She sees the concern in their eyes. She hears, “we’ll take good care of you–both.” Then, she awakes to learn her child is in intensive care, 3 lb. 7 oz. and eight weeks early. Days into his stay, he is jaundiced—a complication of sepsis. Thus, begins the adventure into the unknown.

 – Reflections from a preemie’s parent

Sepsis diagnoses in neonatal intensive care units (NICUs) often take hours after onset, despite the availability of volumes of data and high healthcare provider-to-patient ratios. Dr. David Van Laere, a neonatal specialist at Antwerp University Hospital (Belgium) and founder of Innocens BV,  was convinced the solution to swift diagnosis and treatment was buried within the enormous amounts of structured and unstructured patient data—metrics, measurements and imagery captured during an infant’s NICU stay. Could artificial intelligence and edge computing provide the much-needed insights to help speed treatment?

Why sepsis ravages pre-term infants

Babies born prematurely, especially those under 1500 grams (3.3 lbs.), are susceptible to significant health challenges. Their immature neurological, cardiac, pulmonary, renal and immune systems can make them vulnerable to life-threatening complications. To ensure their conditions are monitored around the clock, these infants are assigned to a highly specialized NICU for care. When issues surface, physicians and healthcare staff must respond quickly. The bloodstream infection, sepsis, is one of the critical health challenges. Without rapid intervention, up to 20% of premature infants perish due to sepsis complications. Timely diagnosis and treatment can be the difference between successful outcomes or heartbreak.

Experience drives innovations in sepsis diagnoses 

For more than a decade, Dr. Van Laere has cared for some of the smallest infants in Australian and Belgian NICUs. The lessons he learned while treating infants afflicted with sepsis impacted his life’s path. In addition to his practice, he founded the Innocens Project. The organization was established at the University Hospital at Antwerp in Belgium with the mission to speed time to diagnoses and treatment of sepsis.

In his own words

– Dr. David Van Laere, a neonatal specialist at Antwerp University Hospital, founder of Innocens BV

“At the bedside, I started monitoring data trends. My research focused on signal analysis and trying to extract additional information from vital signs that related to complications, such as sepsis,” said Dr. Van Laere. He searched for a technology solution that securely managed and analyzed personal patient data, automated and modernized the diagnosis process, predicted when an infant was trending toward sepsis and triggered an evaluation protocol. He discussed the challenge while biking weekly with his neighbor Dirk Claessens, a managing director with IBM Global Markets.

Although Claessens primarily focused on large customers in the industrial sector, his in-depth AI and predictive analytics expertise and IBM ecosystem knowledge allowed him to find a solution to the healthcare challenge swiftly. Thus, began the partnership between Dr. Van Laere, Innocens and IBM. With the expertise of data scientists and developers at the IBM Watson® Center in Munich, the collaboration resulted in an edge computing solution powered by IBM Cloud that captures real-time data generated by the existing sensors. In addition, data modeling and analysis is facilitated through the open-source Red Hat® OpenShift® Container Platform and IBM Watson® Studio on IBM Cloud Pak® for Data.

Attaining remarkable results in pre-clinical trial stage

“I felt that we needed to have both a research and a deployment focus at the same time. We needed a trusted tech partner that could deliver on all the aspects of trustworthy AI. And that’s what I found with IBM,” said Dr. Van Laere. Innocens earned the distinction of the 2021 IBM Beacon Award for Outstanding Data & AI Solution through the collaboration.

Using current and historical patient data integrated with artificial intelligence, machine learning and data modeling capabilities provided the ability to identify infants at risk of sepsis up to several hours, in some cases, before the standard protocol for monitoring and testing.  The AI solution is 75% accurate in detecting severe sepsis with less than one false alarm per week. Clinical trials are expected to confirm that early prediction leading to a rapid diagnosis and timely treatment can improve clinical outcomes at a reduced cost.

Looking forward to new opportunities with AI and Edge Computing

Dr. Van Laere and the Innocens team have just begun their AI and edge computing journey. The team plans to deploy the sepsis diagnosis and treatment solution within other NICU hospitals and systems. “Basically, the sky’s the limit. Next, we can try to build a model to predict brain injury, lung disease or retinopathy in preterm infants.,” Dr. Van Laere concludes. “There are exciting times ahead for us in the neonatal intensive care unit in Antwerp University Hospital and at Innocens.”

To learn more about the Innocens Project, view Dr. Van Laere’s IBM Health Forum session replay “Every hour counts: Catching Sepsis early in NICU Infants.”

Explore the capabilities of IBM Cloud Pak for Data.