Neonatal Brain Microstructure and Machine-Learning-Based Prediction of Early Language Development in Children Born Very Preterm

Genetic pathways in cerebral palsy: a review of the implications for precision diagnosis and understanding disease mechanisms

ABSTRACT

Cerebral palsy is a diagnostic term utilized to describe a group of permanent disorders affecting movement and posture. Patients with cerebral palsy are often only capable of limited activity, resulting from non-progressive disturbances in the fetal or neonatal brain. These disturbances severely impact the child's daily life and impose a substantial economic burden on the family. Although cerebral palsy encompasses various brain injuries leading to similar clinical outcomes, the understanding of its etiological pathways remains incomplete owing to its complexity and heterogeneity. This review aims to summarize the current knowledge on the genetic factors influencing cerebral palsy development. It is now widely acknowledged that genetic mutations and alterations play a pivotal role in cerebral palsy development, which can be further influenced by environmental factors. Despite continuous research endeavors, the underlying factors contributing to cerebral palsy remain are still elusive. However, significant progress has been made in genetic research that has markedly enhanced our comprehension of the genetic factors underlying cerebral palsy development. Moreover, these genetic factors have been categorized based on the identified gene mutations in patients through clinical genotyping, including thrombosis, angiogenesis, mitochondrial and oxidative phosphorylation function, neuronal migration, and cellular autophagy. Furthermore, exploring targeted genotypes holds potential for precision treatment. In conclusion, advancements in genetic research have substantially improved our understanding of the genetic causes underlying cerebral palsy. These breakthroughs have the potential to pave the way for new treatments and therapies, consequently shaping the future of cerebral palsy research and its clinical management. The investigation of cerebral palsy genetics holds the potential to significantly advance treatments and management strategies. By elucidating the underlying cellular mechanisms, we can develop targeted interventions to optimize outcomes. A continued collaboration between researchers and clinicians is imperative to comprehensively unravel the intricate genetic etiology of cerebral palsy.

Predicting mental and psychomotor delay in very pre-term infants using machine learning

BACKGROUND

Very preterm infants are at elevated risk for neurodevelopmental delays. Earlier prediction of delays allows timelier intervention and improved outcomes. Machine learning (ML) was used to predict mental and psychomotor delay at 25 months.

METHODS

We applied RandomForest classifier to data from 1109 very preterm infants recruited over 20 years. ML selected key predictors from 52 perinatal and 16 longitudinal variables (1-22 mo assessments). SHapley Additive exPlanations provided model interpretability.

RESULTS

Balanced accuracy with perinatal variables was 62%/61% (mental/psychomotor). Top predictors of mental and psychomotor delay overlapped and included: birth year, days in hospital, antenatal MgSO4, days intubated, birth weight, abnormal cranial ultrasound, gestational age, mom's age and education, and intrauterine growth restriction. Highest balanced accuracy was achieved with 19-month follow-up scores and perinatal variables (72%/73%).

CONCLUSIONS

Combining perinatal and longitudinal data, ML modeling predicted 24 month mental/psychomotor delay in very preterm infants ½ year early, allowing intervention to start that much sooner. Modeling using only perinatal features fell short of clinical application. Birth year's importance reflected a linear decline in predicting delay as birth year became more recent.

IMPACT

Combining perinatal and longitudinal data, ML modeling was able to predict 24 month mental/psychomotor delay in very preterm infants ½ year early (25% of their lives) potentially advancing implementation of intervention services. Although cognitive/verbal and fine/gross motor delays require separate interventions, in very preterm infants there is substantial overlap in the risk factors that can be used to predict these delays. Birth year has an important effect on ML prediction of delay in very preterm infants, with those born more recently (1989-2009) being increasing less likely to be delayed, perhaps reflecting advances in medical practice.

The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review

Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.

Impact of postnatal weight gain on brain white matter maturation in very preterm infants

BACKGROUND AND PURPOSE

Very preterm infants (VPIs, <32 weeks gestational age at birth) are prone to long-term neurological deficits. While the effects of birth weight and postnatal growth on VPIs' neurological outcome are well established, the neurobiological mechanism behind these associations remains elusive. In this study, we utilized diffusion tensor imaging (DTI) to characterize how birth weight and postnatal weight gain influence VPIs' white matter (WM) maturation.

METHODS

We included VPIs with complete birth and postnatal weight data in their health record, and DTI scan as part of their predischarge Magnetic Resonance Imaging (MRI). We conducted voxel-wise general linear model and tract-based regression analyses to explore the impact of birth weight and postnatal weight gain on WM maturation.

RESULTS

We included 91 VPIs in our analysis. After controlling for gestational age at birth and time between birth and scan, higher birth weight Z-scores were associated with DTI markers of more mature WM tracts, most prominently in the corpus callosum and sagittal striatum. The postnatal weight Z-score changes over the first 4 weeks of life were also associated with increased maturity in these WM tracts, when controlling for gestational age at birth, birth weight Z-score, and time between birth and scan.

CONCLUSIONS

In VPIs, birth weight and post-natal weight gain are associated with markers of brain WM maturation, particularly in the corpus callosum, which can be captured on discharge MRI. These neuroimaging metrics can serve as potential biomarkers for the early effects of nutritional interventions on VPIs' brain development.

Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer

Predictive models in neuroimaging are increasingly designed with the intent to improve risk stratification and support interventional efforts in psychiatry. Many of these models have been developed in samples of children school-aged or older. Nevertheless, despite growing evidence that altered brain maturation during the fetal, infant, and toddler (FIT) period modulates risk for poor mental health outcomes in childhood, these models are rarely implemented in FIT samples. Applications of predictive modeling in children of these ages provide an opportunity to develop powerful tools for improved characterization of the neural mechanisms underlying development. To facilitate the broader use of predictive models in FIT neuroimaging, we present a brief primer and systematic review on the methods used in current predictive modeling FIT studies. Reflecting on current practices in more than 100 studies conducted over the past decade, we provide an overview of topics, modalities, and methods commonly used in the field and under-researched areas. We then outline ethical and future considerations for neuroimaging researchers interested in predicting health outcomes in early life, including researchers who may be relatively new to either advanced machine learning methods or using FIT data. Altogether, the last decade of FIT research in machine learning has provided a foundation for accelerating the prediction of early-life trajectories across the full spectrum of illness and health.

Review of Machine Learning and Artificial Intelligence (ML/AI) for the Pediatric Neurologist

Artificial intelligence (AI) and a popular branch of AI known as machine learning (ML) are increasingly being utilized in medicine and to inform medical research. This review provides an overview of AI and ML (AI/ML), including definitions of common terms. We discuss the history of AI and provide instances of how AI/ML can be applied to pediatric neurology. Examples include imaging in neuro-oncology, autism diagnosis, diagnosis from charts, epilepsy, cerebral palsy, and neonatal neurology. Topics such as supervised learning, unsupervised learning, and reinforcement learning are discussed.

Early brain morphometrics from neonatal MRI predict motor and cognitive outcomes at 2-years corrected age in very preterm infants

Infants born very preterm face a range of neurodevelopmental challenges in cognitive, language, behavioural and/or motor domains. Early accurate identification of those at risk of adverse neurodevelopmental outcomes, through clinical assessment and Magnetic Resonance Imaging (MRI), enables prognostication of outcomes and the initiation of targeted early interventions. This study utilises a prospective cohort of 181 infants born <31 weeks gestation, who had 3T MRIs acquired at 29-35 weeks postmenstrual age and a comprehensive neurodevelopmental evaluation at 2 years corrected age (CA). Cognitive, language and motor outcomes were assessed using the Bayley Scales of Infant and Toddler Development - Third Edition and functional motor outcomes using the Neuro-sensory Motor Developmental Assessment. By leveraging advanced structural MRI pre-processing steps to standardise the data, and the state-of-the-art developing Human Connectome Pipeline, early MRI biomarkers of neurodevelopmental outcomes were identified. Using Least Absolute Shrinkage and Selection Operator (LASSO) regression, significant associations between brain structure on early MRIs with 2-year outcomes were obtained (r = 0.51 and 0.48 for motor and cognitive outcomes respectively) on an independent 25% of the data. Additionally, important brain biomarkers from early MRIs were identified, including cortical grey matter volumes, as well as cortical thickness and sulcal depth across the entire cortex. Adverse outcome on the Bayley-III motor and cognitive composite scores were accurately predicted, with an Area Under the Curve of 0.86 for both scores. These associations between 2-year outcomes and patient prognosis and early neonatal MRI measures demonstrate the utility of imaging prior to term equivalent age for providing earlier commencement of targeted interventions for infants born preterm.

Machine learning for understanding and predicting neurodevelopmental outcomes in premature infants: a systematic review

BACKGROUND

Machine learning has been attracting increasing attention for use in healthcare applications, including neonatal medicine. One application for this tool is in understanding and predicting neurodevelopmental outcomes in preterm infants. In this study, we have carried out a systematic review to identify findings and challenges to date.

METHODS

This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Four databases were searched in February 2022, with articles then screened in a non-blinded manner by two authors.

RESULTS

The literature search returned 278 studies, with 11 meeting the eligibility criteria for inclusion. Convolutional neural networks were the most common machine learning approach, with most studies seeking to predict neurodevelopmental outcomes from images and connectomes describing brain structure and function. Studies to date also sought to identify features predictive of outcomes; however, results varied greatly.

CONCLUSIONS

Initial studies in this field have achieved promising results; however, many machine learning techniques remain to be explored, and the consensus is yet to be reached on which clinical and brain features are most predictive of neurodevelopmental outcomes.

IMPACT

This systematic review looks at the question of whether machine learning can be used to predict and understand neurodevelopmental outcomes in preterm infants. Our review finds that promising initial works have been conducted in this field, but many challenges and opportunities remain. Quality assessment of relevant articles is conducted using the Newcastle-Ottawa Scale. This work identifies challenges that remain and suggests several key directions for future research. To the best of the authors' knowledge, this is the first systematic review to explore this topic.

Language Impairment in Children of Mothers with Gestational Diabetes, Preeclampsia, and Preterm Delivery: Current Hypothesis and Potential Underlying Mechanisms : Language Impartment and Pregnancy Complications

Many conditions may impair or delay language development, including socioeconomic status, parent's education, or intrauterine environment. Accordingly, increasing evidence has described that pregnancy complications, including gestational diabetes mellitus (GDM), preeclampsia, and preterm delivery, are associated with the offspring's impaired neurodevelopment. Since language is one of the high brain functions, alterations in this function are another sign of neurodevelopment impairment. How these maternal conditions may generate language impairment has yet to be entirely understood. However, since language development requires adequate structural formation and function/connectivity of the brain, these processes must be affected by alterations in maternal conditions. However, the underlying mechanisms of these structural alterations are largely unknown. This manuscript critically analyzes the literature focused on the risk of developing language impairment in children of mothers with GDM, preeclampsia, and preterm delivery. Furthermore, we highlight potential underlying molecular mechanisms associated with these alterations, such as neuroinflammatory and metabolic and cerebrovascular alterations.

Diffuse excessive high signal intensity in the preterm brain on advanced MRI represents widespread neuropathology

Preterm brains commonly exhibit elevated signal intensity in the white matter on T2-weighted MRI at term-equivalent age. This signal, known as diffuse excessive high signal intensity (DEHSI) or diffuse white matter abnormality (DWMA) when quantitatively assessed, is associated with abnormal microstructure on diffusion tensor imaging. However, postmortem data are largely lacking and difficult to obtain, and the pathological significance of DEHSI remains in question. In a cohort of 202 infants born preterm at ≤32 weeks gestational age, we leveraged two newer diffusion MRI models - Constrained Spherical Deconvolution (CSD) and neurite orientation dispersion and density index (NODDI) - to better characterize the macro and microstructural properties of DWMA and inform the ongoing debate around the clinical significance of DWMA. With increasing DWMA volume, fiber density broadly decreased throughout the white matter and fiber cross-section decreased in the major sensorimotor tracts. Neurite orientation dispersion decreased in the centrum semiovale, corona radiata, and temporal lobe. These findings provide insight into DWMA's biological underpinnings and demonstrate that it is a serious pathology.

A self-training deep neural network for early prediction of cognitive deficits in very preterm infants using brain functional connectome data

BACKGROUND

Deep learning has been employed using brain functional connectome data for evaluating the risk of cognitive deficits in very preterm infants. Although promising, training these deep learning models typically requires a large amount of labeled data, and labeled medical data are often very difficult and expensive to obtain.

OBJECTIVE

This study aimed to develop a self-training deep neural network (DNN) model for early prediction of cognitive deficits at 2 years of corrected age in very preterm infants (gestational age ≤32 weeks) using both labeled and unlabeled brain functional connectome data.

MATERIALS AND METHODS

We collected brain functional connectome data from 343 very preterm infants at a mean (standard deviation) postmenstrual age of 42.7 (2.5) weeks, among whom 103 children had a cognitive assessment at 2 years (i.e. labeled data), and the remaining 240 children had not received 2-year assessments at the time this study was conducted (i.e. unlabeled data). To develop a self-training DNN model, we built an initial student model using labeled brain functional connectome data. Then, we applied the trained model as a teacher model to generate pseudo-labels for unlabeled brain functional connectome data. Next, we combined labeled and pseudo-labeled data to train a new student model. We iterated this procedure to obtain the best student model for the early prediction task in very preterm infants.

RESULTS

In our cross-validation experiments, the proposed self-training DNN model achieved an accuracy of 71.0%, a specificity of 71.5%, a sensitivity of 70.4% and an area under the curve of 0.75, significantly outperforming transfer learning models through pre-training approaches.

CONCLUSION

We report the first self-training prognostic study in very preterm infants, efficiently utilizing a small amount of labeled data with a larger share of unlabeled data to aid the model training. The proposed technique is expected to facilitate deep learning with insufficient training data.

[Early detection of primary developmental language disorders-increasing relevance due to changes in diagnostic criteria?]

Language development disorders (in German: Sprachentwicklungsstörungen, SES) are the most common developmental disorders in childhood. In contrast to "secondary SES," "primary SES" (prevalence about 7%) are not (co-)caused by other developmental disorders or diseases. In the German modification of the International Statistical Classification of Diseases and Related Health Problems (ICD-10-GM-22), primary SES are referred to as "circumscribed developmental disorders of speech and language" (in German: USES; international previously known as Specific Language Impairment SLI), with an intelligence quotient (IQ) < 85 as an exclusion criterion, among other criteria. In ICD-11, primary SES are listed as "developmental language disorders" (DLD).German-speaking speech and language therapists would now like to replace the term "USES" with "DLD" using the diagnostic criteria proposed by the international CATALISE consortium (Criteria and Terminology Applied to Language Impairments Synthesizing the Evidence), in an effort to redefine the disorder. However, according to this conceptualization, only children with an intellectual disability (IQ < 70) would be excluded from the diagnosis. This change in the diagnostic criteria would most likely result in an increase in prevalence of DLDs. This makes the issue of early detection more important than ever. This discussion paper explains that the public health relevance of primary SES is growing and that systematic early detection examinations will play an even more important role. With early diagnosis and treatment, risks in the areas of mental health, behaviour and skill development can be mitigated.Currently, diagnosis (and therapy) are usually carried out relatively late. The way out could lie in the application of neurobiological parameters. However, this requires further studies that examine child cohorts for early indicators in a prospective longitudinal design. The formation of an early detection index from several indicators should also be considered.

Machine Learning Prediction Models for Neurodevelopmental Outcome After Preterm Birth: A Scoping Review and New Machine Learning Evaluation Framework

BACKGROUND AND OBJECTIVES

Outcome prediction of preterm birth is important for neonatal care, yet prediction performance using conventional statistical models remains insufficient. Machine learning has a high potential for complex outcome prediction. In this scoping review, we provide an overview of the current applications of machine learning models in the prediction of neurodevelopmental outcomes in preterm infants, assess the quality of the developed models, and provide guidance for future application of machine learning models to predict neurodevelopmental outcomes of preterm infants.

METHODS

A systematic search was performed using PubMed. Studies were included if they reported on neurodevelopmental outcome prediction in preterm infants using predictors from the neonatal period and applying machine learning techniques. Data extraction and quality assessment were independently performed by 2 reviewers.

RESULTS

Fourteen studies were included, focusing mainly on very or extreme preterm infants, predicting neurodevelopmental outcome before age 3 years, and mostly assessing outcomes using the Bayley Scales of Infant Development. Predictors were most often based on MRI. The most prevalent machine learning techniques included linear regression and neural networks. None of the studies met all newly developed quality assessment criteria. Studies least prone to inflated performance showed promising results, with areas under the curve up to 0.86 for classification and R2 values up to 91% in continuous prediction. A limitation was that only 1 data source was used for the literature search.

CONCLUSIONS

Studies least prone to inflated prediction results are the most promising. The provided evaluation framework may contribute to improved quality of future machine learning models.

Early Predictors of Poor Neurologic Outcomes in a Prospective Cohort of Infants With Antenatal Exposure to Zika Virus

BACKGROUND

Identify early predictors of poor neurodevelopment in infants with antenatal Zika virus (ZIKV) exposure.

METHODS

Analysis of a prospective cohort of infants with antenatal ZIKV exposure confirmed by maternal or infant RT-PCR or IgM during the epidemic in Rio de Janeiro, Brazil. Clinical findings before 3 months of age were associated with Bayley-III Scales of Infant and Toddler Development conducted after 6 months of age.

RESULTS

ZIKV exposure was confirmed in 219 cases; 162 infants were normocephalic, 53 were microcephalic, 4 had no head circumference recorded because of perinatal death/LTFU. Seven of the 112 normocephalic infants developed secondary microcephaly between 3 weeks and 8 months of age. Among the normocephalic at birth cohort, the mean HCZ among normal, at risk, and developmentally delayed children was significantly different (ANOVA, P = 0.02). In particular, the mean HCZ of the developmentally delayed group was significantly lower than that of the normal group (Tukey's test, P = 0.014). HCZ was more strongly associated with lower expressive language scores (P = 0.04) than receptive language scores (P = 0.06). The rate of auditory abnormalities differed among the normal, at risk, and developmentally delayed groups (Chi-squared test, P = 0.016), which was driven by the significant difference between the normal and at risk groups (post hoc test, P = 0.011, risk ratio 3.94). Auditory abnormalities were associated with both expressive and receptive language delays (P = 0.02 and P = 0.02, respectively).

CONCLUSIONS

Clear predictors of neurodevelopment in normocephalic ZIKV-exposed children have not been previously identified. Our findings demonstrate that smaller HCZ and auditory abnormalities in these infants correlate with poor neurodevelopment as toddlers. Language delay is the most prominent developmental concern among these children, who will require frequent auditory and speech evaluations throughout childhood.

Language function following preterm birth: prediction using machine learning

BACKGROUND

Preterm birth can lead to impaired language development. This study aimed to predict language outcomes at 2 years corrected gestational age (CGA) for children born preterm.

METHODS

We analysed data from 89 preterm neonates (median GA 29 weeks) who underwent diffusion MRI (dMRI) at term-equivalent age and language assessment at 2 years CGA using the Bayley-III. Feature selection and a random forests classifier were used to differentiate typical versus delayed (Bayley-III language composite score <85) language development.

RESULTS

The model achieved balanced accuracy: 91%, sensitivity: 86%, and specificity: 96%. The probability of language delay at 2 years CGA is increased with: increasing values of peak width of skeletonized fractional anisotropy (PSFA), radial diffusivity (PSRD), and axial diffusivity (PSAD) derived from dMRI; among twins; and after an incomplete course of, or no exposure to, antenatal corticosteroids. Female sex and breastfeeding during the neonatal period reduced the risk of language delay.

CONCLUSIONS

The combination of perinatal clinical information and MRI features leads to accurate prediction of preterm infants who are likely to develop language deficits in early childhood. This model could potentially enable stratification of preterm children at risk of language dysfunction who may benefit from targeted early interventions.

IMPACT

A combination of clinical perinatal factors and neonatal DTI measures of white matter microstructure leads to accurate prediction of language outcome at 2 years corrected gestational age following preterm birth. A model that comprises clinical and MRI features that has potential to be scalable across centres. It offers a basis for enhancing the power and generalizability of diagnostic and prognostic studies of neurodevelopmental disorders associated with language impairment. Early identification of infants who are at risk of language delay, facilitating targeted early interventions and support services, which could improve the quality of life for children born preterm.

The Soundscape of Neonatal Intensive Care: A Mixed-Methods Study of the Parents' Experience

Parents who have infants hospitalised in neonatal intensive care units (NICUs) experience high levels of stress, including post-traumatic stress disorder (PTSD) symptoms. However, whether sounds contribute to parents’ stress remains largely unknown. Critically, researchers lack a comprehensive instrument to investigate the relationship between sounds in NICUs and parental stress. To address this gap, this report presents the “Soundscape of NICU Questionnaire” (SON-Q), which was developed specifically to capture parents’ perceptions and beliefs about the impact that sound had on them and their infants, from pre-birth throughout the NICU stay and in the first postdischarge period. Parents of children born preterm (n = 386) completed the SON-Q and the Perinatal PTSD Questionnaire (PPQ). Principal Component Analysis identifying underlying dimensions comprising the parental experience of the NICU soundscape was followed by an exploration of the relationships between subscales of the SON-Q and the PPQ. Moderation analysis was carried out to further elucidate relationships between variables. Finally, thematic analysis was employed to analyse one memory of sounds in NICU open question. The results highlight systematic associations between aspects of the NICU soundscape and parental stress/trauma. The findings underscore the importance of developing specific studies in this area and devising interventions to best support parents’ mental health, which could in turn support infants’ developmental outcomes.

Heart Rate Variability in the Perinatal Period: A Critical and Conceptual Review

Neonatal intensive care units (NICUs) greatly expand the use of technology. There is a need to accurately diagnose discomfort, pain, and complications, such as sepsis, mainly before they occur. While specific treatments are possible, they are often time-consuming, invasive, or painful, with detrimental effects for the development of the infant. In the last 40 years, heart rate variability (HRV) has emerged as a non-invasive measurement to monitor newborns and infants, but it still is underused. Hence, the present paper aims to review the utility of HRV in neonatology and the instruments available to assess it, showing how HRV could be an innovative tool in the years to come. When continuously monitored, HRV could help assess the baby’s overall wellbeing and neurological development to detect stress-/pain-related behaviors or pathological conditions, such as respiratory distress syndrome and hyperbilirubinemia, to address when to perform procedures to reduce the baby’s stress/pain and interventions, such as therapeutic hypothermia, and to avoid severe complications, such as sepsis and necrotizing enterocolitis, thus reducing mortality. Based on literature and previous experiences, the first step to efficiently introduce HRV in the NICUs could consist in a monitoring system that uses photoplethysmography, which is low-cost and non-invasive, and displays one or a few metrics with good clinical utility. However, to fully harness HRV clinical potential and to greatly improve neonatal care, the monitoring systems will have to rely on modern bioinformatics (machine learning and artificial intelligence algorithms), which could easily integrate infant’s HRV metrics, vital signs, and especially past history, thus elaborating models capable to efficiently monitor and predict the infant’s clinical conditions. For this reason, hospitals and institutions will have to establish tight collaborations between the obstetric, neonatal, and pediatric departments: this way, healthcare would truly improve in every stage of the perinatal period (from conception to the first years of life), since information about patients’ health would flow freely among different professionals, and high-quality research could be performed integrating the data recorded in those departments.