Automated attention flags in chronic disease care planning

Objectives: To assess the value of computerised decision support in the man agement of chronic respiratory disease by comparing agreement between three respiratory specialists, general practitioners (care coordinators), and de cision support software. Methods: Care guidelines for two chronic obstructive pulmonary disease proj ects of the SA HealthPlus Coordinated Care Trial were formulated. Decision support software, Care Plan On-Line (CPOL), was created to represent the in tent of these guidelines via automated attention flags to appear in patient s' electronic medical records. For a random sample of 20 patients with care plans, decisions about the use of nine additional services (eg, smoking ce ssation, pneumococcal vaccination) were compared between the respiratory sp ecialists, the patients' GPs and the CPOL attention flags. Results: Agreement among the specialists was at the lower end of moderate ( intraclass correlation coefficient [ICC], 0.48; 95% Cl, 0.39-0.56), with a 20% rate of contradictory decisions. Agreement with recommendations of spec ialists was moderate to poor for GPs (kappa, 0.49; 95% Cl, 0.33-0.66) and m oderate to good for CPOL (kappa, 0.72; 95% Cl, 0.55-0.90). CPOL agreement w ith GPs was moderate to poor (kappa, 0.41; 95% Cl, 0.24-0.58). GPs were les s likely than specialists or CPOL to decide in favour of an additional serv ice (P < 0.001). CPOL was 87% accurate as an indicator of specialist decisi ons. It gave a 16% false-positive rate according to specialist decisions, a nd flagged 61% of decisions where GPs said No and specialists said Yes. Conclusions: Automated decision support may provide GPs with improved acces s to the intent of guidelines; however, further investigation is required.