Making prognostic algorithms useful in shared decision-making: Patients and clinicians’ requirements for the Predict:Breast Cancer interface

Abstract

ObjectivesTo develop a new interface for the widely used prognostic breast cancer tool: PREDICT. To facilitate shared decision-making around post-surgery breast cancer treatments. To derive insights into communicating the outputs of prognostic models to patients and their clinicians.MethodWe applied user-centred design principles in developing a new interface for PREDICT. The research involved online surveys, focus groups, meetings, and usability testing with patients, clinicians and the public.ResultsThe new interface has been launched and delivers around 30,000 sessions per month. We identified several principles that are useful when communicating the output of prognostic models, including multiple presentation formats, and contextualising statistics. A programme of future work based on patient and clinician feedback has been developed, including the provision of quantitative data on the adverse effects of adjuvant breast cancer treatments.ConclusionsFor prognostic algorithms to fulfil their potential to assist with shared decision-making they need carefully designed interfaces. User-centred design puts patients and clinicians needs at the forefront, allowing them to derive the maximum benefit from prognostic models.

Informing Patients With Esophagogastric Cancer About Treatment Outcomes by Using a Web-Based Tool and Training: Development and Evaluation Study

“…However, to date, no web-based prediction tool exists for use in clinical consultations targeted at patients with esophageal and gastric cancer [ 39 ]. Moreover, the probabilities of side effects and HRQoL related to the treatment options are not addressed in the current tools, although patients express information needs related to these outcomes [ 32 , 40 ]. Furthermore, several training programs are available to improve the communication skills of cancer care providers [ 41 , 42 ].…”

Clinical Impact of the Predict Prostate Risk Communication Tool in Men Newly Diagnosed with Nonmetastatic Prostate Cancer: A Multicentre Randomised Controlled Trial

“…The modelling and tool was designed to meet all American Joint Committee on Cancer (AJCC) criteria for model adoption, and has been demonstrated to outperform existing risk-models, with concordance indices in excess of 0.8 in a number of international datasets (6, 7). The interface was based on a design with extensive input from patients and quantitative testing in order to improve risk comprehension and support decision-making without being 'persuasive' to patients in a particular way (8). Previous work has demonstrated the tool impacts upon clinician perceptions and treatment recommendations (9).…”

Clinical impact of the Predict Prostate risk communication tool in men newly diagnosed with non-metastatic prostate cancer: a multi-centre randomised controlled trial

“…The modelling and tool was designed to meet all American Joint Committee on Cancer (AJCC) criteria for model adoption, and has been demonstrated to outperform existing risk-models, with concordance indices in excess of 0.8 in a number of international datasets (6, 7). The interface was based on a design with extensive input from patients and quantitative testing in order to improve risk comprehension and support decision-making without being ‘persuasive’ to patients in a particular way (8). Previous work has demonstrated the tool impacts upon clinician perceptions and treatment recommendations (9).…”