5 Reasons Healthcare Organizations Must Consider AI/ML

By Puneet Pandit, Glassbeam, Inc.

Artificial intelligence and machine learning (AI and ML, respectively) are the technologies du jour. IT and product teams are applying AI and ML solutions to everything from robotics to refrigerators, everywhere machines produce performance and/or environmental data. But how can AI and ML benefit healthcare equipment maintenance, not typically viewed as a hotbed of innovation? In fact, there is an abundance of ways AI and ML can bring new levels of revenue increases and cost savings to healthcare organizations by rapidly creating new, actionable insights for maintenance teams.

Teams often view the mountain of machine log data as a burden they don’t have time to address. Data appears in a variety of formats, some is structured, some semi-structured and other data is unstructured, complicating the ability to analyze it. However, gold is buried in that data for the managers willing to apply AI and ML solutions to analyze it and sift out predictive and prescriptive insights. Here are just five of those gold nuggets.

Increased Machine Uptime

Today, many hospital management and IT teams are content with machines that experience 95-97 percent uptime. But uptime is money in the bank for a healthcare provider. By analyzing machine data in near real-time, teams can catch anomalous behavior, alert system engineers and plan for maintenance and repairs without disrupting the flow of patient care. That means more patient throughput per machine per year and therefore more revenues for the provider.

Improved Asset Utilization

Healthcare organizations spend millions every year unnecessarily by over provisioning imaging machines, especially at acute or emergency care locations. This is done in spite of the fact that their staff may be underutilizing the equipment assets they own. CT scanners and MRI machines, for example, operate below capacity at certain facilities while the organizations purchase additional machines in nearby facilities, due to a lack of understanding of how the overall fleet utilization is working. Today, teams typically collect manual data from legacy systems, scheduling software or CMMS systems, all of which produce reports that lack necessary detail and often take a long time to generate, making them are virtually useless. However, combining transactional data from CMMS systems with machine data and applying AI/ML analytics can predict machine utilization with far greater accuracy, a game changer for healthcare organizations.

Better Cap Ex Practices

AI/ML analytics can inform the finance team of optimal timing and strategy for replacing complex hospital equipment. As analytics indicate an increasing frequency of anomalies that result in increased downtime, the organization can calculate the optimal cost/benefit for purchasing replacement equipment to minimize overlap. In addition, these analytics can help organizations determine the level of functionality and type of features the organization should purchase. For example, analysis might demonstrate that demand for a type of equipment might be just 80 percent of the machine’s maximum uptime. As a result, managers might purchase a machine that performs its functions 10-20 percent slower and costs 30-40 percent less than the machine it replaces.

Optimized Supply Chain

AI/ML analytics enable healthcare organization maintenance teams to purchase spare parts on an as-needed basis, saving budget and storage space. Many healthcare equipment OEMs today prescribe specific maintenance schedules and part replacement based on time versus when the part stops functioning. As a result, parts that wear out sooner than expected can cause expensive, unplanned downtime, while at the other extreme, hospital staff may throw away parts that are still functioning effectively.

For healthcare equipment OEMs, AI/ML analytics bring the concept of just-in-time to manufacturing. Rather than purchasing parts and building expensive equipment that sits idle at various depots until a healthcare organization needs it, manufacturers can build and deliver new equipment, tailored to historical trends and projected demand in that region, as insights from analytics indicate replacement is necessary.

Bringing Airbnb To Healthcare Equipment

What does Airbnb have to do with healthcare equipment? In many urban and suburban areas, healthcare facilities are often located in proximity to each other. Sharing machine data analytics allows managers at multiple facilities to see what CT scanners (for example) might be available another facility when their CT scanner has downtime. This is a much less expensive alternative than either purchasing another scanner or placing rush orders for new parts.

While people may not want their refrigerators to talk to them, healthcare teams definitely want their complex, expensive equipment to inform them when conditions are less than optimal – whether a part is failing, the room is too warm or cool, or another type of anomaly. Today’s new generation of AI/ML solutions can both provide that information and the predictive/prescriptive insights that will help healthcare organizations optimize revenues.

About The Author

Puneet Pandit is the Founder and CEO of Glassbeam, the premier machine data analytics company. With more than 20 years of global IT experience Puneet founded Glassbeam in 2009 with the mission of bringing structure and meaning to complex data generated from any connected machine in the Industrial IoT industry. With a strong focus on medical devices, Glassbeam’s next generation cloud-based platform is designed to transform, analyze, and build Artificial Intelligence applications from multi-structured logs, delivering powerful solutions on customer support and product intelligence for companies.