Why continuous monitoring will challenge CIOs and their IT systems

Combining analysis with real-time data creates a powerful tool for prediction and clinical decision support, but IT executives face several significant barriers in implementing solutions.


The successful implementation of real-time patient safety initiatives have long been a goal of health system CIOs.

Unfortunately, parsing notifications from individual medical devices, reliance on physical spot checks of patients, and the lack of rules-based analytics to assess a patient’s current condition in real-time or identify signs of deterioration puts that achievement out of reach for many hospitals and health systems.

Opioid-induced respiratory depression (OIRD) resulting from inadequate patient monitoring, recently ranked fourth in the ECRI Institute’s Top 10 Health Technology Hazards for 2017, is a microcosm of the larger patient safety challenges facing healthcare organizations.

More than half of medication-related deaths and 20,000 incidences of respiratory depression-related interventions annually are attributed to the delivery of opioids in a care setting—and at a cost of approximately $2 billion per year to the U.S. healthcare system. According to the Joint Commission’s Sentinel Event database, 29 percent of adverse events are related to improper patient monitoring.

Continuous electronic monitoring (CEM) is the obvious best practice—and one recommended by the Joint Commission, the Anesthesia Patient Safety Foundation and other healthcare advocates and agencies. Although it is more often utilized in high-acuity settings, such as intensive care and med-surg units, ever-increasing emphasis on detecting potential adverse clinical events makes enterprise-wide CEM a tantalizing solution.

A January 2017 Gartner report, “The Role of the Alarms and Notifications Platform in the Real-Time Health System,” determined that as “a key enabler of the real-time health system, healthcare provider CIOs will need to familiarize themselves with the A&N [alarm and notification] platform value proposition.” The report also noted that, “A&N platforms are important to operational efficiency and critical to patient safety and care quality.”

However, CIOs considering adoption of this solution face a number of significant barriers, including:
  • Inadequate vendor-neutral device connectivity and the inability to send notifications and real-time patient data to mobile clinical communication devices.
  • The adoption of additional monitoring devices, such as pulse oximeters and capnographs, which bring with them an incredible number of false notifications—triggered by patient movement, suspect measurements or other non-actionable alerts—that increase the risk of alert fatigue.
  • Data filtering that lacks rules-based analytics for real-time prediction and clinical decision support.

More intelligent methods are required for detecting actionable conditions—analytics that extend beyond the mere setting of vital signs thresholds.

The ability to track patients throughout the hospital, continuously add new devices, and distribute real-time patient monitoring to centralized dashboards and mobile devices should be a major consideration for CIOs tasked with implementing real-time healthcare solutions. Challenges include the following.

Medical device integration. Most MDI solutions gather and filter data to support documentation in an EHR. However, to achieve real-time monitoring, a more clinically significant capability, MDI should be able to collect data at variable speeds to meet the requirements of various clinical operational settings. Because data will be used for real-time intervention, any delay in their delivery to the correct individuals can have deleterious effects. As such, it is vitally important to understand the implications of requirements on data delivery latency, response, and integrity.

Precision alarms. Optimization of the alarm limits on bedside devices and silencing of non-actionable alarms is a good first step but not enough to eliminate the risk of alarm fatigue, especially for clinicians away from the patient’s bedside receiving alarms and alerts on a mobile device. Only systems that can monitor all the real-time patient data in conjunction with the alarms coming from devices can provide precision alarms that identify clinically relevant trends, sustained conditions, reoccurrences and combinatorial indications that may indicate a degraded patient condition prior to the violation of any individual parameter alarm threshold.

Real-time analytics. In addition to driving improved patient safety related to alarms and alerts, settings and adjustments data from bedside devices can support real-time surveillance of adherence or deviation from evidence based care plans and best-practice protocols to enable better outcomes and reduced cost of care.

Integration. Even modest net-new IT implementations can be disruptive to clinical workflow and a significant cost burden. CIOs should assess platforms that are both scalable and interoperable with existing technology and hospital infrastructure.

Our team recently concluded a study (to be published in the Journal of Biomedical Instrumentation & Technology) in collaboration with an East Coast hospital to determine if selectively delayed notifications using adjustable, multi-variable thresholds, to identify clinically actionable events and significantly reducing the overall number of alarms without increasing risks to patients in a post-anesthesia care unit.

The study measured pulse (HR), oxygen saturation (SpO2), respiratory rate (RR), and end-tidal carbon dioxide (ETCO2) continuously and compared alarms received through the bedside monitoring device with remote alerts designed to trigger only after a selective delay. The goal was to reduce the total number of alarms without increasing risk to patients who have been diagnosed with or are at risk for obstructive sleep apnea (OSA).

Using only sustained alarms as the filter for notifications reduced alerts from 22,812 to 13,000, a number high enough to still risk alarm fatigue. However, passing multiple series of data through a multi-variable rules engine that monitored the values of HR, RR, SPO2 and ETCO2 in order to determine which alarms to send to the nurse-call phone system brought the number of respiratory depression alerts down to 209—a 99 percent reduction.

An important observation made during this study was that remote alarm communication was an important adjunct to in-room monitoring alarm annunciation. A key argument that is made for in-room annunciation in the case of conscious or waking sleep apnea patients is the room audible alert. Yet, in every observed case of OIRD, the in-room audible annunciation had no effect on waking or stirring the patients. Hence, the need for a remote monitoring capability to catch such instances is motivated more strongly to ensure patients do not slip through the cracks.

Beyond high-acuity areas, healthcare systems are creating a foundation for other real-time healthcare innovations, including clinical surveillance modules, medical device integration in an EHR and virtual ICUs.

Combining analysis with real-time data at the point of collection creates a powerful tool for prediction and clinical decision support. The ability to track patients throughout the hospital, continuously add new devices, and distribute real-time patient monitoring to centralized dashboards and mobile devices should be a major consideration for CIOs tasked with achieving real-time healthcare capabilities.

More for you

Loading data for hdm_tax_topic #better-outcomes...