Thought Leaders' Corner:
It’s no surprise that reducing hospital readmissions is a major priority in the goal of lowering overall national healthcare spending. One in five hospitalized Medicare patients are readmitted within 30 days, and more than half of U.S. hospitals will soon pay Medicare readmission penalties. In fiscal year 2016, penalties are estimated to reach $420 million across nearly 2,600 hospitals.
Although focused efforts and steep incentive programs have tried to offer solutions, readmission rates have dropped only 0.1 percent since 2007. So how do we change this? With predictive analytics.
By analyzing pertinent patient data that’s been predictive of a transfer in the past, home health clinicians can identify which patients are most at risk for transferring off census before their 60-day care episodes complete and which patients could most benefit from additional care episodes.
When this knowledge is organized in a relative patient risk ranking, clinicians can more easily make informed, unbiased decisions about next steps and appropriate interventions. For instance, clinicians could call risky patients, either manually or through an automated system, to further investigate a risky patient’s care needs and determine what should be changed or improved to remediate preventable rehospitalizations.
Predictive analytics can distill large amounts of valuable clinical data to provide clinicians with unbiased intelligence. These analytics can add an additional dimension of understanding that when combined with a care provider’s instinct, education and experience can positively impact patient care like never before. Medalogix Touch, my company’s readmission reduction predictive analytics solution, has helped home health providers reduce their relative rate of 30-day readmissions by more than 20 percent—or avoid more than 150 preventable transfers over a seven month period.
Chief Executive Officer