Background
Acute appendicitis is the most common diagnosis considered in patients presenting to the emergency department with right lower quadrant pain. However, atypical presentations often lead to unnecessary surgeries and increased healthcare costs. This study aimed to improve diagnostic accuracy in acute appendicitis using a hybrid machine learning (ML) model.
Methods
A retrospective analysis was performed on 395 patients who underwent appendectomy for suspected acute appendicitis between 2020 and 2024 at Ankara University Faculty of Medicine, Department of General Surgery. Demographic, clinical, laboratory, and radiological variables were collected. ML algorithms including NaiveBayes, MultilayerPerceptron, IBk, AdaBoost, RandomForest, and a Hybrid Model combining NaiveBayes, AdaBoost, and RandomForest were applied. The dataset was evaluated using 10-fold cross-validation and repeated 1000 times. Accuracy, F-measure, Matthews Correlation Coefficient (MCC), ROC area, and Precision-Recall Curve (PRC) area were used as performance criteria.
Results
Among the 395 patients, 52.9% were male, with a mean age of 37.3±15.6 years. Histopathological examination confirmed acute appendicitis in 341 (86.3%) and negative appendectomy in 54 (13.7%) patients. The diagnostic accuracy of the Alvarado score at a cutoff of ≥6 was 79.0%. Among ML algorithms, the Hybrid Model achieved the best performance, with 92.9% accuracy, 93% F-measure, 70.4% MCC, 90.8% ROC area, and 93.4% PRC area. This model correctly predicted 95.6% of acute appendicitis cases and 75.9% of negative appendectomy cases.
Conclusion
The Hybrid ML model provides superior diagnostic accuracy compared to the Alvarado score in acute appendicitis. Integration of such models into clinical practice could reduce negative appendectomy rates and enhance patient management by enabling faster and more reliable diagnosis.

Keywords: acute appendicitis, diagnostic accuracy, hybrid model, machine learning, negative appendectomy

Akut Apandisit Tanýsýnda Tanýsal Doðruluðu Artýrmaya Yönelik Hibrit Makine Öðrenmesi Yaklaþýmý

Amaç
Akut apandisit, acil serviste sað alt kadran aðrýsý ile baþvuran hastalarda en sýk deðerlendirilen tanýdýr. Ancak atipik bulgular tanýsal güçlükler yaratmakta, gereksiz operasyonlara ve maliyet artýþýna yol açabilmektedir. Bu çalýþmanýn amacý, hibrit makine öðrenmesi (ML) modeli kullanýlarak akut apandisit tanýsýnda doðruluðun artýrýlmasýdýr.
Yöntem
2020–2024 yýllarý arasýnda Ankara Üniversitesi Týp Fakültesi Genel Cerrahi Anabilim Dalý’nda akut apandisit ön tanýsý ile opere edilen 395 hasta retrospektif olarak incelendi. Demografik, klinik, laboratuvar ve radyolojik veriler deðerlendirildi. NaiveBayes, MultilayerPerceptron, IBk, AdaBoost, RandomForest ve bu modellerin kombinasyonundan oluþturulan Hibrit Model uygulandý. Veriler 10-kat çapraz doðrulama ile analiz edildi. Doðruluk, F-measure, Matthews Korelasyon Katsayýsý (MCC), ROC ve PRC alaný performans kriteri olarak kullanýldý.
Bulgular
Çalýþmaya dahil edilen hastalarýn %52,9’u erkek olup ortalama yaþ 37,3±15,6 yýl idi. Histopatolojik incelemede 341 (%86,3) olgu akut apandisit, 54 (%13,7) olgu negatif apendektomi olarak raporlandý. Alvarado skoru ≥6 için tanýsal doðruluk %79,0 bulundu. ML algoritmalarý içinde en iyi sonuç Hibrit Model ile elde edildi. Bu model %92,9 doðruluk oraný, %93 F-measure, %70,4 MCC, %90,8 ROC ve %93,4 PRC alaný saðladý. Ayrýca, akut apandisitli olgularýn %95,6’sý ve negatif apendektomi grubunun %75,9’u doðru tahmin edildi.
Sonuç
Hibrit ML modeli, akut apandisit tanýsýnda Alvarado skoruna kýyasla daha yüksek doðruluk sunmaktadýr. Bu yaklaþýmýn klinik kullanýma entegrasyonu, negatif apendektomi oranlarýný azaltarak hasta yönetimini iyileþtirebilir.

Anahtar Kelimeler: akut apandisit, hibrit model, makine öðrenimi, negatif apendektomi, tanýsal doðruluk