Fixing the leaky pipe: how to improve the uptake of patient reported outcomes-based prognostic and predictive models in cancer clinical practice

PURPOSE
This discussion paper outlines challenges and proposes solutions for successfully implementing prediction models that incorporate patient-reported outcomes (PROs) in cancer practice.
DESIGN
We organised a full day multidisciplinary meeting of people with expertise in cancer care delivery, PRO collection, PRO use in prediction modelling, computing, implementation and decision science. The discussions –presented here—focussed on identifying challenges to the development, implementation and use of prediction models incorporating PROs, and suggesting possible solutions.
RESULTS
Specific challenges and solutions were identified across three broad areas. 1) Understanding decision making and implementation: necessitating multidisciplinary collaboration in the early stages and throughout; early stakeholder engagement to define the decision problem and ensure acceptability of PROs in prediction; understanding patient/clinician interpretation of PRO predictions and uncertainty to optimise prediction impact; striving for model integration into existing electronic health records; and early regulatory alignment. 2) Recognising the limitations to PRO collection and their impact on prediction: incorporating validated, clinically important PROs to maximise model generalisability and clinical engagement; and minimising missing PRO data (resulting from both structural digital exclusion and time-varying factors) to avoid exacerbating existing inequalities. 3) Statistical and modelling challenges: incorporating statistical methods to address missing data; ensuring predictive modelling recognises complex causal relationships; and considering temporal and geographic re-calibration so model predictions reflect the relevant population.
CONCLUSION
Developing and implementing PRO-based predictive models in cancer care requires extensive multidisciplinary working from the earliest stages, recognition of implementation challenges due to PRO collection and model presentation and robust statistical methods to manage missing data, causality and calibration. Predictive models incorporating PROs should be viewed as complex interventions with their development and impact assessment carried out to reflect this.