An Artificial Intelligence-Based Tool for Data Analysis and Prognosis in Cancer Patients: Results from the Clarify...

Area of Science:

• Oncology
• Biomedical Informatics
• Artificial Intelligence

Background:

• Artificial intelligence (AI) has shown promise in addressing biomedical challenges, including cancer research.
• Despite AI's potential, impactful AI tools specifically for oncology remain limited.
• This study addresses the need for advanced AI solutions in cancer patient data analysis.

Purpose of the Study:

• To present an AI-based tool for analyzing cancer patient data.
• To assist clinicians in identifying factors linked to poor prognosis, relapse, and survival.
• To develop a prognostic model for patient risk stratification.

Main Methods:

• Utilized clinical data from 5,275 patients with non-small cell lung cancer, breast cancer, and non-Hodgkin lymphoma.
• Integrated data from wearable devices and quality of life questionnaires.
• Employed AI for data analysis, descriptive statistics, survival probability calculations, and prognostic model development.

Main Results:

• AI tool successfully analyzed integrated data from 5,275 cancer patients.
• Descriptive analyses characterized patient demographics and clinical profiles.
• A prognostic model was developed, successfully stratifying patients into low- and high-risk groups.

Conclusions:

• AI effectively reconstructed population risk profiles for cancer prediction.
• The AI-based prognostic model demonstrated clinical utility.
• Potential applications include enhanced risk stratification, early detection, and surveillance for cancer patients.