Excerpt: “EHR audit files are generally used for data security and privacy management. However, since they provide automatic time stamped data, they can also track activity in the EHR and document EHR related transactions. That makes them a ‘valuable resource’ to understand how time is used, according to the study’s authors.
The researchers used data from 36,437 primary care encounters in 26 of Geisinger Health System’s primary care clinics. They found that an adult office visit took an average of 54.6 minutes. Of that, a patient spent 45% of that time waiting, either in the waiting room or the exam room without a nurse or physician. The average time with a nurse was 5 minutes; the average time with a doctor was 15.5 minutes. About 9 minutes was spent in preparation, checking out and similar activities. The researchers also found that the time spent with a patient varied somewhat. The total time was greater for older patients, those with higher-level visits, and those with specific diseases. Women had longer times waiting at clinicians. Not surprisingly, patients who checked in later than their scheduled appointment time spent less time in the waiting room and less time with clinicians.
‘The ability to study EHR audit data retrospectively makes this low-cost method of workflow analysis uniquely suited to evaluating the rapid changes in operations and health policy. The longitudinal data available in an organization’s audit files allow for the comparison of workflow, wait time, and provider face-time before and after a range of changes, from the expansion of clinic hours to changes in Medicare reimbursement,’ the authors write. They go on to say that more traditional workflow analysis requires a ‘prospective study design and advanced notice of pending policy changes in order to evaluate the impact of these changes.’ They add that as hospitals try to navigate health reform, those types of studies are ‘generally not feasible.’”
WBB Statement: Data-mining and process mining of EHR data can reveal variation in workflow that are not easily or cost-effectively discovered by traditional means. The insights from process mining have been used to target process improvements and provide operational support in near real-time. EHR logs have been used for machine learning in order to predict probable outcomes by creating decision trees that reflect how previous cases progressed. Decision trees can assist management in detecting cases that have begun to follow a path that has previously led to undesirable outcomes, and enable timely evidence-based intervention. WBB has used process mining of EHR logs to perform process discovery and quality improvement in Emergency Departments.
Source: Fierce Healthcare