Senior Vice President and Chief Information Officer, PeraHealth
A common, yet complicated occurrence during hospital stays is the patient transfer, where patients are moved between departments or to other facilities, or discharged. These transitions of care often occur at a critical point in the patient’s care journey, requiring strategic support from many players within a health system to ensure the transfer process does not negatively impact the patient. Unplanned patient transfers—particularly to and from the intensive care unit (ICU)—can lead to preventable, adverse health events, according to industry studies1. The choice to discharge a patient is also critical, and preventable hospital readmissions are another common issue health organizations face each day, at a time when rehospitalization rates (preventable and not) have hit a record high2. Patient transfers are made up of a number of complex organizational processes that are tied to quality of patient care and overall costs, and health systems place a high importance on ensuring these protocols run efficiently and smoothly.
With a wealth of patient health data available today and living in electronic health records (EHRs), health systems have an opportunity to improve these types of organizational processes by leveraging EHR data and clinical surveillance technology. Paired with clinical and predictive analytics, surveillance solutions can provide clinicians a real-time visual of changes in patient conditions that enable a “right patient, right bed” mentality—helping health systems streamline their transfer process and ultimately improve patient mortality, coding, length of stay, unplanned transfers, and readmission rates.
Thanks to technology innovation and adoption, health data is not only available at the point of care but also has the potential to provide great value and insight into a patient’s condition. While health data is often siloed and difficult to access and use without the right tools, the proper organization of that data transforms it into a usable and valuable form. Data—such as lab and vitals data found in the EHR, along with information from detailed nursing assessments—is collected by clinical surveillance technology and used to create early-warning systems that paint a complete picture of a patient’s health in real time.
Predictive models guiding decisions
Clinical surveillance solutions that utilize EHR data along with predictive analytics technology not only measure a patient’s current condition, but they can also help drive the delivery of more proactive care and help avoid adverse events. However, how they work is often a mystery. Analytics models are often referred to as a “black box,” where the outcomes and issues they help solve are well recognized and understood, but the way the models work are not. Better education around the information involved in data analytics models will help those who need them most better utilize them. It is important that clinicians understand the inputs into models, as well as the weights and influence of these inputs in order to have confidence in the solution. For example, a patient’s risk of death increases significantly when the patient stops eating in the hospital. And this risk is compounded by the deterioration of other inputs into the models. Understanding how the inputs individually impact a patient’s condition leads to a better appreciation of the model’s results.
With the insights gathered from surveillance tools and predictive models, clinicians are given the opportunity to intervene before their condition becomes emergent, thanks to early warning signs that alert them to a patient’s deterioration. This also enables clinicians to make more informed decisions around care—such as when to discharge a patient or when a transfer may be safest, based on his or her condition.
Right patient, right bed
Hospitals strive to get their patients in the right bed the first time they treat them. However, if subtle changes in a patient’s condition go undetected, a patient that seemed healthy one morning could end up in the ICU later that day. Surveillance tools empower clinicians with better bed management decision-making by providing a real-time visualization of patient condition.
For example, if a transfer request is made to move a patient out of the ICU but insights gathered from the surveillance technology indicate the patient’s condition is not improving or may actually be declining, the care team can opt to keep the patient in the ICU longer. More-informed transfer decisions help avoid unnecessarily moving the patient out of the ICU only to have them return. In addition to reducing unplanned transfers and readmissions, clinical surveillance technology helps ensure patients receive the right level of care, ultimately improving length of stay, risk of coding and ultimately, patient mortality.
Paired with readily available health data, surveillance technology makes it possible to improve patient care and health system processes, such as bed management and readmissions. Clinical surveillance technology coupled with the power of predictive tools arms clinicians with a real-time visualization of the patient condition that enables more informed decision-making related to hospital discharges, patient transfers and overall delivery of care. As a result, hospitals are learning to work smarter, not harder, using deeper insights from their own patient data and only stand to benefit further due to the promise of health technology advancements down the road.
References
