Predicting Mesothelioma Using Artificial Intelligence: A Scoping Review of Common Models and Applications

Area of Science:

• Oncology
• Medical Informatics
• Data Science

Background:

• Mesothelioma is a serious lung cancer often caused by asbestos exposure.
• Early diagnosis is critical for improving patient survival rates.
• Artificial intelligence (AI) presents a promising avenue for enhancing mesothelioma diagnosis and staging.

Purpose of the Study:

• To review recent research on AI applications for mesothelioma prediction and management.
• To identify the most effective AI models and their applications in mesothelioma research.

Main Methods:

• A comprehensive literature search was conducted across PubMed, Scopus, and Web of Science databases until April 24, 2023.
• Nineteen relevant articles were selected after initial screening and duplicate removal.
• Data extraction and synthesis were performed using standardized forms and presented in figures and tables.

Main Results:

• AI applications in mesothelioma research primarily focus on tumor diagnosis and classification (73.69%).
• Other applications include prevention, prognosis (21.05%), and tumor volumetric measurement (5.26%).
• Prominent AI models like Support Vector Machines (SVM), Decision Trees (DT), and Random Forests (RF) demonstrated high accuracies (78.3%–99.97%).

Conclusions:

• AI, especially machine learning models (NN, DT, RF, SVM), shows significant potential in predicting and managing mesothelioma.
• These AI tools can enhance early detection and improve patient outcomes for mesothelioma.
• Further research into AI applications can refine diagnostic and prognostic capabilities for this disease.