# An auxiliary diagnostic model based on joint learning of brain and lung data

## TL;DR

This paper introduces a new AI model that improves diagnosis by combining brain and lung data to capture connections between diseases.

## Contribution

The novelty lies in a joint learning model that integrates multi-disease data to enhance diagnostic accuracy.

## Key findings

- The model trained on both brain and lung data outperforms single-disease models.
- Multi-disease joint learning captures latent pathological relationships between diseases.
- The approach provides more precise and comprehensive diagnostic support for clinicians.

## Abstract

Artificial intelligence has significantly improved diagnostic accuracy and efficiency in medical imaging-assisted diagnosis. However, existing systems often focus on a single disease, neglecting the pathological connections between diseases. To fully leverage multi-disease information, this paper proposes an auxiliary diagnostic model based on joint learning of brain and lung data (ADMBLD), aiming to enhance the comprehensiveness and accuracy of diagnoses through cross-disease correlation learning. The model integrates imaging data and clinical history of brain and lung diseases to identify potential correlations between different diseases. Experimental results show that the model trained on both brain and lung data outperforms those trained separately, validating the effectiveness of the multi-disease joint learning diagnostic model. This confirms that integrating multi-disease information captures latent pathological relationships, overcoming the limitations of single-disease models, thereby providing clinicians with more precise and comprehensive diagnostic support and demonstrating its potential in advancing intelligent diagnostic systems.