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
BackgroundGrowth 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 burden...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-11-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2024/1/e54641 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846151110436323328 |
|---|---|
| author | Kyungchul Song Taehoon Ko Hyun Wook Chae Jun Suk Oh Ho-Seong Kim Hyun Joo Shin Jeong-Ho Kim Ji-Hoon Na Chae Jung Park Beomseok Sohn |
| author_facet | Kyungchul Song Taehoon Ko Hyun Wook Chae Jun Suk Oh Ho-Seong Kim Hyun Joo Shin Jeong-Ho Kim Ji-Hoon Na Chae Jung Park Beomseok Sohn |
| author_sort | Kyungchul Song |
| collection | DOAJ |
| description |
BackgroundGrowth 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.
ObjectiveThis study aimed to develop a machine learning–based model using sella MRI–based radiomics and clinical parameters to diagnose GHD and ISS.
MethodsA 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.
ResultsThe 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.
ConclusionsOur 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. |
| format | Article |
| id | doaj-art-68f75e9d6da04e71a7d0b1796d083901 |
| institution | Kabale University |
| issn | 1438-8871 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj-art-68f75e9d6da04e71a7d0b1796d0839012024-11-27T21:00:34ZengJMIR PublicationsJournal of Medical Internet Research1438-88712024-11-0126e5464110.2196/54641Development 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 StudyKyungchul Songhttps://orcid.org/0000-0002-8497-5934Taehoon Kohttps://orcid.org/0000-0002-4045-0036Hyun Wook Chaehttps://orcid.org/0000-0001-5016-8539Jun Suk Ohhttps://orcid.org/0000-0002-5765-2347Ho-Seong Kimhttps://orcid.org/0000-0003-1135-099XHyun Joo Shinhttps://orcid.org/0000-0002-7462-2609Jeong-Ho Kimhttps://orcid.org/0000-0003-2479-0548Ji-Hoon Nahttps://orcid.org/0000-0002-3051-2010Chae Jung Parkhttps://orcid.org/0000-0002-5567-8658Beomseok Sohnhttps://orcid.org/0000-0002-6765-8056 BackgroundGrowth 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. ObjectiveThis study aimed to develop a machine learning–based model using sella MRI–based radiomics and clinical parameters to diagnose GHD and ISS. MethodsA 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. ResultsThe 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. ConclusionsOur 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.https://www.jmir.org/2024/1/e54641 |
| spellingShingle | Kyungchul Song Taehoon Ko Hyun Wook Chae Jun Suk Oh Ho-Seong Kim Hyun Joo Shin Jeong-Ho Kim Ji-Hoon Na Chae Jung Park Beomseok Sohn 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 Journal of Medical Internet Research |
| title | 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 |
| title_full | 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 |
| title_fullStr | 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 |
| title_full_unstemmed | 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 |
| title_short | 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 |
| title_sort | 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 |
| url | https://www.jmir.org/2024/1/e54641 |
| work_keys_str_mv | AT kyungchulsong developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT taehoonko developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT hyunwookchae developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT junsukoh developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT hoseongkim developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT hyunjooshin developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT jeonghokim developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT jihoonna developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT chaejungpark developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy AT beomseoksohn developmentandvalidationofapredictionmodelusingsellamagneticresonanceimagingbasedradiomicsandclinicalparametersforthediagnosisofgrowthhormonedeficiencyandidiopathicshortstaturecrosssectionalmulticenterstudy |