Fresenius Medical Care has developed a predictive model using machine learning and cloud computing to help proactively identify when kidney dialysis patients might be suffering a potentially life-threatening complication. Credit: Pete Waguespack and Hanjie Zhang / Fresenius Medical Care & Renal Research Institute Hemodialysis is a life-saving treatment for those suffering from kidney failure. The procedure, often called kidney dialysis, cleansing a patient’s blood, substituting for the function of the kidneys, and is not without risk, however. German healthcare company Fresenius Medical Care, which specializes in providing kidney dialysis services, is using a combination of near real-time IoT data and clinical data to predict one of the most common complications of the procedure. Fresenius operates a network of more than 4,000 outpatient dialysis centers globally, primarily treating patients with end-stage renal disease (ESRD), which requires those patients to receive dialysis three times a week for the rest of their lives. About 10% of hemodialysis treatments result in intradialytic hypotension (IDH) — low blood pressure. “IDH holds a potentially severe immediate risk for patients during dialysis and therefore requires immediate attention from staff,” says Hanjie Zhang, director of computational statistics and artificial intelligence at the Renal Research Institute, a wholly owned subsidiary of Fresenius Medical Care Holdings. “As such, IDH not only reduces patients’ quality of life and is associated with morbidity and mortality, but also results in lower clinical efficiency and effectiveness.” Dr. Peter Kotanko, research director of the Renal Research Institute, adds, “Whenever a patient’s blood pressure drops and IDH ensues, healthcare providers need to intervene, and the operations of a clinic can be disrupted.” In September 2021, Fresenius set out to use machine learning and cloud computing to develop a model that could predict IDH 15 to 75 minutes in advance, enabling personalized care of patients with proactive intervention at the point of care. To do so, the team had to overcome three major challenges: scalability, quality and proactive monitoring, and accuracy. The project, dubbed Real-Time Prediction of Intradialytic Hypotension Using Machine Learning and Cloud Computing Infrastructure, has earned Fresenius Medical Care a 2023 CIO 100 Award in IT Excellence. Putting data to work to improve health outcomes “Predicting IDH in hemodialysis patients is challenging due to the numerous patient- and treatment-related factors that affect IDH risk,” says Pete Waguespack, director of data and analytics architecture and engineering for Fresenius Medical Care North America. “Clinically, prediction is more useful if it predicts an IDH event for a given patient during an ongoing dialysis treatment. It was imperative to bring a cross-functional team of clinical, operational, and technology experts together to define the needs of the near real-time prediction and response.” The solution needed to scale to all of Fresenius’s dialysis centers, with each location sending 10MBps of treatment data at peak times. A low-latency, time-sensitive solution of 10 seconds from data origination from dialysis machines and medical sensors to reporting and notification was critical. In addition, systematic and automated monitoring and alerting mechanisms were necessary to help the team spot problems and resolve them quickly. The solution uses CloudWatch alerts to send notifications to the DataOps team when there are failures or errors, while Kinesis Data Analytics and Kinesis Data Streams are used to generate data quality alerts. “Using an agile approach, we prioritized features to deliver a minimal viable prototype over a six-month period,” Waguespack says. “Our primary challenge was in our ability to scale the real-time data engineering, inferences, and real-time monitoring to meet service-level agreements during peak loads (6K messages per second, 19MBps with 60K concurrent lambda invocations per second) and throughout the day (processing more than 500 million messages daily, 24/7).” Fresenius’s machine learning model uses electronic health records comprising intradialytic blood pressure measurements and multiple treatment- and patient-level variables. The team trained and validated the model using observational data from 42,656 hemodialysis sessions in 693 in-center hemodialysis patients. In the training cohort, the model was optimized to generate an IDH alert between 15 and 75 minutes before an IDH event. Transforming dialysis Waguespack says the project was new ground for Fresenius, requiring the organization to explore measures to protect health information in the cloud and the role AI can play in a clinical setting. Each of those were associated with blockers, real and perceived. “It was imperative for us to gain full partnership from all our stakeholders by creating absolute alignment focused on quality improvement, complete transparency in our work, and showing the utmost integrity by living up to our own expectations,” he says. He notes that success required the IT organization to become more agile, embrace failing fast, and internalize that learning is a deliverable as valuable as adding a new feature. “This shift in attitude and expectations needed to come top down and bottom up,” he says. “Top down, to provide the support and space to change. Bottom up, from those experienced in an agile approach and able to model behavior day in and day out. This shift could be seen in the words we used, the way we celebrated learning and progress, and the respectful and supportive nature of the team.” The IDH tool has not yet been evaluated or cleared for use by the US Food and Drug Administration (FDA), but Zhang says the team recently published its findings in a top peer-reviewed kidney journal. While further clinical studies are required to validate whether prediction of IDH followed by timely, appropriate preventative measures translates into lower IDH rates and improved patient outcomes, Zhang says the model’s high performance in the validation cohort is promising. Waguespack adds that the project has been another step in Fresenius Medical Care’s ongoing digital transformation. “The opportunity to predict IDH during a dialysis treatment is one of several building blocks to transform our company into the world of the Internet of Things, big data, and artificial intelligence,” he says. “Building on the success of this initiative, we continued our journey to collect terabytes of data from novel sources in a modern data platform. From here, we continue to iterate on the process and technology to effectively manage our data so that it can enable continued innovation, including machine learning for image classification apps, genomic research, large language models, and beyond.” Related content brandpost Sponsored by Randstad How CIOs can use internal mobility and redeployment for successful digital transformation The role of your people is key a factor in the success of digital transformation. Find out how redeployment and talent transition experts, Randstad RiseSmart, can help organizations at all stages of the digital transformation journey. By Neal Weinberg May 28, 2024 5 mins Digital Transformation opinion Navigating the Cybersecurity Threat Landscape in the UAE: Strategies for CISOs By Andrea Benito May 28, 2024 4 mins feature 10 most difficult-to-fill IT roles — and how to address the gap With AI, cybersecurity, and data analytics talent in short supply, IT leaders are upskilling, recruiting from the business, highlighting culture, and relying on contractors to secure the talent they need. By Stephanie Overby May 28, 2024 11 mins Hiring Staff Management feature Sun Country enhances customer experience with IT The low-cost regional airline turned to IT to develop a self-service e-voucher program aimed at easing the hassles that come with flight delays and cancellations. By Paula Rooney May 28, 2024 6 mins CIO 100 Travel and Hospitality Industry Digital Transformation PODCASTS VIDEOS RESOURCES EVENTS SUBSCRIBE TO OUR NEWSLETTER From our editors straight to your inbox Get started by entering your email address below. Please enter a valid email address Subscribe