Researchers at the Harvard Pilgrim Health Care Institute developed and validated a data-driven prediction model to accurately identify sound-alike/look-alike (SALA) medication pairs to prevent potential errors. To conduct the study, the team from Harvard Pilgrim evaluated 82 medication name similarities and seven product attribute measures with 40,000 samples of medication pairs. They then created a prediction model comprised of 13 of the strongest predictors for potential medication errors, such as having the same first letter in the medication names or coming from the same manufacturer. Mistakes from SALA medications contribute to as many as 250,000 hospitalizations each year.
Making Health Care Better
The Alliance of Community Health Plans is a national leadership organization bringing together innovative health plans and provider groups that are among America’s best at delivering affordable, high-quality coverage and care. Our plans are shaping the future of health care - driving better health outcomes, building healthier communities and inspiring an entire industry to do better.