Early clinical and MRI biomarkers of cognitive and motor outcomes in very preterm born infants

Machine learning techniques for predicting neurodevelopmental impairments in premature infants: a systematic review

Background and objective

Very preterm infants are highly susceptible to Neurodevelopmental Impairments (NDIs), including cognitive, motor, and language deficits. This paper presents a systematic review of the application of Machine Learning (ML) techniques to predict NDIs in premature infants.

Methods

This review presents a comparative analysis of existing studies from January 2018 to December 2023, highlighting their strengths, limitations, and future research directions.

Results

We identified 26 studies that fulfilled the inclusion criteria. In addition, we explore the potential of ML algorithms and discuss commonly used data sources, including clinical and neuroimaging data. Furthermore, the inclusion of omics data as a contemporary approach employed, in other diagnostic contexts is proposed.

Conclusions

We identified limitations and emphasized the significance of employing multimodal data models and explored various alternatives to address the limitations identified in the reviewed studies. The insights derived from this review guide researchers and clinicians toward improving early identification and intervention strategies for NDIs in this vulnerable population.

Diagnostic accuracy of early neonatal MRI in predicting adverse motor outcomes in children born preterm: Systematic review and meta-analysis

AIM

To examine the diagnostic accuracy of Early structural and diffusion-weighted magnetic resonance imaging (MRI) (acquired at < 36 weeks postmenstrual age) to detect cerebral palsy (CP) or other adverse motor outcomes at or beyond 3 years corrected age in infants born preterm.

METHOD

In this systematic review and meta-analysis, we searched the CINAHL, Embase, PubMed, and Web of Science databases for studies without language restrictions and a prospectively registered protocol up to October 2023. We extracted the study details, associations presented, and meta-analyses conducted with pooled sensitivity and specificity.

RESULTS

Twenty-seven articles met the overall inclusion criteria. White matter injury, cerebellar haemorrhage, intraventricular haemorrhage, and lower thalamic volume were associated with poorer motor outcomes. Abnormal Early structural MRI detected infants with a later diagnosis of CP (n = 448, eight studies) with a pooled sensitivity of 98% (95% confidence interval [CI] = 86-100), specificity of 75% (95% CI = 51-93), and adverse motor outcomes (n = 215, four studies), with a pooled sensitivity of 39% (95% CI = 20-59) and a specificity of 90% (95% CI = 88-94).

INTERPRETATION

Early abnormal structural MRI predicted later CP with high sensitivity and specificity, while specificity was higher than sensitivity in predicting adverse motor outcomes using the Movement Assessment Battery for Children, Second Edition. Further research into diagnostic accuracy and association between Early MRI and long-term motor outcomes is warranted.

Diagnostic accuracy of neonatal structural MRI scores to predict 6-year motor outcomes of children born very preterm

AIMS

This study aimed to (1) evaluate associations between Early and Term structural MRI (sMRI) brain abnormality scores and adverse motor outcomes at 6-years corrected age (CA), (2) determine their diagnostic accuracy in predicting adverse motor outcomes and cerebral palsy (CP) at 6-years CA.

METHODS

Infants born < 31-weeks gestational age (GA) returning for 6-year follow-up were included. Early and Term sMRI were scored using a validated method, deriving white matter, cortical grey matter, deep grey matter, cerebellar and global brain abnormality scores (GBAS). At 6-years CA, Movement Assessment Battery for Children-2nd Edition (MABC-2) was administered. Linear regression assessed associations between Early and Term GBAS/subscale scores and 6-year MABC-2 total score. For diagnostic accuracy, sMRI scores were categorised as none/mild vs moderate/severe, MABC-2 cut-off ≤ 5th percentile, and CP as present/absent.

RESULTS

Infants had Early MRI (n = 123) at mean PMA 32.5-weeks (median GA 28.4-weeks; mean birthweight 1101 g) and n = 114 had Term MRI (Mean PMA 40.8-weeks). Nine had CP and n = 116 had MABC-2 scores. Early (B: -1.92; p ≤ 0.001) and Term (B: -1.67; p ≤ 0.01) GBAS were negatively associated with MABC-2 scores. Both Early and Term GBAS had high specificity (Sp) and low sensitivity (Se) in predicting MABC-2 ≤ 5th percentile (Early: Se 36 %, Sp 82 %; Term: Se 28 %, Sp 93 %) and predicted CP with high Se and Sp (Early: Se 78 %, Sp 78 %; Term: Se 75 %, Sp 89 %).

CONCLUSION

High Sp of Early and Term MRI predicting an outcome on MABC-2 may help accurately identify infants unlikely to develop motor impairments at 6-years CA.

Diagnostic accuracy of the Hammersmith Neonatal Neurological Examination in predicting motor outcome at 12 months for infants born very preterm

AIM

To evaluate the predictive validity of the Hammersmith Neonatal Neurological Examination (HNNE) performed early (at 32 weeks postmenstrual age) and at term-equivalent age (TEA) for 12-month motor outcomes in infants born very preterm.

METHOD

This was a diagnostic study using data from a prospective birth cohort. A total of 104 infants born preterm at less than 31 weeks gestational age (males n = 61; mean = 28 weeks 1 day [SD 1 week 6 days], range 23 weeks 1 day-30 weeks 6 days) underwent HNNE early and at TEA, which were scored by comparison with term data. Motor outcomes at 12 months corrected age were determined using the Bayley Scales of Infant and Toddler Development, Third Edition (scores ≤85). Cut-off points were determined using receiver operating characteristic curves.

RESULTS

Sixteen (15%) infants born preterm had motor impairment at 12 months corrected age. The HNNE total score cut-off points with the best combination of sensitivity and specificity at early and TEA assessments were 15.2 or lower (sensitivity 77%, 95% confidence interval [CI] = 46%-95%; specificity 74%, 95% CI = 63%-83%) and 23.5 or lower (sensitivity 67%, 95% CI = 38%-88%; specificity 66%, 95% CI = 54%-76%) respectively. The most predictive subscale at the early assessment was reflexes (sensitivity 86%, 95% CI = 57%-98%; specificity 62%, 95% CI = 51%-72%; cut-off point ≤3); at TEA, it was spontaneous movements (sensitivity 73%, 95% CI = 45%-92%; specificity 60%, 95% CI = 48%-70%; cut-off point ≤2).

INTERPRETATION

The HNNE provides moderate predictive accuracy for motor outcome at 12 months corrected age in infants born very preterm. Although modest at both time points, early assessment had stronger predictive ability for motor outcomes than TEA when scored using term data, highlighting the value of performing the HNNE earlier in the neonatal period. Performing HNNE earlier may assist risk stratification when planning follow-up services.

Early detection of developmental delay in infants born very preterm or with very low birthweight

AIM

This study aimed to identify early clinical biomarkers from birth to 16 weeks corrected age to predict typical outcome and developmental delay in infants born very preterm or with very low birthweight.

METHOD

A prospective cohort of infants on the Sunshine Coast, Australia, was assessed using the Premie-Neuro Examination, the General Movement Assessment (GMA), the Alberta Infant Motor Scale, and the Infant Sensory Profile 2. At 24 months corrected age, delay was identified using the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III) and Neurosensory Motor Developmental Assessment (NSMDA).

RESULTS

One hundred and four infants were recruited; 79 completed outcome assessments (43 females, 36 males; mean gestational age 30 weeks [SD 1 week 6 days], mean birthweight 1346 g [SD 323]). The incidence of developmental delay (motor or cognitive) was 6.3%. Suboptimal quality of fidgety general movements (temporal organization) at 16 weeks corrected age demonstrated the best predictive accuracy (Bayley-III motor: sensitivity 100% [95% confidence interval {CI} 3-100], specificity 75% [95% CI 63-84], area under the curve [AUC] 0.87); Bayley-III cognitive: sensitivity 100% [95% CI 3-100], specificity 75% [95% CI 64-84], AUC 0.88); NSMDA motor: sensitivity 100% [95% CI 40-100], specificity 81% [95% CI 70-90], AUC 0.91 [95% CI 0.86-0.95]). GMA trajectories that combined abnormal writhing general movements at 4 to 5 weeks corrected age with suboptimal quality of fidgety movement at 16 weeks corrected age were strongly predictive of developmental delay, superior to all other clinical tools, and perinatal and demographic variables investigated (p = 0.01, Akaike information criterion method 18.79 [score corrected for small sample size], accounting for 93% of the cumulative weight).

INTERPRETATION

Only the GMA had sufficient predictive validity to act as a biomarker for both conditions: typical outcome and developmental delay (motor or cognitive). GMA trajectories that assessed both writhing general movements at 4 to 5 weeks corrected age and quality of fidgety movement at 16 weeks corrected age predicted adverse neurodevelopmental outcome, accurately differentiating between infants with typical outcomes and those at increased risk for motor or cognitive delay.

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.

Neurological examination at 32-weeks postmenstrual age predicts 12-month cognitive outcomes in very preterm-born infants

BACKGROUND

To determine the diagnostic accuracy of Hammersmith Neonatal Neurological Examination (HNNE) at 30-32 weeks postmenstrual age (PMA, 'Early') and term equivalent age (TEA) in infants born <31 weeks PMA to predict cognitive outcomes at 12 months corrected age (CA).

METHODS

Prospective cohort study of 119 infants (73 males; median 28.4 weeks gestational age at birth) who underwent Early and TEA HNNE. At 12 months CA, 104 participants completed Bayley Scales of Infant and Toddler Development, 3rd Edition, (Bayley-III). Optimum cut-off points for each HNNE subscale were determined to establish diagnostic accuracy for predicting adverse cognitive outcomes on the Bayley-III Cognitive Composite Scale (≤85).

RESULTS

The best diagnostic accuracy for HNNE total score at 30-32 weeks PMA predicting cognitive impairment occurred at cut-off ≤16.7 (sensitivity (Se) = 71%, specificity (Sp) = 51%). The Abnormal Signs subscale demonstrated the best balance of sensitivity/specificity combination (Se = 71%, Sp = 71%; cut-off ≤1.5). For HNNE at TEA, the total score at cut-off ≤24.5 had Se = 71% and Sp = 47% for predicting cognitive impairment. The Tone Patterns subscale demonstrated the strongest diagnostic accuracy at TEA (Se = 71%, Sp = 63%; cut-off ≤3).

CONCLUSIONS

Early and TEA HNNE demonstrated moderate diagnostic accuracy for cognitive outcomes at 12-months CA in infants born <31 weeks gestational age.

CLINICAL TRIAL REGISTRATION

Australian New Zealand Clinical Trials Registry; Trial Registration Number: ACTRN12613000280707; web address of trial: http://www.ANZCTR.org.au/ACTRN12613000280707.aspx .

IMPACT

Early Hammersmith Neonatal Neurological Examination (HNNE) assessment at 30-32 weeks postmenstrual age has moderate diagnostic accuracy for cognitive outcomes at 12 months corrected age in infants born <31 weeks gestation. Early HNNE at 30-32 weeks has stronger predictive validity than HNNE at term equivalent age. Early HNNE may provide an early marker for risk-stratification to optimise the planning of post-discharge support and follow-up services for infants born preterm.

Early Motor Repertoire of Very Preterm Infants and Relationships with 2-Year Neurodevelopment

The Motor Optimality Score, revised (MOS-R) is an extension of the Prechtl General Movements Assessment. This study aims to determine the relationship between MOS-R and 2-year neurodevelopmental outcomes in a cohort of 169 infants born very preterm (<31 weeks’ gestational age), and to examine the predictive validity of the MOS-R at 3−4 months’ corrected age (CA) above perinatal variables associated with poor outcomes, including Prechtl fidgety movements. Development at 2 years’ CA was assessed using Bayley Scales of Infant and Toddler Development, Third edition (Bayley-III) (motor/cognitive impairment: Bayley-III ≤ 85) and Neurological, Sensory, Motor, Developmental Assessment (NSMDA) (neurosensory motor impairment: NSMDA ≥ 12). Cerebral palsy (CP) was classified at 2 years as definite or clinical. The MOS-R was related to 2-year outcomes: Bayley-III motor (BMOS-R = 1.24 95% confidence interval (0.78, 1.70)), cognitive (BMOS-R = 0.91 (0.48, 1.35)), NSMDA scores (BMOS-R = −0.34 (−0.42, −0.25)), definite CP (odds ratio [OR] 0.67 (0.53, 0.86)), clinical CP (OR 0.74 (0.66, 0.83)) for each 1-point increase in MOS-R. MOS-R ≤ 23 predicted motor (sensitivity 78% (60−91%); specificity 63% (54−72%)) and neurosensory motor impairment (sensitivity 86% (64−97%); specificity 59% (51−68%)). The MOS-R is strongly related to CP and motor and cognitive delay at 2 years and is a good predictor of motor and neurosensory motor impairment.

Predictors of long-term neurodevelopmental outcomes of children born extremely preterm

Children born extremely preterm (<28 weeks' gestation) are at high risk of a range of adverse neurodevelopmental outcomes in later childhood compared with their peers born at term, including cognitive, motor, and behavioral difficulties. These difficulties can be associated with poorer academic achievement and health outcomes at school age. In this review, we discuss several predictors in the newborn period of early childhood neurodevelopmental outcomes including perinatal risk factors, neuroimaging findings and neurobehavioral assessments, along with social and environmental influences for children born extremely preterm. Given the complexity of predicting long-term outcomes in children born extremely preterm, we recommend multi-disciplinary teams in clinical practice to assist in determining an individual child's risk for adverse long-term outcomes and need for referral to targeted intervention, based upon their risk.

Functional movement assessment with the Test of Infant Motor Performance

The purpose of this article is to review research on the Test of Infant Motor Performance, a functional assessment of movement capabilities with age standards for infants from 34 weeks postmenstrual age through 17 weeks post term (corrected age). The Test of Infant Motor Performance was normed on a U.S. population-based sample to support its use as a tool for diagnosing delayed motor development in early infancy. The test is one of the preferred methods for parents of babies in special care nurseries to learn about their infant's development. The test was used in a variety of clinical trials to document effects of early therapy and can be used as a short-term outcome measure for other interventions expected to impact functional motor performance.

Associations Between Malaria in Pregnancy and Neonatal Neurological Outcomes: Malaria in Pregnancy and Neonatal Neurological Outcomes

OBJECTIVE

To compare neurological functioning of neonates born to mothers with and without malaria in pregnancy.

METHODS

Pregnant women presenting at Korle Bu Teaching Hospital, Ghana were recruited into this prospective observational study. Malaria exposure was determined by clinically-documented antenatal malaria infection; parasitemia in maternal, placental, or umbilical cord blood; or placental histology. Neurological functioning was assessed using the Hammersmith Neonatal Neurological Examination within 48 hours of birth. Performance was classified as "optimal" or "suboptimal" by subdomain and overall.

RESULTS

Between 21^st November 2018 and 10^th February 2019, 211 term-born neonates, of whom 27 (13%) were exposed to malaria, were included. In the reflexes subdomain, exposed neonates tended to score lower (adjusted mean difference: -0.34, 95% CI: -0.70-0.03) with increased risk (adjusted risk ratio: 1.63, 95% CI: 1.09-2.44) of suboptimal performance compared to unexposed neonates. There were no significant between-group differences in scores or optimality classification for the remaining subdomains and overall.

CONCLUSION

Malaria-exposed neonates had similar neurological functioning relative to unexposed neonates, with differences confined to the reflexes subdomain, suggesting potential underlying neurological immaturity or injury. Further studies are needed to confirm these findings and determine the significance of malaria in pregnancy on long-term neurological outcomes.