1
|
Chung HW, Chen JC, Chen HL, Ko FY, Ho SY. Developing a practical neurodevelopmental prediction model for targeting high-risk very preterm infants during visit after NICU: a retrospective national longitudinal cohort study. BMC Med 2024; 22:68. [PMID: 38360711 PMCID: PMC10870669 DOI: 10.1186/s12916-024-03286-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 02/05/2024] [Indexed: 02/17/2024] Open
Abstract
BACKGROUND Follow-up visits for very preterm infants (VPI) after hospital discharge is crucial for their neurodevelopmental trajectories, but ensuring their attendance before 12 months corrected age (CA) remains a challenge. Current prediction models focus on future outcomes at discharge, but post-discharge data may enhance predictions of neurodevelopmental trajectories due to brain plasticity. Few studies in this field have utilized machine learning models to achieve this potential benefit with transparency, explainability, and transportability. METHODS We developed four prediction models for cognitive or motor function at 24 months CA separately at each follow-up visits, two for the 6-month and two for the 12-month CA visits, using hospitalized and follow-up data of VPI from the Taiwan Premature Infant Follow-up Network from 2010 to 2017. Regression models were employed at 6 months CA, defined as a decline in The Bayley Scales of Infant Development 3rd edition (BSIDIII) composite score > 1 SD between 6- and 24-month CA. The delay models were developed at 12 months CA, defined as a BSIDIII composite score < 85 at 24 months CA. We used an evolutionary-derived machine learning method (EL-NDI) to develop models and compared them to those built by lasso regression, random forest, and support vector machine. RESULTS One thousand two hundred forty-four VPI were in the developmental set and the two validation cohorts had 763 and 1347 VPI, respectively. EL-NDI used only 4-10 variables, while the others required 29 or more variables to achieve similar performance. For models at 6 months CA, the area under the receiver operating curve (AUC) of EL-NDI were 0.76-0.81(95% CI, 0.73-0.83) for cognitive regress with 4 variables and 0.79-0.83 (95% CI, 0.76-0.86) for motor regress with 4 variables. For models at 12 months CA, the AUC of EL-NDI were 0.75-0.78 (95% CI, 0.72-0.82) for cognitive delay with 10 variables and 0.73-0.82 (95% CI, 0.72-0.85) for motor delay with 4 variables. CONCLUSIONS Our EL-NDI demonstrated good performance using simpler, transparent, explainable models for clinical purpose. Implementing these models for VPI during follow-up visits may facilitate more informed discussions between parents and physicians and identify high-risk infants more effectively for early intervention.
Collapse
Affiliation(s)
- Hao Wei Chung
- Division of Neonatology, Department of Pediatrics, Kaohsiung Medical University Chung-Ho Memorial Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
- Department of Pediatrics, Kaohsiung Municipal Siaogang Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Center for Big Data Research, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Ju-Chieh Chen
- Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Hsiu-Lin Chen
- Division of Neonatology, Department of Pediatrics, Kaohsiung Medical University Chung-Ho Memorial Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Department of Respiratory Therapy, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Fang-Yu Ko
- Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Shinn-Ying Ho
- Department of Biological Science and Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
- Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
- Center for Intelligent Drug Systems and Smart Bio-Devices, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
- College of Health Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan.
| |
Collapse
|
2
|
Tréluyer L, Nuytten A, Guellec I, Jarreau PH, Benhammou V, Cambonie G, Truffert P, Marchand-Martin L, Ancel PY, Torchin H. Neurodevelopment and healthcare utilisation at age 5-6 years in bronchopulmonary dysplasia: an EPIPAGE-2 cohort study. Arch Dis Child Fetal Neonatal Ed 2023; 109:26-33. [PMID: 37364896 DOI: 10.1136/archdischild-2023-325376] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 06/07/2023] [Indexed: 06/28/2023]
Abstract
OBJECTIVE We aimed to study neurodevelopmental outcomes and healthcare utilisation at age 5-6 years in very preterm children with bronchopulmonary dysplasia (BPD). DESIGN Prospective and national population-based study. SETTING All the neonatal units in 25 French regions (21 of the 22 metropolitan regions and 4 overseas regions). PATIENTS Children born before 32 weeks' gestation in 2011. INTERVENTIONS Blind, comprehensive and standardised assessment by trained neuropsychologists and paediatricians at age 5-6 years. MAIN OUTCOME MEASURES Overall neurodevelopmental disabilities, behavioural difficulties, developmental coordination disorders, full-scale IQ, cerebral palsy, social interaction disorders, rehospitalisation in the previous 12 months and detailed developmental support. RESULTS Of the 3186 children included, 413 (11.7%) had BPD. The median gestational age of children with BPD was 27 weeks (IQR 26.0-28.0) and without BPD was 30 weeks (28.0-31.0). At age 5-6 years, 3150 children were alive; 1914 (60.8%) had a complete assessment. BPD was strongly associated with mild, moderate and severe overall neurodevelopmental disabilities (OR 1.49, 95% CI 1.05 to 2.20; 2.20, 1.41 to 3.42 and 2.71, 1.67 to 4.40). BPD was associated with developmental coordination disorders, behavioural difficulties, lower IQ score as well as rehospitalisation in the last 12 months and developmental support. The association between BPD and cerebral palsy was statistically significant before adjustment but not in adjusted analyses. CONCLUSIONS BPD was strongly and independently associated with many neurodevelopmental disabilities. Improving medical and neurodevelopmental management of BPD in very preterm children should be a priority to reduce its long-term consequences.
Collapse
Affiliation(s)
- Ludovic Tréluyer
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
- Department of Neonatal Medicine of Port-Royal, Cochin Hospital, FHU PREMA, AP-HP Centre, Université Paris Cité, Paris, France
| | - Alexandra Nuytten
- CHU Lille, Department of Neonatal Medicine, Jeanne de Flandre Hospital, Lille, France
- CHU Lille, ULR 2694-METRICS: Évaluation des technologies de santé et des pratiques médicales, University of Lille, Lille, France
| | - Isabelle Guellec
- Department of Neonatal Medecine, University Hospital of Nice, Nice, France
| | - Pierre-Henri Jarreau
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
- Department of Neonatal Medicine of Port-Royal, Cochin Hospital, FHU PREMA, AP-HP Centre, Université Paris Cité, Paris, France
| | - Valérie Benhammou
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
| | - Gilles Cambonie
- Department of Neonatal Medicine, Montpellier University Hospital, Montpellier, France
| | - Patrick Truffert
- CHU Lille, Department of Neonatal Medicine, Jeanne de Flandre Hospital, Lille, France
- CHU Lille, ULR 2694-METRICS: Évaluation des technologies de santé et des pratiques médicales, University of Lille, Lille, France
| | - Laetitia Marchand-Martin
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
| | - Pierre Yves Ancel
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
- Clinical Research Unit, Center for Clinical Investigation P1419, Assistance Publique Hôpitaux de Paris, F-75014, Paris, France
| | - Héloïse Torchin
- Epidemiology and Statistics Research Center/CRESS, INSERM, INRAE, Paris Cité University, Paris, France
- Department of Neonatal Medicine of Port-Royal, Cochin Hospital, FHU PREMA, AP-HP Centre, Université Paris Cité, Paris, France
| |
Collapse
|
3
|
Kyriakopoulou A, Papaevangelou V, Argyropoulou M, Papathanasiou M, Xydis V, Giorgi M, Ntorkou A, Chlapoutaki C, Alexopoulou E. Fetal brain imaging provides valuable information in cCMV infected infants. J Matern Fetal Neonatal Med 2023; 36:2220564. [PMID: 37290964 DOI: 10.1080/14767058.2023.2220564] [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: 04/28/2022] [Revised: 05/01/2023] [Accepted: 05/23/2023] [Indexed: 06/10/2023]
Abstract
BACKGROUND Congenital CMV infection (cCMV) is the most common congenital infection with 10-15% of cases developing symptomatic disease. Early antiviral treatment is of essence when symptomatic disease is suspected. Recently, the use of neonatal imaging has been implicated as a prognostic tool for long term sequalae among asymptomatic newborns at high risk. Even though neonatal MRI is commonly used in neonatal symptomatic cCMV disease, it is less often used in asymptomatic newborns, mainly due to cost, access and difficulty to perform. We have therefore developed an interest in assessing the use of fetal imaging as an alternative. Our primary aim was to compare the fetal and neonatal MRIs in a small cohort 10 asymptomatic neonates with congenital CMV infection. METHODS We performed a single-center retrospective cohort study (case-series) on a convenience sample of children born from January 2014 to March 2021 with confirmed congenital CMV infection who had undergone both fetal and neonatal MRIs. We created a checklist of relevant cerebral abnormalities and asked 4 blinded radiologists to assess the MRIs (2 for each, namely fetal and neonatal) and then compared the findings between the fetal and neonatal imaging as well as the concordance in reporting of abnormalities within each category. FINDINGS Overall concordance between prenatal and postnatal scans was high (70%). When comparing the two blinded reports for each MRI, we found high levels of concordance: 90% concordance for fetal MRIs and 100% for neonatal MRIs. The most common abnormalities identified in both fetal and neonatal scans were "abnormal white matter hyperintensity" and "subependymal cysts." INTERPRETATION Even though this is a small descriptive study, it indicates that fetal MRI could potentially provide us with similar information as neonatal imaging. This study could form the basis for subsequent larger future studies.
Collapse
Affiliation(s)
- A Kyriakopoulou
- National and Kapodistrian University of Athens, Third Department of Paediatrics, Attikon General University Hospital, Athens, Greece
| | - V Papaevangelou
- National and Kapodistrian University of Athens, Third Department of Paediatrics, Attikon General University Hospital, Athens, Greece
| | - M Argyropoulou
- Department of Radiology Medical School, University of Ioannina, Ioannina, Greece
| | - M Papathanasiou
- School of Medicine, National and Kapodistrian University of Athens, 2nd Department of Radiology, General University Hospital Attikon, Athens, Greece
| | - V Xydis
- Department of Radiology Medical School, University of Ioannina, Ioannina, Greece
| | - M Giorgi
- National and Kapodistrian University of Athens, Third Department of Paediatrics, Attikon General University Hospital, Athens, Greece
| | - A Ntorkou
- Department of Paediatric Radiology, Robert Debré University Hospital, AP-HP, Paris, France
| | | | - E Alexopoulou
- School of Medicine, National and Kapodistrian University of Athens, 2nd Department of Radiology, General University Hospital Attikon, Athens, Greece
| |
Collapse
|
4
|
Nordvik T, Server A, Espeland CN, Schumacher EM, Larsson PG, Pripp AH, Stiris T. Combining MRI and Spectral EEG for Assessment of Neurocognitive Outcomes in Preterm Infants. Neonatology 2023; 120:482-490. [PMID: 37290419 DOI: 10.1159/000530648] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Accepted: 03/31/2023] [Indexed: 06/10/2023]
Abstract
INTRODUCTION Predicting impairment in preterm children is challenging. Our aim is to explore the association between MRI at term-equivalent age (TEA) and neurocognitive outcomes in late childhood and to assess whether the addition of EEG improves prognostication. METHODS This prospective observational study included forty infants with gestational age 24 + 0-30 + 6. Children were monitored with multichannel EEG for 72 h after birth. Total absolute band power for the delta band on day 2 was calculated. Brain MRI was performed at TEA and scored according to the Kidokoro scoring system. At 10-12 years of age, we evaluated neurocognitive outcomes with Wechsler Intelligence Scale for Children 4th edition, Vineland adaptive behavior scales 2nd edition and Behavior Rating Inventory of Executive Function. We performed linear regression analysis to examine the association between outcomes and MRI and EEG, respectively, and multiple regression analysis to explore the combination of MRI and EEG. RESULTS Forty infants were included. There was a significant association between global brain abnormality score and composite outcomes of WISC and Vineland test, but not the BRIEF test. The adjusted R2 was 0.16 and 0.08, respectively. For EEG, adjusted R2 was 0.34 and 0.15, respectively. When combining MRI and EEG data, adjusted R2 changed to 0.36 for WISC and 0.16 for the Vineland test. CONCLUSION There was a small association between TEA MRI and neurocognitive outcomes in late childhood. Adding EEG to the model improved the explained variance. Combining EEG and MRI data did not have any additional benefit over EEG alone.
Collapse
Affiliation(s)
- Tone Nordvik
- Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Andres Server
- Section of Neuroradiology, Department of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
| | - Cathrine N Espeland
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Eva M Schumacher
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Pål G Larsson
- Department of Neurosurgery, Oslo University Hospital, Oslo, Norway
| | - Are H Pripp
- Oslo Center of Biostatistics and Epidemiology, Research Support Services, Oslo University Hospital, Oslo, Norway
| | - Tom Stiris
- Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| |
Collapse
|
5
|
Wellmann S, Hagmann CF, von Felten S, Held L, Klebermass-Schrehof K, Truttmann AC, Knöpfli C, Fauchère JC, Bührer C, Bucher HU, Rüegger CM. Safety and Short-term Outcomes of High-Dose Erythropoietin in Preterm Infants With Intraventricular Hemorrhage: The EpoRepair Randomized Clinical Trial. JAMA Netw Open 2022; 5:e2244744. [PMID: 36459138 PMCID: PMC9719050 DOI: 10.1001/jamanetworkopen.2022.44744] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/03/2022] Open
Abstract
IMPORTANCE Intraventricular hemorrhage (IVH) is a major cause of neonatal morbidity and mortality in preterm infants without a specific medical treatment to date. OBJECTIVE To assess the safety and short-term outcomes of high-dose erythropoietin in preterm infants with IVH. DESIGN, SETTING, AND PARTICIPANTS Between April 1, 2014, and August 3, 2018, a randomized double-blind clinical trial enrolled 121 preterm infants (gestational age <32 weeks or birth weight <1500 g) aged 8 or less days with moderate to severe IVH identified by cerebral ultrasonography from 8 Swiss and Austrian tertiary neonatal units. Statistical analyses were performed between October 1, 2019, and September 12, 2022. INTERVENTIONS Infants received intravenous high-dose erythropoietin (2000 units/kg body weight) or placebo at 4 time points between weeks 1 and 4 of life. MAIN OUTCOMES AND MEASURES Secondary outcomes included (1) mortality and morbidity rates and (2) brain magnetic resonance imaging findings at term-equivalent age (TEA). The primary outcome was the composite intelligence quotient at 5 years of age (not available before 2023). RESULTS Sixty infants (48% male [n = 29]) were randomly assigned to receive erythropoietin, and 61 infants (61% male [n = 37]) were randomly assigned to receive placebo. The median birth weight was 832 g (IQR, 687-990 g) in the erythropoietin group and 870 g (IQR, 680-1110 g) in the placebo group. Median gestation was 26.1 weeks (IQR, 24.8-27.3 weeks) in the erythropoietin group and 27.0 weeks (24.9-28.1 weeks) in the placebo group. The 2 groups had similar baseline characteristics and morbidities. Up to TEA, 10 newborns died (16.7%) in the erythropoietin group, and 5 newborns (8.2%) died in the placebo group (adjusted odds ratio, 2.24 [95% CI, 0.74-7.66]; P = .15). Infants receiving erythropoietin had higher mean hematocrit levels. Conventional magnetic resonance imaging at TEA for 100 infants showed no significant differences in global or regional brain injury scores. CONCLUSIONS AND RELEVANCE This preliminary report of a randomized clinical trial found no evidence that high-dose erythropoietin in preterm infants with IVH affects brain injury scores on conventional magnetic resonance imaging at TEA. Higher mortality in the erythropoietin group was not significant but should be reassessed based on future results from similar trials. TRIAL REGISTRATION ClinicalTrials.gov Identifier: NCT02076373.
Collapse
Affiliation(s)
- Sven Wellmann
- Department of Neonatology, University Children’s Hospital Regensburg, Hospital St Hedwig of the Order of St John, University of Regensburg, Regensburg, Germany
- Division of Neonatology, University Children’s Hospital Basel, University of Basel, Basel, Switzerland
| | - Cornelia F. Hagmann
- Department of Neonatology and Pediatric Intensive Care, University Children’s Hospital Zurich, Zurich, Switzerland
- Children’s Research Center, University Children’s Hospital Zurich, Zurich, Switzerland
| | - Stefanie von Felten
- Department of Biostatistics, Institute of Epidemiology, Biostatistics and Prevention, University of Zurich, Zurich, Switzerland
| | - Leonard Held
- Department of Biostatistics, Institute of Epidemiology, Biostatistics and Prevention, University of Zurich, Zurich, Switzerland
| | | | - Anita C. Truttmann
- Clinic of Neonatology, Department of Women Mother Child, University Center Hospital and University of Lausanne, Vaud, Switzerland
| | - Claudia Knöpfli
- Newborn Research, Department of Neonatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Jean-Claude Fauchère
- Newborn Research, Department of Neonatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Christoph Bührer
- Department of Neonatology, Charité–Universitätsmedizin Berlin, Berlin, Germany
| | - Hans Ulrich Bucher
- Newborn Research, Department of Neonatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Christoph M. Rüegger
- Newborn Research, Department of Neonatology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| |
Collapse
|