▸USE PILOTS: First, Triple Aim pilots should be established in which demonstration sites are required to compare population, individual, and stratified approaches; conduct opportunity analyses; and apply predictive risk and impact ability models.
▸REDUCE DATA LAGS: Second, the use of predictive modeling should be promoted by reducing lags in the availability of information from the Medicare limited data set as well as files available for specific uses, such as those for accountable care organizations. The Medicare limited data set lags by more than a year, and the specific-use files lag by several months. Since some factors recorded in routine data are
strongly predictive of an imminent Triple Fail event, reducing the time lag between the occurrence of such factors and their availability in the data improves the accuracy of the predictive model.
▸CONDUCT AN ETHICAL REVIEW: Third, there should be appropriate ethical reviews of both the design and implementation of predictive and impact ability models.
▸RECORD MORE EVENTS: Finally, the use of database indicators should be expanded to cover more potentially adverse events. For example, the Hospital Episode Statistics database in England records whether each admission was elective or not, thereby indicating whether the event was a likely Triple Fail event.
▸USE PILOTS: First, Triple Aim pilots should be established in which demonstration sites are required to compare population, individual, and stratified approaches; conduct opportunity analyses; and apply predictive risk and impact ability models.
▸REDUCE DATA LAGS: Second, the use of predictive modeling should be promoted by reducing lags in the availability of information from the Medicare limited data set as well as files available for specific uses, such as those for accountable care organizations. The Medicare limited data set lags by more than a year, and the specific-use files lag by several months. Since some factors recorded in routine data are
strongly predictive of an imminent Triple Fail event, reducing the time lag between the occurrence of such factors and their availability in the data improves the accuracy of the predictive model.
▸CONDUCT AN ETHICAL REVIEW: Third, there should be appropriate ethical reviews of both the design and implementation of predictive and impact ability models.
▸RECORD MORE EVENTS: Finally, the use of database indicators should be expanded to cover more potentially adverse events. For example, the Hospital Episode Statistics database in England records whether each admission was elective or not, thereby indicating whether the event was a likely Triple Fail event.
การแปล กรุณารอสักครู่..