Abstract
A recent trend in medical research is to develop prediction models aiming to improve patient care and health outcomes. While statisticians and data scientists are well-trained in the methods and process of developing a prediction model, their role post-model-development is less clear. This paper covers the critical scientific reasoning step in the prediction pipeline after a model is developed. Working collaboratively with domain experts, statisticians and data scientists should critically evaluate models, carefully implement models into practice, and assess the model’s impact in real world settings. Constructs from implementation science are discussed in the context of prediction modeling. The paper focuses on clinical prediction models, but these ideas apply to other domains as well.
Highlights
A recent trend in medical research is to develop prediction models aiming to improve patient care and health outcomes
We focus on prediction modeling in an academic research setting
Of the paper, dissemination of prediction models will be discussed through an implementation science lens, as well as challenges that may arise with prediction model implementation
Summary
A recent trend in medical research is to develop prediction models aiming to improve patient care and health outcomes. Model development typically involves an interdisciplinary team of researchers, including domain experts in medicine and/or clinical practice, as well as statisticians or data scientists. Assuming all goes well with the development process, the prediction model is released into the wild, usually through a publication in a journal. This paper will address key steps that should be taken after a prediction model is developed, including critical evaluation of the data and model, and implementation of the model. The main process after model development includes critical evaluation, publication, external validation and calibration, implementation, and evaluation of impact. We focus on prediction modeling in an academic research setting This process may look different in industry, but critical evaluation and careful implementation into practice remain essential for the prediction model pipeline
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
