Filtration & fluid control Smart pumps: what does the evidence show?
Connecting infusion pumps to electronic health records offers a practical example of how greater intelligence and connectivity can change fluid delivery. A 2026 systematic review in BMJ Health & Care
Informatics examined bidirectional interoperability between smart infusion pumps and electronic health records in hospitals. In such systems, patient-specific information, including drug concentration and infusion rate, can pass from the electronic health record to the pump. In contrast, infusion data can travel back for confirmation and documentation.
The review identified seven US studies published between 2011 and 2024. Six considered system compliance and workflow efficiency, three examined medication errors, and two assessed economic outcomes.
Overall, the findings were mainly positive. All three studies examining medication errors reported reductions in the types of errors investigated, although the reduction was statistically significant in only two. Other studies associated interoperability with factors including fewer pump-programming steps, reduced nursing time for programming and improved documentation. But the authors urged caution. All seven studies were observational and non- randomised, and the review judged the overall quality of evidence to be low. The fact that all were conducted in the US also limits how readily their findings can be applied to other healthcare systems.
The authors concluded that interoperability may reduce medication errors and improve system compliance and workflow efficiency, but said more rigorous studies
are needed. Source: Effects of a bidirectional interoperability between electronic health records and smart infusion pumps in hospital settings: a systematic review. BMJ Health & Care Informatics.
performance”, as well as to enterprise connectivity, which “allows fluid management systems to become part of a broader healthcare ecosystem rather than operating as stand-alone devices”.
In other words, data from such set-ups can now be pulled into other systems more easily, making it easier for healthcare professionals to view it in context with other information. Rather than generating separate data streams, fluidic medical set-ups are becoming integrated into one overarching picture.
“AI models are being used in image analysis for flow, cell counting and flow trajectory determination. Important too is the development of smart pumps.”
Rucha Natu
Essentially, Nesterenko says, such devices can increasingly collect, transmit and contextualise fluid-related data in real time. And, crucially, that is “enabling clinicians and healthcare organisations to make more informed decisions”.
And since said data can be viewed remotely, many argue that fluidic devices with intelligent technology also open up greater options for out-of- hospital care.
Looking for patterns
The growing use of intelligent technologies is a pattern being seen across a variety of fluidic devices. And, given how many devices depend on assessing or controlling a liquid or gas, that spans a range of clinical and diagnostic areas.
56
Mechanical engineer Rucha Natu, who has worked in fluidic medical device development and evaluation for close to a decade, has specific experience in micro-flow or low-flow devices for blood diagnostics. She highlights a few key areas where such devices are benefiting from intelligent technologies. That notably includes the intelligent technology that has drawn so much attention in recent years: artificial intelligence (AI), in which computers perform tasks that would traditionally have required human intelligence.
Natu, a former fellow at the US Food and Drug Administration and senior research associate at Case Western Reserve University, says AI models are being used in “image analysis for flow, cell counting and flow trajectory determination”. She also speaks of “flow systems closely mimicking human blood flow with real-time monitoring” that are highly sensitive to minute changes. Important too is the development of “smart pumps with capabilities down to a few microlitres operating in feedback loops”.
The result is systems that can understand tiny variations in fluid volume, and respond to them. For mechanical engineers like Natu, a further result is what she describes as more flexibility to “stretch the limits” of medical device design, thanks to the improved sensitivity and capabilities that intelligent technologies bring. This presents both challenges and opportunities. Designing a fluidic device is no longer solely about ensuring appropriate physical movement of that fluid through the system. It’s also about factoring in a whole host of additional dimensions that become relevant in the context of intelligent technologies.
“Engineers must now consider the entire experience surrounding the device, including connectivity, cybersecurity, interoperability, usability, human factors, and data management,” says Nesterenko.
A key issue is ensuring that these increasingly smart devices deliver meaningful information without unnecessarily increasing complexity for the user. After all, a fluidic device that collects a mass of precise data is only helpful if it presents that information at the right time and in a logical format. As Nesterenko puts it: “Successful designs simplify workflows, reduce cognitive burden, and present actionable information at the right time and in the right context.”
When it gets complicated
The need to avoid complications while capitalising on technological developments equally extends to the manufacture of such devices. Here again, there is a need for a “systems-level approach”, says Nesterenko, combining “hardware, software, connectivity and data infrastructure”.
www.medicaldevice-developments.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102
