Current AI Studies in Oncology Nursing Lack Evidence of Ethics and Efficacy

For their scoping review, the researchers evaluated 28 published studies about AI in oncology nursing, half of which used a descriptive design. The majority involved hybrid AI methods (28.6%) or machine learning (25.0%), which were primarily used for risk identification and prediction (28.6%). Nearly half (46.4%) reported on the AI technologies’ developmental stages. 

Thirteen of the studies in the review involved AI systems for specific types of cancer: 10 for breast cancer and 1 each for ovarian, prostate, and gastric cancer. Although only two of the reviewed studies reported that oncology nurses were involved in the AI technology’s validation, the current researchers determined that 68,319 patients with cancer and 212 oncology nurses participated in the AI system across all studies. 

Few discussed any ethical considerations, the researchers noted (https://doi.org/10.1097/NCC.0000000000001254), and “there is a lack of evidence on the efficacy of these technologies in practice. More randomized controlled trials in real-life oncology nursing settings are still needed.” 

However, technology is evolving quickly, and AI could have a “potentially huge impact on oncology nursing. With the advancement of machine learning and deep learning in AI, remote and real-time symptom risk prediction can help oncology nurses better manage symptoms,” the researchers concluded (https://doi.org/10.1097/NCC.0000000000001254). 

Listen to the Oncology Nursing Podcast Episode 281: Nursing’s Role in AI in Health Care (https://www.ons.org/podcasts/episode-281-nursings-role-ai-health-care) to learn more about nursing’s contributions and opportunities to shape in AI in health care.