The utilization of basal luteinizing hormone in combination with the basal luteinizing hormone and follicle-stimulating hormone ratio as a diagnostic tool for central precocious puberty in girls

Development and Validation of a Prediction Model Using Sella Magnetic Resonance Imaging-Based Radiomics and Clinical Parameters for the Diagnosis of Growth Hormone Deficiency and Idiopathic Short Stature: Cross-Sectional, Multicenter Study

BACKGROUND

Growth hormone deficiency (GHD) and idiopathic short stature (ISS) are the major etiologies of short stature in children. For the diagnosis of GHD and ISS, meticulous evaluations are required, including growth hormone provocation tests, which are invasive and burdensome for children. Additionally, sella magnetic resonance imaging (MRI) is necessary for assessing etiologies of GHD, which cannot evaluate hormonal secretion. Recently, radiomics has emerged as a revolutionary technique that uses mathematical algorithms to extract various features for the quantitative analysis of medical images.

OBJECTIVE

This study aimed to develop a machine learning-based model using sella MRI-based radiomics and clinical parameters to diagnose GHD and ISS.

METHODS

A total of 293 children with short stature who underwent sella MRI and growth hormone provocation tests were included in the training set, and 47 children who met the same inclusion criteria were enrolled in the test set from different hospitals for this study. A total of 186 radiomic features were extracted from the pituitary glands using a semiautomatic segmentation process for both the T2-weighted and contrast-enhanced T1-weighted image. The clinical parameters included auxological data, insulin-like growth factor-I, and bone age. The extreme gradient boosting algorithm was used to train the prediction models. Internal validation was conducted using 5-fold cross-validation on the training set, and external validation was conducted on the test set. Model performance was assessed by plotting the area under the receiver operating characteristic curve. The mean absolute Shapley values were computed to quantify the impact of each parameter.

RESULTS

The area under the receiver operating characteristic curves (95% CIs) of the clinical, radiomics, and combined models were 0.684 (0.590-0.778), 0.691 (0.620-0.762), and 0.830 (0.741-0.919), respectively, in the external validation. Among the clinical parameters, the major contributing factors to prediction were BMI SD score (SDS), chronological age-bone age, weight SDS, growth velocity, and insulin-like growth factor-I SDS in the clinical model. In the combined model, radiomic features including maximum probability from a T2-weighted image and run length nonuniformity normalized from a T2-weighted image added incremental value to the prediction (combined model vs clinical model, P=.03; combined model vs radiomics model, P=.02). The code for our model is available in a public repository on GitHub.

CONCLUSIONS

Our model combining both radiomics and clinical parameters can accurately predict GHD from ISS, which was also proven in the external validation. These findings highlight the potential of machine learning-based models using radiomics and clinical parameters for diagnosing GHD and ISS.

Diagnostic utility of the average peak LH levels measured during GnRH stimulation test

OBJECTIVES

Gonadotropin-releasing hormone (GnRH) test is the gold standard test to evaluate the hypothalamus-pituitary-gonadal (HPG) axis for the diagnosis of central precocious puberty (CPP). However, the diagnosis of cases with clinical features of CPP whilst have borderline peak luteinizing hormone (LH) remain challenges. We aimed to evaluate diagnostic performance of the average of LH levels measured during GnRH stimulation test.

METHODS

Cases with diagnosis of CPP and premature thelarche (PT) who had a GnRH stimulation test results were retrospectively reviewed. Anthropometric measurements (weight, height, and body mass index), age and sex-specific standard deviation scores, growth velocity, puberty stages, bone ages, serum FSH, LH, and estradiol levels were measured by electrochemiluminescence immunological method (ECLIA), and the GnRH stimulation test results, which performed by obtaining venous blood samples at basal, 20th, and 40th minutes for FSH and LH measurement, were recorded.

RESULTS

A total of 76 girls (38 CPP, 38 PT) were included. We detected an average peak LH cut-off value of 4.25 IU/L with 94.7 % sensitivity and 97.4 % specificity, a 97.3 % positive predictive value, and a 94.9 % negative predictive value in GnRH test to differentiate cases with CPP from PT.

CONCLUSIONS

This is the first study evaluating the diagnostic utility of the average of LH levels measured during GnRH stimulation test. We showed that the average of two LH measurements has a high diagnostic performance. Therefore, it can be used as a valid and reliable diagnostic tool for assessment of HPG axis activation, particularly for cases with a borderline peak LH level.

Screening for central precocious puberty by single basal Luteinizing Hormone levels

PURPOSE

To identify cut-off for basal LH levels and for pelvic ultrasound uterine and ovarian parameters indicating an Hypotalamic-Pituitary-Gonadal (HPG) axis activation as diagnostic of Central Precocious Puberty (CPP).

METHODS

248 girls referred for suspected precocious/early puberty who had undergone a GnRH stimulation test were enrolled and divided into three groups: Premature Idiopathic Thelarche (PIT), CPP, and Early Puberty (EA). For every patient basal serum Luteinising Hormone (LH) and Follicle Stimulating Hormone (FSH), basal LH/FSH ratio and pelvic ultrasonographic parameters were also collected. Through the use of Receiver Operating Curves (ROCs) the sensitivity (Se) and specificity (Sp) of basal LH, FSH, LH/FSH ratio and ultrasonographic parameters were evaluated at each level and Area Under the Curve (AUC) was measured.

RESULTS

Basal LH model ≥0.14 mIU/mL reached the highest predictability (90.6% and 78.2%, Se and Sp, respectively). Basal LH/FSH ratio ≥0.1 showed a sensitivity of 85.90% and a specificity of 78.14%, while basal FSH cut-off (≥2.36 mIU/mL) had the lowest predictability, with a less favourable sensitivity (71%) and specificity (70.5%). Cut-off point for uterine length as 35 mm, (83.5% and 42.9% of Se and Sp, respectively) was calculated. For ovarian volumes, ROC curves showed very low sensitivity and specificity.

CONCLUSION

A single basal LH measurement under the cut-off limit may be adequate to exclude an HPG axis activation as CPP.

Bioelectrical impedance parameters add incremental value to waist-to-hip ratio for prediction of metabolic dysfunction associated steatotic liver disease in youth with overweight and obesity

Introduction

Metabolic dysfunction-associated steatotic liver disease (MASLD) presents a growing health concern in pediatric populations due to its association with obesity and metabolic syndrome. Bioelectrical impedance analysis (BIA) offers a non-invasive and potentially effective alternative for identifying MASLD risk in youth with overweight or obesity. Therefore, this study aimed to assess the utility of BIA for screening for MASLD in the youth.

Method

This retrospective, cross-sectional study included 206 children and adolescents aged <20 years who were overweight and obese. The correlations between anthropometric measurements and BIA parameters and alanine aminotransferase (ALT) levels were assessed using Pearson's correlation analysis. Logistic regression analysis was performed to examine the associations between these parameters and ALT level elevation and MASLD score. Receiver operating characteristic (ROC) curves were generated to assess the predictive ability of the parameters for MASLD.

Results

Pearson's correlation analysis revealed that waist-to-hip ratio (WHR), percentage body fat (PBF), and BIA parameters combined with anthropometric measurements were correlated with ALT level. Logistic regression revealed that WHR, skeletal muscle mass/WHR, PBF-WHR, fat-free mass/WHR, and appendicular skeletal muscle mass/WHR were correlated with ALT level elevation after adjusting for age, sex, and puberty. WHR, PBF-WHR, and visceral fat area (VFA)-WHR were positively correlated with the MASLD score in the total population after adjusting for age, sex, and puberty. PBF-WHR and VFA-WHR were correlated with the MASLD score even in youth with a normal ALT level. The cutoff points and area under the ROC curves were 34.6 and 0.69 for PBF-WHR, respectively, and 86.6 and 0.79 for VFA-WHR, respectively.

Discussion

This study highlights the utility of combining BIA parameters and WHR in identifying the risk of MASLD in overweight and obese youth, even in those with a normal ALT level. BIA-based screening offers a less burdensome and more efficient alternative to conventional MASLD screening methods, facilitating early detection and intervention in youth at risk of MASLD.

Meta-analysis of machine learning models for the diagnosis of central precocious puberty based on clinical, hormonal (laboratory) and imaging data

Background

Central precocious puberty (CPP) is a common endocrine disorder in children, and its diagnosis primarily relies on the gonadotropin-releasing hormone (GnRH) stimulation test, which is expensive and time-consuming. With the widespread application of artificial intelligence in medicine, some studies have utilized clinical, hormonal (laboratory) and imaging data-based machine learning (ML) models to identify CPP. However, the results of these studies varied widely and were challenging to directly compare, mainly due to diverse ML methods. Therefore, the diagnostic value of clinical, hormonal (laboratory) and imaging data-based ML models for CPP remains elusive. The aim of this study was to investigate the diagnostic value of ML models based on clinical, hormonal (laboratory) and imaging data for CPP through a meta-analysis of existing studies.

Methods

We conducted a comprehensive search for relevant English articles on clinical, hormonal (laboratory) and imaging data-based ML models for diagnosing CPP, covering the period from the database creation date to December 2023. Pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), summary receiver operating characteristic (SROC) curve, and area under the curve (AUC) were calculated to assess the diagnostic value of clinical, hormonal (laboratory) and imaging data-based ML models for diagnosing CPP. The I2 test was employed to evaluate heterogeneity, and the source of heterogeneity was investigated through meta-regression analysis. Publication bias was assessed using the Deeks funnel plot asymmetry test.

Results

Six studies met the eligibility criteria. The pooled sensitivity and specificity were 0.82 (95% confidence interval (CI) 0.62-0.93) and 0.85 (95% CI 0.80-0.90), respectively. The LR+ was 6.00, and the LR- was 0.21, indicating that clinical, hormonal (laboratory) and imaging data-based ML models exhibited an excellent ability to confirm or exclude CPP. Additionally, the SROC curve showed that the AUC of the clinical, hormonal (laboratory) and imaging data-based ML models in the diagnosis of CPP was 0.90 (95% CI 0.87-0.92), demonstrating good diagnostic value for CPP.

Conclusion

Based on the outcomes of our meta-analysis, clinical and imaging data-based ML models are excellent diagnostic tools with high sensitivity, specificity, and AUC in the diagnosis of CPP. Despite the geographical limitations of the study findings, future research endeavors will strive to address these issues to enhance their applicability and reliability, providing more precise guidance for the differentiation and treatment of CPP.