Distinct effects of prematurity on MRI metrics of brain functional connectivity, activity, and structure: Univariate and multivariate analyses

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.

Evaluation of deep gray matter for early brain development using quantitative susceptibility mapping

OBJECTIVES

To evaluate susceptibility values associated with iron accumulation in the deep gray matter during postnatal development and to compare magnetic susceptibility between patients with normal and delayed development.

METHODS

Patients with postmenstrual age (PMA) ≤ 1000 days underwent MR scans between August 2015 and April 2020 at our hospital. Quantitative susceptibility mapping (QSM) was performed, and magnetic susceptibility was measured using three-dimensional volumes of interest (VOIs) for the caudate nucleus (CN), globus pallidus (GP), putamen (PT), and ventrolateral thalamic nucleus (VL). Cross-sectional analysis was performed for 99 patients with normal development and 39 patients with delayed development. Longitudinal analysis was also performed to interpret changes over time in 13 patients with normal development. Correlations between magnetic susceptibility in VOIs and PMA or chronological age (CA) were assessed.

RESULTS

Susceptibility values for CN, GP, PT, and VL showed positive moderate correlations with both PMA (ρ = 0.45, 0.69, 0.62, and 0.33, respectively) and CA (ρ = 0.53, 0.69, 0.66, and 0.39, respectively). The slope of the correlation between susceptibility values and age was highest in the GP among the four gray matter areas. Susceptibility values for the CN, GP, PT, and VL were higher with normal development than with delayed development at early postnatal age, although a significant difference was only observed for the CN. Susceptibility values also increased with age in the longitudinal analysis.

CONCLUSIONS

Magnetic susceptibility values in deep gray matter increased with age ≤ 1000 days. The normal development group showed higher susceptibility values than the delayed development group at early postnatal age (PMA ≤ 285 days).

KEY POINTS

• Magnetic susceptibilities in deep gray matter nuclei increased with age (postmenstrual age ≤ 1000 days) in a large number of pediatric patients. • The normal development group showed higher susceptibility values than the delayed development group in the basal ganglia and ventrolateral thalamic nucleus at early postnatal age (PMA ≤ 285 days).

Predicting response to tVNS in patients with migraine using functional MRI: A voxels-based machine learning analysis

Background

Migraine is a common disorder, affecting many patients. However, for one thing, lacking objective biomarkers, misdiagnosis, and missed diagnosis happen occasionally. For another, though transcutaneous vagus nerve stimulation (tVNS) could alleviate migraine symptoms, the individual difference of tVNS efficacy in migraineurs hamper the clinical application of tVNS. Therefore, it is necessary to identify biomarkers to discriminate migraineurs as well as select patients suitable for tVNS treatment.

Methods

A total of 70 patients diagnosed with migraine without aura (MWoA) and 70 matched healthy controls were recruited to complete fMRI scanning. In study 1, the fractional amplitude of low-frequency fluctuation (fALFF) of each voxel was calculated, and the differences between healthy controls and MWoA were compared. Meaningful voxels were extracted as features for discriminating model construction by a support vector machine. The performance of the discriminating model was assessed by accuracy, sensitivity, and specificity. In addition, a mask of these significant brain regions was generated for further analysis. Then, in study 2, 33 of the 70 patients with MWoA in study 1 receiving real tVNS were included to construct the predicting model in the generated mask. Discriminative features of the discriminating model in study 1 were used to predict the reduction of attack frequency after a 4-week tVNS treatment by support vector regression. A correlation coefficient between predicted value and actual value of the reduction of migraine attack frequency was conducted in 33 patients to assess the performance of predicting model after tVNS treatment. We vislized the distribution of the predictive voxels as well as investigated the association between fALFF change (post-per treatment) of predict weight brain regions and clinical outcomes (frequency of migraine attack) in the real group.

Results

A biomarker containing 3,650 features was identified with an accuracy of 79.3%, sensitivity of 78.6%, and specificity of 80.0% (p < 0.002). The discriminative features were found in the trigeminal cervical complex/rostral ventromedial medulla (TCC/RVM), thalamus, medial prefrontal cortex (mPFC), and temporal gyrus. Then, 70 of 3,650 discriminative features were identified to predict the reduction of attack frequency after tVNS treatment with a correlation coefficient of 0.36 (p = 0.03). The 70 predictive features were involved in TCC/RVM, mPFC, temporal gyrus, middle cingulate cortex (MCC), and insula. The reduction of migraine attack frequency had a positive correlation with right TCC/RVM (r = 0.433, p = 0.021), left MCC (r = 0.451, p = 0.016), and bilateral mPFC (r = 0.416, p = 0.028), and negative with left insula (r = −0.473, p = 0.011) and right superior temporal gyrus/middle temporal gyrus (r = −0.684, p < 0.001), respectively.

Conclusions

By machine learning, the study proposed two potential biomarkers that could discriminate patients with MWoA and predict the efficacy of tVNS in reducing migraine attack frequency. The pivotal features were mainly located in the TCC/RVM, thalamus, mPFC, and temporal gyrus.

Distinct effects of prematurity on MRI metrics of brain functional connectivity, activity, and structure: Univariate and multivariate analyses

Premature birth affects the developmental trajectory of the brain during a period of intense maturation with possible lifelong consequences. To better understand the effect of prematurity on brain structure and function, we performed blood‐oxygen‐level dependent (BOLD) and anatomical magnetic resonance imaging (MRI) at 40 weeks of postmenstrual age on 88 newborns with variable gestational age (GA) at birth and no evident radiological alterations. We extracted measures of resting‐state functional connectivity and activity in a set of 90 cortical and subcortical brain regions through the evaluation of BOLD correlations between regions and of fractional amplitude of low‐frequency fluctuation (fALFF) within regions, respectively. Anatomical information was acquired through the assessment of regional volumes. We performed univariate analyses on each metric to examine the association with GA at birth, the spatial distribution of the effects, and the consistency across metrics. Moreover, a data‐driven multivariate analysis (i.e., Machine Learning) framework exploited the high dimensionality of the data to assess the sensitivity of each metric to the effect of premature birth. Prematurity was associated with bidirectional alterations of functional connectivity and regional volume and, to a lesser extent, of fALFF. Notably, the effects of prematurity on functional connectivity were spatially diffuse, mainly within cortical regions, whereas effects on regional volume and fALFF were more focal, involving subcortical structures. While the two analytical approaches delivered consistent results, the multivariate analysis was more sensitive in capturing the complex pattern of prematurity effects. Future studies might apply multivariate frameworks to identify premature infants at risk of a negative neurodevelopmental outcome.