⚡ Quick Summary
This systematic review evaluated the role of artificial intelligence (AI) in cancer care following diagnosis, analyzing 15 prospective studies. The findings indicate that most AI applications remain experimental, lacking clinical validation and real-world deployment.
🔍 Key Details
- 📊 Studies Reviewed: 15 articles from January 2013 to May 2023
- 🧩 Focus: AI applications in post-diagnostic cancer pathways
- ⚙️ Assessment Tools: Risk of Bias Assessment for RCTs and Non-randomised Studies
- 🏆 Key Findings: Majority of AI research remains experimental without clinical validation
🔑 Key Takeaways
- 📉 Clinical Readiness: Most AI applications lack prospective clinical validation.
- 💡 Efficacy-Outcome Gap: AI efficacy has not translated into beneficial clinical outcomes.
- 🔄 Research Standardization: There is a significant need for standardization in AI research.
- 🌐 Health System Interoperability: Current AI research faces challenges in compatibility with health systems.
- 🛠️ Implementation Analysis: Considerations for time, cost, and resources were largely absent.
- 🤝 Collaborative Research: Future studies should focus on multicollaborative AI implementation.
- ⚖️ Equity Considerations: Equity in AI applications was not adequately addressed in the studies.
📚 Background
The integration of artificial intelligence into healthcare has gained momentum, particularly in cancer care, due to an ageing population and workforce shortages. However, the effectiveness of AI in enhancing the quality, efficiency, and equity of cancer care beyond diagnostics remains uncertain. This systematic review aims to clarify the current state of AI applications in cancer pathways following diagnosis.
🗒️ Study
The systematic review involved a comprehensive search of PubMed and Web of Science databases, identifying 15 prospective studies published between January 2013 and May 2023. Each study was critically appraised using established quality assessment tools to evaluate the clinical evidence and feasibility of AI applications in real-world settings.
📈 Results
The review revealed that the majority of AI research in oncology remains in the experimental phase, with most studies failing to establish clinical validity. Furthermore, there was a notable gap between measured AI efficacy and actual clinical outcomes, highlighting the need for further validation and research standardization.
🌍 Impact and Implications
The findings of this review underscore the challenges faced in the deployment of AI in cancer care. Addressing the triad of low-level clinical evidence, the efficacy-outcome gap, and the lack of interoperability in research ecosystems is crucial. Future efforts should prioritize collaborative research that aligns with current standards and local health systems to enhance the integration of AI in cancer pathways.
🔮 Conclusion
This systematic review highlights the potential of AI in transforming cancer care, yet emphasizes the need for rigorous clinical validation and standardization. As we move forward, it is essential to focus on collaborative research efforts that can bridge the existing gaps and ensure that AI technologies are effectively integrated into clinical practice for improved patient outcomes.
💬 Your comments
What are your thoughts on the current state of AI in cancer care? Do you believe that future research can overcome the existing challenges? Let’s engage in a discussion! 💬 Share your insights in the comments below or connect with us on social media:
Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review.
Abstract
The role of artificial intelligence (AI) in cancer care has evolved in the face of ageing population, workforce shortages and technological advancement. Despite recent uptake in AI research and adoption, the extent to which it improves quality, efficiency and equity of care beyond cancer diagnostics is uncertain to date. Henceforth, the objective of our systematic review is to assess the clinical readiness and deployability of AI through evaluation of prospective studies of AI in cancer care following diagnosis. We undertook a systematic review to determine the types of AI involved and their respective outcomes. A PubMed and Web of Science search between 1 January 2013 and 1 May 2023 identified 15 articles detailing prospective evaluation of AI in postdiagnostic cancer pathway. We appraised all studies using Risk of Bias Assessment of Randomised Controlled Trials and Risk of Bias In Non-randomised Studies-of Interventions quality assessment tools, as well as implementational analysis concerning time, cost and resource, to ascertain the quality of clinical evidence and real-world feasibility of AI. The results revealed that the majority of AI oncological research remained experimental without prospective clinical validation or deployment. Most studies failed to establish clinical validity and to translate measured AI efficacy into beneficial clinical outcomes. AI research are limited by lack of research standardisation and health system interoperability. Furthermore, implementational analysis and equity considerations of AI were largely missing. To overcome the triad of low-level clinical evidence, efficacy-outcome gap and incompatible research ecosystem for AI, future work should focus on multicollaborative AI implementation research designed and conducted in accordance with up-to-date research standards and local health systems.
Author: [‘Macheka S’, ‘Ng PY’, ‘Ginsburg O’, ‘Hope A’, ‘Sullivan R’, ‘Aggarwal A’]
Journal: BMJ Oncol
Citation: Macheka S, et al. Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review. Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review. 2024; 3:e000255. doi: 10.1136/bmjonc-2023-000255