Development and Validation of a Combined MRI Radiomics, Imaging and Clinical Parameter-Based Machine Learning Model for Identifying Idiopathic Central Precocious Puberty in Girls.

BACKGROUND: Idiopathic central precocious puberty (ICPP) impairs child development, without early intervention. The current reference standard, the gonadotropin-releasing hormone stimulation test, is invasive which may hinder diagnosis and intervention. PURPOSE: To develop a model for accurate diagnosis of ICPP, by integrating pituitary MRI, carpal bone age, gonadal ultrasound, and basic clinical data. STUDY TYPE: Retrospective. POPULATION: A total of 492 girls with PP (185 with ICPP and 307 peripheral precocious puberty [PPP]) were randomly divided by reference standard into training (75%) and internal validation (25%) data. Fifty-one subjects (16 with ICPP, 35 with PPP) provided by another hospital as external validation. FIELD STRENGTH/SEQUENCE: T1-weighted (spin echo [SE], fast SE, cube) and T2-weighted (fast SE-fat suppression) imaging at 3.0 T or 1.5 T. ASSESSMENT: Radiomics features were extracted from pituitary MRI after manual segmentation. Carpal bone age, ovarian, follicle and uterine volumes and endometrium presence were assessed from radiographs and gonadal ultrasound. Four machine learning methods were developed: a pituitary MRI radiomics model, an integrated image model (with pituitary MRI, gonadal ultrasound and bone age), a basic clinical model (with age and sex hormone data), and an integrated multimodal model combining all features. STATISTICAL TESTS: Intraclass correlation coefficients were used to assess consistency of segmentation. Receiver operating characteristic (ROC) curves and the Delong tests were used to assess and compare the diagnostic performance of models. P < 0.05 was considered statistically significant. RESULTS: The area under of the ROC curve (AUC) of the pituitary MRI radiomics model, integrated image model, basic clinical model, and integrated multimodal model in the training data was 0.668, 0.809, 0.792, and 0.860. The integrated multimodal model had higher diagnostic efficacy (AUC of 0.862 and 0.866 for internal and external validation). CONCLUSION: The integrated multimodal model may have potential as an alternative clinical approach to diagnose ICPP. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Growth hormone deficiency interferes with dynamic brain networks in short children.

PURPOSE: This study aimed to explore the disparities in dynamic brain networks between children with growth hormone deficiency (GHD) and idiopathic short stature (ISS, non-growth hormone deficiency). METHODS: This study enrolled 65 children with GHD and 60 sex- and age-matched children with ISS. Resting-state functional magnetic resonance imaging (rs-fMRI) was performed for all participants to obtain information on dynamic regional homogeneity (dReHo) and functional connectivity (FC) in dynamic (dFC) or static (sFC) state. The rs-fMRI metrics were subsequently compared between the GHD and ISS groups. RESULTS: Compared to the ISS group, the GHD group showed significant dynamic abnormalities in intra-networks of the central executive and cerebellar networks and in inter-networks of the central executive network to attentional, sensorimotor, and visual networks, as well as cerebellar network to default mode, sensorimotor, and visual networks. In addition, FC changes in the dynamic state were different from those in the static state. CONCLUSIONS: The abnormal dynamics in intra- and inter-networks involved in cognitive, emotional, and motor functions in children with GHD extend the knowledge on brain functional alterations in children with GHD as reflected by dynamic changes in macroscopic neural activity patterns. These findings may help explain how GHD leads to various behavioral and cognitive deficits in children with short stature.

Prediction of Early Mortality Among Children With Moderate or Severe Traumatic Brain Injury Based on a Nomogram Integrating Radiological and Inflammation-Based Biomarkers.

Inflammation-based scores have been increasingly used for prognosis prediction in neurological diseases. This study aimed to investigate the predictive value of inflammation-based scores combined with radiological characteristics in children with moderate or severe traumatic brain injury (MS-TBI). A total of 104 pediatric patients with MS-TBI were retrospectively enrolled and randomly divided into training and validation cohorts at a 7:3 ratio. Univariate and multivariate logistic regression analyses were performed to identify independent predictors of prognosis in pediatric patients with MS-TBI. A prognostic nomogram was constructed, and its predictive performance was validated in both the training and validation cohorts. Sex, admission platelet-to-lymphocyte ratio, and basal cistern status from initial CT findings were identified as independent prognostic predictors for children with MS-TBI in multivariate logistic analysis. Based on these findings, a nomogram was then developed and its concordance index values were 0.918 [95% confidence interval (CI): 0.837-0.999] in the training cohort and 0.86 (95% CI: 0.70-1.00) in the validation cohort, which significantly outperformed those of the Rotterdam, Marshall, and Helsinki CT scores. The proposed nomogram, based on routine complete blood count and initial CT scan findings, can contribute to individualized prognosis prediction and clinical decision-making in children with MS-TBI.

Early death prediction in children with traumatic brain injury using computed tomography scoring systems.

PURPOSE: Marshall and Rotterdam are the most commonly used CT scoring systems to predict the outcome following traumatic brain injury (TBI). Although several studies have compared the performance of the two scoring systems in adult patients, none of these studies has evaluated the performance of the two scoring systems in pediatric patients. This study aimed to determine the predictive value of the Marshall and Rotterdam scoring systems in pediatric patients with TBI. METHODS: This retrospective study included 105 children with admission GCS < 12, with a mean age of 6.2 (±3.5) years. Their initial CT and status at hospital discharge (dead or alive) were reviewed, and both the Marshall and Rotterdam scores were calculated. We examined whether each score was related to the early death of pediatric patients. RESULTS: The pediatric patients with higher Marshall and Rotterdam scores had a higher mortality rate. There was a good correlation between the Marshall and Rotterdam scoring systems (Spearman's rho = 0.618, significant at the 0.05 level). Both systems demonstrated a high degree of discrimination when predicting early mortality. The Marshall scoring system had reasonable discrimination (AUC 0.782), and the Rotterdam scoring system had good discrimination (AUC 0.729). Comparing the two CT scoring systems, the Marshall scoring system provided a better positive predictive value (90%) for early mortality than the Rotterdam scoring system (78%). CONCLUSIONS: Both the Marshall and Rotterdam scoring systems have good predictability for assessing mortality in pediatric patients with TBI. The performance of the Marshall scoring system was equal to or slightly better than that of the Rotterdam scoring system.