A prospective observational study of artificial intelligence based radiotherapy treatment planning for cervical, head and neck and prostate cancer.

50% of patients with cancer require radiotherapy during their disease course, however, only 10-40% of patients in low and middle-income countries (LMICs), have access to it. The current radiotherapy planning pathway is inefficient requiring several labor intensive processes and takes weeks to months to deliver in LMICs. This has contributed to long waiting times for treatment resulting in cancer progression, increased morbidity, and inferior survival outcomes. In addition, errors at each stage of radiotherapy planning can directly impact on patient outcomes in terms of survival and both short- and long-term toxicities.  As well as a shortage of equipment, severe shortfalls in the specialized workforce needed to deliver radiotherapy has been identified as the most significant barrier to expanding radiotherapy capacity in LMICs.

The proposed study aims to test a novel Artificial intelligence (AI) based software which can automate two components of the radiotherapy planning pathway, 1. Outlining of anatomical areas that are at risk of tumor spread and at risk of radiation damage. 2. Definition of the position, size, and shape of the radiation beams. It has the potential to reduce the clinician time needed to outline treatment structures (from hours to minutes), reduce variation between clinicians in delineation (improve quality of plans), and support better use of human resources.  We propose a 48-month prospective study to evaluate the quality and economic benefit of AI based automated radiotherapy treatment planning for cervical cancer and head and neck cancers, which are common in LMICs, and for which radiotherapy is the main curative treatment.  The study will recruit 706 patients across six public sector cancer hospitals in India (n=2), Jordan (n=1), Malaysia (n=1), and South Africa (n=2) to ensure we include a broad range of patients, and the representativeness of the findings will support implementation of the software in LMICs. Patient partners have informed the scope, objectives, and design of the study, and will have an active role in the entire life cycle of the study including study conduct, and co-design of the planned results dissemination and public engagement activities.

If the study objectives are met, the AI based software will be offered as a not-for-profit web service to public sector state hospitals in LMICs to support rapid implementation in daily practice, and expansion of high-quality radiotherapy in these regions. This will improve access, and affordability of this key treatment option and directly addresses Rising Tide’s mission to establish innovative approaches to improve survival and the quality of life of patients with cancer globally.