Apply Streaming Analytics Technology to Improve Medical Care

In this first of our three-part blog series focusing on the application of streaming analytics to an industry problem, we cover use cases in the healthcare sector.

The emergence of real-time streaming analytics technology in the last decade has significantly improved medical analysis while reducing the workload on nurses and doctors. Using Internet of Things technologies and streaming analytics, leading healthcare providers are harnessing data streams to spot trends and patterns sooner. As a result, they are improving patient care and also lowering costs.

Streaming analytics enables healthcare providers to apply predictive analytics to data in motion for continuous decisions, allowing them to capture and analyze data—all the time, just in time. The end goal is to save lives, shorten hospital stays, and build healthier communities through preventive care.

Three ways streaming analytics helps save lives

  1. Fusing different data sources continuously: Medical devices provide visual displays of vital signs through physiological streams such as an electrocardiogram, heart rate, blood- oxygen saturation, and respiratory rate. Electronic health-record initiatives around the world create more sources of medical data. Life-threatening conditions such as nosocomial infection, pneumothorax, intraventricular hemorrhage, and periventricular leukomalacia can be detected using analytics that fuse different data sources.
  2. Highly personalized care: Detect signs earlier to improve patient outcomes and reduce the length of hospital stays. Automated or clinician-driven knowledge discovery helps identify new relationships between data-stream events and medical conditions.
  3. Proactive treatment: Build a profile for each patient based on personalized data streams and receive insights continuously.

Now let’s look at some real-time streaming analytics healthcare use cases.

Real-time ICU monitoring

The amount of data in a critical care setting has grown dramatically. Data generated from medical monitors, imaging technology, and electronic charting systems generate thousands of data points, leading to data overload for care providers. Patient monitors in Intensive Care Units today provide alarms whenever a vital measurement such as heart rate exceeds a predefined threshold. The care provider then must react quickly to make an instant decision about whether the alarm is false or if immediate action is required to prevent a crisis in the patient’s condition.

According to the Association for the Advancement of Medical Instrumentation (AAMI), between 85 percent and 99 percent of alarm signals do not require clinical intervention. Streaming analytics technology can mitigate the need for clinicians to operate in a constant state of urgency by enabling proactive management with real-time data.

Preventive care

Data streams are used by leading hospitals in many different areas—from neonatal for pediatric to adults for internal medicine and neurological applications. There’s plenty of data to explore, generated by sensors and other devices showing vital-sign trending data and clinical alarms, that can be accessed anywhere, anytime. Healthcare providers around the world are using data access, analytic algorithms, and visualization to detect illness earlier and reduce healthcare costs. A key to their success has been the ability to fuse different data sources in real time.

Diabetes management

Diabetes is one of the greatest global health threats. Today, 415 million adults worldwide have type I or type II diabetes, and that total is expected to grow to more than 600 million by 2040.

Individuals with diabetes take the brunt of it. They see their doctors for a few minutes every few months, so it’s largely up to them to manage their conditions—finding a balance between not having enough sugar in their blood and having too much.

Healthcare providers can develop mobile personal assistant apps powered by streaming analytics that provide real-time actionable glucose insights and predictions for individuals with diabetes, helping to make it easier for them to manage the disease. Streaming analytics can help to analyze data from wearable devices and use machine-learning models to assess the risk of patients’ glucose levels falling outside the safe threshold.

Solve healthcare problems with Informatica’s streaming architecture

Informatica® Data Engineering Streaming can help healthcare providers prepare and process streams of patient data such as heart rate, blood pressure, and temperature events. Providers can uncover insights by correlating and integrating the streaming data with batch data for acting in real-time to trigger alerts for preventive care. For example, if a patient’s heart rate increases by five percent or blood pressure drops by 10 percent, those actions can trigger an alert for a nurse or a doctor to take immediate action. The solution can scale out horizontally and vertically to handle petabytes of data while honoring business service-level agreements.

Informatica Data Engineering Streaming offers a “sense-reason-act” framework for real-time streaming analytics. The framework provides end-to-end data-engineering capabilities to ingest real-time sensor data coming from medical devices, apply enrichments on the data in real-time or in batches, and operationalize the actions on the data in a single platform using a simple and unified user experience.

The Informatica Data Engineering Streaming framework

Get more information on Informatica’s streaming solution and meet our experts at one of these upcoming events: