Correspondence: Haifeng Shi,
| | - Zhuqing Jiao
- School of Microelectronics and Control Engineering, Changzhou University, Changzhou, China
- School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, China
- Zhuqing Jiao,
| |
Collapse
|
18
|
Mattioli F, Porcaro C, Baldassarre G. A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface. J Neural Eng 2021; 18. [PMID: 34920443 DOI: 10.1088/1741-2552/ac4430] [Citation(s) in RCA: 30] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Accepted: 12/17/2021] [Indexed: 11/11/2022]
Abstract
OBJECTIVE Brain-computer interface (BCI) aims to establish communication paths between the brain processes and external devices. Different methods have been used to extract human intentions from electroencephalography (EEG) recordings. Those based on motor imagery (MI) seem to have a great potential for future applications. These approaches rely on the extraction of EEG distinctive patterns during imagined movements. Techniques able to extract patterns from raw signals represent an important target for BCI as they do not need labor-intensive data pre-processing. APPROACH We propose a new approach based on a 10-layer one-dimensional convolution neural network (1D-CNN) to classify five brain states (four MI classes plus a 'baseline' class) using a data augmentation algorithm and a limited number of EEG channels. In addition, we present a transfer learning method used to extract critical features from the EEG group dataset and then to customize the model to the single individual by training its outer layers with only 12-minute individual-related data. MAIN RESULTS The model tested with the 'EEG Motor Movement/Imagery Dataset' outperforms the current state-of-the-art models by achieving a 99.38% accuracy at the group level. In addition, the transfer learning approach we present achieves an average accuracy of 99.46%. SIGNIFICANCE The proposed methods could foster future BCI applications relying on few-channel portable recording devices and individual-based training.
Collapse
Affiliation(s)
- Francesco Mattioli
- Institute of Cognitive Sciences and Technologies (ISTC), CNR, Via San Martino della Battaglia, Roma, Lazio, 00185, ITALY
| | - Camillo Porcaro
- Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche, Via S. Martino della Battaglia, 44, Roma, 00185, ITALY
| | - Gianluca Baldassarre
- Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche, Via S. Martino della Battaglia, 44, Roma, 00185, ITALY
| |
Collapse
|
19
|
Montazeri S, Pinchefsky E, Tse I, Marchi V, Kohonen J, Kauppila M, Airaksinen M, Tapani K, Nevalainen P, Hahn C, Tam EWY, Stevenson NJ, Vanhatalo S. Building an Open Source Classifier for the Neonatal EEG Background: A Systematic Feature-Based Approach From Expert Scoring to Clinical Visualization. Front Hum Neurosci 2021; 15:675154. [PMID: 34135744 PMCID: PMC8200402 DOI: 10.3389/fnhum.2021.675154] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2021] [Accepted: 04/30/2021] [Indexed: 11/13/2022] Open
Abstract
Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8-16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81-100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies.
Collapse
Affiliation(s)
- Saeed Montazeri
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Elana Pinchefsky
- Division of Neurology, Department of Paediatrics, Sainte-Justine University Hospital Centre, University of Montreal, Montreal, QC, Canada
| | - Ilse Tse
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Viviana Marchi
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Department of Developmental Neuroscience, Stella Maris Scientific Institute, IRCCS Fondazione Stella Maris Foundation, Pisa, Italy
| | - Jukka Kohonen
- Department of Computer Science, Aalto University, Espoo, Finland
| | - Minna Kauppila
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Manu Airaksinen
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland
| | - Karoliina Tapani
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Päivi Nevalainen
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Cecil Hahn
- Department of Paediatrics (Neurology), The Hospital for Sick Children and University of Toronto, Toronto, ON, Canada
| | - Emily W. Y. Tam
- Department of Paediatrics (Neurology), The Hospital for Sick Children and University of Toronto, Toronto, ON, Canada
| | - Nathan J. Stevenson
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia
| | - Sampsa Vanhatalo
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Neuroscience Center, Helsinki Institute of Life Science, University of Helsinki, Helsinki, Finland
| |
Collapse
|
20
|
Liu G, Xiao R, Xu L, Cai J. Minireview of Epilepsy Detection Techniques Based on Electroencephalogram Signals. Front Syst Neurosci 2021; 15:685387. [PMID: 34093143 PMCID: PMC8173051 DOI: 10.3389/fnsys.2021.685387] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Accepted: 04/20/2021] [Indexed: 12/11/2022] Open
Abstract
Epilepsy is one of the most common neurological disorders typically characterized by recurrent and uncontrollable seizures, which seriously affects the quality of life of epilepsy patients. The effective tool utilized in the clinical diagnosis of epilepsy is the Electroencephalogram (EEG). The emergence of machine learning promotes the development of automated epilepsy detection techniques. New algorithms are continuously introduced to shorten the detection time and improve classification accuracy. This minireview summarized the latest research of epilepsy detection techniques that focused on acquiring, preprocessing, feature extraction, and classification of epileptic EEG signals. The application of seizure prediction and localization based on EEG signals in the diagnosis of epilepsy was also introduced. And then, the future development trend of epilepsy detection technology has prospected at the end of the article.
Collapse
Affiliation(s)
- Guangda Liu
- College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China
| | - Ruolan Xiao
- College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China
| | - Lanyu Xu
- College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China
| | - Jing Cai
- College of Instrumentation and Electrical Engineering, Jilin University, Changchun, China
| |
Collapse
|