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

A new era in the science and care of kidney diseases

Notable progress in basic, translational and clinical nephrology research has been made over the past five decades. Nonetheless, many challenges remain, including obstacles to the early detection of kidney disease, disparities in access to care and variability in responses to existing and emerging therapies. Innovations in drug development, research technologies, tissue engineering and regenerative medicine have the potential to improve patient outcomes. Exciting prospects include the availability of new drugs to slow or halt the progression of chronic kidney disease, the development of bioartificial kidneys that mimic healthy kidney functions, and tissue engineering techniques that could enable transplantable kidneys to be created from the cells of the recipient, removing the risk of rejection. Cell and gene therapies have the potential to be applied for kidney tissue regeneration and repair. In addition, about 30% of kidney disease cases are monogenic and could potentially be treated using these genetic medicine approaches. Systemic diseases that involve the kidney, such as diabetes mellitus and hypertension, might also be amenable to these treatments. Continued investment, communication, collaboration and translation of innovations are crucial to realize their full potential. In addition, increasing sophistication in exploring large datasets, implementation science, and qualitative methodologies will improve the ability to deliver transformational kidney health strategies.

Digital Health Support: Current Status and Future Development for Enhancing Dialysis Patient Care and Empowering Patients

Chronic kidney disease poses a growing global health concern, as an increasing number of patients progress to end-stage kidney disease requiring kidney replacement therapy, presenting various challenges including shortage of care givers and cost-related issues. In this narrative essay, we explore innovative strategies based on in-depth literature analysis that may help healthcare systems face these challenges, with a focus on digital health technologies (DHTs), to enhance removal and ensure better control of broader spectrum of uremic toxins, to optimize resources, improve care and outcomes, and empower patients. Therefore, alternative strategies, such as self-care dialysis, home-based dialysis with the support of teledialysis, need to be developed. Managing ESKD requires an improvement in patient management, emphasizing patient education, caregiver knowledge, and robust digital support systems. The solution involves leveraging DHTs to automate HD, implement automated algorithm-driven controlled HD, remotely monitor patients, provide health education, and enable caregivers with data-driven decision-making. These technologies, including artificial intelligence, aim to enhance care quality, reduce practice variations, and improve treatment outcomes whilst supporting personalized kidney replacement therapy. This narrative essay offers an update on currently available digital health technologies used in the management of HD patients and envisions future technologies that, through digital solutions, potentially empower patients and will more effectively support their HD treatments.

Advances in Human-Centered Care to Address Contemporary Unmet Needs in Chronic Dialysis

Advances in the treatment of kidney failure with chronic dialysis have stagnated over the past three decades, with over 50% of patients still managed by conventional in-hospital haemodialysis. In parallel, the demands of chronic dialysis medical care have changed and evolved due to a growing population that has higher frailty and multimorbidity. Thus, the gap between the needs of kidney failure patients and the healthcare capability to provide effective overall management has widened. To address this problem, healthcare policy has increasingly aligned towards a human-centred approach. The paradigm shift of human-centred approach places patients at the forefront of decision-making processes, ensuring that specific needs are understood and prioritised. Integration of human-centred approaches with patient care has been shown to improve satisfaction and quality of life. The aim of this narrative is to evaluate the current clinical challenges for managing kidney failure for dialysis providers; summarise current experiences and unmet needs of chronic dialysis patients; and finally emphasise how human-centred care has advanced chronic dialysis care. Specific incremental advances include implementation of renal supportive care; home-assisted dialysis; hybrid dialysis; refinements to dialysis methods; whereas emerging advances include portable and wearable dialysis devices and the potential for the integration of artificial intelligence in clinical practice.

Artificial intelligence and machine learning for clinical pharmacology

Artificial intelligence (AI) will impact many aspects of clinical pharmacology, including drug discovery and development, clinical trials, personalized medicine, pharmacogenomics, pharmacovigilance and clinical toxicology. The rapid progress of AI in healthcare means clinical pharmacologists should have an understanding of AI and its implementation in clinical practice. As with any new therapy or health technology, it is imperative that AI tools are subject to robust and stringent evaluation to ensure that they enhance clinical practice in a safe and equitable manner. This review serves as an introduction to AI for the clinical pharmacologist, highlighting current applications, aspects of model development and issues surrounding evaluation and deployment. The aim of this article is to empower clinical pharmacologists to embrace and lead on the safe and effective use of AI within healthcare.

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.

Artificial intelligence: a new field of knowledge for nephrologists?

Artificial intelligence (AI) is a science that involves creating machines that can imitate human intelligence and learn. AI is ubiquitous in our daily lives, from search engines like Google to home assistants like Alexa and, more recently, OpenAI with its chatbot. AI can improve clinical care and research, but its use requires a solid understanding of its fundamentals, the promises and perils of algorithmic fairness, the barriers and solutions to its clinical implementation, and the pathways to developing an AI-competent workforce. The potential of AI in the field of nephrology is vast, particularly in the areas of diagnosis, treatment and prediction. One of the most significant advantages of AI is the ability to improve diagnostic accuracy. Machine learning algorithms can be trained to recognize patterns in patient data, including lab results, imaging and medical history, in order to identify early signs of kidney disease and thereby allow timely diagnoses and prompt initiation of treatment plans that can improve outcomes for patients. In short, AI holds the promise of advancing personalized medicine to new levels. While AI has tremendous potential, there are also significant challenges to its implementation, including data access and quality, data privacy and security, bias, trustworthiness, computing power, AI integration and legal issues. The European Commission's proposed regulatory framework for AI technology will play a significant role in ensuring the safe and ethical implementation of these technologies in the healthcare industry. Training nephrologists in the fundamentals of AI is imperative because traditionally, decision-making pertaining to the diagnosis, prognosis and treatment of renal patients has relied on ingrained practices, whereas AI serves as a powerful tool for swiftly and confidently synthesizing this information.

Opportunities to improve the management of anemia in peritoneal dialysis patients: lessons from a national study in routine clinical practice

Background

Current guidelines establish the same hemoglobin (Hb) and iron biomarkers targets for hemodialysis (HD) and peritoneal dialysis (PD) in patients receiving erythropoiesis-stimulating agents (ESAs) even though patients having PD are usually younger, more active and less comorbid. Unfortunately, specific renal anemia [anemia in chronic kidney disease (aCKD)] trials or observational studies on PD are scanty. The aims of this study were to describe current aCKD management, goals and adherence to clinical guidelines, identifying opportunities for healthcare improvement in PD patients.

Methods

This was a retrospective, nationwide, multicentre study including patients from 19 PD units. The nephrologists collected baseline data, demographics, comorbidities and data related to anemia management (laboratory values, previously prescribed treatments and subsequent adjustments) from electronic medical records. The European adaptation of KDIGO guidelines was the reference for definitions, drug prescriptions and targets.

Results

A total of 343 patients (mean age 62.9 years, 61.2% male) were included; 72.9% were receiving ESAs and 33.2% iron therapy [20.7% intravenously (IV)]. Eighty-two patients were receiving ESA without iron therapy, despite 53 of them having an indication according to the European Renal Best Practice guidelines. After laboratory results, iron therapy was only started in 15% of patients. Among ESA-treated patients, 51.9% had an optimal control [hemoglobin (Hb) 10-12 g/dL] and 28.3% between 12-12.9 g/dL. Seventeen patients achieved Hb >13 g/dL, and 12 of them remained on ESA after overshooting. Only three patients had Hb <10 g/dL without ESAs. Seven patients (2%) met criteria for ESA resistance (epoetin dose >300 IU/kg/week). The highest tertile of erythropoietin resistance index (>6.3 UI/kg/week/g/dL) was associated with iron deficiency and low albumin corrected by renal replacement therapy vintage and hospital admissions in the previous 3 months.

Conclusion

Iron therapy continues to be underused (especially IV). Low albumin, iron deficiency and prior events explain most of the ESA hyporesponsiveness. Hb targets are titrated to/above the upper limits. Thus, several missed opportunities for adequate prescriptions and adherence to guidelines were identified.

From electronic health records to clinical management systems: how the digital transformation can support healthcare services

Healthcare systems worldwide are currently undergoing significant transformations in response to increasing costs, a shortage of healthcare professionals and the growing complexity of medical needs among the population. Value-based healthcare reimbursement systems are emerging as an attempt to incentivize patient-centricity and cost containment. From a technological perspective, the transition to digitalized services is intended to support these transformations. A Health Information System (HIS) is a technological solution designed to govern the data flow generated and consumed by healthcare professionals and administrative staff during the delivery of healthcare services. However, the exponential growth of digital capabilities and applied advanced analytics has expanded their traditional functionalities and brought the promise of automating administrative procedures and simple repetitive tasks, while enhancing the efficiency and outcomes of healthcare services by incorporating decision support tools for clinical management. The future of HIS is headed towards modular architectures that can facilitate implementation and adaptation to different environments and systems, as well as the integration of various tools, such as artificial intelligence (AI) models, in a seamless way. As an example, we present the experience and future developments of the European Clinical Database (EuCliD®). EuCliD is a multilingual HIS used by 20 000 nurses and physicians on a daily basis to manage 105 000 patients treated in 1100 clinics in 43 different countries. EuCliD encompasses patients' follow-up, automatic reporting and mobile applications while enabling efficient management of clinical processes. It is also designed to incorporate multiagent systems to automate repetitive tasks, AI modules and advanced dynamic dashboards.

Bridging the Worlds of Pharmacometrics and Machine Learning

Precision medicine requires individualized modeling of disease and drug dynamics, with machine learning-based computational techniques gaining increasing popularity. The complexity of either field, however, makes current pharmacological problems opaque to machine learning practitioners, and state-of-the-art machine learning methods inaccessible to pharmacometricians. To help bridge the two worlds, we provide an introduction to current problems and techniques in pharmacometrics that ranges from pharmacokinetic and pharmacodynamic modeling to pharmacometric simulations, model-informed precision dosing, and systems pharmacology, and review some of the machine learning approaches to address them. We hope this would facilitate collaboration between experts, with complementary strengths of principled pharmacometric modeling and flexibility of machine learning leading to synergistic effects in pharmacological applications.

Predicting dry weight change in Hemodialysis patients using machine learning

BACKGROUND

Machine Learning has been increasingly used in the medical field, including managing patients undergoing hemodialysis. The random forest classifier is a Machine Learning method that can generate high accuracy and interpretability in the data analysis of various diseases. We attempted to apply Machine Learning to adjust dry weight, the appropriate volume status of patients undergoing hemodialysis, which requires a complex decision-making process considering multiple indicators and the patient's physical conditions.

METHODS

All medical data and 69,375 dialysis records of 314 Asian patients undergoing hemodialysis at a single dialysis center in Japan between July 2018 and April 2020 were collected from the electronic medical record system. Using the random forest classifier, we developed models to predict the probabilities of adjusting the dry weight at each dialysis session.

RESULTS

The areas under the receiver-operating-characteristic curves of the models for adjusting the dry weight upward and downward were 0.70 and 0.74, respectively. The average probability of upward adjustment of the dry weight had sharp a peak around the actual change over time, while the average probability of downward adjustment of the dry weight formed a gradual peak. Feature importance analysis revealed that median blood pressure decline was a strong predictor for adjusting the dry weight upward. In contrast, elevated serum levels of C-reactive protein and hypoalbuminemia were important indicators for adjusting the dry weight downward.

CONCLUSIONS

The random forest classifier should provide a helpful guide to predict the optimal changes to the dry weight with relative accuracy and may be useful in clinical practice.

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.

Mechanisms of hemoglobin cycling in anemia patients treated with erythropoiesis-stimulating agents

Patients with renal anemia are frequently treated with erythropoiesis-stimulating agents (ESAs), which are dynamically dosed in order to stabilize blood hemoglobin levels within a specified target range. During typical ESA treatments, a fraction of patients experience hemoglobin 'cycling' periods during which hemoglobin levels periodically over- and undershoot the target range. Here we report a specific mechanism of hemoglobin cycling, whereby cycles emerge from the patient's delayed physiological response to ESAs and concurrent ESA dose adjustments. We introduce a minimal theoretical model that can explain dynamic hallmarks of observed hemoglobin cycling events in clinical time series and elucidates how physiological factors (such as red blood cell lifespan and ESA responsiveness) and treatment-related factors (such as dosing schemes) affect cycling. These results show that in general, hemoglobin cycling cannot be attributed to patient physiology or ESA treatment alone but emerges through an interplay of both, with consequences for the design of ESA treatment strategies.

Integration of artificial intelligence and multi-omics in kidney diseases

Kidney disease is a leading cause of death worldwide. Currently, the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features, which do not reveal the underlying molecular pathways. More recent surge of ∼omics studies has greatly catalyzed disease research. The advent of artificial intelligence (AI) has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge. This review discusses how AI and multi-omics can be applied and integrated, to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases. The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis, shedding new light on biomarkers and disease classification, as well as providing possibilities of precise treatment.

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.

Artificial intelligence and digital health for volume maintenance in hemodialysis patients

Chronic fluid overload is associated with morbidity and mortality in hemodialysis patients. Optimizing the diagnosis and treatment of fluid overload remains a priority for the nephrology community. Although current methods of assessing fluid status, such as bioimpedance and lung ultrasound, have prognostic and diagnostic value, no single system or technique can be used to maintain euvolemia. The difficulty in maintaining and assessing fluid status led to a publication by the Kidney Health Initiative in 2019 aimed at fostering innovation in fluid management therapies. This review article focuses on the current limitations in our assessment of extracellular volume, and the novel technology and methods that can create a new paradigm for fluid management. The cardiology community has published research on multiparametric wearable devices that can create individualized predictions for heart failure events. In the future, similar wearable technology may be capable of tracking fluid changes during the interdialytic period and enabling behavioral change. Machine learning methods have shown promise in the prediction of volume-related adverse events. Similar methods can be leveraged to create accurate, automated predictions of dry weight that can potentially be used to guide ultrafiltration targets and interdialytic weight gain goals.

Biomechanical behaviour of tension-band-reconstruction titanium plate in open-door laminoplasty: a study based on finite element analysis

OBJECTIVE

To investigate and evaluate the biomechanical behaviour of tension-band-reconstruction (TBR) and ordinary titanium plates in open-door laminoplasty by finite element (FE) analysis.

METHODS

TBR titanium plate and ordinary titanium plate were implanted into a validated finite element model of healthy adult cervical vertebrae. Among them, 5 ordinary titanium plate were used in model A, 2 TBR titanium plates and 3 ordinary titanium plates were used in model B, and 5 TBR titanium plates were used in model C. The same loading conditions was applied identically to all models. Range of motion (ROM) of the vertebral body, stress distribution of the titanium plate and intradiscal pressure (IDP) were compared in flexion, extension, lateral bending and rotation.

RESULTS

The ROM of model B and C was similar in flexion and extension, and both were smaller than that of model A. The highest von Mises stress in the titanium plate appears is in model C. The IDP in C2/3 was significantly higher than that in other segments in flexion. There was no significant difference in IDP among three models in left lateral bending and left axial rotation.

CONCLUSION

Application of TBR titanium plate in open-door laminoplasty can reduced ROM in flexion, extension and axial rotation of the cervical vertebrae. But the increase of stress in TBR titanium plate could lead to higher risk of adverse events such as titanium plate deformation. Moreover, compared with complete TBR titanium plate, the combination of TBR titanium plate for C3 and C7 with ordinary titanium plate for the other vertebrae largely reduce the stress of the titanium plates by ensuring stability. The proposed FE model (C2-T1) exhibits a great potential in evaluating biomechanical behaviour of TBR titanium plate for open-door laminoplasty.

Using a machine learning model to predict the development of acute kidney injury in patients with heart failure

Background

Heart failure (HF) is a life-threatening complication of cardiovascular disease. HF patients are more likely to progress to acute kidney injury (AKI) with a poor prognosis. However, it is difficult for doctors to distinguish which patients will develop AKI accurately. This study aimed to construct a machine learning (ML) model to predict AKI occurrence in HF patients.

Materials and methods

The data of HF patients from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database was retrospectively analyzed. A ML model was established to predict AKI development using decision tree, random forest (RF), support vector machine (SVM), K-nearest neighbor (KNN), and logistic regression (LR) algorithms. Thirty-nine demographic, clinical, and treatment features were used for model establishment. Accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) were used to evaluate the performance of the ML algorithms.

Results

A total of 2,678 HF patients were engaged in this study, of whom 919 developed AKI. Among 5 ML algorithms, the RF algorithm exhibited the highest performance with the AUROC of 0.96. In addition, the Gini index showed that the sequential organ function assessment (SOFA) score, partial pressure of oxygen (PaO₂), and estimated glomerular filtration rate (eGFR) were highly relevant to AKI development. Finally, to facilitate clinical application, a simple model was constructed using the 10 features screened by the Gini index. The RF algorithm also exhibited the highest performance with the AUROC of 0.95.

Conclusion

Using the ML model could accurately predict the development of AKI in HF patients.

Design, effectiveness, and economic outcomes of contemporary chronic disease clinical decision support systems: a systematic review and meta-analysis

Objectives

Electronic health record-based clinical decision support (CDS) has the potential to improve health outcomes. This systematic review investigates the design, effectiveness, and economic outcomes of CDS targeting several common chronic diseases.

Material and Methods

We conducted a search in PubMed (Medline), EBSCOHOST (CINAHL, APA PsychInfo, EconLit), and Web of Science. We limited the search to studies from 2011 to 2021. Studies were included if the CDS was electronic health record-based and targeted one or more of the following chronic diseases: cardiovascular disease, diabetes, chronic kidney disease, hypertension, and hypercholesterolemia. Studies with effectiveness or economic outcomes were considered for inclusion, and a meta-analysis was conducted.

Results

The review included 76 studies with effectiveness outcomes and 9 with economic outcomes. Of the effectiveness studies, 63% described a positive outcome that favored the CDS intervention group. However, meta-analysis demonstrated that effect sizes were heterogenous and small, with limited clinical and statistical significance. Of the economic studies, most full economic evaluations (n = 5) used a modeled analysis approach. Cost-effectiveness of CDS varied widely between studies, with an estimated incremental cost-effectiveness ratio ranging between USD$2192 to USD$151 955 per QALY.

Conclusion

We summarize contemporary chronic disease CDS designs and evaluation results. The effectiveness and cost-effectiveness results for CDS interventions are highly heterogeneous, likely due to differences in implementation context and evaluation methodology. Improved quality of reporting, particularly from modeled economic evaluations, would assist decision makers to better interpret and utilize results from these primary research studies.

Registration

PROSPERO (CRD42020203716)

The promise of artificial intelligence for kidney pathophysiology

PURPOSE OF REVIEW

We seek to determine recent advances in kidney pathophysiology that have been enabled or enhanced by artificial intelligence. We describe some of the challenges in the field as well as future directions.

RECENT FINDINGS

We first provide an overview of artificial intelligence terminologies and methodologies. We then describe the use of artificial intelligence in kidney diseases to discover risk factors from clinical data for disease progression, annotate whole slide imaging and decipher multiomics data. We delineate key examples of risk stratification and prognostication in acute kidney injury (AKI) and chronic kidney disease (CKD). We contextualize these applications in kidney disease oncology, one of the subfields to benefit demonstrably from artificial intelligence using all if these approaches. We conclude by elucidating technical challenges and ethical considerations and briefly considering future directions.

SUMMARY

The integration of clinical data, patient derived data, histology and proteomics and genomics can enhance the work of clinicians in providing more accurate diagnoses and elevating understanding of disease progression. Implementation research needs to be performed to translate these algorithms to the clinical setting.

Clinical Applications of Artificial Intelligence-An Updated Overview

Artificial intelligence has the potential to revolutionize modern society in all its aspects. Encouraged by the variety and vast amount of data that can be gathered from patients (e.g., medical images, text, and electronic health records), researchers have recently increased their interest in developing AI solutions for clinical care. Moreover, a diverse repertoire of methods can be chosen towards creating performant models for use in medical applications, ranging from disease prediction, diagnosis, and prognosis to opting for the most appropriate treatment for an individual patient. In this respect, the present paper aims to review the advancements reported at the convergence of AI and clinical care. Thus, this work presents AI clinical applications in a comprehensive manner, discussing the recent literature studies classified according to medical specialties. In addition, the challenges and limitations hindering AI integration in the clinical setting are further pointed out.

The Use of Artificial Intelligence in Complementary and Alternative Medicine: A Systematic Scoping Review

Background: The development of artificial intelligence (AI) in the medical field has been growing rapidly. As AI models have been introduced in complementary and alternative medicine (CAM), a systematized review must be performed to understand its current status.

Objective: To categorize and seek the current usage of AI in CAM.

Method: A systematic scoping review was conducted based on the method proposed by the Joanna Briggs Institute. The three databases, PubMed, Embase, and Cochrane Library, were used to find studies regarding AI and CAM. Only English studies from 2000 were included. Studies without mentioning either AI techniques or CAM modalities were excluded along with the non-peer-reviewed studies. A broad-range search strategy was applied to locate all relevant studies.

Results: A total of 32 studies were identified, and three main categories were revealed: 1) acupuncture treatment, 2) tongue and lip diagnoses, and 3) herbal medicine. Other CAM modalities were music therapy, meditation, pulse diagnosis, and TCM syndromes. The majority of the studies utilized AI models to predict certain patterns and find reliable computerized models to assist physicians.

Conclusion: Although the results from this review have shown the potential use of AI models in CAM, future research ought to focus on verifying and validating the models by performing a large-scale clinical trial to better promote AI in CAM in the era of digital health.

Novelle QLL 2020 – welche Auswirkungen haben die neu empfohlenen Hämoglobin-Transfusionstrigger auf die klinische Versorgung?

In der Gesamtnovelle der Querschnittsleitlinie (QLL) Hämotherapie der Bundesärztekammer (BÄK) 2020 wurde der Hämoglobin-Transfusionstrigger (Hb-Transfusionstrigger) bei akutem Blutverlust ohne zusätzliche Risikofaktoren aufgrund einer Neubewertung der internationalen Evidenz von 3,7 mmol/l (6 g/dl) auf 4,3 mmol/l (7 g/dl) angepasst. Ziel der vorliegenden Studie ist die retrospektive Analyse des Transfusionsverhaltens von EK bezüglich der Maßgaben der QLL. Zu diesem Zweck analysierten wir individuelle Prä- und Posttransfusions-Hb-Werte von Erythrozytenkonzentraten (EK), die im 4. Quartal 2019 (4946 EKs, 129 560 Hb-Werte) und 2020 (5502 EKs, 134 404 Hb-Werte) am Universitätsklinikum Leipzig (UKL) transfundiert wurden. Der mediane Hb-Wert vor der Transfusion betrug 4,3 mmol/l (7 g/dl) (680 medizinische Fälle, die 2724 EK in 1801 Transfusionen im Jahr 2019 erhielten). Von allen Transfusionen im Jahr 2019 zeigten 899 (49,9%) Transfusionen Hb-Werte < 4,3 mmol/l (7 g/dl) vor der Transfusion, während 152 (8,4%) Hb-Werte < 3,7 mmol/l (6 g/dl) aufwiesen. 2020 wurden jeweils vergleichbare Ergebnisse ermittelt. Wir zeigen, dass der mediane Hb-Anstieg nach der Transfusion eines EK 0,6 mmol/l (1 g/dl) betrug. 34,7% aller Transfusionen erreichten den erwarteten Anstieg von 0,6 mmol/l (1 g/dl) pro EK. Der absolute Anstieg nahm bei Transfusionen mit mehreren EK im Vergleich zu Transfusionen mit einem EK nicht linear zu. Der Grad der Hb-Erhöhung korrelierte invers mit dem Hb-Wert vor Transfusion. Der Hb-Wert nach der Transfusion wurde bei 96,3% der Fälle innerhalb von 24 Stunden nach Hämotherapie kontrolliert. Zusammenfassend spiegelt das Transfusionsverhalten generell die Empfehlungen der Leitlinie. Um ein optimiertes, individualisiertes und dennoch restriktives Transfusionsverhalten bei EK zu erreichen, schlagen wir die Implementierung eines klinischen Entscheidungsunterstützungssystems (CDSS) bei Verschreibung jeder einzelnen EK-Transfusion vor, welches Ärzte bei der Einhaltung der Transfusionsleitlinie unterstützt und über Abweichungen informiert.

How to assess the risks associated with the usage of a medical device based on predictive modeling: the case of an anemia control model certified as medical device

BACKGROUND

The successful application of Machine Learning (ML) to many clinical problems can lead to its implementation as a medical device (MD), which is important to assess the associated risks.

METHODS

An anemia control model (ACM), certified as MD, may face adverse events as a result of wrong predictions that are translated into suggestions of doses of erythropoietic stimulating agents to dialysis patients. Risks are assessed as the combination of severity and probability of a given hazard. While severities are typically assessed by clinicians, probabilities are tightly related to the performance of the predictive model.

RESULTS

A postmarketing data set formed by all adult patients registered in French, Portuguese, and Spanish clinics, belonging to an international network, was considered; 3876 patients and 11,508 suggestions were eventually included. The achieved results show that there are no statistical differences between the probabilities of adverse events that are estimated in the ACM test set (using only Spanish clinics) and those actually observed in the postmarketing cohort.

CONCLUSIONS

The risks of an ACM-MD can be accurately and robustly estimated, thus enhancing patients' safety. The proposed methodology is applicable to other clinical decisions based on predictive models since our proposal does not depend on the particular predictive model.

Big Data in Nephrology

A huge array of data in nephrology is collected through patient registries, large epidemiological studies, electronic health records, administrative claims, clinical trial repositories, mobile health devices and molecular databases. Application of these big data, particularly using machine-learning algorithms, provides a unique opportunity to obtain novel insights into kidney diseases, facilitate personalized medicine and improve patient care. Efforts to make large volumes of data freely accessible to the scientific community, increased awareness of the importance of data sharing and the availability of advanced computing algorithms will facilitate the use of big data in nephrology. However, challenges exist in accessing, harmonizing and integrating datasets in different formats from disparate sources, improving data quality and ensuring that data are secure and the rights and privacy of patients and research participants are protected. In addition, the optimism for data-driven breakthroughs in medicine is tempered by scepticism about the accuracy of calibration and prediction from in silico techniques. Machine-learning algorithms designed to study kidney health and diseases must be able to handle the nuances of this specialty, must adapt as medical practice continually evolves, and must have global and prospective applicability for external and future datasets.

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.

Dialysis adequacy predictions using a machine learning method

Dialysis adequacy is an important survival indicator in patients with chronic hemodialysis. However, there are inconveniences and disadvantages to measuring dialysis adequacy by blood samples. This study used machine learning models to predict dialysis adequacy in chronic hemodialysis patients using repeatedly measured data during hemodialysis. This study included 1333 hemodialysis sessions corresponding to the monthly examination dates of 61 patients. Patient demographics and clinical parameters were continuously measured from the hemodialysis machine; 240 measurements were collected from each hemodialysis session. Machine learning models (random forest and extreme gradient boosting [XGBoost]) and deep learning models (convolutional neural network and gated recurrent unit) were compared with multivariable linear regression models. The mean absolute percentage error (MAPE), root mean square error (RMSE), and Spearman's rank correlation coefficient (Corr) for each model using fivefold cross-validation were calculated as performance measurements. The XGBoost model had the best performance among all methods (MAPE = 2.500; RMSE = 2.906; Corr = 0.873). The deep learning models with convolutional neural network (MAPE = 2.835; RMSE = 3.125; Corr = 0.833) and gated recurrent unit (MAPE = 2.974; RMSE = 3.230; Corr = 0.824) had similar performances. The linear regression models had the lowest performance (MAPE = 3.284; RMSE = 3.586; Corr = 0.770) compared with other models. Machine learning methods can accurately infer hemodialysis adequacy using continuously measured data from hemodialysis machines.

Machine learning directed interventions associate with decreased hospitalization rates in hemodialysis patients

BACKGROUND

An integrated kidney disease company uses machine learning (ML) models that predict the 12-month risk of an outpatient hemodialysis (HD) patient having multiple hospitalizations to assist with directing personalized interdisciplinary interventions in a Dialysis Hospitalization Reduction Program (DHRP). We investigated the impact of risk directed interventions in the DHRP on clinic-wide hospitalization rates.

METHODS

We compared the hospital admission and day rates per-patient-year (ppy) from all hemodialysis patients in 54 DHRP and 54 control clinics identified by propensity score matching at baseline in 2015 and at the end of the pilot in 2018. We also used paired T test to compare the between group difference of annual hospitalization rate and hospitalization days rates at baseline and end of the pilot.

RESULTS

The between group difference in annual hospital admission and day rates was similar at baseline (2015) with a mean difference between DHRP versus control clinics of -0.008 ± 0.09 ppy and -0.05 ± 0.96 ppy respectively. The between group difference in hospital admission and day rates became more distinct at the end of follow up (2018) favoring DHRP clinics with the mean difference being -0.155 ± 0.38 ppy and -0.97 ± 2.78 ppy respectively. A paired t-test showed the change in the between group difference in hospital admission and day rates from baseline to the end of the follow up was statistically significant (t-value = 2.73, p-value < 0.01) and (t-value = 2.29, p-value = 0.02) respectively.

CONCLUSIONS

These findings suggest ML model-based risk-directed interdisciplinary team interventions associate with lower hospitalization rates and hospital day rate in HD patients, compared to controls.

A hybrid machine learning/pharmacokinetic approach outperforms maximum a posteriori Bayesian estimation by selectively flattening model priors

Model‐informed precision dosing (MIPD) approaches typically apply maximum a posteriori (MAP) Bayesian estimation to determine individual pharmacokinetic (PK) parameters with the goal of optimizing future dosing regimens. This process combines knowledge about the individual, in the form of drug levels or pharmacodynamic biomarkers, with prior knowledge of the drug PK in the general population. Use of “flattened priors” (FPs), in which the weight of the model priors is reduced relative to observations about the patient, has been previously proposed to estimate individual PK parameters in instances where the patient is poorly described by the PK model. However, little is known about the predictive performance of FPs and when to apply FPs in MIPD. Here, FP is evaluated in a data set of 4679 adult patients treated with vancomycin. Depending on the PK model, prediction error could be reduced by applying FPs in 42–55% of PK parameter estimations. Machine learning (ML) models could identify instances where FPs would outperform MAPs with a specificity of 81–86%, reducing overall root mean squared error (RMSE) of PK model predictions by 12–22% (0.5–1.2 mg/L) relative to MAP alone. The factors most indicative of the use of FPs were past prediction residuals and bias in past PK predictions. A more clinically practical minimal model was developed using only these two features, reducing RMSE by 5–18% (0.20–0.93 mg/L) relative to MAP. This hybrid ML/PK approach advances the precision dosing toolkit by leveraging the power of ML while maintaining the mechanistic insight and interpretability of PK models.

A Roadmap for Automating Lineage Tracing to Aid Automatically Explaining Machine Learning Predictions for Clinical Decision Support

Using machine learning predictive models for clinical decision support has great potential in improving patient outcomes and reducing health care costs. However, most machine learning models are black boxes that do not explain their predictions, thereby forming a barrier to clinical adoption. To overcome this barrier, an automated method was recently developed to provide rule-style explanations of any machine learning model’s predictions on tabular data and to suggest customized interventions. Each explanation delineates the association between a feature value pattern and an outcome value. Although the association and intervention information is useful, the user of the automated explaining function often requires more detailed information to better understand the patient’s situation and to aid in decision making. More specifically, consider a feature value in the explanation that is computed by an aggregation function on the raw data, such as the number of emergency department visits related to asthma that the patient had in the prior 12 months. The user often wants to rapidly drill through to see certain parts of the related raw data that produce the feature value. This task is frequently difficult and time-consuming because the few pieces of related raw data are submerged by many pieces of raw data of the patient that are unrelated to the feature value. To address this issue, this paper outlines an automated lineage tracing approach, which adds automated drill-through capability to the automated explaining function, and provides a roadmap for future research.

Machine learning in pharmacometrics: Opportunities and challenges

The explosive growth in medical devices, imaging and diagnostics, computing, and communication and information technologies in drug development and healthcare has created an ever-expanding data landscape that the pharmacometrics (PMX) research community must now traverse. The tools of machine learning (ML) have emerged as a powerful computational approach in other data-rich disciplines but its effective utilization in the pharmaceutical sciences and PMX modelling is in its infancy. ML-based methods can complement PMX modelling by enabling the information in diverse sources of big data, e.g. population-based public databases and disease-specific clinical registries, to be harnessed because they are capable of efficiently identifying salient variables associated with outcomes and delineating their interdependencies. ML algorithms are computationally efficient, have strong predictive capabilities and can enable learning in the big data setting. ML algorithms can be viewed as providing a computational bridge from big data to complement PMX modelling. This review provides an overview of the strengths and weaknesses of ML approaches vis-à-vis population methods, assesses current research into ML applications in the pharmaceutical sciences and provides perspective for potential opportunities and strategies for the successful integration and utilization of ML in PMX.

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 enabled applications in kidney disease

Artificial intelligence (AI) is considered as the next natural progression of traditional statistical techniques. Advances in analytical methods and infrastructure enable AI to be applied in health care. While AI applications are relatively common in fields like ophthalmology and cardiology, its use is scarcely reported in nephrology. We present the current status of AI in research toward kidney disease and discuss future pathways for AI. The clinical applications of AI in progression to end-stage kidney disease and dialysis can be broadly subdivided into three main topics: (a) predicting events in the future such as mortality and hospitalization; (b) providing treatment and decision aids such as automating drug prescription; and (c) identifying patterns such as phenotypical clusters and arteriovenous fistula aneurysm. At present, the use of prediction models in treating patients with kidney disease is still in its infancy and further evidence is needed to identify its relative value. Policies and regulations need to be addressed before implementing AI solutions at the point of care in clinics. AI is not anticipated to replace the nephrologists' medical decision-making, but instead assist them in providing optimal personalized care for their patients.

Artificial intelligence supported anemia control system (AISACS) to prevent anemia in maintenance hemodialysis patients

Anemia, for which erythropoiesis-stimulating agents (ESAs) and iron supplements (ISs) are used as preventive measures, presents important difficulties for hemodialysis patients. Nevertheless, the number of physicians able to manage such medications appropriately is not keeping pace with the rapid increase of hemodialysis patients. Moreover, the high cost of ESAs imposes heavy burdens on medical insurance systems. An artificial-intelligence-supported anemia control system (AISACS) trained using administration direction data from experienced physicians has been developed by the authors. For the system, appropriate data selection and rectification techniques play important roles. Decision making related to ESAs poses a multi-class classification problem for which a two-step classification technique is introduced. Several validations have demonstrated that AISACS exhibits high performance with correct classification rates of 72%-87% and clinically appropriate classification rates of 92%-98%.

Artificial Intelligence: Help or Hindrance for Family Physicians?

The use of Artificial Intelligence (AI) and related technologies is rapidly increasing and its application in clinical practice is a promising area of development. Artificial Intelligence can be a solution in the future as a physician’s new assistant; AI-physician combinations can act like models of ‘peaceful co-existence’. While it has the potential to mold many dimensions of patient care and can augment quality improvement, it cannot replace a family physician’s diagnostic intelligence, empathy and relationships. Physicians need to strike a balance between these combinations for better health outcomes without increasing patients’ frustration.

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.

Increasing tendency of urine protein is a risk factor for rapid eGFR decline in patients with CKD: A machine learning-based prediction model by using a big database

Artificial intelligence is increasingly being adopted in medical fields to predict various outcomes. In particular, chronic kidney disease (CKD) is problematic because it often progresses to end-stage kidney disease. However, the trajectories of kidney function depend on individual patients. In this study, we propose a machine learning-based model to predict the rapid decline in kidney function among CKD patients by using a big hospital database constructed from the information of 118,584 patients derived from the electronic medical records system. The database included the estimated glomerular filtration rate (eGFR) of each patient, recorded at least twice over a period of 90 days. The data of 19,894 patients (16.8%) were observed to satisfy the CKD criteria. We characterized the rapid decline of kidney function by a decline of 30% or more in the eGFR within a period of two years and classified the available patients into two groups—those exhibiting rapid eGFR decline and those exhibiting non-rapid eGFR decline. Following this, we constructed predictive models based on two machine learning algorithms. Longitudinal laboratory data including urine protein, blood pressure, and hemoglobin were used as covariates. We used longitudinal statistics with a baseline corresponding to 90-, 180-, and 360-day windows prior to the baseline point. The longitudinal statistics included the exponentially smoothed average (ESA), where the weight was defined to be 0.9*(t/b), where t denotes the number of days prior to the baseline point and b denotes the decay parameter. In this study, b was taken to be 7 (7-day ESA). We used logistic regression (LR) and random forest (RF) algorithms based on Python code with scikit-learn library (https://scikit-learn.org/) for model creation. The areas under the curve for LR and RF were 0.71 and 0.73, respectively. The 7-day ESA of urine protein ranked within the first two places in terms of importance according to both models. Further, other features related to urine protein were likely to rank higher than the rest. The LR and RF models revealed that the degree of urine protein, especially if it exhibited an increasing tendency, served as a prominent risk factor associated with rapid eGFR decline.

Development of machine learning-based clinical decision support system for hepatocellular carcinoma

There is a significant discrepancy between the actual choice for initial treatment option for hepatocellular carcinoma (HCC) and recommendations from the currently used BCLC staging system. We develop a machine learning-based clinical decision support system (CDSS) for recommending initial treatment option in HCC and predicting overall survival (OS). From hospital records of 1,021 consecutive patients with HCC treated at a single centre in Korea between January 2010 and October 2010, we collected information on 61 pretreatment variables, initial treatment, and survival status. Twenty pretreatment key variables were finally selected. We developed the CDSS from the derivation set (N = 813) using random forest method and validated it in the validation set (N = 208). Among the 1,021 patients (mean age: 56.9 years), 81.8% were male and 77.0% had positive hepatitis B BCLC stages 0, A, B, C, and D were observed in 13.4%, 26.0%, 18.0%, 36.6%, and 6.3% of patients, respectively. The six multi-step classifier model was developed for treatment decision in a hierarchical manner, and showed good performance with 81.0% of accuracy for radiofrequency ablation (RFA) or resection versus not, 88.4% for RFA versus resection, and 76.8% for TACE or not. We also developed seven survival prediction models for each treatment option. Our newly developed HCC-CDSS model showed good performance in terms of treatment recommendation and OS prediction and may be used as a guidance in deciding the initial treatment option for HCC.

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.

Predicting mortality in hemodialysis patients using machine learning analysis

Background

Besides the classic logistic regression analysis, non-parametric methods based on machine learning techniques such as random forest are presently used to generate predictive models. The aim of this study was to evaluate random forest mortality prediction models in haemodialysis patients.

Methods

Data were acquired from incident haemodialysis patients between 1995 and 2015. Prediction of mortality at 6 months, 1 year and 2 years of haemodialysis was calculated using random forest and the accuracy was compared with logistic regression. Baseline data were constructed with the information obtained during the initial period of regular haemodialysis. Aiming to increase accuracy concerning baseline information of each patient, the period of time used to collect data was set at 30, 60 and 90 days after the first haemodialysis session.

Results

There were 1571 incident haemodialysis patients included. The mean age was 62.3 years and the average Charlson comorbidity index was 5.99. The mortality prediction models obtained by random forest appear to be adequate in terms of accuracy [area under the curve (AUC) 0.68–0.73] and superior to logistic regression models (ΔAUC 0.007–0.046). Results indicate that both random forest and logistic regression develop mortality prediction models using different variables.

Conclusions

Random forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.

Hierarchical Clustering Analysis for Predicting 1-Year Mortality After Starting Hemodialysis

Introduction

For patients with end-stage renal disease (ESRD), due to the heterogeneity of the population, appropriate risk assessment approaches and strategies for further follow-up remain scarce. We aimed to conduct a pilot study for better risk stratification, applying machine learning–based classification to patients with ESRD who newly started maintenance hemodialysis.

Methods

We prospectively studied 101 patients with ESRD, who were new to maintenance hemodialysis therapy, between August 2016 and March 2018. Baseline values of variables such as blood and urine tests were obtained before the initiation of hemodialysis. Agglomerative hierarchical clustering was conducted with the collected continuous data. The resulting clusters were followed up for the primary outcome of 1-year mortality, as analyzed by the Kaplan-Meier survival curve with log-rank test and the Cox proportional hazard model.

Results

The participants were divided into 3 clusters (cluster 1, n = 62; cluster 2, n = 15; cluster 3, n = 24) by hierarchical clustering, using 46 clinical variables. Patients in cluster 3 showed lower systolic blood pressures, and lower serum creatinine and urinary liver-type fatty acid-binding protein levels, before the initiation of hemodialysis. Consequently, cluster 3 was associated with the highest 1-year mortality in the study cohort (P < 0.001), and the difference was significant after adjustment for age and sex (hazard ratio: 10.2; 95% confidence interval: 2.94–46.8, cluster 1 as reference).

Conclusion

In this proof-of-concept study, hierarchical clustering discovered a subgroup with a higher 1-year mortality at the initiation of hemodialysis. Applying machine learning–derived classification to patients with ESRD may contribute to better risk stratification.

Artificial Intelligence-Based Clinical Decision Support Systems Using Advanced Medical Imaging and Radiomics

Artificial intelligence (AI) is poised to make a veritable impact in medicine. Clinical decision support (CDS) is an important area where AI can augment the clinician's capability to collect, understand and make inferences on an overwhelming volume of patient data to reach the optimal clinical decision. Advancements in medical image analysis, such as Radiomics, and data computation, such as machine learning, have expanded our understanding of disease processes and their management. In this article, we review the most relevant concepts of AI as applicable to advanced imaging-based clinical decision support systems.

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.