Determination of Gender By Machine Learning Algorithms, Through Using Craniocervical Junction Parameters and Dimensions of the Cervical Spinal Canal

Gamze Taşkın Senol; İbrahim Kürtül; Abdullah Ray; Gülçin Ahmetoğlu; Yusuf Seçgin; Zülal Öner

Makale detayları

Determination of Gender By Machine Learning Algorithms, Through Using Craniocervical Junction Parameters and Dimensions of the Cervical Spinal Canal

Yazarlar:

Gamze Taşkın Senol | İbrahim Kürtül | Abdullah Ray | Gülçin Ahmetoğlu | Yusuf Seçgin | Zülal Öner

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Sağlık Kurumları Yönetimi

Dergi:

Osmangazi Tıp Dergisi Vol.45 Issue 5, pp.672-677

Belge Tipi:

Makale

Yayın Tarihi:

9/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001293342

pISSN:

1305-4953

Anahtar kelimeler:

Özet:

 Gender determination is the first step for biological identification. With the widespread use of machine learning algorithms MLA for diagnosis, the significance of applying them also in gender determination studies has become apparent. This study has therefore aimed at determining gender from the parameters obtained out of magnetic resonance images MRI of the cranio-cervical junction and cervical-spinal canal by using MLA. MRI of the craniocervical junction and cervical-spinal canal of 110 men and 110 women were included in this study. The 15 parameters were tested with Decision Tree DT, Random Forest RF, Logistic Regression LR, Linear Discriminant Analysis LDA, Quadratic Discriminant Analysis QDA algorithms. Accuracy Acc, Specificity Spe, Sensitivity Sen, F1 score F1, Matthews-correlation coefficient Mcc values were used as performance criteria. The Acc, Spe, Sen, F1, and Mcc were found to be 1.00 in the LR, LDA, QDA and RF algorithms. The ratios of the Acc, Spe, Sen, and F1 were 0.98, and of the Mcc was 0.96 in the DT algorithm. It was found that the ratio between the SHAP analyzer of the RF algorithm and the belt of the ratio between the arch of the atlas and the anterior-posterior distance of the dens R3 parameter had a higher contribution to the estimation of gender compared to other parameters. It was concluded that the LDA, QDA, LR, DT and RF algorithms applied to the parameters acquired from the MRI of the craniocervical junction and cervical-spinal canal, could determine the gender with very high accuracy.

 Gender determination is the first step for biological identification. With the widespread use of machine learning algorithms MLA for diagnosis, the significance of applying them also in gender determination studies has become apparent. This study has therefore aimed at determining gender from the parameters obtained out of magnetic resonance images MRI of the cranio-cervical junction and cervical-spinal canal by using MLA. MRI of the craniocervical junction and cervical-spinal canal of 110 men and 110 women were included in this study. The 15 parameters were tested with Decision Tree DT, Random Forest RF, Logistic Regression LR, Linear Discriminant Analysis LDA, Quadratic Discriminant Analysis QDA algorithms. Accuracy Acc, Specificity Spe, Sensitivity Sen, F1 score F1, Matthews-correlation coefficient Mcc values were used as performance criteria. The Acc, Spe, Sen, F1, and Mcc were found to be 1.00 in the LR, LDA, QDA and RF algorithms. The ratios of the Acc, Spe, Sen, and F1 were 0.98, and of the Mcc was 0.96 in the DT algorithm. It was found that the ratio between the SHAP analyzer of the RF algorithm and the belt of the ratio between the arch of the atlas and the anterior-posterior distance of the dens R3 parameter had a higher contribution to the estimation of gender compared to other parameters. It was concluded that the LDA, QDA, LR, DT and RF algorithms applied to the parameters acquired from the MRI of the craniocervical junction and cervical-spinal canal, could determine the gender with very high accuracy.

 Gender determination is the first step for biological identification. With the widespread use of machine learning algorithms MLA for diagnosis, the significance of applying them also in gender determination studies has become apparent. This study has therefore aimed at determining gender from the parameters obtained out of magnetic resonance images MRI of the cranio-cervical junction and cervical-spinal canal by using MLA. MRI of the craniocervical junction and cervical-spinal canal of 110 men and 110 women were included in this study. The 15 parameters were tested with Decision Tree DT, Random Forest RF, Logistic Regression LR, Linear Discriminant Analysis LDA, Quadratic Discriminant Analysis QDA algorithms. Accuracy Acc, Specificity Spe, Sensitivity Sen, F1 score F1, Matthews-correlation coefficient Mcc values were used as performance criteria. The Acc, Spe, Sen, F1, and Mcc were found to be 1.00 in the LR, LDA, QDA and RF algorithms. The ratios of the Acc, Spe, Sen, and F1 were 0.98, and of the Mcc was 0.96 in the DT algorithm. It was found that the ratio between the SHAP analyzer of the RF algorithm and the belt of the ratio between the arch of the atlas and the anterior-posterior distance of the dens R3 parameter had a higher contribution to the estimation of gender compared to other parameters. It was concluded that the LDA, QDA, LR, DT and RF algorithms applied to the parameters acquired from the MRI of the craniocervical junction and cervical-spinal canal, could determine the gender with very high accuracy.

 Cinsiyet belirleme, biyolojik tanımlama için ilk adımdır. Makine öğrenmesi algoritmalarının MLA teşhis için yaygın olarak kullanılmasıyla birlikte, cinsiyet belirleme çalışmalarında da uygulanmasının önemi ortaya çıkmıştır. Bu nedenle bu çalışmada, MLA kullanılarak kranio-servikal bileşke ve servikal-spinal kanalın manyetik rezonans görüntülerinden MRG elde edilen parametrelerden cinsiyetin belirlenmesi amaçlanmıştır. Bu çalışmaya 110 erkek ve 110 kadının kraniyoservikal bileşke ve servikal-spinal kanal MR görüntüleri dahil edildi. 15 parametre Karar Ağacı DT, Rastgele Orman RF, Lojistik Regresyon LR, Doğrusal Diskriminant Analizi LDA, Kuadratik Diskriminant Analizi QDA algoritmaları ile test edilmiştir. Performans kriterleri olarak Doğruluk Acc, Özgüllük Spe, Duyarlılık Sen, F1 skoru F1, Matthews-korelasyon katsayısı Mcc değerleri kullanılmıştır. Sonuçlar: Acc, Spe, Sen, F1 ve Mcc değerleri LR, LDA, QDA ve RF algoritmalarında 1.00 olarak bulunmuştur. DT algoritmasında Acc, Spe, Sen ve F1 oranları 0.98, Mcc oranı ise 0.96 olarak bulunmuştur. RF algoritmasının SHAP analizörü ile atlasın kavisi ile densin ön-arka mesafesi arasındaki oranın kemeri R3 parametresinin cinsiyet tahminine katkısının diğer parametrelere kıyasla daha yüksek olduğu bulunmuştur. Kraniyoservikal bileşke ve servikal-spinal kanal MRGsinden elde edilen parametrelere uygulanan LDA, QDA, LR, DT ve RF algoritmalarının cinsiyeti çok yüksek doğrulukla belirleyebildiği sonucuna varılmıştır.

Makale detayları

Determination of Gender By Machine Learning Algorithms, Through Using Craniocervical Junction Parameters and Dimensions of the Cervical Spinal Canal

Yazarlar:

Gamze Taşkın Senol | İbrahim Kürtül | Abdullah Ray | Gülçin Ahmetoğlu | Yusuf Seçgin | Zülal Öner

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Sağlık Kurumları Yönetimi

Dergi:

Osmangazi Tıp Dergisi Vol.45 Issue 5, pp.672-677

Belge Tipi:

Makale

Yayın Tarihi:

9/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001293342

pISSN:

1305-4953

Craniocervical Junction

Cervical Spinal Canal

Magnetic Resonance Imaging

Sex Determination

Machine Learning Algorithmskraniyoservikal bileşke

servikal spinal kanal

manyetik rezonanans görüntüleme

cinsiyet tayini

makine öğrenim algoritması

Sayı

Makale detayları

Yazarlar: Gamze Taşkın Senol | İbrahim Kürtül | Abdullah Ray | Gülçin Ahmetoğlu | Yusuf Seçgin | Zülal Öner

Yayıncı: Eskişehir Osmangazi University

Ana Başlıklar: Sağlık Kurumları Yönetimi

Dergi: Osmangazi Tıp Dergisi Vol.45 Issue 5, pp.672-677

Belge Tipi: Makale

Yayın Tarihi: 9/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001293342

pISSN: 1305-4953

Sayı

Yazarlar:

Gamze Taşkın Senol | İbrahim Kürtül | Abdullah Ray | Gülçin Ahmetoğlu | Yusuf Seçgin | Zülal Öner

Yayıncı:

Eskişehir Osmangazi University

Ana Başlıklar:

Sağlık Kurumları Yönetimi

Dergi:

Osmangazi Tıp Dergisi Vol.45 Issue 5, pp.672-677

Belge Tipi:

Makale

Yayın Tarihi:

9/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001293342

pISSN:

1305-4953