CAT Boost-Driven Multi-Condition Risk Prediction for Newborns in Neonatal Intensive Care using Structured Clinical Data

A Sai Prasad 1, N Thanuja 2, K Uday Kumar3, G Mounika 4 , S Praveen 5
1 Senior Assistant Professor ,Computer Science and Engineering, Sanketika Vidya Parishad Engineering College,
Vishakhapatnam, Andhra Pradesh, India
2,3,4,5 B.Tech Final Semester, Bachelor of Technology, Computer Science and Engineering, Sanketika Vidya Parishad
Engineering College, Vishakhapatnam, Andhra Pradesh, India

Abstract - Early identification of health risks in newborns admitted to the Intensive Care Unit (ICU) is essential for enabling timely clinical intervention and improving survivaloutcomes. Traditional neonatal monitoring methods primarily  rely on fixed threshold-based evaluations and manual assessments, which often fail to capture complex relationships among multiple physiological and clinical parameters. To address these limitations, this study proposes a machinelearning–based framework for early risk detection in  newborns using structured data, including gestational age,anthropometric measurements, vital signs, feeding patterns, APGAR scores, and biochemical indicators. The proposed system utilizes a CATBoost-based multi-class classification  model to predict condition-specific risk levels associated with jaundice, cardiac, and respiratory complications. The model is well-suited for healthcare applications due to its efficient handling of categorical features and robustness againstoverfitting. Furthermore, the system is supported by a  modular architecture that integrates automated datapreprocessing, model training, and real-time inference through secure APIs. An interactive user interface enables visualization of risk predictions and clinical insights, therebyassisting healthcare professionals in making informed, data- driven decisions in critical care environments.