The Use and Effectiveness of an Online Diagnostic Support System for Blood Film Interpretation: Comparative Observational Study

• DOI: 10.2196/20815
• Publication Date: 2021-08-09T13:15:55Z
• Authors: Claire Hutchinson; Michelle Brereton; Julie Adams; Barbara De La Salle; Jon Sims; Keith Hyde; Richard Chasty; Rachel Brown; Karen Rees-Unwin; John Burthem
• Keywords: Original Paper; Computer applications to medicine. Medical informatics; R858-859.7; Online Systems; Morphology education; ResearchInstitutes_Networks_Beacons/mcrc; name=Manchester Cancer Research Centre; Decision support; 3. Good health; 03 medical and health sciences; 0302 clinical medicine; Surveys and Questionnaires; Diagnosis; Digital morphology; Humans; External quality assessment in hematology; Public aspects of medicine; RA1-1270; Blood cell morphology

Background The recognition and interpretation of abnormal blood cell morphology is often the first step in diagnosing underlying serious systemic illness or leukemia. Supporting staff who interpret film therefore essential for a safe laboratory service. This paper describes an open-access, web-based decision support tool, developed by authors to morphological diagnosis, arising from earlier studies identifying mechanisms error reporting. effectiveness this intervention was assessed using unique resource offered online digital Continuing Professional Development scheme (DM scheme) UK National External Quality Assessment Service Haematology, with more than 3000 registered users. allowed be tested within defined user group, each whom viewed interpreted identical films. Objective primary objective study test system supporting users identify features. secondary determine pattern frequency use different case types, how perceived terms their confidence decision-making. Methods comparative films evaluated either without support. Selected cases DM were rereleased as new but made available; comparison data sets To address objectives, used quantitative evaluation statistical comparisons identification features between two releases. objective, web analytical tools, while questionnaire assess perceptions system. Results Cases aid had significantly improved accuracy relevant (mean improvement 9.8%) those 11%). particularly significant higher complexity rarer diagnoses. Analysis website usage demonstrated high access pages 9298 case, range 2661-24,276). Users reported that increased feature (4.8/5) (4.3/5), both context training (4.6/5) also wider practice (4.4/5). Conclusions findings demonstrate directed improves educational films, potentially extending use.