A new machine learning approach for predicting the response to anemia treatment in a large cohort of End Stage Renal Disease patients undergoing dialysis

Artificial Intelligence in the Intensive Care Unit: Current Evidence on an Inevitable Future Tool

Artificial intelligence (AI) is a technique that attempts to replicate human intelligence, analytical behavior, and decision-making ability. This includes machine learning, which involves the use of algorithms and statistical techniques to enhance the computer's ability to make decisions more accurately. Due to AI's ability to analyze, comprehend, and interpret considerable volumes of data, it has been increasingly used in the field of healthcare. In critical care medicine, where most of the patient load requires timely interventions due to the perilous nature of the condition, AI's ability to monitor, analyze, and predict unfavorable outcomes is an invaluable asset. It can significantly improve timely interventions and prevent unfavorable outcomes, which, otherwise, is not always achievable owing to the constrained human ability to multitask with optimum efficiency. AI has been implicated in intensive care units over the past many years. In addition to its advantageous applications, this article discusses its disadvantages, prospects, and the changes needed to train future critical care professionals. A comprehensive search of electronic databases was performed using relevant keywords. Data from articles pertinent to the topic was assimilated into this review article.

Early erythroferrone levels can predict the long-term haemoglobin responses to erythropoiesis-stimulating agents

BACKGROUND AND PURPOSE

Our previous study reported that erythroferrone (ERFE), a newly identified hormone produced by erythroblasts, responded to recombinant human erythropoietin (rHuEPO) sensitively but its dynamics was complicated by double peaks and circadian rhythm. This study intends to elucidate the underlying mechanisms for the double peaks of ERFE dynamics and further determine whether early ERFE measurements can predict haemoglobin responses to rHuEPO.

EXPERIMENTAL APPROACH

By using the purified recombinant rat ERFE protein and investigating its deposition in rats, the production of ERFE was deconvoluted. To explore the role of iron in ERFE production, we monitored short-term changes of iron status after injection of rHuEPO or deferiprone. Pharmacokinetic/pharmacodynamic (PK/PD) modelling was used to confirm the mechanisms and examine the predictive ability of ERFE for long-term haemoglobin responses.

KEY RESULTS

The rRatERFE protein was successfully purified. The production of ERFE was deconvoluted and showed two independent peaks (2 and 8 h). Transient iron decrease was observed at 4 h after rHuEPO injection and deferiprone induced significant increases of ERFE. Based on this mechanism, the PK/PD model could characterize the complex dynamics of ERFE. In addition, the model predictions further revealed a stronger correlation between ERFE and haemoglobin peak values than that for observed values.

CONCLUSIONS AND IMPLICATIONS

The complex dynamics of ERFE should be composited by an immediate release and transient iron deficiency-mediated secondary production of ERFE. The early peak values of ERFE, which occur within a few hours, can predict haemoglobin responses several weeks after ESA treatment.

The Use of Anemia Control Model Is Associated with Improved Hemoglobin Target Achievement, Lower Rates of Inappropriate Erythropoietin Stimulating Agents, and Severe Anemia among Dialysis Patients

INTRODUCTION

The Anemia Control Model (ACM) is a certified medical device suggesting the optimal ESA and iron dosage for patients on hemodialysis. We sought to assess the effectiveness and safety of ACM in a large cohort of hemodialysis patients.

METHODS

This is a retrospective study of dialysis patients treated in NephroCare centers between June 1, 2013 and December 31, 2019. We compared patients treated according to ACM suggestions and patients treated in clinics where ACM was not activated. We stratified patients belonging to the reference group by historical target achievement rates in their referral centers (tier 1: <70%; tier 2: 70-80%; tier 3: >80%). Groups were matched by propensity score.

RESULTS

After matching, we obtained four groups with 85,512 patient-months each. ACM had 18% higher target achievement rate, 63% smaller inappropriate ESA administration rate, and 59% smaller severe anemia risk compared to Tier 1 centers (all p < 0.01). The corresponding risk ratios for ACM compared to Tier 2 centers were 1.08 (95% CI: 1.08-1.09), 0.49 (95% CI: 0.47-0.51), and 0.64 (95% CI: 0.61-0.68); for ACM compared to Tier 3 centers, 1.01 (95% CI: 1.01-1.02), 0.66 (95% CI: 0.63-0.69), and 0.94 (95% CI: 0.88-1.00), respectively. ACM was associated with statistically significant reductions in ESA dose administration.

CONCLUSION

ACM was associated with increased hemoglobin target achievement rate, decreased inappropriate ESA usage and a decreased incidence of severe anemia among patients treated according to ACM suggestion.

Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review

OBJECTIVES

In this systematic review we aimed at assessing how artificial intelligence (AI), including machine learning (ML) techniques have been deployed to predict, diagnose, and treat chronic kidney disease (CKD). We systematically reviewed the available evidence on these innovative techniques to improve CKD diagnosis and patient management.

METHODS

We included English language studies retrieved from PubMed. The review is therefore to be classified as a "rapid review", since it includes one database only, and has language restrictions; the novelty and importance of the issue make missing relevant papers unlikely. We extracted 16 variables, including: main aim, studied population, data source, sample size, problem type (regression, classification), predictors used, and performance metrics. We followed the Preferred Reporting Items for Systematic Reviews (PRISMA) approach; all main steps were done in duplicate.

RESULTS

From a total of 648 studies initially retrieved, 68 articles met the inclusion criteria. Models, as reported by authors, performed well, but the reported metrics were not homogeneous across articles and therefore direct comparison was not feasible. The most common aim was prediction of prognosis, followed by diagnosis of CKD. Algorithm generalizability, and testing on diverse populations was rarely taken into account. Furthermore, the clinical evaluation and validation of the models/algorithms was perused; only a fraction of the included studies, 6 out of 68, were performed in a clinical context.

CONCLUSIONS

Machine learning is a promising tool for the prediction of risk, diagnosis, and therapy management for CKD patients. Nonetheless, future work is needed to address the interpretability, generalizability, and fairness of the models to ensure the safe application of such technologies in routine clinical practice.

ESKD Risk Prediction Model in a Multicenter Chronic Kidney Disease Cohort in China: A Derivation, Validation, and Comparison Study

BACKGROUND AND OBJECTIVES

In light of the growing burden of chronic kidney disease (CKD), it is of particular importance to create disease prediction models that can assist healthcare providers in identifying cases of CKD individual risk and integrate risk-based care for disease progress management. The objective of this study was to develop and validate a new pragmatic end-stage kidney disease (ESKD) risk prediction utilizing the Cox proportional hazards model (Cox) and machine learning (ML).

DESIGN, SETTING, PARTICIPANTS, AND MEASUREMENTS

The Chinese Cohort Study of Chronic Kidney Disease (C-STRIDE), a multicenter CKD cohort in China, was employed as the model's training and testing datasets, with a split ratio of 7:3. A cohort from Peking University First Hospital (PKUFH cohort) served as the external validation dataset. The participants' laboratory tests in those cohorts were conducted at PKUFH. We included individuals with CKD stages 1~4 at baseline. The incidence of kidney replacement therapy (KRT) was defined as the outcome. We constructed the Peking University-CKD (PKU-CKD) risk prediction model employing the Cox and ML methods, which include extreme gradient boosting (XGBoost) and survival support vector machine (SSVM). These models discriminate metrics by applying Harrell's concordance index (Harrell's C-index) and Uno's concordance (Uno's C). The calibration performance was measured by the Brier score and plots.

RESULTS

Of the 3216 C-STRIDE and 342 PKUFH participants, 411 (12.8%) and 25 (7.3%) experienced KRT with mean follow-up periods of 4.45 and 3.37 years, respectively. The features included in the PKU-CKD model were age, gender, estimated glomerular filtration rate (eGFR), urinary albumin-creatinine ratio (UACR), albumin, hemoglobin, medical history of type 2 diabetes mellitus (T2DM), and hypertension. In the test dataset, the values of the Cox model for Harrell's C-index, Uno's C-index, and Brier score were 0.834, 0.833, and 0.065, respectively. The XGBoost algorithm values for these metrics were 0.826, 0.825, and 0.066, respectively. The SSVM model yielded values of 0.748, 0.747, and 0.070, respectively, for the above parameters. The comparative analysis revealed no significant difference between XGBoost and Cox, in terms of Harrell's C, Uno's C, and the Brier score (p = 0.186, 0.213, and 0.41, respectively) in the test dataset. The SSVM model was significantly inferior to the previous two models (p < 0.001), in terms of discrimination and calibration. The validation dataset showed that XGBoost was superior to Cox, regarding Harrell's C, Uno's C, and the Brier score (p = 0.003, 0.027, and 0.032, respectively), while Cox and SSVM were almost identical concerning these three parameters (p = 0.102, 0.092, and 0.048, respectively).

CONCLUSIONS

We developed and validated a new ESKD risk prediction model for patients with CKD, employing commonly measured indicators in clinical practice, and its overall performance was satisfactory. The conventional Cox regression and certain ML models exhibited equal accuracy in predicting the course of CKD.

Multi-head self-attention mechanism enabled individualized hemoglobin prediction and treatment recommendation systems in anemia management for hemodialysis patients

Anemia is a critical complication in hemodialysis patients, but the response to erythropoietin-stimulating agents (ESA) treatment varies from patient to patient and is not linear across different time points. The aim of this study was to develop deep learning algorithms for individualized anemia management. We retrospectively collected 36,677 data points from 623 hemodialysis patients, including clinical data, laboratory values, hemoglobin levels, and previous ESA doses. To reduce the computational complexity associated with recurrent neural networks (RNN) in processing time-series data, we developed neural networks based on multi-head self-attention mechanisms in an efficient and effective hemoglobin prediction model. Our proposed model achieved a more accurate hemoglobin prediction than the state-of-the-art RNN model, as shown by the smaller mean absolute error (MAE) of hemoglobin (0.451 vs. 0.593 g/dL, p = 0.014). In ESA (including darbepoetin and epoetin) dose recommendation, the simulation results by our model revealed a higher rate of achieved hemoglobin targets (physician prescription vs. model: 86.3 % vs. 92.7 %, p < 0.001), a lower rate of hemoglobin levels below 10 g/dL (13.7 % vs. 7.3 %, p < 0.001) and smaller change in hemoglobin levels (0.6 g/dL vs. 0.4 g/dL, p < 0.001) in all patients. Our model holds great potential for individualized anemia management as a computerized clinical decision support system for hemodialysis patients. Further external validation with other datasets and prospective clinical utility studies are warranted.

Model for Predicting Complications of Hemodialysis Patients Using Data From the Internet of Medical Things and Electronic Medical Records

Intelligent models for predicting hemodialysis-related complications, i.e., hypotension and the deterioration of the quality or obstruction of the AV fistula, based on machine learning (ML) methods were established to offer early warnings to medical staff and give them enough time to provide pre-emptive treatment. A novel integration platform collected data from the Internet of Medical Things (IoMT) at a dialysis center and inspection results from electronic medical records (EMR) to train ML algorithms and build models. The selection of the feature parameters was implemented using Pearson's correlation method. Then, the eXtreme Gradient Boost (XGBoost) algorithm was chosen to create the predictive models and optimize the feature choice. 75% of collected data are used as a training dataset and the other 25% are used as a testing dataset. We adopted the prediction precision and recall rate of hypotension and AV fistula obstruction to measure the effectiveness of the predictive models. These rates were sufficiently high at approximately 71%-90%. In the context of hemodialysis, hypotension and the deterioration of the quality or obstruction of the arteriovenous (AV) fistula affect treatment quality and patient safety and may lead to a poor prognosis. Our prediction models with high accuracies can provide excellent references and signals for clinical healthcare service providers. Clinical and Translational Impact Statement-With the integrated dataset collected from IoMT and EMR, the superior predictive results of our models for complications of hemodialysis patients are demonstrated. We believe, after enough clinical tests are implemented as planned, these models can assist the healthcare team in making appropriate preparations in advance or adjusting the medical procedures to avoid these adverseevents.

Physician Compliance with Computerized Clinical Decision Support System is a Complete Intermediate Factor in the Anemia Management of Patients with End-Stage Kidney Disease on Hemodialysis: A Retrospective Electronic Health Record Observational Study (Preprint)

BACKGROUND

Previous studies on clinical decision support systems (CDSSs) for the management of renal anemia in patients with end-stage kidney disease undergoing hemodialysis have previously focused solely on the effects of the CDSS. However, the role of physician compliance in the efficacy of the CDSS remains ill-defined.

OBJECTIVE

We aimed to investigate whether physician compliance was an intermediate variable between the CDSS and the management outcomes of renal anemia.

METHODS

We extracted the electronic health records of patients with end-stage kidney disease on hemodialysis at the Far Eastern Memorial Hospital Hemodialysis Center (FEMHHC) from 2016 to 2020. FEMHHC implemented a rule-based CDSS for the management of renal anemia in 2019. We compared the clinical outcomes of renal anemia between the pre- and post-CDSS periods using random intercept models. Hemoglobin levels of 10 to 12 g/dL were defined as the on-target range. Physician compliance was defined as the concordance of adjustments of the erythropoietin-stimulating agent (ESA) between the CDSS recommendations and the actual physician prescriptions.

RESULTS

We included 717 eligible patients on hemodialysis (mean age 62.9, SD 11.6 years; male n=430, 59.9%) with a total of 36,091 hemoglobin measurements (average hemoglobin and on-target rate were 11.1, SD 1.4, g/dL and 59.9%, respectively). The on-target rate decreased from 61.3% (pre-CDSS) to 56.2% (post-CDSS) owing to a high hemoglobin percentage of >12 g/dL (pre: 21.5%; post: 29%). The failure rate (hemoglobin <10 g/dL) decreased from 17.2% (pre-CDSS) to 14.8% (post-CDSS). The average weekly ESA use of 5848 (SD 4211) units per week did not differ between phases. The overall concordance between CDSS recommendations and physician prescriptions was 62.3%. The CDSS concordance increased from 56.2% to 78.6%. In the adjusted random intercept model, the post-CDSS phase showed increased hemoglobin by 0.17 (95% CI 0.14-0.21) g/dL, weekly ESA by 264 (95% CI 158-371) units per week, and 3.4-fold (95% CI 3.1-3.6) increased concordance rate. However, the on-target rate (29%; odds ratio 0.71, 95% CI 0.66-0.75) and failure rate (16%; odds ratio 0.84, 95% CI 0.76-0.92) were reduced. After additional adjustments for concordance in the full models, increased hemoglobin and decreased on-target rate tended toward attenuation (from 0.17 to 0.13 g/dL and 0.71 to 0.73 g/dL, respectively). Increased ESA and decreased failure rate were completely mediated by physician compliance (from 264 to 50 units and 0.84 to 0.97, respectively).

CONCLUSIONS

Our results confirmed that physician compliance was a complete intermediate factor accounting for the efficacy of the CDSS. The CDSS reduced failure rates of anemia management through physician compliance. Our study highlights the importance of optimizing physician compliance in the design and implementation of CDSSs to improve patient outcomes.

Recent Advances and Future Perspectives in the Use of Machine Learning and Mathematical Models in Nephrology

We reviewed some of the latest advancements in the use of mathematical models in nephrology. We looked over 2 distinct categories of mathematical models that are widely used in biological research and pointed out some of their strengths and weaknesses when applied to health care, especially in the context of nephrology. A mechanistic dynamical system allows the representation of causal relations among the system variables but with a more complex and longer development/implementation phase. Artificial intelligence/machine learning provides predictive tools that allow identifying correlative patterns in large data sets, but they are usually harder-to-interpret black boxes. Chronic kidney disease (CKD), a major worldwide health problem, generates copious quantities of data that can be leveraged by choice of the appropriate model; also, there is a large number of dialysis parameters that need to be determined at every treatment session that can benefit from predictive mechanistic models. Following important steps in the use of mathematical methods in medical science might be in the intersection of seemingly antagonistic frameworks, by leveraging the strength of each to provide better care.

The Efficacy of Machine-Learning-Supported Smart System for Heart Disease Prediction

The disease may be an explicit status that negatively affects human health. Cardiopathy is one of the common deadly diseases that is attributed to unhealthy human habits compared to alternative diseases. With the help of machine learning (ML) algorithms, heart disease can be noticed in a short time as well as at a low cost. This study adopted four machine learning models, such as random forest (RF), decision tree (DT), AdaBoost (AB), and K-nearest neighbor (KNN), to detect heart disease. A generalized algorithm was constructed to analyze the strength of the relevant factors that contribute to heart disease prediction. The models were evaluated using the datasets Cleveland, Hungary, Switzerland, and Long Beach (CHSLB), and all were collected from Kaggle. Based on the CHSLB dataset, RF, DT, AB, and KNN models predicted an accuracy of 99.03%, 96.10%, 100%, and 100%, respectively. In the case of a single (Cleveland) dataset, only two models, namely RF and KNN, show good accuracy of 93.437% and 97.83%, respectively. Finally, the study used Streamlit, an internet-based cloud hosting platform, to develop a computer-aided smart system for disease prediction. It is expected that the proposed tool together with the ML algorithm will play a key role in diagnosing heart diseases in a very convenient manner. Above all, the study has made a substantial contribution to the computation of strength scores with significant predictors in the prognosis of heart disease.

Developing neural network model for predicting cardiac and cardiovascular health using bioelectrical signal processing

Coronary vascular disease (CHD) is one of the most fatal diseases worldwide. Cardio vascular diseases are not easily diagnosed in early disease stages. Early diagnosis is important for effective treatment, however, medical diagnoses are based on physician's personal experiences of the disease which increase time and testing cost to reach diagnosis. Physicians assess patients' condition based on electrocardiography, sonography and blood test results. In this research we develop classification model of the functional state of the cardiovascular system based on the monitoring of the evolution of the amplitudes of the first and second harmonics of the system rhythm of 0.1 Hz. We separate the signal to three streams; the first stream works with natural electro cardio signal, the other two streams are obtained as a result of frequency analysis of the amplitude- and frequency-detected electro cardio signal. We use sliding window of a demodulated electro cardio signal by means of amplitude and frequency detectors. The developed NN model showed an increase in accuracy of diagnostic efficiency by 11%. The neural network model can be trained to give accurate early detection of disease class.

Machine Learning Analysis of Time-Dependent Features for Predicting Adverse Events During Hemodialysis Therapy: Model Development and Validation Study

BACKGROUND

Hemodialysis (HD) therapy is an indispensable tool used in critical care management. Patients undergoing HD are at risk for intradialytic adverse events, ranging from muscle cramps to cardiac arrest. So far, there is no effective HD device-integrated algorithm to assist medical staff in response to these adverse events a step earlier during HD.

OBJECTIVE

We aimed to develop machine learning algorithms to predict intradialytic adverse events in an unbiased manner.

METHODS

Three-month dialysis and physiological time-series data were collected from all patients who underwent maintenance HD therapy at a tertiary care referral center. Dialysis data were collected automatically by HD devices, and physiological data were recorded by medical staff. Intradialytic adverse events were documented by medical staff according to patient complaints. Features extracted from the time series data sets by linear and differential analyses were used for machine learning to predict adverse events during HD.

RESULTS

Time series dialysis data were collected during the 4-hour HD session in 108 patients who underwent maintenance HD therapy. There were a total of 4221 HD sessions, 406 of which involved at least one intradialytic adverse event. Models were built by classification algorithms and evaluated by four-fold cross-validation. The developed algorithm predicted overall intradialytic adverse events, with an area under the curve (AUC) of 0.83, sensitivity of 0.53, and specificity of 0.96. The algorithm also predicted muscle cramps, with an AUC of 0.85, and blood pressure elevation, with an AUC of 0.93. In addition, the model built based on ultrafiltration-unrelated features predicted all types of adverse events, with an AUC of 0.81, indicating that ultrafiltration-unrelated factors also contribute to the onset of adverse events.

CONCLUSIONS

Our results demonstrated that algorithms combining linear and differential analyses with two-class classification machine learning can predict intradialytic adverse events in quasi-real time with high AUCs. Such a methodology implemented with local cloud computation and real-time optimization by personalized HD data could warn clinicians to take timely actions in advance.

Erythropoiesis stimulating agent recommendation model using recurrent neural networks for patient with kidney failure with replacement therapy

In patients with kidney failure with replacement therapy (KFRT), optimizing anemia management in these patients is a challenging problem because of the complexities of the underlying diseases and heterogeneous responses to erythropoiesis-stimulating agents (ESAs). Therefore, we propose a ESA dose recommendation model based on sequential awareness neural networks. Data from 466 KFRT patients (12,907 dialysis sessions) in seven tertiary-care general hospitals were included in the experiment. First, a Hb prediction model was developed to simulate longitudinal heterogeneous ESA and Hb interactions. Based on the prediction model as a prospective study simulator, we built an ESA dose recommendation model to predict the required amount of ESA dose to reach a target hemoglobin level after 30 days. Each model's performance was evaluated in the mean absolute error (MAE). The MAEs presenting the best results of the prediction and recommendation model were 0.59 (95% confidence interval: 0.56-0.62) g/dL and 43.2 μg (ESAs dose), respectively. Compared to the results in the real-world clinical data, the recommendation model achieved a reduction of ESA dose (Algorithm: 140 vs. Human: 150 μg/month, P < 0.001), a more stable monthly Hb difference (Algorithm: 0.6 vs. Human: 0.8 g/dL, P < 0.001), and an improved target Hb success rate (Algorithm: 79.5% vs. Human: 62.9% for previous month's Hb < 10.0 g/dL; Algorithm: 95.7% vs. Human:73.0% for previous month's Hb 10.0-12.0 g/dL). We developed an ESA dose recommendation model for optimizing anemia management in patients with KFRT and showed its potential effectiveness in a simulated prospective study.

Predicting Kidney Discard Using Machine Learning

BACKGROUND

Despite the kidney supply shortage, 18%-20% of deceased donor kidneys are discarded annually in the United States. In 2018, 3569 kidneys were discarded.

METHODS

We compared machine learning (ML) techniques to identify kidneys at risk of discard at the time of match run and after biopsy and machine perfusion results become available. The cohort consisted of adult deceased donor kidneys donated between December 4, 2014, and July 1, 2019. The studied ML models included Random Forests (RF), Adaptive Boosting (AdaBoost), Neural Networks (NNet), Support Vector Machines (SVM), and K-nearest Neighbors (KNN). In addition, a Logistic Regression (LR) model was fitted and used for comparison with the ML models' performance.

RESULTS

RF outperformed other ML models. Of 8036 discarded kidneys in the test dataset, LR correctly classified 3422 kidneys, whereas RF correctly classified 4762 kidneys (area under the receiver operative curve [AUC]: 0.85 versus 0.888, and balanced accuracy: 0.681 versus 0.759). For the kidneys with kidney donor profile index of >85% (6079 total), RF significantly outperformed LR in classifying discard and transplant prediction (AUC: 0.814 versus 0.717, and balanced accuracy: 0.732 versus 0.657). More than 388 kidneys were correctly classified using RF. Including biopsy and machine perfusion variables improved the performance of LR and RF (LR's AUC: 0.888 and balanced accuracy: 0.74 versus RF's AUC: 0.904 and balanced accuracy: 0.775).

CONCLUSIONS

Kidneys that are at risk of discard can be more accurately identified using ML techniques such as RF.

Opportunities in the cloud or pie in the sky? Current status and future perspectives of telemedicine in nephrology

The use of telehealth to support, enhance or substitute traditional methods of delivering healthcare is becoming increasingly common in many specialties, such as stroke care, radiology and oncology. There is reason to believe that this approach remains underutilized within nephrology, which is somewhat surprising given the fact that nephrologists have always driven technological change in developing dialysis technology. Despite the obvious benefits that telehealth may provide, robust evidence remains lacking and many of the studies are anecdotal, limited to small numbers or without conclusive proof of benefit. More worryingly, quite a few studies report unexpected obstacles, pitfalls or patient dissatisfaction. However, with increasing global threats such as climate change and infectious disease, a change in approach to delivery of healthcare is needed. The current pandemic with coronavirus disease 2019 (COVID-19) has prompted the renal community to embrace telehealth to an unprecedented extent and at speed. In that sense the pandemic has already served as a disruptor, changed clinical practice and shown immense transformative potential. Here, we provide an update on current evidence and use of telehealth within various areas of nephrology globally, including the fields of dialysis, inpatient care, virtual consultation and patient empowerment. We also provide a brief primer on the use of artificial intelligence in this context and speculate about future implications. We also highlight legal aspects and pitfalls and discuss the 'digital divide' as a key concept that healthcare providers need to be mindful of when providing telemedicine-based approaches. Finally, we briefly discuss the immediate use of telenephrology at the onset of the COVID-19 pandemic. We hope to provide clinical nephrologists with an overview of what is currently available, as well as a glimpse into what may be expected in the future.

Machine learning in nephrology: scratching the surface

Machine learning shows enormous potential in facilitating decision-making regarding kidney diseases. With the development of data preservation and processing, as well as the advancement of machine learning algorithms, machine learning is expected to make remarkable breakthroughs in nephrology. Machine learning models have yielded many preliminaries to moderate and several excellent achievements in the fields, including analysis of renal pathological images, diagnosis and prognosis of chronic kidney diseases and acute kidney injury, as well as management of dialysis treatments. However, it is just scratching the surface of the field; at the same time, machine learning and its applications in renal diseases are facing a number of challenges. In this review, we discuss the application status, challenges and future prospects of machine learning in nephrology to help people further understand and improve the capacity for prediction, detection, and care quality in kidney diseases.

Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 2-Comparison of the Performance of Artificial Intelligence and Traditional Pharmacoepidemiological Techniques

Aim: To summarize the evidence on the performance of artificial intelligence vs. traditional pharmacoepidemiological techniques.

Methods: Ovid MEDLINE (01/1950 to 05/2019) was searched to identify observational studies, meta-analyses, and clinical trials using artificial intelligence techniques having a drug as the exposure or the outcome of the study. Only studies with an available full text in the English language were evaluated.

Results: In all, 72 original articles and five reviews were identified via Ovid MEDLINE of which 19 (26.4%) compared the performance of artificial intelligence techniques with traditional pharmacoepidemiological methods. In total, 44 comparisons have been performed in articles that aimed at 1) predicting the needed dosage given the patient’s characteristics (31.8%), 2) predicting the clinical response following a pharmacological treatment (29.5%), 3) predicting the occurrence/severity of adverse drug reactions (20.5%), 4) predicting the propensity score (9.1%), 5) identifying subpopulation more at risk of drug inefficacy (4.5%), 6) predicting drug consumption (2.3%), and 7) predicting drug-induced lengths of stay in hospital (2.3%). In 22 out of 44 (50.0%) comparisons, artificial intelligence performed better than traditional pharmacoepidemiological techniques. Random forest (seven out of 11 comparisons; 63.6%) and artificial neural network (six out of 10 comparisons; 60.0%) were the techniques that in most of the comparisons outperformed traditional pharmacoepidemiological methods.

Conclusion: Only a small fraction of articles compared the performance of artificial intelligence techniques with traditional pharmacoepidemiological methods and not all artificial intelligence techniques have been compared in a Pharmacoepidemiological setting. However, in 50% of comparisons, artificial intelligence performed better than pharmacoepidemiological techniques.

Sodium, volume and pressure control in haemodialysis patients for improved cardiovascular outcomes

Chronic volume overload is pervasive in patients on chronic haemodialysis and substantially increases the risk of cardiovascular death. The rediscovery of the three-compartment model in sodium metabolism revolutionizes our understanding of sodium (patho-)physiology and is an effect modifier that still needs to be understood in the context of hypertension and end-stage kidney disease. Assessment of fluid overload in haemodialysis patients is central yet difficult to achieve, because traditional clinical signs of volume overload lack sensitivity and specificity. The highest all-cause mortality risk may be found in haemodialysis patients presenting with high fluid overload but low blood pressure before haemodialysis treatment. The second highest risk may be found in patients with both high blood pressure and fluid overload, while high blood pressure but normal fluid overload may only relate to moderate risk. Optimization of fluid overload in haemodialysis patients should be guided by combining the traditional clinical evaluation with objective measurements such as bioimpedance spectroscopy in assessing the risk of fluid overload. To overcome the tide of extracellular fluid, the concept of time-averaged fluid overload during the interdialytic period has been established and requires possible readjustment of a negative target post-dialysis weight. ²³Na-magnetic resonance imaging studies will help to quantitate sodium accumulation and keep prescribed haemodialytic sodium mass balance on the radar. Cluster-randomization trials (e.g. on sodium removal) are underway to improve our therapeutic approach to cardioprotective haemodialysis management.

Enhanced prediction of hemoglobin concentration in a very large cohort of hemodialysis patients by means of deep recurrent neural networks

Erythropoiesis Stimulating Agents (ESAs) have become a standard anemia management tool for End Stage Renal Disease (ESRD) patients. However, dose optimization constitutes an extremely challenging task due to huge inter and intra-patient variability in the responses to ESA administration. Current data-based approaches to anemia control focus on learning accurate hemoglobin prediction models, which can be later utilized for testing competing treatment choices and choosing the optimal one. These methods, despite being proven effective in practice, present several shortcomings which this paper intends to tackle. Namely, they are limited to a small cohort of patients and, even then, they fail to provide suggestions when some strict requirements are not met (such as having a three month history prior to the prediction). Here, recurrent neural networks (RNNs) are used to model whole patient histories, providing predictions at every time step since the very first day. Furthermore, an unprecedented amount of data (∼110,000 patients from many different medical centers in twelve countries, without exclusion criteria) was used to train it, thus allowing it to generalize for every single patient. The resulting model outperforms state-of-the-art Hemoglobin prediction, providing excellent results even when tested on a prospective dataset. Simultaneously, it allows to bring the benefits of algorithmic anemia control to a very large group of patients.

Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 1-Overview of Knowledge Discovery Techniques in Artificial Intelligence

Aim

To perform a systematic review on the application of artificial intelligence (AI) based knowledge discovery techniques in pharmacoepidemiology.

Study Eligibility Criteria

Clinical trials, meta-analyses, narrative/systematic review, and observational studies using (or mentioning articles using) artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data Sources

Articles recorded from 1950/01/01 to 2019/05/06 in Ovid MEDLINE were screened.

Participants

Studies including humans (real or simulated) exposed to a drug.

Results

In total, 72 original articles and 5 reviews were identified via Ovid MEDLINE. Twenty different knowledge discovery methods were identified, mainly from the area of machine learning (66/72; 91.7%). Classification/regression (44/72; 61.1%), classification/regression + model optimization (13/72; 18.0%), and classification/regression + features selection (12/72; 16.7%) were the three most frequent tasks in reviewed literature that machine learning methods has been applied to solve. The top three used techniques were artificial neural networks, random forest, and support vector machines models.

Conclusions

The use of knowledge discovery techniques of artificial intelligence techniques has increased exponentially over the years covering numerous sub-topics of pharmacoepidemiology.

Systematic Review Registration

Systematic review registration number in PROSPERO: CRD42019136552.

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.

A recurrent neural network approach to predicting hemoglobin trajectories in patients with End-Stage Renal Disease

The most severe form of kidney disease, End-Stage Renal Disease (ESRD) is treated with various forms of dialysis - artificial blood cleansing. Dialysis patients suffer many health burdens including high mortality and hospitalization rates, and symptomatic anemia: a low red blood cell count as indicated by a low hemoglobin (Hgb) level. ESRD-induced anemia is treated, with variable patient response, by erythropoiesis stimulating agents (ESAs): expensive injectable medications typically administered during dialysis sessions. The dosing protocol is typically a population level protocol based on original clinical trials, the use of which often results in Hgb cycling. This cycling phenomenon occurs primarily due to the mismatch in the time between dosing decisions and the time it takes for the effects of a dosing change to be fully realized. In this paper we develop a recurrent neural network approach that uses historic data together with future ESA and iron dosing data to predict the 1, 2, and 3 month Hgb levels of patients with ESRD-induced anemia. The results of extensive experimentation indicate that this approach generates predictions that are clinically relevant: the mean absolute error of the predictions is comparable to estimates of the intra-individual variability of the laboratory test for Hgb.

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.

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.

Optimal EPO dosing in hemodialysis patients using a non-linear model predictive control approach

Anemia management with erythropoiesis stimulating agents is a challenging task in hemodialysis patients since their response to treatment varies highly. In general, it is difficult to achieve and maintain the predefined hemoglobin (Hgb) target levels in clinical practice. The aim of this study is to develop a fully personalizable controller scheme to stabilize Hgb levels within a narrow target window while keeping drug doses low to mitigate side effects. First in-silico results of this framework are presented in this paper. Based on a model of erythropoiesis we formulate a non-linear model predictive control (NMPC) algorithm for the individualized optimization of epoetin alfa (EPO) doses. Previous to this work, model parameters were estimated for individual patients using clinical data. The optimal control problem is formulated for a continuous drug administration. This is currently a hypothetical form of drug administration for EPO as it would require a programmable EPO pump similar to insulin pumps used to treat patients with diabetes mellitus. In each step of the NMPC method the open-loop problem is solved with a projected quasi-Newton method. The controller is successfully tested in-silico on several patient parameter sets. An appropriate control is feasible in the tested patients under the assumption that the controlled quantity is measured regularly and that continuous EPO administration is adjusted on a daily, weekly or monthly basis. Further, the controller satisfactorily handles the following challenging problems in simulations: bleedings, missed administrations and dosing errors.

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.

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.

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.

Neural Network-Based Coronary Heart Disease Risk Prediction Using Feature Correlation Analysis

Background

Of the machine learning techniques used in predicting coronary heart disease (CHD), neural network (NN) is popularly used to improve performance accuracy.

Objective

Even though NN-based systems provide meaningful results based on clinical experiments, medical experts are not satisfied with their predictive performances because NN is trained in a “black-box” style.

Method

We sought to devise an NN-based prediction of CHD risk using feature correlation analysis (NN-FCA) using two stages. First, the feature selection stage, which makes features acceding to the importance in predicting CHD risk, is ranked, and second, the feature correlation analysis stage, during which one learns about the existence of correlations between feature relations and the data of each NN predictor output, is determined.

Result

Of the 4146 individuals in the Korean dataset evaluated, 3031 had low CHD risk and 1115 had CHD high risk. The area under the receiver operating characteristic (ROC) curve of the proposed model (0.749 ± 0.010) was larger than the Framingham risk score (FRS) (0.393 ± 0.010).

Conclusions

The proposed NN-FCA, which utilizes feature correlation analysis, was found to be better than FRS in terms of CHD risk prediction. Furthermore, the proposed model resulted in a larger ROC curve and more accurate predictions of CHD risk in the Korean population than the FRS.

Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm

Cardiovascular disease is one of the most rampant causes of death around the world and was deemed as a major illness in Middle and Old ages. Coronary artery disease, in particular, is a widespread cardiovascular malady entailing high mortality rates. Angiography is, more often than not, regarded as the best method for the diagnosis of coronary artery disease; on the other hand, it is associated with high costs and major side effects. Much research has, therefore, been conducted using machine learning and data mining so as to seek alternative modalities. Accordingly, we herein propose a highly accurate hybrid method for the diagnosis of coronary artery disease. As a matter of fact, the proposed method is able to increase the performance of neural network by approximately 10% through enhancing its initial weights using genetic algorithm which suggests better weights for neural network. Making use of such methodology, we achieved accuracy, sensitivity and specificity rates of 93.85%, 97% and 92% respectively, on Z-Alizadeh Sani dataset.

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

Managing anemia in hemodialysis patients can be challenging because of competing therapeutic targets and individual variability. Because therapy recommendations provided by a decision support system can benefit both patients and doctors, we evaluated the impact of an artificial intelligence decision support system, the Anemia Control Model (ACM), on anemia outcomes. Based on patient profiles, the ACM was built to recommend suitable erythropoietic-stimulating agent doses. Our retrospective study consisted of a 12-month control phase (standard anemia care), followed by a 12-month observation phase (ACM-guided care) encompassing 752 patients undergoing hemodialysis therapy in 3 NephroCare clinics located in separate countries. The percentage of hemoglobin values on target, the median darbepoetin dose, and individual hemoglobin fluctuation (estimated from the intrapatient hemoglobin standard deviation) were deemed primary outcomes. In the observation phase, median darbepoetin consumption significantly decreased from 0.63 to 0.46 μg/kg/month, whereas on-target hemoglobin values significantly increased from 70.6% to 76.6%, reaching 83.2% when the ACM suggestions were implemented. Moreover, ACM introduction led to a significant decrease in hemoglobin fluctuation (intrapatient standard deviation decreased from 0.95 g/dl to 0.83 g/dl). Thus, ACM support helped improve anemia outcomes of hemodialysis patients, minimizing erythropoietic-stimulating agent use with the potential to reduce the cost of treatment.