Plain-language summary
Artificial intelligence (AI) is an emerging powerful technology that differs from traditional computer programs in its ability to learn from its results and enhance performance, mimicking human intelligence; hence the name. AI is already an important part of most computer-based tasks in our daily lives. Everyday examples include internet search engines and products that provide face recognition or predict the outbreak of diseases.
Research interests in AI appear to be limited to, hence constricted by, available pre-existing information and datasets rather than addressing patients’ priorities and clinical needs. The National Institute for Health and Care Excellence in England noted that current medical technologies using AI lack robust research backing and NHS patient involvement.
While some AI-based products are currently in clinical use – for example, in identifying abnormal cells in cervical smears – AI remains largely in the research phase in gynaecology oncology. Researchers have reported good results of its performance in fields such as prediction of lymph node involvement in cervical, endometrial, and ovarian cancers – which are important for treatment planning, distinguishing benign from malignant pelvic masses – and cervical cancer screening in low and high-income countries. AI products have learning that is supervised and some AI modalities use technology which learns from itself
There are ethical concerns surrounding the use of AI in health care. Many of these concerns relate to the quality of data used in training AI systems, i.e data should be inclusive so that results can be applicable in the future irrespective of race, ethnicity, socio-economic background or place of residence. It is also not clear who should take responsibility for clinical recommendation made by AI systems: is it the doctor using it, the hospital employing the doctor, or the creators of the AI product. Concerns have also been raised regarding how the roll-out of AI might affect jobs for doctors, nurses and administration staff.
AI is expected to contribute to health care in many positive ways. This can be achieved with good scrutiny and appropriate legislations to protect patients’ health and privacy in addition to identifying important research and implementation areas through a collaborative partnership among investors, investigators, clinicians, and patients.
Version history
This is the first edition of this paper.
Please note that the Scientific Advisory Committee regularly assesses the need to update. Further information on this review is available on request.
Developer declaration of interests
Available upon request.