An international observational study suggests that artificial intelligence for clinical decision support optimizes anemia management in hemodialysis patients

Artificial Intelligence and Machine Learning Applied at the Point of Care

Introduction

The increasing availability of healthcare data and rapid development of big data analytic methods has opened new avenues for use of Artificial Intelligence (AI)- and Machine Learning (ML)-based technology in medical practice. However, applications at the point of care are still scarce.

Objective

Review and discuss case studies to understand current capabilities for applying AI/ML in the healthcare setting, and regulatory requirements in the US, Europe and China.

Methods

A targeted narrative literature review of AI/ML based digital tools was performed. Scientific publications (identified in PubMed) and grey literature (identified on the websites of regulatory agencies) were reviewed and analyzed.

Results

From the regulatory perspective, AI/ML-based solutions can be considered medical devices (i.e., Software as Medical Device, SaMD). A case series of SaMD is presented. First, tools for monitoring and remote management of chronic diseases are presented. Second, imaging applications for diagnostic support are discussed. Finally, clinical decision support tools to facilitate the choice of treatment and precision dosing are reviewed. While tested and validated algorithms for precision dosing exist, their implementation at the point of care is limited, and their regulatory and commercialization pathway is not clear. Regulatory requirements depend on the level of risk associated with the use of the device in medical practice, and can be classified into administrative (manufacturing and quality control), software-related (design, specification, hazard analysis, architecture, traceability, software risk analysis, cybersecurity, etc.), clinical evidence (including patient perspectives in some cases), non-clinical evidence (dosing validation and biocompatibility/toxicology) and other, such as e.g. benefit-to-risk determination, risk assessment and mitigation. There generally is an alignment between the US and Europe. China additionally requires that the clinical evidence is applicable to the Chinese population and recommends that a third-party central laboratory evaluates the clinical trial results.

Conclusions

The number of promising AI/ML-based technologies is increasing, but few have been implemented widely at the point of care. The need for external validation, implementation logistics, and data exchange and privacy remain the main obstacles.

Using Artificial Intelligence Resources in Dialysis and Kidney Transplant Patients: A Literature Review

BACKGROUND

The purpose of this review is to depict current research and impact of artificial intelligence/machine learning (AI/ML) algorithms on dialysis and kidney transplantation. Published studies were presented from two points of view: What medical aspects were covered? What AI/ML algorithms have been used?

METHODS

We searched four electronic databases or studies that used AI/ML in hemodialysis (HD), peritoneal dialysis (PD), and kidney transplantation (KT). Sixty-nine studies were split into three categories: AI/ML and HD, PD, and KT, respectively. We identified 43 trials in the first group, 8 in the second, and 18 in the third. Then, studies were classified according to the type of algorithm.

RESULTS

AI and HD trials covered: (a) dialysis service management, (b) dialysis procedure, (c) anemia management, (d) hormonal/dietary issues, and (e) arteriovenous fistula assessment. PD studies were divided into (a) peritoneal technique issues, (b) infections, and (c) cardiovascular event prediction. AI in transplantation studies were allocated into (a) management systems (ML used as pretransplant organ-matching tools), (b) predicting graft rejection, (c) tacrolimus therapy modulation, and (d) dietary issues.

CONCLUSIONS

Although guidelines are reluctant to recommend AI implementation in daily practice, there is plenty of evidence that AI/ML algorithms can predict better than nephrologists: volumes, Kt/V, and hypotension or cardiovascular events during dialysis. Altogether, these trials report a robust impact of AI/ML on quality of life and survival in G5D/T patients. In the coming years, one would probably witness the emergence of AI/ML devices that facilitate the management of dialysis patients, thus increasing the quality of life and survival.

Leveraging Data Science for a Personalized Haemodialysis

Background

The 2019 Science for Dialysis Meeting at Bellvitge University Hospital was devoted to the challenges and opportunities posed by the use of data science to facilitate precision and personalized medicine in nephrology, and to describe new approaches and technologies. The meeting included separate sections for issues in data collection and data analysis. As part of data collection, we presented the institutional ARGOS e-health project, which provides a common model for the standardization of clinical practice. We also pay specific attention to the way in which randomized controlled trials offer data that may be critical to decision-making in the real world. The opportunities of open source software (OSS) for data science in clinical practice were also discussed.

Summary

Precision medicine aims to provide the right treatment for the right patients at the right time and is deeply connected to data science. Dialysis patients are highly dependent on technology to live, and their treatment generates a huge volume of data that has to be analysed. Data science has emerged as a tool to provide an integrated approach to data collection, storage, cleaning, processing, analysis, and interpretation from potentially large volumes of information. This is meant to be a perspective article about data science based on the experience of the experts invited to the Science for Dialysis Meeting and provides an up-to-date perspective of the potential of data science in kidney disease and dialysis.

Key messages

Healthcare is quickly becoming data-dependent, and data science is a discipline that holds the promise of contributing to the development of personalized medicine, although nephrology still lags behind in this process. The key idea is to ensure that data will guide medical decisions based on individual patient characteristics rather than on averages over a whole population usually based on randomized controlled trials that excluded kidney disease patients. Furthermore, there is increasing interest in obtaining data about the effectiveness of available treatments in current patient care based on pragmatic clinical trials. The use of data science in this context is becoming increasingly feasible in part thanks to the swift developments in OSS.

The Role of Feedback Control Design in Developing Anemia Management Protocols

The optimal use of erythropoiesis stimulating agents to treat anemia of end-stage renal disease remains difficult due to reported associations with adverse events. A patient's hemoglobin response to these agents cannot be accurately described using population-level models due to many individual factors including chronic inflammation, red blood cell lifespan, and acute blood loss. As a consequence, it is generally understood that current one-size-fits-all anemia management protocols result in suboptimal outcomes. In this paper, we report on our collaboration with the medical community in designing anemia management protocols. In clinical implementation, these new dosing protocols have led to improved outcomes due to their use of control-relevant modelling, model parameter identification, and principles of feedback control. This is an example of medical professionals and control engineers working together to positively affect the performance of anemia management protocols in end-stage renal disease.

Prediction of the Mortality Risk in Peritoneal Dialysis Patients using Machine Learning Models: A Nation-wide Prospective Cohort in Korea

Herein, we aim to assess mortality risk prediction in peritoneal dialysis patients using machine-learning algorithms for proper prognosis prediction. A total of 1,730 peritoneal dialysis patients in the CRC for ESRD prospective cohort from 2008 to 2014 were enrolled in this study. Classification algorithms were used for prediction of N-year mortality including neural network. The survival hazard ratio was presented by machine-learning algorithms using survival statistics and was compared to conventional algorithms. A survival-tree algorithm presented the most accurate prediction model and outperformed a conventional method such as Cox regression (concordance index 0.769 vs 0.745). Among various survival decision-tree models, the modified Charlson Comorbidity index (mCCI) was selected as the best predictor of mortality. If peritoneal dialysis patients with high mCCI (>4) were aged ≥70.5 years old, the survival hazard ratio was predicted as 4.61 compared to the overall study population. Among the various algorithm using longitudinal data, the AUC value of logistic regression was augmented at 0.804. In addition, the deep neural network significantly improved performance to 0.841. We propose machine learning-based final model, mCCI and age were interrelated as notable risk factors for mortality in Korean peritoneal dialysis patients.

Promises of Big Data and Artificial Intelligence in Nephrology and Transplantation

Kidney diseases form part of the major health burdens experienced all over the world. Kidney diseases are linked to high economic burden, deaths, and morbidity rates. The great importance of collecting a large quantity of health-related data among human cohorts, what scholars refer to as “big data”, has increasingly been identified, with the establishment of a large group of cohorts and the usage of electronic health records (EHRs) in nephrology and transplantation. These data are valuable, and can potentially be utilized by researchers to advance knowledge in the field. Furthermore, progress in big data is stimulating the flourishing of artificial intelligence (AI), which is an excellent tool for handling, and subsequently processing, a great amount of data and may be applied to highlight more information on the effectiveness of medicine in kidney-related complications for the purpose of more precise phenotype and outcome prediction. In this article, we discuss the advances and challenges in big data, the use of EHRs and AI, with great emphasis on the usage of nephrology and transplantation.

A nurse prescriber-led protocol for anaemia management in established haemodialysis patients: A retrospective study

AIM AND OBJECTIVE

To evaluate the impact of a nurse prescriber-led protocol compared to a traditional physician-led nonprotocol-based approach had on maintaining targeted haemoglobin levels in patients on maintenance haemodialysis.

BACKGROUND

Anaemia is a common complication of chronic kidney disease and has a profound impact on the patients' well-being. Current practices place a greater emphasis on the decision-making role of nurses in renal anaemia management. The introduction of nurse prescribing in this area is a relatively new concept.

DESIGN

A retrospective cohort design, covering an eight-month period pre- and post introduction of a nurse prescriber-led anaemia protocol; study adheres to the STROBE Statement.

METHODS

Using a nonprobability convenience sample, data extracted from the medical records and electronic patient records system (eMed) related to 74 patients at a single outpatient haemodialysis centre located within an acute general teaching hospital. The primary outcome was patients' haemoglobin level pre- and post introduction of the protocol. Secondary outcomes included erythropoietin-stimulating agent and iron dosage, and serum ferritin and transferrin saturation levels.

RESULTS

There were no statistically significant differences between pre- and post protocol serum haemoglobin level and erythropoietin-stimulating agent dosage. Under the management of the nurse prescriber, patients experienced a significant improvement in serum ferritin and transferrin saturation levels and required significantly less intravenous iron dosage.

CONCLUSIONS

This study, the first of its kind, found that patients receiving haemodialysis experience a significant improvement in iron indices while receiving a significantly lower amount of intravenous iron when managed by a nurse prescriber. Furthermore, the nurse prescribers' decision-making capacity is as effective as a physician-led nonprotocol-based approach in achieving haemoglobin target levels.

RELEVANCE TO CLINICAL PRACTICE

Nurse prescribers have a role in implementing a safe, standardised and sustained approach to anaemia management in outpatient haemodialysis settings without compromising patient care.

Model-Informed Artificial Intelligence: Reinforcement Learning for Precision Dosing

The availability of multidimensional data together with the development of modern techniques for data analysis represent an exceptional opportunity for clinical pharmacology. Data science-defined in this special issue as the novel approaches to the collection, aggregation, and analysis of data-can significantly contribute to characterize drug-response variability at the individual level, thus enabling clinical pharmacology to become a critical contributor to personalized healthcare through precision dosing. We propose a minireview of methodologies for achieving precision dosing with a focus on an artificial intelligence technique called reinforcement learning, which is currently used for individualizing dosing regimen in patients with life-threatening diseases. We highlight the interplay of such techniques with conventional pharmacokinetic/pharmacodynamic approaches and discuss applicability in drug research and early development.

Role of Artificial Intelligence in Kidney Disease

Artificial intelligence (AI), as an advanced science technology, has been widely used in medical fields to promote medical development, mainly applied to early detections, disease diagnoses, and management. Owing to the huge number of patients, kidney disease remains a global health problem. Challenges remain in its diagnosis and treatment. AI could take individual conditions into account, produce suitable decisions and promise to make great strides in kidney disease management. Here, we review the current studies of AI applications in kidney disease in alerting systems, diagnostic assistance, guiding treatment and evaluating prognosis. Although the number of studies related to AI applications in kidney disease is small, the potential of AI in the management of kidney disease is well recognized by clinicians; AI will greatly enhance clinicians' capacity in their clinical practice in the future.

Artificial Intelligence in Nephrology: How Can Artificial Intelligence Augment Nephrologists' Intelligence?

BACKGROUND

Artificial intelligence (AI) now plays a critical role in almost every area of our daily lives and academic disciplines due to the growth of computing power, advances in methods and techniques, and the explosion of the amount of data; medicine is not an exception. Rather than replacing clinicians, AI is augmenting the intelligence of clinicians in diagnosis, prognosis, and treatment decisions.

SUMMARY

Kidney disease is a substantial medical and public health burden globally, with both acute kidney injury and chronic kidney disease bringing about high morbidity and mortality as well as a huge economic burden. Even though the existing research and applied works have made certain contributions to more accurate prediction and better understanding of histologic pathology, there is a lot more work to be done and problems to solve.

KEY MESSAGES

AI applications of diagnostics and prognostics for high-prevalence and high-morbidity types of nephropathy in medical-resource-inadequate areas need special attention; high-volume and high-quality data need to be collected and prepared; a consensus on ethics and safety in the use of AI technologies needs to be built.

History and application of artificial neural networks in dentistry

Artificial intelligence (AI) is a commonly used term in daily life, and there are now two subconcepts that divide the entire range of meanings currently encompassed by the term. The coexistence of the concepts of strong and weak AI can be seen as a result of the recognition of the limits of mathematical and engineering concepts that have dominated the definition. This presentation reviewed the concept, history, and the current application of AI in daily life. Applications of AI are becoming a reality that is commonplace in all areas of modern human life. Efforts to develop robots controlled by AI have been continuously carried out to maximize human convenience. AI has also been applied in the medical decision-making process, and these AI systems can help nonspecialists to obtain expert-level information. Artificial neural networks are highly interconnected networks of computer processors inspired by biological nervous systems. These systems may help connect dental professionals all over the world. Currently, the use of AI is rapidly advancing beyond text-based, image-based dental practice. This presentation reviewed the history of artificial neural networks in the medical and dental fields, as well as current application in dentistry. As the use of AI in the entire medical field increases, the role of AI in dentistry will be greatly expanded. Currently, the use of AI is rapidly advancing beyond text-based, image-based dental practice. In addition to diagnosis of visually confirmed dental caries and impacted teeth, studies applying machine learning based on artificial neural networks to dental treatment through analysis of dental magnetic resonance imaging, computed tomography, and cephalometric radiography are actively underway, and some visible results are emerging at a rapid pace for commercialization.

Artificial Intelligence in Nephrology: Core Concepts, Clinical Applications, and Perspectives

Artificial intelligence is playing an increasingly important role in many fields of medicine, assisting physicians in most steps of patient management. In nephrology, artificial intelligence can already be used to improve clinical care, hemodialysis prescriptions, and follow-up of transplant recipients. However, many nephrologists are still unfamiliar with the basic principles of medical artificial intelligence. This review seeks to provide an overview of medical artificial intelligence relevant to the practicing nephrologist, in all fields of nephrology. We define the core concepts of artificial intelligence and machine learning and cover the basics of the functioning of neural networks and deep learning. We also discuss the most recent clinical applications of artificial intelligence in nephrology and medicine; as an example, we describe how artificial intelligence can predict the occurrence of progressive immunoglobulin A nephropathy. Finally, we consider the future of artificial intelligence in clinical nephrology and its impact on medical practice, and conclude with a discussion of the ethical issues that the use of artificial intelligence raises in terms of clinical decision making, physician-patient relationship, patient privacy, and data collection.

A roadmap for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling

Predictive modeling based on machine learning with medical data has great potential to improve healthcare and reduce costs. However, two hurdles, among others, impede its widespread adoption in hdealthcare. First, medical data are by nature longitudinal. Pre-processing them, particularly for feature engineering, is labor intensive and often takes 50-80% of the model building effort. Predictive temporal features are the basis of building accurate models, but are difficult to identify. This is problematic. Healthcare systems have limited resources for model building, while inaccurate models produce sub-optimal outcomes and are often useless. Second, most machine learning models provide no explanation of their prediction results. However, offering such explanations is essential for a model to be used in usual clinical practice. To address these two hurdles, this paper outlines: 1) a data-driven method for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling; and 2) a method of using these features to automatically explain machine learning prediction results and suggest tailored interventions. This provides a roadmap for future research.

Personalized Anemia Management and Precision Medicine in ESA and Iron Pharmacology in End-Stage Kidney Disease

Substantial progress has been made in the application of computer-driven methods to provide erythropoietic dosing information for patients with anemia resulting from chronic kidney disease. Initial solutions were simply computerized versions of traditional paper-based anemia management protocols. True personalization was achieved through the use of advanced modeling techniques such as artificial neural networks, physiologic models, and feedback control systems. The superiority of any one technique over another has not been determined, but all methods have shown an advantage in at least one area over the traditional paper expert system used by most dialysis facilities. Improvements in the percentage of hemoglobin measurements within target range, decreased within-subject hemoglobin variability, decreased erythropoiesis-stimulating agent dose, and decreased transfusion rates all have been shown.

Individualized anemia management in a dialysis facility - long-term utility as a single-center quality improvement experience

Background: Standard protocol-based approaches to erythropoiesis stimulating agent (ESA) dosing in anemia management of end-stage renal disease (ESRD) fail to address the inter-individual variability in patient’s response to ESA. We conducted a single-center quality improvement project to investigate the long-term performance of a computer-designed dosing system. Materials and methods: The study was a retrospective case-control study with long-term follow-up. All hemodialysis patients who received treatment at University Kidney Center (Louisville, KY, USA) between September 1, 2009, and March 31, 2017, were included. We implemented an individualized ESA dosing algorithm into an electronic health records database software to provide patient-specific ESA dose recommendations to anemia managers at monthly intervals. The primary outcome was the percentage of hemoglobin (Hb) concentrations between 10 and 12 g/dL during the case-control study and 9 and 11 g/dL during follow-up. Secondary outcomes were intra- and inter-individual Hb variability. For the case-control study, we compared outcomes over 12 months before and after implementation of the algorithm. Subjects served as their own controls. We used the last Hb concentration of the month and ESA dose per week. Long-term follow-up examined trends in proportion within the target range, Hb, and ESA dose. Results: Individualized ESA dosing in 56 subjects was associated with a moderate (6.6%) increase of mean Hb maintenance within target over the 12-month observation period (62.7% before vs. 69.3% after, p = 0.063). Intra-individual mean Hb variability decreased (1.1 g/dL before vs. 0.8 g/dL after, p < 0.001), so did inter-individual mean Hb variability (1.2 g/dL before vs. 1.0 g/dL after, p = 0.010). Long-term follow-up in 233 subjects for 42 months demonstrated stability of the achieved Hb despite an increasing ESA resistance in the patient population. Conclusion: Implementation of the individualized ESA dosing algorithm facilitates improvement in Hb maintenance within target, decreases Hb variability and reduces the dose of ESA required to achieve Hb target.

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

Background

Fluid volume and blood pressure (BP) management are crucial endpoints for end-stage kidney disease patients. BP control in clinical practice mainly relies on reducing extracellular fluid volume overload by diminishing targeted postdialysis weight. This approach exposes dialysis patients to intradialytic hypotensive episodes.

Summary

Both chronic hypertension and intradialytic hypotension lead to adverse long-term outcomes. Achieving the optimal trade-off between adequate fluid removal and the risk of intradialytic adverse events is a complex task in clinical practice given the multiple patient-related and dialysis-related factors affecting the hemodynamic response to treatment. State-of-the-art artificial intelligence has been adopted in other complex decision-making tasks for dialysis patients and may help personalize the multiple dialysis-related prescriptions affecting patients' intradialytic hemodynamics. As a proof of concept, we developed a multiple-endpoint model predicting session-specific Kt/V, fluid volume removal, heart rate, and BP based on patient characteristics, historic hemodynamic responses, and dialysis-related prescriptions.

Key Messages

The accuracy and precision of this preliminary model is extremely encouraging. Such analytic tools may be used to anticipate patients' reactions through simulation so that the best strategy can be chosen based on clinical judgment or formal utility functions.

Progress in the Development and Challenges for the Use of Artificial Kidneys and Wearable Dialysis Devices

Background

Renal transplantation is the treatment of choice for chronic kidney disease (CKD) patients, but the shortage of kidneys and the disabling medical conditions these patients suffer from make dialysis essential for most of them. Since dialysis drastically affects the patients' lifestyle, there are great expectations for the development of wearable artificial kidneys, although their use is currently impeded by major concerns about safety. On the other hand, dialysis patients with hemodynamic instability do not usually tolerate intermittent dialysis therapy because of their inability to adapt to a changing scenario of unforeseen events. Thus, the development of novel wearable dialysis devices and the improvement of clinical tolerance will need contributions from new branches of engineering such as artificial intelligence (AI) and machine learning (ML) for the real-time analysis of equipment alarms, dialysis parameters, and patient-related data with a real-time feedback response. These technologies are endowed with abilities normally associated with human intelligence such as learning, problem solving, human speech understanding, or planning and decision-making. Examples of common applications of AI are visual perception (computer vision), speech recognition, and language translation. In this review, we discuss recent progresses in the area of dialysis and challenges for the use of AI in the development of artificial kidneys.

Summary and Key Messages

Emerging technologies derived from AI, ML, electronics, and robotics will offer great opportunities for dialysis therapy, but much innovation is needed before we achieve a smart dialysis machine able to analyze and understand changes in patient homeostasis and to respond appropriately in real time. Great efforts are being made in the fields of tissue engineering and regenerative medicine to provide alternative cell-based approaches for the treatment of renal failure, including bioartificial renal systems and the implantation of bioengineered kidney constructs.

Artificial-Intelligence-Based Prediction of Clinical Events among Hemodialysis Patients Using Non-Contact Sensor Data

Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16% with 96.21% mean precision, and 88.47% mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.

The anaemia control model: Does it help nephrologists in therapeutic decision-making in the management of anaemia?

INTRODUCTION

Anaemia is common in haemodialysis patients and treating it with erythropoiesis-stimulating agents (ESAs) is complex due to many factors.

OBJECTIVES

To assess the usefulness of the Anaemia Control Model (ACM) in the treatment of anaemia in haemodialysis.

METHODS

ACM is a software that predicts the optimal dose of darbepoetin and iron sucrose to achieve target haemoglobin (Hb) and ferritin levels, and makes prescription suggestions. Study conducted in dialysis clinics lasting 18months with two intervention phases (IPs) with ACM (IP1, n:213; IP2, n:218) separated by a control phase (CP, n:219). The primary outcome was the percentage of Hb in range and the median dose of ESAs, and the secondary outcomes were transfusion, hospitalisation and cardiovascular events. Clinical and patient analyses were performed. Hb variability was assessed by the standard deviation (SD) of the Hb. We also analysed the patients with most of the suggestions confirmed (ACM compliant group).

RESULTS

ACM increased the percentage of Hb in range: 80.9% in IP2, compared with 72.7% in the CP and reduced the intake of darbepoetin (IP1: 20 [70]; CP 30 [80] μg P=0.032) with less Hb fluctuation (0.91±0.49 in the CP to 0.82±0.37g/dl in IP2, P<0.05), improving in the ACM compliant group. The secondary outcomes decreased with the use of ACM.

CONCLUSIONS

ACM helps to obtain better anaemia results in haemodialysis patients, minimising the risks of treatment with ESAs and reducing costs.

Artificial Intelligence for the Artificial Kidney: Pointers to the Future of a Personalized Hemodialysis Therapy

Background

Current dialysis devices are not able to react when unexpected changes occur during dialysis treatment or to learn about experience for therapy personalization. Furthermore, great efforts are 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, a branch of engineering involved with the creation of devices that simulate intelligent behavior. The incorporation of artificial intelligence should provide a fully new approach to data analysis, enabling future advances in personalized dialysis therapies. With the purpose to learn about the present and potential future impact on medicine from experts in artificial intelligence and machine learning, a scientific meeting was organized in the Hospital Universitari Bellvitge (L'Hospitalet, Barcelona). As an outcome of that meeting, the aim of this review is to investigate artificial intel ligence experiences on dialysis, with a focus on potential barriers, challenges, and prospects for future applications of these technologies.

Summary and Key Messages

Artificial intelligence 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. Artificial neural networks and medical decision support systems have been used to make predictions about anemia, total body water, or intradialysis hypotension and are promising approaches for the prescription and monitoring of hemodialysis therapy. Current dialysis machines are continuously improving due to innovative technological developments, but patient safety is still a key challenge. 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.

Beyond playing games: nephrologist vs machine in pediatric dialysis prescribing

In a recent article in Pediatric Nephrology, Olivier Niel and colleagues applied an artificial intelligence algorithm to a clinical problem that continues to challenge experienced pediatric nephrologists: optimizing the target weight of children on dialysis. They compared blood pressure, antihypertensive medication and intradialytic symptoms in children whose target weight was prescribed firstly by a nephrologist, then subsequently using a machine learning algorithm. Improvements in all outcome measures are reported. Their innovative approach to tackling this important clinical problem appears promising. In this editorial, we discuss the strengths and weaknesses of their study and consider to what extent machine learning strategies are suited to optimizing pediatric dialysis outcomes.

Developing a classification system for haemoglobin management in patients with end-stage renal disease on haemodialysis: a secondary data analysis

BACKGROUND

Ongoing discussion on anaemia management and target haemoglobin (Hb) levels in patients on haemodialysis with erythropoietin treatment require a systematic approach in evaluating current practice. Aim of the present study was to develop a new classification system to easily monitor Hb trajectories and categorise patients on haemodialysis.

METHODS

Routine data from five dialysis centres in the USA collected between 2010 and 2016. Data were anonymised and only those from patients with fortnightly Hb values were included in the analysis. Entries on blood parameters and medication were standardised to achieve overall comparability. Data from each patient was grouped in periods of 120 days. Hb values above or below the target level of 10-12 g/dL were counted for each period. Periods were then assigned to Hb-classes according to the number of Hb values out of range per period: Hb-class I with 0-2, Hb-class II for 3-5 and Hb-class III for ≥6 values out of range.

RESULTS

Records from 3349 patients with fortnightly Hb values, information on haemodialysis data, laboratory parameters correlated to red blood cells and data on medication with erythropoiesis-stimulating agents (ESAs) were available. Patients were 64.4±15.9 years old; 55.0% were men. Statistical analysis revealed significant differences between Hb-classes in all of the examined parameters, except erythrocytes mean corpuscular volume and C reactive protein above the threshold, with more critical values in higher Hb-classes. The usage of ESAs showed a mean difference between Hb-class III and Hb-class I of 6.4 units/day and kilogram body weight in a 120-day period.

CONCLUSION

Our classification system allows an easily achievable overview of the patients' responsiveness and performance of Hb management. Integrated into a disease management programme or continuous quality improvement, the classification delivers an instant appraisal without complex statistical or mathematical processing.

Automating Construction of Machine Learning Models With Clinical Big Data: Proposal Rationale and Methods

Background

To improve health outcomes and cut health care costs, we often need to conduct prediction/classification using large clinical datasets (aka, clinical big data), for example, to identify high-risk patients for preventive interventions. Machine learning has been proposed as a key technology for doing this. Machine learning has won most data science competitions and could support many clinical activities, yet only 15% of hospitals use it for even limited purposes. Despite familiarity with data, health care researchers often lack machine learning expertise to directly use clinical big data, creating a hurdle in realizing value from their data. Health care researchers can work with data scientists with deep machine learning knowledge, but it takes time and effort for both parties to communicate effectively. Facing a shortage in the United States of data scientists and hiring competition from companies with deep pockets, health care systems have difficulty recruiting data scientists. Building and generalizing a machine learning model often requires hundreds to thousands of manual iterations by data scientists to select the following: (1) hyper-parameter values and complex algorithms that greatly affect model accuracy and (2) operators and periods for temporally aggregating clinical attributes (eg, whether a patient’s weight kept rising in the past year). This process becomes infeasible with limited budgets.

Objective

This study’s goal is to enable health care researchers to directly use clinical big data, make machine learning feasible with limited budgets and data scientist resources, and realize value from data.

Methods

This study will allow us to achieve the following: (1) finish developing the new software, Automated Machine Learning (Auto-ML), to automate model selection for machine learning with clinical big data and validate Auto-ML on seven benchmark modeling problems of clinical importance; (2) apply Auto-ML and novel methodology to two new modeling problems crucial for care management allocation and pilot one model with care managers; and (3) perform simulations to estimate the impact of adopting Auto-ML on US patient outcomes.

Results

We are currently writing Auto-ML’s design document. We intend to finish our study by around the year 2022.

Conclusions

Auto-ML will generalize to various clinical prediction/classification problems. With minimal help from data scientists, health care researchers can use Auto-ML to quickly build high-quality models. This will boost wider use of machine learning in health care and improve patient outcomes.