AI-enhanced lung cancer prediction: a hybrid model's precision triumph
Cargando...
Archivos
Fecha
2025-09
Título de la revista
ISSN de la revista
Título del volumen
Editor
Institute of Electrical and Electronics Engineers Inc.
Resumen
Lung cancer is considered one of the most dangerous cancers, with a 5-year survival rate, ranking the disease among the top three deadliest cancers globally. Effectively combating lung cancer requires early detection for timely targeted interventions. However, ensuring early detection poses a major challenge, giving rise to innovative approaches. The emergence of artificial intelligence offers revolutionary solutions for predicting cancer. While marking a significant healthcare shift, the imperative to enhance artificial intelligence models remains a focus, particularly in precision medicine. This study introduces a hybrid deep learning model, incorporating Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory Networks (BiLSTM), designed for lung cancer detection from patients' medical notes. Comparative analysis with the MIMIC IV dataset reveals the model's superiority, achieving an MCC of 96.2% with an Accuracy of 98.1%, and outperforming LSTM and BioBERT with an MCC of 93.5%, an accuracy of 97.0% and MCC of 95.5 with an accuracy of 98.0% respectively. Another comprehensive comparison was conducted with state-of-the-art results using the Yelp Review Polarity dataset. Remarkably, our model significantly outperforms the compared models, showcasing its superior performance and potential impact in the field. This research signifies a significant stride toward precise and early lung cancer detection, emphasizing the ongoing necessity for Artificial Intelligence model refinement in precision medicine.
Palabras clave
CNN BiLSTM attention
Deep learning model
Lung cancer
Natural language processing
Text classification
Deep learning model
Lung cancer
Natural language processing
Text classification
Descripción
Materias
Cita
Kesiku, C. Y., & Garcia-Zapirain, B. (2025). AI-enhanced lung cancer prediction: a hybrid model’s precision triumph. IEEE Journal of Biomedical and Health Informatics, 29(9), 6287-6300. https://doi.org/10.1109/JBHI.2024.3447583