Premature babies in neonatal intensive care units often require constant monitoring, but the process can be invasive and stressful. Frequent blood tests to measure glucose, sodium, and other vital indicators involve repeated needle pricks, while multiple wires and sensors can irritate their fragile, still-developing skin. To provide a gentler alternative, researchers from Tufts University’s Silklab, Helmholtz Munich, Ludwig Maximilian University (LMU) Munich, and the Technical University of Munich have developed a lightweight, silk-based wearable patch that can continuously monitor four key health markers without needles or wires.
Described in ACS Sensors, the coin-sized patch simultaneously measures temperature, pH, sodium, and glucose by analysing tiny amounts of interstitial fluid that naturally pass through the skin of premature infants. The patch changes colour in response to these biomarkers, and an artificial intelligence (AI) system interprets the colour shifts using images captured with a standard camera, even in the dim, humid conditions of an incubator. The technology converts the colour patterns into precise measurements, providing clinicians with real-time information about a baby’s condition.
The researchers say monitoring several biomarkers at the same time offers a more complete picture of an infant’s health than tracking a single measurement alone. “There is a lot more information in how multiple variables move relative to one another than in any single variable on its own,” said Fiorenzo Omenetto, Director of the Silklab at Tufts University. “If you only watch one number, you’re reading one line of a much longer story. We wanted to create a sensing interface that gives clinicians the whole paragraph.” Anne Hilgendorff, a neonatologist and researcher at Helmholtz Munich, LMU Munich, and the Carl von Ossietzky University Oldenburg, added that the patch was designed specifically for the unique needs of premature babies, eliminating the discomfort caused by needles, wires, and adhesive sensors.
The multilayer sensor combines silk fibroin derived from silkworm cocoons with wax-printed paper and a waterproof medical adhesive. The silk stabilises sensitive biological molecules, including enzymes that normally require refrigeration, allowing the patch to remain durable and shelf-stable. The paper layer channels microscopic amounts of interstitial fluid to individual sensing spots, while the adhesive seals the patch against the warm, humid incubator environment and allows it to move comfortably with the baby’s skin. Because premature infants naturally lose higher amounts of interstitial fluid through their underdeveloped skin barrier, the device turns this biological vulnerability into a continuous, painless source of diagnostic information.
Each sensing spot changes colour when exposed to specific biomarkers, such as from yellow to deep red for glucose or from blue to purple for sodium. Since lighting conditions can affect colour interpretation, the team developed a deep-learning AI model that automatically corrects for lighting, viewing angle, and movement before converting the colour changes into quantitative measurements. The system achieved more than 91% accuracy for key health indicators and over 98% accuracy in detecting low blood sugar. According to Benjamin Schubert, who leads computational health research at Helmholtz Munich, the patch is not intended to replace laboratory testing but to continuously detect gradual physiological changes that may occur between routine blood tests, enabling earlier intervention before problems become emergencies.
The researchers emphasise that the current device is a proof-of-principle, with larger clinical studies planned to compare patch measurements directly with conventional blood tests and to refine the AI further using data from different neonatal care settings. They also envision expanding the platform to monitor additional health indicators, including oxygen saturation and carbon dioxide. Because the patch is inexpensive to manufacture and requires no power source, refrigeration, or wired connections, the technology could also improve newborn care in low-resource hospitals and remote communities where advanced monitoring equipment is often unavailable. “A piece of paper, a drop of silk, and a smartphone camera,” Omenetto said. “If that were to become all it takes to keep a baby safer, then we should be putting one in every incubator on the planet.”
More information: Alejandra Castelblanco et al, Artificial Intelligence-Supported Colorimetric Multibiomarker Sensor to Enable Critical Neonatal Monitoring, ACS Sensors. DOI: 10.1021/acssensors.5c04171
Journal information: ACS Sensors Provided by Tufts University
