Intelligent Automation and Dialysis

Introduction

Intelligent Automation and Dialysis. Miguel Huesoa Miguel Huesoa, Department of Nephrology, Hospital Universitari Bellvitge and Bellvitge Research Institute (IDIBELL), L’Hospitalet de Llobregat, Spain. Received Date : April 01, 2024 Accepted Date : April 03, 2024 Published Date : May 03, 2024 Technology is a major component of modern medical science. Some of the most remarkable technological advances in this field have been made in the creation of non-invasive procedures, which aim to enhance the measurement and examination of the human body. The creation of devices to support treatments for particular illnesses is the subject of another section. The prosthetic kidney, which is the subject of extensive research from many angles and raises high hopes for dialysis patients, is one example of this.

Though research on artificial kidneys is still in its early stages, a number of obstacles need to be cleared before these devices are used in nephrology patient care.The safety of patients using these modern dialysis machines is one of these significant difficulties. Effective monitoring methods are required because of safety issues. The proliferation of electronic devices surrounding the patient at the point of care has resulted in the ongoing generation of data in electronic format. This has created a demand for analytical techniques that can convert this data into knowledge that will ultimately aid in the treatment of patients. Some of the most promising findings as analytical tools are currently being offered by the artificial intelligence (AI) field.

Artificial Intelligence is a catch-all word that neatly encompasses ideas from various disciplines, including statistics, algorithmics, machine learning (ML), information retrieval, and data science in general. All scientific disciplines have been made possible by the exact advancements in computational technologies.to evolve into surroundings rich in data. In particular, data analysis with artificial intelligence (AI) and associated techniques is yielding huge benefits for medicine. It is possible for these advantages to spread throughout the healthcare industry thanks to the standardization of the usage of electronic health records at the point of treatment. The six papers published in this edition of Kidney Diseases are the result of the Second Science for Dialysis Meeting: Artificial Intelligence, which was held in Barcelona, Spain, at the Hospital Universitari de Bellvitge.

Participants in the meeting from the medical and AI research communities discussed how Applications of AI could make prosthetic kidneys safer. There are four sections to the current issue. First, Hueso et al. ^[1] addresses the advancements and difficulties of artificial intelligence (AI), machine learning (ML), and medical decision support systems in their application to nephrology and artificial kidneys. Second, Vellido ^[2] explores the numerous societal issues related to artificial kidneys cases involving the use of artificial intelligence in medicine. The idea of Reinforcement Learning, a branch of machine learning influenced by goal-oriented algorithms, is introduced in Part II. which acquire knowledge via engagement with their surroundings ^[3]. Two articles by Ribas Ripoll and Vellido ^[4] and Barbieri et al.

^[5] about AI and ML techniques for blood pressure assessment and management are included in Part III. The former employs methods from deep learning. Patients with end-stage renal disease are involved in the latter. In order to increase dialysis dose accuracy, part IV concludes with experience using Mishina’s artificial pancreas, which was recently implemented in clinical practice ^[6]. This involves individualizing the response to dialysis treatment.

References

1. Hueso M, Navarro E, Sandoval D, Cruzado JM. Progress in the development and challenges for the use of artificial kidneys and wearable dialysis devices. Kidney Dis. 2019; 5:3–10.
2. Vellido A. Societal issues concerning the application of artificialintelligenceinmedicine.KidneyDis.2019;5:11–17.
3. Jonsson A. Deep reinforcement learning in medicine. Kidney Dis. 2019;5:18–22.
4. Ribas Ripoll V, Vellido A. Blood pressure assessment with differential pulse transit time and deep learning: a proof of concept. Kidney Dis. 2019;5:23–27. Editorial
5. BarbieriC,CattinelliI,NeriL,MariF,RamosR,Brancaccio D, et al. Development of an artificial intelligence model to guide the management of blood pressure, fluid volume and dialysis dose in end-stage kidney disease patients: proof of concept and first clinical assessment. Kidney Dis. 2019;5:28–33. 6. 6 Mishina S. Self-correcting abilities to improve accuracy of medical devices based on biofeedbacks. Kidney Dis. Forthcoming 2018. Editorial

This is a text version generated from the article. For the formatted version of record (with original tables & figures), download the PDF →