Abstract:

Artificial intelligence technology is trending in nearly every medical area. It offers the possibility for improving analytics, therapy outcome, and user experience during therapy. In dialysis, the application of artificial intelligence as a therapy-individualization tool is led more by start-ups than consolidated players, and innovation in dialysis seems comparably stagnant. Factors such as technical requirements or regulatory processes are important and necessary but can slow down the implementation of artificial intelligence due to missing data infrastructure and undefined approval processes. Current research focuses mainly on analyzing health records or wearable technology to add to existing health data. It barely uses signal data from treatment devices to apply artificial intelligence models. This article, therefore, discusses requirements for signal processing through artificial intelligence in health care and compares these with the status quo in dialysis therapy. It offers solutions for given barriers to speed up innovation with sensor data, opening access to existing and untapped sources, and shows the unique advantage of signal processing in dialysis compared to other health care domains. This research shows that even though the combination of different data is vital for improving patients' therapy, adding signal-based treatment data from dialysis devices to the picture can benefit the understanding of treatment dynamics, improving and individualizing therapy.

Abstract:

BACKGROUND AND PURPOSE: Atomoxetine is a selective noradrenaline reuptake inhibitor, recently approved for the treatment of attention-deficit/hyperactivity disorder. So far, atomoxetine has been shown to be well tolerated, and cardiovascular effects were found to be negligible. However, two independent cases of QT interval prolongation, associated with atomoxetine overdose, have been reported recently. We therefore analysed acute and subacute effects of atomoxetine on cloned human Ether-a-Go-Go-Related Gene (hERG) channels. EXPERIMENTAL APPROACH: hERG channels were heterologously expressed in Xenopus oocytes and in a human embryonic kidney cell line and hERG currents were measured using voltage clamp and patch clamp techniques. Action potential recordings were made in isolated guinea-pig cardiomyocytes. Gene expression and channel surface expression were analysed using quantitative reverse transcriptase polymerase chain reaction, Western blot and the patch clamp techniques. KEY RESULTS: In human embryonic kidney cells, atomoxetine inhibited hERG current with an IC(50) of 6.3 micromol.L(-1). Development of block and washout were fast. Channel activation and inactivation were not affected. Inhibition was state-dependent, suggesting an open channel block. No use-dependence was observed. Inhibitory effects of atomoxetine were attenuated in the pore mutants Y652A and F656A. In guinea-pig cardiomyocytes, atomoxetine lengthened action potential duration without inducing action potential triangulation. Overnight incubation with high atomoxetine concentrations resulted in a decrease of channel surface expression. CONCLUSIONS AND IMPLICATIONS: Whereas subacute effects of atomoxetine seem negligible under therapeutically relevant concentrations, hERG channel block should be considered in cases of atomoxetine overdose and when administering atomoxetine to patients at increased risk for the development of acquired long-QT syndrome.

Abstract:

As digitalization moves forward in the health sector, new ways of measuring the patients’ outcome and current status are evolving. Additionally with User-Centered Design, also Patient-Centered Therapy becomes more important. Instead of measuring the pure medical output of patients, circumstances and journey of the patient plays a bigger role. Quality of Life of chronically ill patients is measured to offer the best support for individuals to nudge them sticking to their therapy and enjoying their lives as good as possible. Patients that suffer from End-Stage Renal Disease (ESRD) need to wait in average four years for their transplantation [1]. The dialysis therapy occupies big parts of their life and freedom during this waiting time. The use of computer-aided technologies to measure patients’ quality of life and well-being can make the process easier to handle for patients. Complications can be detected earlier, psychological illnesses can be tracked and treatment can be simplified. Following this idea, this thesis is researching on possible levers for quality of life, technologies for measurement and influencing factors. Further, fluid measurement of dialysis patients through detecting shifts in hand swelling is proposed as an option of improving patients monitoring and maintain quality of life level. When monitoring the patient, also measurement burden needs to be considered as it reduces the perceived quality of life. Therefore the goal is to measure the patient seamlessly and continuously. Image analysis and pervasive sensing are promising. Especially video analysis offers many measurement opportunities of psychological as well as physiological status. Many symptoms that threaten the Quality of Life (QoL) can be measured and diagnosed via optical measurements. The Proof of Concept (PoC) of measuring fluid status of dialysis patients by taking pictures of their hands showed the technical feasibility of the concept. It could be shown that the hand would approximately swell 1,5 mm if the dialysis patient is suffering from 3 litres of fluid overload which is common. This change should be detectable by an average smartphone camera. Pictures of different-sized hands were taken and analysed regarding area change of the hand contour. The same procedure was repeated for pictures of water-filled gloves and hand-in-water-filled-gloves. The area size in pixels was then converted into cm by accounting the known size and pixel area of a 5 cents coin. Even if only few experiments were made, results showed a significant correlation with a p-value of 5.7 e-06 between measured pixel area and real volume change of the hand or glove. Next steps would be to apply this process to real swollen hands to test if the gradient is big enough to measure the fluid changes in binary and later quantitative concerns in dialysis patients. Applying deep learning algorithms to the pictures could be added in a later step. Wrinkles, skin colour and reflection as well as other until now unknown factors can be therefore considered in the fluid status determination and may lead to more precise results. As the PoC was focussed on tightly controlled circumstances and surroundings, more experiments are necessary to determine, if the same results can be found when applying a more unstable environment as different backgrounds, skin colour, lighting and others.