Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study
<b>Background</b>: Accurate diagnosis of acute appendicitis in children remains challenging due to variable presentations and limitations of existing clinical scoring systems. While machine learning (ML) offers a promising approach to enhance diagnostic precision, most prior studies have...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Children |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9067/12/7/937 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733293198540800 |
|---|---|
| author | Emrah Aydın Taha Eren Sarnıç İnan Utku Türkmen Narmina Khanmammadova Ufuk Ateş Mustafa Onur Öztan Tamer Sekmenli Necip Fazıl Aras Tülin Öztaş Ali Yalçınkaya Murat Özbek Deniz Gökçe Hatice Sonay Yalçın Cömert Osman Uzunlu Aliye Kandırıcı Nazile Ertürk Alev Süzen Fatih Akova Mehmet Paşaoğlu Egemen Eroğlu Gülnur Göllü Bahadır Ahmet Murat Çakmak Salim Bilici Ramazan Karabulut Mustafa İmamoğlu Haluk Sarıhan Süleyman Cüneyt Karakuş |
| author_facet | Emrah Aydın Taha Eren Sarnıç İnan Utku Türkmen Narmina Khanmammadova Ufuk Ateş Mustafa Onur Öztan Tamer Sekmenli Necip Fazıl Aras Tülin Öztaş Ali Yalçınkaya Murat Özbek Deniz Gökçe Hatice Sonay Yalçın Cömert Osman Uzunlu Aliye Kandırıcı Nazile Ertürk Alev Süzen Fatih Akova Mehmet Paşaoğlu Egemen Eroğlu Gülnur Göllü Bahadır Ahmet Murat Çakmak Salim Bilici Ramazan Karabulut Mustafa İmamoğlu Haluk Sarıhan Süleyman Cüneyt Karakuş |
| author_sort | Emrah Aydın |
| collection | DOAJ |
| description | <b>Background</b>: Accurate diagnosis of acute appendicitis in children remains challenging due to variable presentations and limitations of existing clinical scoring systems. While machine learning (ML) offers a promising approach to enhance diagnostic precision, most prior studies have been limited by small sample sizes, single-center data, or a lack of external validation. <b>Methods</b>: This prospective, multicenter study included 8586 pediatric patients to develop a machine learning-based diagnostic model using routinely available clinical and hematological parameters. A separate, prospectively collected external validation cohort of 3000 patients was used to assess model performance. The Random Forest algorithm was selected based on its superior performance during model comparison. Diagnostic accuracy, sensitivity, specificity, Area Under Curve (AUC), and calibration metrics were evaluated and compared with traditional scoring systems such as Pediatric Appendicitis Score (PAS), Alvarado, and Appendicitis Inflammatory Response Score (AIRS). <b>Results</b>: The ML model outperformed traditional clinical scores in both development and validation cohorts. In the external validation set, the Random Forest model achieved an AUC of 0.996, accuracy of 0.992, sensitivity of 0.998, and specificity of 0.993. Feature-importance analysis identified white blood cell count, red blood cell count, and mean platelet volume as key predictors. <b>Conclusions</b>: This large, prospectively validated study demonstrates that a machine learning-based scoring system using commonly accessible data can significantly improve the diagnosis of pediatric appendicitis. The model offers high accuracy and clinical interpretability and has the potential to reduce diagnostic delays and unnecessary imaging. |
| format | Article |
| id | doaj-art-a55cc186a12449da95a0491bcbb266ee |
| institution | DOAJ |
| issn | 2227-9067 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Children |
| spelling | doaj-art-a55cc186a12449da95a0491bcbb266ee2025-08-20T03:08:05ZengMDPI AGChildren2227-90672025-07-0112793710.3390/children12070937Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation StudyEmrah Aydın0Taha Eren Sarnıç1İnan Utku Türkmen2Narmina Khanmammadova3Ufuk Ateş4Mustafa Onur Öztan5Tamer Sekmenli6Necip Fazıl Aras7Tülin Öztaş8Ali Yalçınkaya9Murat Özbek10Deniz Gökçe11Hatice Sonay Yalçın Cömert12Osman Uzunlu13Aliye Kandırıcı14Nazile Ertürk15Alev Süzen16Fatih Akova17Mehmet Paşaoğlu18Egemen Eroğlu19Gülnur Göllü Bahadır20Ahmet Murat Çakmak21Salim Bilici22Ramazan Karabulut23Mustafa İmamoğlu24Haluk Sarıhan25Süleyman Cüneyt Karakuş26Department of Pediatric Surgery, Tekirdağ Namık Kemal University School of Medicine, Tekirdağ 59030, TurkeyCenter for Applied Data Science, TED University, Ankara 06420, TurkeyCenter for Applied Data Science, TED University, Ankara 06420, TurkeyDepartment of Pediatric Surgery, Tekirdağ Namık Kemal University School of Medicine, Tekirdağ 59030, TurkeyDepartment of Pediatric Surgery, Ankara University School of Medicine, Ankara 06100, TurkeyDepartment of Pediatric Surgery, İzmir Katip Çelebi University School of Medicine, İzmir 35620, TurkeyDepartment of Pediatric Surgery, Selçuk University School of Medicine, Konya 42130, TurkeyDepartment of Pediatric Surgery, Yozgat State Hospital, Yozgat 66100, TurkeyDepartment of Pediatric Surgery, Diyarbakır Gazi Yaşargil Training and Research Hospital, Diyarbakır 21090, TurkeyDepartment of Pediatric Surgery, Gazi University School of Medicine, Ankara 06500, TurkeyDepartment of Pediatric Surgery, Gazi University School of Medicine, Ankara 06500, TurkeyDepartment of Pediatric Surgery, Gazi University School of Medicine, Ankara 06500, TurkeyDepartment of Pediatric Surgery, Karadeniz Teknik University School of Medicine, Trabzon 61080, TurkeyDepartment of Pediatric Surgery, Pamukkale University School of Medicine, Denizli 20160, TurkeyDepartment of Pediatric Surgery, Okmeydanı Prof. Dr. Cemil Taşçıoğlu State Hospital, İstanbul 34384, TurkeyDepartment of Pediatric Surgery, Muğla Sıtkı Koçman University School of Medicine, Muğla 48000, TurkeyDepartment of Pediatric Surgery, Muğla Sıtkı Koçman University School of Medicine, Muğla 48000, TurkeyDepartment of Pediatric Surgery, Biruni University School of Medicine, İstanbul 34010, TurkeyDepartment of Pediatric Surgery, Biruni University School of Medicine, İstanbul 34010, TurkeyDepartment of Pediatric Surgery, Amerikan Hospital, İstanbul 34365, TurkeyDepartment of Pediatric Surgery, Ankara University School of Medicine, Ankara 06100, TurkeyDepartment of Pediatric Surgery, Ankara University School of Medicine, Ankara 06100, TurkeyDepartment of Pediatric Surgery, Diyarbakır Gazi Yaşargil Training and Research Hospital, Diyarbakır 21090, TurkeyDepartment of Pediatric Surgery, Gazi University School of Medicine, Ankara 06500, TurkeyDepartment of Pediatric Surgery, Karadeniz Teknik University School of Medicine, Trabzon 61080, TurkeyDepartment of Pediatric Surgery, Karadeniz Teknik University School of Medicine, Trabzon 61080, TurkeyDepartment of Pediatric Surgery, Muğla Sıtkı Koçman University School of Medicine, Muğla 48000, Turkey<b>Background</b>: Accurate diagnosis of acute appendicitis in children remains challenging due to variable presentations and limitations of existing clinical scoring systems. While machine learning (ML) offers a promising approach to enhance diagnostic precision, most prior studies have been limited by small sample sizes, single-center data, or a lack of external validation. <b>Methods</b>: This prospective, multicenter study included 8586 pediatric patients to develop a machine learning-based diagnostic model using routinely available clinical and hematological parameters. A separate, prospectively collected external validation cohort of 3000 patients was used to assess model performance. The Random Forest algorithm was selected based on its superior performance during model comparison. Diagnostic accuracy, sensitivity, specificity, Area Under Curve (AUC), and calibration metrics were evaluated and compared with traditional scoring systems such as Pediatric Appendicitis Score (PAS), Alvarado, and Appendicitis Inflammatory Response Score (AIRS). <b>Results</b>: The ML model outperformed traditional clinical scores in both development and validation cohorts. In the external validation set, the Random Forest model achieved an AUC of 0.996, accuracy of 0.992, sensitivity of 0.998, and specificity of 0.993. Feature-importance analysis identified white blood cell count, red blood cell count, and mean platelet volume as key predictors. <b>Conclusions</b>: This large, prospectively validated study demonstrates that a machine learning-based scoring system using commonly accessible data can significantly improve the diagnosis of pediatric appendicitis. The model offers high accuracy and clinical interpretability and has the potential to reduce diagnostic delays and unnecessary imaging.https://www.mdpi.com/2227-9067/12/7/937appendicitispediatricsmachine learningdiagnosisrandom forestclinical decision support |
| spellingShingle | Emrah Aydın Taha Eren Sarnıç İnan Utku Türkmen Narmina Khanmammadova Ufuk Ateş Mustafa Onur Öztan Tamer Sekmenli Necip Fazıl Aras Tülin Öztaş Ali Yalçınkaya Murat Özbek Deniz Gökçe Hatice Sonay Yalçın Cömert Osman Uzunlu Aliye Kandırıcı Nazile Ertürk Alev Süzen Fatih Akova Mehmet Paşaoğlu Egemen Eroğlu Gülnur Göllü Bahadır Ahmet Murat Çakmak Salim Bilici Ramazan Karabulut Mustafa İmamoğlu Haluk Sarıhan Süleyman Cüneyt Karakuş Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study Children appendicitis pediatrics machine learning diagnosis random forest clinical decision support |
| title | Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study |
| title_full | Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study |
| title_fullStr | Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study |
| title_full_unstemmed | Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study |
| title_short | Diagnostic Accuracy of a Machine Learning-Derived Appendicitis Score in Children: A Multicenter Validation Study |
| title_sort | diagnostic accuracy of a machine learning derived appendicitis score in children a multicenter validation study |
| topic | appendicitis pediatrics machine learning diagnosis random forest clinical decision support |
| url | https://www.mdpi.com/2227-9067/12/7/937 |
| work_keys_str_mv | AT emrahaydın diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT tahaerensarnıc diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT inanutkuturkmen diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT narminakhanmammadova diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT ufukates diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT mustafaonuroztan diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT tamersekmenli diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT necipfazılaras diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT tulinoztas diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT aliyalcınkaya diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT muratozbek diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT denizgokce diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT haticesonayyalcıncomert diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT osmanuzunlu diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT aliyekandırıcı diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT nazileerturk diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT alevsuzen diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT fatihakova diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT mehmetpasaoglu diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT egemeneroglu diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT gulnurgollubahadır diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT ahmetmuratcakmak diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT salimbilici diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT ramazankarabulut diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT mustafaimamoglu diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT haluksarıhan diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy AT suleymancuneytkarakus diagnosticaccuracyofamachinelearningderivedappendicitisscoreinchildrenamulticentervalidationstudy |