Application of Deep Learning Models in Clinical Data Analysis for Lung Disease Diagnosis

Abstract

Lung disease recurrence remains a significant challenge in healthcare, requiring efficient predictive models to improve patient monitoring and treatment strategies. This study investigates the application of deep learning models on clinical data to diagnose lung disease recurrence and analyze seasonal patterns affecting patient conditions. The proposed framework integrates K-Nearest Neighbors (KNN) for classification and Recurrent Neural Networks (RNN) for time series prediction, focusing on examining recurrence patterns from patient registration data. The main objective of the study is to improve Improving diagnostic precision and computational efficiency by tackling existing challenges the challenges of data imbalance and seasonal variation. The results of the experiments indicate the effectiveness of the proposed approach, with accuracy metrics, model validation, and graphical visualizations presented to illustrate the performance of each model. These results highlight the potential of integrating KNN and RNN in accurately diagnosing lung diseases, providing insights for healthcare professionals in decision making.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint