PP100 Improving The Assessment Of Effectiveness For Digital Applications Using The B Statistic: Using WtsWrng As A Case Study

Introduction The performance of diagnostic health technologies is usually assessed by comparing them with standard care using the kappa statistic. These comparisons are made based on comprehensive clinical information (e.g., anamnesis and complementary tests). However, not all digital applications (DAs) execute over complete information, which leads to work under non-uniform distribution values. Using statistic in this situation has serious methodological limitations. Kappa assumes that marginal values uniformly distributed highly weights discordant when calculating concordance, underestimates real effectiveness DAs (i.e., observed concordance). We aimed present application B WtsWrng, a symptom triage DA for individuals. Methods WtsWrng was used 382 patients at emergency department hospital. Diagnoses provided given 19 symptoms, were compared those logged hospital’s electronic records discharge. Observed concordance calculated contingency tables. statistics 12 most frequent diagnoses hospital Sensitivity specificity also calculated. Results Real fluctuated from 0.4 0.98 diagnoses, eight had greater than 0.8. results ranged -0.005 0.37 0.36 0.99 sensitivity 0.8 three respectively. Conclusions show closer assumptions fulfilled DA. Therefore, better suited assessing type technology. Analysis showed its close clinicians, arrived information. Moreover, high suggests it good tool determining appropriate use healthcare resources.