Predictive analytics of complex healthcare systems using deep learning based disease diagnosis model

Area of Science:

• Medical imaging analysis
• Computational biology
• Artificial intelligence in healthcare

Background:

• Lung and colon cancer (LCC) are leading causes of mortality, necessitating accurate and timely diagnosis.
• Histopathological diagnoses are crucial for LCC detection and patient treatment planning.
• Deep learning (DL) offers potential for rapid and cost-effective analysis of large patient datasets.

Purpose of the Study:

• To propose a novel DL-based method, PACHS-DLBDDM, for accurate detection and classification of LCC.
• To enhance early disease diagnosis, thereby reducing patient fatality rates.
• To leverage advanced AI techniques for complex healthcare system analytics.

Main Methods:

• Utilized Gabor Filtering (GF) for preprocessing medical images.
• Employed Faster SqueezeNet for feature vector generation.
• Applied a Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) for LCC classification.
• Optimized CNN-LSTM hyperparameters using the Chaotic Tunicate Swarm Algorithm (CTSA).

Main Results:

• The PACHS-DLBDDM model demonstrated superior performance in LCC detection and classification.
• Achieved a high accuracy of 99.54% on a medical image dataset.
• Outperformed other DL models in the conducted simulations.

Conclusions:

• The PACHS-DLBDDM method provides a highly accurate and efficient approach for LCC diagnosis.
• This DL-based model shows significant promise for improving cancer detection in clinical settings.
• Early and precise diagnosis through advanced AI can substantially improve patient outcomes.