It is imperative to build clinician trust to reuse ever-growing amounts of rich clinical data. Utilising a proprietary, structured electronic health record, we address data quality by assessing the plausibility of chiropractors, physical therapists and osteopaths' data entry to help determine if the data is fit for use in predicting outcomes of work-related musculoskeletal disorders using machine learning. For most variables assessed, individual clinician data entry positively correlated to the clinician group's data entry, indicating data is fit for reuse. However, from the clinician's perspective, there were inconsistencies, which could lead to data mistrust. When assessing data quality in EHR studies, it is crucial to engage clinicians with their deep understanding of EHR use, as improvement suggestions could be made. Clinicians should be considered local knowledge experts.
Keywords: Data quality; electronic health records; machine learning.