From the Guidelines
The primary research gaps in the perception of AI use in oncology include the lack of understanding of clinician trust and acceptance, limited patient perspectives, and inadequate exploration of cultural and regional differences, as highlighted in recent studies 1. These gaps are significant because they impact the integration of AI into clinical workflows, affecting clinical outcomes and patient experiences. Some of the key areas that require further research include:
- Longitudinal studies examining how perceptions of AI evolve over time as technologies mature
- Investigation into how different stakeholders perceive AI's role and value in cancer care, particularly regarding potential biases in AI systems
- Examination of how communication about AI-assisted decisions affects doctor-patient relationships and patient confidence in treatment plans
- Research on the economic perception gap, including how healthcare professionals and institutions perceive the cost-benefit ratio of implementing AI systems in oncology practice As AI continues to influence cancer diagnosis, treatment planning, and prognostication, addressing these research gaps is crucial to ensure that AI is used effectively and efficiently in oncology practice, ultimately improving patient outcomes and experiences 1. The use of AI in oncology has the potential to improve clinical decision-making, but it is essential to address the existing research gaps to realize this potential fully, as noted in a recent study published in Frontiers of Medicine 1. By prioritizing research in these areas, we can work towards a better understanding of the perception of AI use in oncology and ultimately improve the quality of care for cancer patients. For instance, a study published in 2024 1 highlighted the importance of understanding the limitations of using heterogeneous data sets, biases in outcomes, and data privacy in the development of AI models for cancer research. Similarly, another study published in the same year 1 emphasized the need for further research on the application of AI methods in cancer diagnosis, treatment planning, and prognostication. Overall, addressing the research gaps in the perception of AI use in oncology is essential to ensure that AI is used effectively and efficiently in clinical practice, ultimately improving patient outcomes and experiences.
From the Research
Research Gaps in AI Use in Oncology
The current state of AI in oncology has several research gaps that need to be addressed. Some of the key gaps include:
- Lack of discussion on ethical challenges with the application of AI technologies in low- and middle-income countries 2
- Limited discussion on problems of bias in AI algorithms 2
- Insufficient justification for the use of AI technologies over traditional statistical methods to address specific research questions in oncology 2
- Need for standardized guidelines for the ethical integration of AI models in cancer care pathways and clinical operations 3
- Concerns about data diversity and data shift, model reliability and algorithm bias, legal oversight, and high information technology and infrastructure costs 3
Clinical Integration and Validation
While there have been significant advancements in AI applications in oncology, there is a need for further validation and clinical integration. For example:
- A mammography-based breast cancer risk model has been validated across diverse populations, demonstrating its potential for broad and equitable improvements in care 4
- However, more research is needed to address the challenges associated with the widespread adoption of AI in cancer care, including data diversity and model reliability 3
Future Directions
The future of AI in oncology holds much promise, with potential applications in: