An update and further testing of a knowledge-based diagnostic clinical decision support system for musculoskeletal disorders of the shoulder for use in a primary care setting.

Abstract

A prototype diagnostic clinical decision support system (CDSS) was developed to assist primary care clinicians (general practitioners) in clinical decision making, aimed at reducing diagnostic errors. The prototype CDSS showed some promise with high levels of validity and reliability; however, issues regarding the underlying Bayesian belief network (BBN), small sample size and use of radiological imaging as a gold standard measure were highlighted that required further investigation before considering clinical testing. The prototype CDSS was reviewed and updated based on computer science literature and expert (orthopaedic consultant) opinion. The updated CDSS was tested by comparing its diagnostic outcome against the diagnosis of 93 case studies as determined by expert opinion combined with arthroscopy findings or radiological imaging. The updated CDSS showed significant high levels of sensitivity (91%), specificity (98%), positive likelihood ratio (53.12) and negative likelihood ratio (0.08) with a kappa value of 0.88 to a confidence level of 99% compared with expert diagnosis combined with arthroscopy findings or radiological imaging. The results suggest that the updated CDSS has addressed the issues highlighted from the initial research while maintaining high levels of validity and reliability. The updated CDSS is now ready for clinical testing.