Real-Time Monitoring of the Artificial Kidney

Introduction of HRO membranes in the clinical routine has enabled the development of a new concept therapy called expanded hemodialysis that modifies the outcome of end-stage kidney disease patients.

In the past few years, many technological innovations in dialysis equipment have been developed, and new modalities and strategies have been introduced; however, assuming that the ideal of dialysis is to replace the function of the failed kidneys as completely as possible with full rehabilitation of the patient and minimal cost to society, one realizes that we are still far from reaching this goal. In some ways, dialysis equipment has advanced quite a bit since 1943 (Vaarwel, sausage casing, hello mass-produced cellulose tubing), but its basic function has remained unchanged for more than 70 years. Not because there are not plenty of things to improve on. Design and manufacturing flaws make dialysis much less efficient than a real kidney at taking bad stuff out of the body and keeping the good stuff in. Moreover, dialysis equipment still cannot perform majority of the biological functions of kidneys. Manufacturers and researchers are working continuously to substantially upgrade the technology and improve the functionality and pore-size of membranes.

Dialysis equipment is being continuously improved owing to the innovative technological developments, but patient safety is still a key challenge. The fundamental innovative process of early dialysis utilized rudimentary membranes and improvised equipment. Today, technology has produced a variety of membrane compounds capable of higher efficiency, higher permeability, greater biocompatibility that ultimately delivers greater outcomes. Dialysis machines are programmable, capable of altering sodium levels, adjusting UF rate via feedback from the automatic blood pressure feature. The wearable kidney is already being trialed. Real-time monitoring systems, coupled with automatic instantaneous biofeedback, will allow changing dialysis prescriptions continuously. The integration of vital sign monitoring with dialysis parameters will produce large data sets that will require the use of data analysis techniques, possibly from the area of machine learning, in order to make better decisions and increase the safety of patients.

Technological Advances
Day-to-day life can be extremely difficult for those who need regular hemodialysis treatment in order to survive, and new technologies could dramatically improve the quality of life for these patients. The current potentially life-changing innovations could not only free up hours of time that would otherwise be spent in hospital, but give patients a completely new lease of life.

Advances in membrane permeability. The advent of ultrafiltration control systems led to the development and use of high-flux (HF) membranes that allowed improved middle molecule removal including ß-2 microglobulin. Further advances in technology have also led to the development of a new class of membranes referred to as protein-leaking membranes or super-flux or high cutoff (HCO). These membranes are more permeable than conventional HF membranes and allow some passage of proteins, including albumin. The rationale for these membranes is the need for increased clearance of low molecular weight proteins and protein-bound solutes. The introduction of HRO membranes in the clinical routine has enabled the development of a new concept therapy called expanded hemodialysis (HD). This new therapy is likely to modify the outcome of end-stage kidney disease patients, thanks to the enhanced removal of molecules traditionally retained by current dialysis techniques.

Online hemodiafiltration. In this technology, large volumes of replacement fluid required are obtained by online filtration of standard dialysate through a series of bacteria- and endotoxin-retaining filters. Currently available systems for online hemodiafiltration are based on conventional dialysis machines with added features to safely prepare and infuse replacement fluid and closely control fluid balance. They provide greater removal of higher molecular weight uremic retention solutes than conventional HF HD, and offer better patient survival as compared with standard HF HD when a high convection volume is delivered.

Wearable artificial kidneys. It is a portable miniature HD machine that can be worn as a belt around the waist. Similar to HD, the WAK is dependent on vascular access to the blood stream. However, unlike traditional HD which depends on energy consumptive roller pumps to sustain the movement of the blood and dialysate fluid in a coordinated fashion, the WAK relies on small, energy-efficient dual chamber pumps that are powered by lightweight batteries to control ultrafiltration (fluid removal), the infusion of anticoagulants, and the delivery of other substances to the dialysate. WAK also eliminates the requirement for large volumes of dialysate fluids, which are needed in conventional dialysis and is based on the sorbent technology to recycle dialysate.

Automated dialysis system with telehealth platform. This new technology is designed to reduce storage and weight handling requirements that come with traditional dialysis therapy. This advanced technology has the potential to greatly enhance home dialysis therapy for patients by providing solution generation on-demand and eliminating some of the barriers that today may keep patients from the lifestyle benefits that home dialysis offers. The technology is also identified as a means to extend care to rural patients with CKD. For example, augmenting a mobile application to feature biometrics reporting, medication and appointment reminders, and access to virtual nutrition clinics expands its functionality beyond static education to empower active patient self-management. Further modifications to include bidirectional communication could facilitate high-risk patient case management.

Innovations in dialysis monitors. In the past two decades, the appearance of dialysis monitors has changed dramatically from robust but frequently not user-friendly machines to more sophisticated ones with a host of alarms. Whereas in the old monitors every parameter was set and controlled manually by the dialysis nurse, in the most recent machines, everything has become plug and play, and the machine handles most of the problems automatically. This evolution has without any doubt positive influences on safety (fewer human errors) and on ergonomics and has thus reduced labor cost. In addition, these user-friendly machines can more easily be used in out-of-hospital settings and in home dialysis.

Outlook
There are various major players working on developing portable dialysis machines that will provide ease of portability in the dialysis process, since the condition is most prevalent among the geriatric population and their mobility is rather limited which decreases the number of hospital visits. Such situations can only be controlled by the introduction of new portable single in-center dialysis machine, which can be useful for such a population.

Even after several advances in the technology, limitations in the pore-size still persist. Current dialysis devices are also not able to react when unexpected changes occur during dialysis treatment or to learn about experience for therapy personalization. Future efforts should be dedicated to develop miniaturized artificial kidneys to achieve a continuous and personalized dialysis therapy, in order to improve the patient’s quality of life. These innovative dialysis devices will require a real-time monitoring of equipment alarms, dialysis parameters, and patient-related data to ensure patient safety and to allow instantaneous changes of the dialysis prescription for the assessment of their adequacy.

The analysis and evaluation of the resulting large-scale data sets enters the realm of big data and will require real-time predictive models. These may come from the fields of machine learning and computational intelligence, both included in artificial intelligence (AI). AI research on dialysis is still in an early stage, and the main challenge relies on interpretability and/or comprehensibility of data models when applied to decision making. The incorporation of AI should provide a fully new approach to data analysis, enabling future advances in personalized dialysis therapies.