Machine learning identifies girls with central precocious puberty based on multisource data

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.

Diagnostic model based on multiple factors for girls with central precocious puberty

OBJECTIVES

The GnRH stimulation test has been used as the gold standard for the diagnosis of central precocious puberty (CPP), but it has some practical barriers. This study intends to build a diagnostic model of CPP in girls based on the population in northern China.

METHODS

A total of 163 girls with precocious puberty (PP) were included from December 2018 to December 2019. Multifactor logistic regression analysis was conducted. Based on the results of multivariate logistic regression analysis, a nomogram was established for clinical application.

RESULTS

A multi logistic regression model showed that LH (OR=1.238, 95 % CI: 1.067-1.436, p=0.005), inhibin B (OR=1.066, 95 % CI: 1.032-1.100, p<0.001), bone age (OR=1.563, 95 % CI: 1.037-2.358, p=0.033), and uterine length (OR=1.180, 95 % CI: 1.034-1.348, p=0.014) were diagnostic factors for CPP. The prediction model AUC was 0.906 (95 % CI: 0.852-0.959, p<0.001).

CONCLUSIONS

We successfully developed a nomogram model for CPP patients based on clinical data. The diagnostic prediction model included four indicators: basal LH, inhibin B, bone age, and uterine body length.

[Value of basal luteinizing hormone level combined with uterine volume measurement in the early diagnosis of central precocious puberty in girls with different Tanner stages]

OBJECTIVES

To study the value of basal luteinizing hormone (LH) level combined with uterine volume measurement in the early diagnosis of central precocious puberty (CPP) in girls with different Tanner stages.

METHODS

A retrospective analysis was performed on the girls who presented with breast development before the age of 8 years and attended the Third Affiliated Hospital of Zhengzhou University from January 2017 to September 2022. According to the results of gonadotropin-releasing hormone (GnRH) agonist test, the girls with peak LH ≥5.0 IU/L and peak LH/follicle stimulating hormone ≥0.6 were enrolled as the positive group, and the other girls were enrolled as the negative group. The two groups were compared in terms of the basal LH level and uterine volume. The receiver operating characteristic (ROC) curve was used to analyze their value in the early diagnosis of CPP.

RESULTS

For the girls with Tanner B2 and B3 stages, the positive group had significantly higher basal LH level and uterine volume than the negative group (P<0.05). The basal LH level had an optimal cut-off value of 0.325 IU/L and 0.505 IU/L respectively in the diagnosis of Tanner stage B2/B3 CPP, while uterine volume had an optimal cut-off value of 1.639 mL and 2.158 mL respectively. Basal LH level combined with uterine volume measurement had a significantly larger area under the ROC curve than uterine volume measurement alone (P<0.001), but with no significant difference compared with that of basal LH level measurement alone (P>0.05).

CONCLUSIONS

Basal LH level combined with uterine volume measurement is valuable in the early diagnosis of CPP in girls with different Tanner stages, which provides a basis and guiding significance for clinical diagnosis of CPP.

Development and Validation of Clinical Diagnostic Model for Girls with Central Precocious Puberty: Machine-learning Approaches

BACKGROUND

A brief gonadotropin-releasing hormone analogues (GnRHa) stimulation test which solely focused on LH 30-minute post-stimulation was considered to identify girls with central precocious puberty (CPP). However, it was tested using traditional statistical methods. With advanced computer science, we aimed to develop a machine learning-based diagnostic model that processed baseline CPP-related variables and a brief GnRHa stimulation test for CPP diagnosis.

METHODS

We recruited girls suspected of precocious puberty and underwent a GnRHa stimulation test at Children Hospital 2, Vietnam, and Cathay General Hospital, Taiwan. Clinical data, bone age measurement, and 30-min post-stimulation blood test were used to build up the predictive model. The candidate model was developed by different machine learning algorithms that were mainly evaluated by sensitivity, specificity, the area under the receiver operator characteristic curve (AUC), and F1-score in internal and external validation data to classify girls as CPP and non-CPP at different time-points (0-min, 30-min, 60-min, and 120-min post-stimulation).

RESULTS

Among the 614 girls diagnosed with PP, 524 (85.3%) had CPP. The random forest algorithm yielded the highest value of F1-score (0.976), specificity (0.893), positive predicted value (0.987), and relatively high value of AUC (0.972) that contributed to high probability to identify CPP. The performance metrics of the 30-min post-stimulation diagnostic model including sensitivity and specificity surpassed those of the 0-minute model (0-min) and were equivalent to those of the model obtained 60-min and 120-min post-stimulation. Hence, our machine learning-based model helps shorten the stimulation test to 30 minutes after GnRHa injection, in general, it requires 120 minutes for a completed GnRHa stimulation test.

CONCLUSIONS

We developed a diagnostic model based on clinical features and a single sample 30-minute post-stimulation to identify CPP in girls that can reduce distress for children caused by multiple blood samplings.

An overview of deep learning applications in precocious puberty and thyroid dysfunction

In the last decade, deep learning methods have garnered a great deal of attention in endocrinology research. In this article, we provide a summary of current deep learning applications in endocrine disorders caused by either precocious onset of adult hormone or abnormal amount of hormone production. To give access to the broader audience, we start with a gentle introduction to deep learning and its most commonly used architectures, and then we focus on the research trends of deep learning applications in thyroid dysfunction classification and precocious puberty diagnosis. We highlight the strengths and weaknesses of various approaches and discuss potential solutions to different challenges. We also go through the practical considerations useful for choosing (and building) the deep learning model, as well as for understanding the thought process behind different decisions made by these models. Finally, we give concluding remarks and future directions.

Explainable Dynamic Multimodal Variational Autoencoder for the Prediction of Patients with Suspected Central Precocious Puberty

Central precocious puberty (CPP) is the most common type of precocious puberty and has a significant effect on children. A gonadotropin-releasing hormone (GnRH)-stimulation test is the gold standard for confirming CPP. This test, however, is costly and unpleasant for patients. Therefore, it is critical to developing alternative methods for CPP diagnosis in order to alleviate patient suffering. This study aims to develop an artificial intelligence (AI) diagnostic system for predicting response to the GnRH-stimulation test using data from laboratory tests, electronic health records (EHRs), and pelvic ultrasonography and left-hand radiography reports. The challenges are in integrating these mul-timodal features into a comprehensive deep learning model in order to achieve an accurate diagnosis while also accounting for the missing or incomplete modalities. To begin, we developed a dynamic multimodal variational autoencoder (DMVAE) that can exploit intrinsic correlations between different modalities to im-pute features for missing modalities. Next, we combined features from all modalities to predict the outcome of a CPP diagnosis. The experimental results (AUROC 0.9086) demonstrate that our DMVAE model is superior to standard methods. Additionally, we showed that by setting appropriate operating thresholds, clinicians could diagnose about two-thirds of patients with confidence (1.0 specificity). Only about one-third of patients require confirmation of their diagnoses using GnRH (or GnRH analog)-stimulation tests. To interpret the results, we implemented an explainer Shapley additive explanation (SHAP) to analyze the local and global feature attributions.