Artificial Intelligence in Radiotherapy: A Philosophical Perspective

Abstract

The increasing uptake of machine learning solutions for segmentation and planning leaves no doubt that artificial intelligence (AI) will soon be providing input into a range of radiotherapy procedures. Although this promises to deliver increased speed and accuracy, the future role of AI in relation to radiotherapy should be thought through carefully. There is currently a gap between published developments and widespread adoption, which provides some space to prepare the workforce and to consider the implications on practice. It is rare to find philosophical input into a medical journal, but the advent of AI makes this perspective increasingly important. Philosophical insight can help explore the potential impact of AI, in particular, on human creativity and oversight. Without this perspective, we run the risk of focusing solely on the immediate logistical impact on patients and departments. This commentary identifies three key aspects of radiotherapy that the authors feel would suffer most under AI control: creativity, innovation, and patient safety, which all demand uniquely human attributes. The article also provides insight from a philosophical perspective with regard to human consciousness, ethics, and empathy. Philosophically we should, perhaps, retain ethical concerns about the widening role of AI in radiotherapy beyond simple quantitative interpretation and image processing. As developments continue, we have time to determine how our roles will evolve and to establish a framework for ensuring appropriate human input into patient care. Most importantly, we must start to embed a philosophical approach to adoption of AI technology from the outset if we are to prepare ourselves for the challenge that lies ahead.

Artificial intelligence technologies and compassion in healthcare: A systematic scoping review

“…This was the strongest theme of the literature and conveyed manifold concerns about AI ethics and regulation ( Zelmer et al, 2018 ; Abdullah et al, 2021 ); ethical design and use of AI technologies in healthcare contexts ( Sikstrom et al, 2022 ); concerns about data privacy, data biases and data collection ( Harris, 2021 ; Ostherr, 2022 ); as well as concerns about trust, care quality, and liability ( Davenport and Kalakota, 2019 ; Sanal et al, 2019 ). There is a strong anticipation perspective relating to concerns about role replacement ( Johnston, 2018 ; Blease et al, 2019 ; Bridge and Bridge, 2019 ; Powell, 2019 ; Blease et al, 2020 ; Doraiswamy et al, 2020 ; Alrassi et al, 2021 ) and which parts of healthcare practice, can and should be entrusted to AI technologies ( Loftus et al, 2020 ; Nadin, 2020 ). Concerns about role replacement discuss the enduring role of critical human attributes for safe and effective healthcare ( Joda et al, 2020 ; Irfan, 2021 ).…”

Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

“…Although AI solutions are best suited to situations in radiology where ground truths are clear, the concept of a ground truth in RT fields is disputable because RT is both a science and an art entailing clinical input and creativity [30]. More specifically, inter-physician variations are present even in contours delineated by boardcertified radiation oncologists from the same institution (e.g., variations in the nodal target volumes in our study; Additional file 1).…”

Radiation therapist perceptions on how artificial intelligence may affect their role and practice

“…Change is upon us, and adaptation is required, 6 RTs' who prepare for and accept this change may prosper, career-wise, whereas those that do not could limit the opportunities AI could provide. 29 Limitations Some limitations are apparent in this study, with the main one being the sample size. A confidence interval of 95% with a 9% margin of error was achieved with a sample size of 105.…”