EHRs can ID inpatients at high risk of readmission

Electronic health records can help predict which inpatients are at high risk for readmission, and do so in real time, according to a new study in BMC Medical Informatics and Decision Making.

Hospital have increasingly been pressed to improve patient outcomes by reducing the readmission rates of discharged patients, but have not achieved as much success as has been hoped. Current claims-based models for predicting which patients may be at high risk of readmission can only be used at patient discharge and were limited to specific diseases or patient types.

The researchers, from the University of Texas Southwest Medical Center and elsewhere, sought to determine if EHR-based risk models could identify patients at high risk for readmission within 30 days of discharge, and how those models would compare to existing, claims-based models currently used to identify these high-risk patients.

The researchers created an EHR model and compared it to two claims based models, one of which is from the Centers for Medicare & Medicaid Services, and analyzed data on 39,604 inpatients admitted for internal medical services at seven large hospitals in the Dallas/Fort Worth area in 2009-2010.  

They found that the model performed better than the claims-based models, and could identify high-risk patients in real time shortly after admission, enabling clinicians to take responsive action sooner. The EHR model also doesn't require manual computation by staff; the information can be derived directly from the EHR. In addition, the model can be used for more generalized patient populations.

"Readmission to a hospital within 30 days can be a marker of poor quality of care, but efforts to reduce such events often involve intensive resource management applied to all patients, or interventions that are timed too late in the admission to support effective multi-disciplinary efforts," the authors said. "Methods that can identify those at the highest risk of adverse events and allow sufficient time to initiate and coordinate the concentration of scarce resources on those most likely to benefit have great potential for accomplishing the 'triple aim' of higher quality, more cost-conscious care for patients and populations."

EHRs continue to demonstrate their value in improving patient safety, identifying patients at high risk for a variety of problems and reducing errors.  Unfortunately, their use comes with its own set of problems that can increase the risk of patient harm, which is increasing as EHRs become more common.

To learn more:
- read the study (.pdf)

Suggested Articles

Roche, which already owned a 12.6% stake in Flatiron Health, has agreed to buy the health IT company for $1.9 billion.

Allscripts managed to acquire two EHR platforms for just $50 million by selling off a portion of McKesson's portfolio for as much as $235 million.

Artificial intelligence could help physicians predict a patient's risk of developing a deadly infection.