Abstract
Machine learning has emerged as a fundamental tool for numerous endeavors within health informatics, bioinformatics, and medicine. However, novices among biomedical researchers and IT developers frequently lack the requisite experience to effectively execute a machine learning project, thereby increasing the likelihood of adopting erroneous practices that may result in common pitfalls or overly optimistic predictions.
The paper presents an assessment of the significance of best practices in the implementation of R\&D projects supporting the medical diagnostic process. Based on the literature and authors' experiences, 27 good practices influencing three fundamental stages of project implementation were identified. The evaluation was based on the Analytic Hierarchy Process, which relies on subjective assessments from experts, whose credibility is expressed through the consensus of assessment.
Initially focusing on DevOps methodology, research integration, interdisciplinary information sharing were prioritized over automation. Furthermore, annotation tools and data / model quality control were identified as of significant importance.
Paper Type
Short Paper
DOI
10.62036/ISD.2024.18
Assessment Of the Relevance of Best Practices in The Development of Medical R&D Projects Based on Machine Learning
Machine learning has emerged as a fundamental tool for numerous endeavors within health informatics, bioinformatics, and medicine. However, novices among biomedical researchers and IT developers frequently lack the requisite experience to effectively execute a machine learning project, thereby increasing the likelihood of adopting erroneous practices that may result in common pitfalls or overly optimistic predictions.
The paper presents an assessment of the significance of best practices in the implementation of R\&D projects supporting the medical diagnostic process. Based on the literature and authors' experiences, 27 good practices influencing three fundamental stages of project implementation were identified. The evaluation was based on the Analytic Hierarchy Process, which relies on subjective assessments from experts, whose credibility is expressed through the consensus of assessment.
Initially focusing on DevOps methodology, research integration, interdisciplinary information sharing were prioritized over automation. Furthermore, annotation tools and data / model quality control were identified as of significant importance.
Recommended Citation
Cychnerski, J. & Dziubich, T. (2024). Assessment Of the Relevance of Best Practices in The Development of Medical R&D Projects Based on Machine Learning. In B. Marcinkowski, A. Przybylek, A. Jarzębowicz, N. Iivari, E. Insfran, M. Lang, H. Linger, & C. Schneider (Eds.), Harnessing Opportunities: Reshaping ISD in the post-COVID-19 and Generative AI Era (ISD2024 Proceedings). Gdańsk, Poland: University of Gdańsk. ISBN: 978-83-972632-0-8. https://doi.org/10.62036/ISD.2024.18