Intervenable Machine Learning Models for Pediatric Appendicitis

Intervenable Machine Learning Models for Pediatric Appendicitis

Dasani Ravikiran Babu1, Sumayya Fathima2, Harshini Gunda3, Akhil Reddy Gangula4,Manoj Kumar Vishwanathula 5, Sai Koushik Vennampalli6

1Electronics & communication  , Jyothishmathi institute of technology and science

2Electronics & communication  , Jyothishmathi institute of technology and science

3Electronics & communication  , Jyothishmathi institute of technology and science

4Electronics & communication  ,  Jyothishmathi institute of technology and science

5Electronics & communication  ,  Jyothishmathi institute of technology and science

6Electronics & communication  ,  Jyothishmathi institute of technology and science

ABSTRACT - Pediatric appendicitis is a common and critical condition requiring timely diagnosis and treatment.  Intervenable machine learning models offer valuable support in diagnosing such conditions by providing both transparency and actionable insights. Interpretable models help clinicians understand the reasoning behind predictions, fostering trust in their use during clinical decision-making. Intervenable models enable targeted decisions by highlighting key diagnostic factors and informing treatment strategies. Combining these qualities improves diagnostic accuracy, enhances patient care, and facilitates the effective integration of machine learning into pediatric healthcare. This approach supports data-informed practices while maintaining clinical relevance and accountability.

Keywords-Machine  learning, Interpretable models, Intervenable models, Clinical decision support, Predictive modeling, Pediatric healthcare