A target product profile for electronic clinical decision support algorithms combined with point-of-care diagnostic test results to support evidence-based decisions during patient consultations by health workers
ABSTRACTHealth workers in low-resource settings often lack the support and tools to follow evidence-based clinical recommendations for diagnosing, treating and managing sick patients. Digital technologies, by combining patient health information and point of care diagnostics with evidence-based clinical protocols, can help improve the quality of care, the rational use of resources (humans, diagnostics and medicines) and save patient lives. The development of a target product profile for electronic clinical decision support algorithms (CDSAs) aimed at guiding preventive or curative consultations, and that integrate diagnostic test results will help align developer and implementer processes and specifications with the needs of end-users, in terms of quality, safety, performance and operational functionality. To identify characteristics for a CDSA, experts from academia, research institutions, and industry as well as policy makers with expertise in diagnostic and CDSA development, and implementation in LMICs were convened. Experts discussed the critical characteristics of a draft TPP which was revised and finalised through a Delphi process to facilitate consensus building. Experts were in overwhelming agreement that, given that CDSAs provide patients’ management recommendations, the underlying clinical algorithms should be available in human readable format and evidence-based. Whenever possible, the algorithm output should take into account pre-test disease probabilities, diagnostic likelihood ratios of clinical or laboratory predictors and disease probability thresholds to test and to treat. Validation processes should at a minimum ensure the CDSA are implementing faithfully the evidence-based algorithm they are based on (internal validation through clinical association and analytical validation). Additionally, clinical validation, bringing practice evidence about the impact of the CDSA use on health outcomes, was recognized as a good to have. The CDSAs should be designed to fit within clinic workflows, connectivity challenges and high volume settings. Data collected through the tool should conform to local patient privacy regulations and international data standards.