Application of prediction levels to OR scheduling.

Many perioperative managers record operating room times (ORTs) and use average ORTs to facilitate scheduling of elective surgical procedures. A second statistic, the upper 95% prediction level (ie, 95% chance the next ORT will be less than the upper prediction level) can be calculated from previous ORTs and used in scheduling elective procedures. The author used eight elective surgical procedures to test a distribution-free method for calculating ORT upper prediction levels. Upper prediction levels can provide perioperative managers better knowledge than average ORTs to facilitate decision making during the scheduling of elective surgical procedures. This method can be used to find upper prediction levels for any desired measure of procedure duration (eg, surgeon, scheduled procedure-specific times).