Pain assessment and management is a fundamental part of nursing care. Opioids are 1 of the interventions utilized to manage pain within the hospital setting and have a known adverse effect called opioid-induced sedation and respiratory depression (OSRD). The purpose of this quantitative study was to create a prediction model with the known risk factors present on admission, to determine how well they predict OSRD. This served as a first step in the creation of a risk screen tool, supported by the cognitive continuum theory, in understanding the judgment and decision-making process to provide safe care. The combination of factors that most accurately predicted the risk of OSRD in patients on admission to an acute care healthcare institution was determined through a retrospective case control analysis. Risk factors present on admission of a case group of 100 patients who had succumbed to OSRD after an opioid administration were matched and compared to a control group of 100 who did not. A binary logistic regression analysis was used to determine how well age, body mass index, obstructive sleep apnea, pulmonary disease, respiratory disease, renal failure, and no opioid use (i.e., being opioid na�ve) predicted OSRD. The presence of pulmonary disease, renal disease, cardiac disease, diabetes, and being opioid na�ve most accurately predicted OSRD. Although only pulmonary disease and renal disease were statistically significant, the final model included other factors that increase the odds of OSRD, which are encompassed in the proposed tool for future research. Through understanding the factors that predict OSRD, a screening tool was created that could save lives in hospital institutions and lead to positive social change by supporting clinical decision making and care.