Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Optimising cancer imaging with AI and ML: what do healthcare professionals want? A User Experience (UX) study.
ABSTRACT
Background:
The need for increased clinical efficacy and efficiency has been the main force behind the development of Artificial Intelligence (AI) in medical imaging. The INCISIVE project is an EU-funded initiative that aims to revolutionize cancer imaging methods using AI technology. It seeks to address limitations in current imaging techniques by developing an AI-based toolbox that improves accuracy, specificity, sensitivity, interpretability, and cost-effectiveness. To ensure successful implementation of this new AI service, a study was conducted to understand the needs, challenges, and expectations of healthcare professionals (HCPs) regarding the proposed INCISIVE toolbox and any potential implementation barriers. By considering the perspective of end-users, INCISIVE aims to develop a solution that effectively meets their needs and drives adoption.
Objective:
To understand the needs, challenges, and expectations of healthcare professionals (HCPs) regarding the proposed INCISIVE toolbox and any potential implementation barriers.
Methods:
A mixed-method research study consisting of two phases was conducted. Phase one involved UX design workshops with users of the INCISIVE AI toolbox. Phase two involved a Delphi study conducted through a series of sequential questionnaires. To recruit participants, a purposive sampling strategy based on the knowledge of the project's consortium was employed. Sixteen HCPs from Serbia, Italy, Greece, Cyprus, Spain, and the UK participated in the UX design workshops and 12 completed the Delphi study. Descriptive statistics were performed using SPSS, enabling the calculation of mean rank scores of the lists generated by the Delphi study. The qualitative data collected via the UX design workshops was analysed using NVivo 12 software.
Results:
The workshops facilitated brainstorming and identification of the INCISIVE AI toolbox desired features and implementation barriers, while the Delphi study allowed for prioritisation of these features and implementation barriers based on end users' perspective. Key findings indicated that the INCISIVE AI toolbox could assist in areas such as misdiagnosis, overdiagnosis, delays in diagnosis, detection of minor lesions, decision-making in disagreement, treatment allocation, disease prognosis, prediction, treatment response prediction, and care integration throughout the patient journey. Several barriers to successful implementation were identified, including limited resources, lack of organizational and managerial support, and data entry variability. HCPs also had an explicit interest in AI explainability, desiring feature relevance explanations or a combination of feature relevance and visual explanations within the toolbox.
Conclusions:
The results provide a thorough examination of the INCISIVE AI toolbox's design elements as required by the end users and potential barriers to its implementation, thus guiding the design and implementation of the INCISIVE technology. The outcome offers information about the degree of AI explainability required of the INCISIVE AI toolbox across the 3 services (Initial Diagnosis, Disease Staging, Differentiation, and Characterization, and Treatment and Follow-up) indicated for the toolbox. Clinical Trial: Not Applicable
Citation
