Using artificial intelligence to bring evidence-based medicine a step closer to making the individual difference

Area of Science:

• Oncology
• Medical Informatics
• Machine Learning

Background:

• Evidence-based medicine aims to integrate research findings with clinical expertise for patient care.
• A significant gap exists between population-based research evidence and the specific needs of individual patients.
• Current methodologies are insufficient to bridge this evidence-practice gap in real-world clinical settings.

Purpose of the Study:

• To propose and evaluate a machine learning-based approach for applying research evidence to individual oncology patients.
• To address the challenge of translating objective, population-based data into personalized patient care strategies.
• To compare the proposed k-nearest-neighbor method with existing strategies for bridging the evidence-practice gap.

Main Methods:

• Utilizing machine learning techniques, specifically the k-nearest neighbors algorithm.
• Developing a methodology to systematically link research evidence with individual patient characteristics.
• Analyzing existing proposals and comparing their benefits and challenges against the proposed approach.

Main Results:

• The k-nearest neighbors approach provides a framework for personalized evidence application in oncology.
• The study examines the feasibility and potential advantages of this machine learning-based strategy.
• Comparative analysis highlights the relative strengths and weaknesses of different methods for bridging the evidence-practice gap.

Conclusions:

• Machine learning offers a viable pathway to close the gap between evidence-based medicine and individual patient care in oncology.
• The k-nearest neighbors algorithm presents a specific, data-driven method for enhancing personalized cancer treatment.
• Further development and validation are needed to fully realize the potential of these approaches in clinical practice.