Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study
Abstract Background Short stature is a prevalent pediatric endocrine disorder for which early detection and prediction are pivotal for improving treatment outcomes. However, existing diagnostic criteria often lack the necessary sensitivity and specificity because of the complex etiology of the disor...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Endocrine Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12902-025-01936-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849309834488315904 |
|---|---|
| author | Jiani Liu Xin Zhang Wei Li Francis Manyori Bigambo Dandan Wang Xu Wang Beibei Teng |
| author_facet | Jiani Liu Xin Zhang Wei Li Francis Manyori Bigambo Dandan Wang Xu Wang Beibei Teng |
| author_sort | Jiani Liu |
| collection | DOAJ |
| description | Abstract Background Short stature is a prevalent pediatric endocrine disorder for which early detection and prediction are pivotal for improving treatment outcomes. However, existing diagnostic criteria often lack the necessary sensitivity and specificity because of the complex etiology of the disorder. Hence, this study aims to employ machine learning techniques to develop an interpretable predictive model for normal-variant short stature and to explore how growth environments influence its development. Methods We conducted a case‒control study including 100 patients with normal-variant short stature who were age-matched with 200 normal controls from the Endocrinology Department of Nanjing Children’s Hospital from April to September 2021. Parental surveys were conducted to gather information on the children involved. We assessed 33 readily accessible medical characteristics and utilized conditional logistic regression to explore how growth environments influence the onset of normal-variant short stature. Additionally, we evaluated the performance of the nine machine learning algorithms to determine the optimal model. The Shapley additive explanation (SHAP) method was subsequently employed to prioritize factor importance and refine the final model. Results In the multivariate logistic regression analysis, children’s weight (OR = 0.92, 95% CI: 0.86, 0.99), maternal height (OR = 0.79, 95% CI: 0.72, 0.87), paternal height (OR = 0.83, 95% CI: 0.75, 0.91), sufficient nighttime sleep duration (OR = 0.48, 95% CI: 0.26, 0.89), and outdoor activity time exceeding three hours (OR = 0.02, 95% CI: 0.00, 0.66) were identified as protective factors for normal-variant short stature. This study revealed that parental height, caregiver education, and children’s weight significantly influenced the prediction of normal-variant short stature risk, and both the random forest model and gradient boosting machine model exhibited the best discriminatory ability among the 9 machine learning models. Conclusions This study revealed a close correlation between environmental growth factors and the occurrence of normal-variant short stature, particularly anthropometric characteristics. The random forest model and gradient boosting machine model performed exceptionally well, demonstrating their potential for clinical applications. These findings provide theoretical support for clinical identification and preventive measures for short stature. |
| format | Article |
| id | doaj-art-e11d8103b03f4e7e9003074fe6b5fc00 |
| institution | Kabale University |
| issn | 1472-6823 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Endocrine Disorders |
| spelling | doaj-art-e11d8103b03f4e7e9003074fe6b5fc002025-08-20T03:53:57ZengBMCBMC Endocrine Disorders1472-68232025-05-0125111310.1186/s12902-025-01936-xExplainable predictive models of short stature and exploration of related environmental growth factors: a case-control studyJiani Liu0Xin Zhang1Wei Li2Francis Manyori Bigambo3Dandan Wang4Xu Wang5Beibei Teng6School of Public Health, Prince of Wales Hospital, The Chinese University of Hong KongDepartment of Pneumology, Children’s Hospital of Nanjing Medical UniversityClinical Medical Research Center, Children’s Hospital of Nanjing Medical UniversityClinical Medical Research Center, Children’s Hospital of Nanjing Medical UniversityDepartment of Endocrinology, Children’s Hospital of Nanjing Medical UniversityClinical Medical Research Center, Children’s Hospital of Nanjing Medical UniversityDepartment of pediatric , Nanjing Luhe People’s Hospital, Yangzhou UniversityAbstract Background Short stature is a prevalent pediatric endocrine disorder for which early detection and prediction are pivotal for improving treatment outcomes. However, existing diagnostic criteria often lack the necessary sensitivity and specificity because of the complex etiology of the disorder. Hence, this study aims to employ machine learning techniques to develop an interpretable predictive model for normal-variant short stature and to explore how growth environments influence its development. Methods We conducted a case‒control study including 100 patients with normal-variant short stature who were age-matched with 200 normal controls from the Endocrinology Department of Nanjing Children’s Hospital from April to September 2021. Parental surveys were conducted to gather information on the children involved. We assessed 33 readily accessible medical characteristics and utilized conditional logistic regression to explore how growth environments influence the onset of normal-variant short stature. Additionally, we evaluated the performance of the nine machine learning algorithms to determine the optimal model. The Shapley additive explanation (SHAP) method was subsequently employed to prioritize factor importance and refine the final model. Results In the multivariate logistic regression analysis, children’s weight (OR = 0.92, 95% CI: 0.86, 0.99), maternal height (OR = 0.79, 95% CI: 0.72, 0.87), paternal height (OR = 0.83, 95% CI: 0.75, 0.91), sufficient nighttime sleep duration (OR = 0.48, 95% CI: 0.26, 0.89), and outdoor activity time exceeding three hours (OR = 0.02, 95% CI: 0.00, 0.66) were identified as protective factors for normal-variant short stature. This study revealed that parental height, caregiver education, and children’s weight significantly influenced the prediction of normal-variant short stature risk, and both the random forest model and gradient boosting machine model exhibited the best discriminatory ability among the 9 machine learning models. Conclusions This study revealed a close correlation between environmental growth factors and the occurrence of normal-variant short stature, particularly anthropometric characteristics. The random forest model and gradient boosting machine model performed exceptionally well, demonstrating their potential for clinical applications. These findings provide theoretical support for clinical identification and preventive measures for short stature.https://doi.org/10.1186/s12902-025-01936-xShort statureMachine learningPredictive modelGrowth environmentSHAP |
| spellingShingle | Jiani Liu Xin Zhang Wei Li Francis Manyori Bigambo Dandan Wang Xu Wang Beibei Teng Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study BMC Endocrine Disorders Short stature Machine learning Predictive model Growth environment SHAP |
| title | Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study |
| title_full | Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study |
| title_fullStr | Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study |
| title_full_unstemmed | Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study |
| title_short | Explainable predictive models of short stature and exploration of related environmental growth factors: a case-control study |
| title_sort | explainable predictive models of short stature and exploration of related environmental growth factors a case control study |
| topic | Short stature Machine learning Predictive model Growth environment SHAP |
| url | https://doi.org/10.1186/s12902-025-01936-x |
| work_keys_str_mv | AT jianiliu explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT xinzhang explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT weili explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT francismanyoribigambo explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT dandanwang explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT xuwang explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy AT beibeiteng explainablepredictivemodelsofshortstatureandexplorationofrelatedenvironmentalgrowthfactorsacasecontrolstudy |