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

Yilin Chen ¹ Xueqin Huang ² Lu Tian ^2*

• ¹ Chongqing Medical University, Chongqing, China
• ² Chongqing Key Laboratory of Pediatrics, Children‘s Hospital of Chongqing Medical University, Chongqing, China

Background: Central precocious puberty (CPP) is a common endocrine disorderin children, and its diagnosis primarily relies on the gonadotropin-releasinghormone (GnRH) stimulation test, which is expensive and time-consuming.With the widespread application of artificial intelligence in medicine, somestudies have utilized clinical, hormonal (laboratory) and imaging data-basedmachine learning (ML) models to identify CPP. However, the results of thesestudies varied widely and were challenging to directly compare, mainly due todiverse ML methods. Therefore, the diagnostic value of clinical, hormonal(laboratory) and imaging data-based ML models for CPP remains elusive. Theaim of this study was to investigate the diagnostic value of ML models based onclinical, hormonal (laboratory) and imaging data for CPP through a meta-analysisof existing studies.Methods: We conducted a comprehensive search for relevant English articles onclinical, hormonal (laboratory) and imaging data-based ML models for diagnosingCPP, covering the period from the database creation date to December 2023.Pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihoodratio (LR-), summary receiver operating characteristic (SROC) curve, and areaunder 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 ofheterogeneity was investigated through meta-regression analysis. Publicationbias was assessed using the Deeks funnel plot asymmetry test.Results: Six studies met the eligibility criteria. The pooled sensitivity andspecificity were 0.82 (95% confidence interval (CI) 0.62-0.93) and 0.85 (95% CI0.80-0.90), respectively. The LR+ was 6.00, and the LR- was 0.21, indicating thatclinical, hormonal (laboratory) and imaging data-based ML models exhibited anexcellent ability to confirm or exclude CPP. Additionally, the SROC curve showedthat the AUC of the clinical, hormonal (laboratory) and imaging data-based MLmodels in the diagnosis of CPP was 0.90 (95% CI 0.87-0.92), demonstrating gooddiagnostic value for CPP.Conclusion: Based on the outcomes of our meta-analysis, clinical and imagingdata-based ML models are excellent diagnostic tools with high sensitivity,specificity, and AUC in the diagnosis of CPP. Despite the geographicallimitations of the study findings, future research endeavors will strive toaddress these issues to enhance their applicability and reliability, providingmore precise guidance for the differentiation and treatment of CPP.