Machine-learning algorithms define pathogen-specific local immune fingerprints in peritoneal dialysis patients with bacterial infections

Artificial Intelligence in Nephrology: Clinical Applications and Challenges

Artificial intelligence (AI) is increasingly used in many medical specialties. However, nephrology has lagged in adopting and incorporating machine learning techniques. Nephrology is well positioned to capitalize on the benefits of AI. The abundance of structured clinical data, combined with the mathematical nature of this specialty, makes it an attractive option for AI applications. AI can also play a significant role in addressing health inequities, especially in organ transplantation. It has also been used to detect rare diseases such as Fabry disease early. This review article aims to increase awareness on the basic concepts in machine learning and discuss AI applications in nephrology. It also addresses the challenges in integrating AI into clinical practice and the need for creating an AI-competent nephrology workforce. Even though AI will not replace nephrologists, those who are able to incorporate AI into their practice effectively will undoubtedly provide better care to their patients. The integration of AI technology is no longer just an option but a necessity for staying ahead in the field of nephrology. Finally, AI can contribute as a force multiplier in transitioning to a value-based care model.

Artificial intelligence and machine learning in peritoneal dialysis: a systematic review of clinical outcomes and predictive modeling

BACKGROUND

The integration of artificial intelligence (AI) and machine learning (ML) in peritoneal dialysis (PD) presents transformative opportunities for optimizing treatment outcomes and informing clinical decision-making. This study aims to provide a comprehensive overview of the applications of AI/ML techniques in PD, focusing on their potential to predict clinical outcomes and enhance patient care.

MATERIALS AND METHODS

This systematic review was conducted according to PRISMA guidelines (2020), searching key databases for articles on AI and ML applications in PD. The inclusion criteria were stringent, ensuring the selection of high-quality studies. The search strategy comprised MeSH terms and keywords related to PD, AI, and ML. 793 articles were identified, with nine ultimately meeting the inclusion criteria. The review utilized a narrative synthesis approach to summarize findings due to anticipated study heterogeneity.

RESULTS

Nine studies met the inclusion criteria. The studies varied in sample size and employed diverse AI and ML techniques, reflecting the breadth of data considered. Mortality prediction emerged as a recurrent theme, demonstrating the significance of AI and ML in prognostic accuracy. Predictive modeling extended to technique failure, hospital stay prediction, and pathogen-specific immune responses, showcasing the versatility of AI and ML applications in PD.

CONCLUSIONS

This systematic review highlights the diverse applications of AI/ML in peritoneal dialysis, demonstrating their potential to enhance predictive accuracy, risk stratification, and decision support. However, limitations such as small sample sizes, single-center studies, and potential biases warrant further research and external validation. Future perspectives include integrating these AI/ML models into routine clinical practice and exploring additional use cases to improve patient outcomes and healthcare decision-making in PD.

Rapid point-of-care test for diagnosis of peritonitis in peritoneal dialysis patients

BACKGROUND

Periplex® is a rapid point-of-care test based on the detection of interleukin-6 (IL-6) or matrix metalloproteinase-8 (MMP-8) to diagnose peritonitis in peritoneal dialysis (PD) patients.

METHODS

This single-centre study was conducted in Singapore General Hospital from 2019 to 2022. The study recruited PD patients suspected of having peritonitis. Periplex was performed at the presentation and recovery of peritonitis. Primary outcomes were sensitivity and specificity of Periplex at presentation. The positive and negative predictive values of tests were also performed.

RESULTS

A total of 120 patients were included in the study. The mean age was 60.9 ± 14.9 years, 53% were male, 79% were Chinese and 47.5% had diabetes mellitus. Periplex was positive in all patients with peritonitis (n = 114); sensitivity of 100%; 95% confidence interval (CI): 100-100%. Periplex was falsely positive in three patients with non-infective eosinophilic peritonitis, resulting in a low specificity of 50%; 95% CI: 41.1-59.0%. Periplex had a positive predictive value of 97.4% and a negative predictive value of 100%. During recovery from peritonitis, Periplex had high specificity (93.6%) and negative predictive value (98.7%) to indicate the resolution of infection. MMP-8 was more sensitive than IL-6 in detecting peritonitis. Periplex was positive in all patients with peritonitis regardless of the types of PD solutions used.

CONCLUSIONS

Periplex had high sensitivity, and positive and negative predictive values in the diagnosis of peritonitis can be considered as a screening tool for peritonitis. Given its high specificity and negative predictive value, it may also be used to document the resolution of peritonitis.

Effect of Remote and Virtual Technology on Home Dialysis

In the United States, regulatory changes dictate telehealth activities. Telehealth was available to patients on home dialysis as early as 2019, allowing patients to opt for telehealth with home as the originating site and without geographic restriction. In 2020, coronavirus disease 2019 was an unexpected accelerant for telehealth use in the United States. Within nephrology, remote patient monitoring has most often been applied to the care of patients on home dialysis modalities. The effect that remote and virtual technologies have on home dialysis patients, telehealth and health care disparities, and health care providers' workflow changes are discussed here. Moreover, the future use of remote and virtual technologies to include artificial intelligence and artificial neural network model to optimize and personalize treatments will be highlighted. Despite these advances in technology challenges continue to exist, leaving room for future innovation to improve patient health outcome and equity. Prospective studies are needed to further understand the effect of using virtual technologies and remote monitoring on home dialysis outcomes, cost, and patient engagement.

Prospectively investigating the impact of AI onshared decision-making in post kidney transplant care (PRIMA-AI): protocol for a longitudinal qualitative study among patients, their support persons and treating physicians at a tertiary care centre

INTRODUCTION

As healthcare is shifting from a paternalistic to a patient-centred approach, medical decision making becomes more collaborative involving patients, their support persons (SPs) and physicians. Implementing shared decision-making (SDM) into clinical practice can be challenging and becomes even more complex with the introduction of artificial intelligence (AI) as a potential actant in the communicative network. Although there is more empirical research on patients' and physicians' perceptions of AI, little is known about the impact of AI on SDM. This study will help to fill this gap. To the best of our knowledge, this is the first systematic empirical investigation to prospectively assess the views of patients, their SPs and physicians on how AI affects SDM in physician-patient communication after kidney transplantation. Using a transdisciplinary approach, this study will explore the role and impact of an AI-decision support system (DSS) designed to assist with medical decision making in the clinical encounter.

METHODS AND ANALYSIS

This is a plan to roll out a 2 year, longitudinal qualitative interview study in a German kidney transplant centre. Semi-structured interviews with patients, SPs and physicians will be conducted at baseline and in 3-, 6-, 12- and 24-month follow-up. A total of 50 patient-SP dyads and their treating physicians will be recruited at baseline. Assuming a dropout rate of 20% per year, it is anticipated that 30 patient-SP dyads will be included in the last follow-up with the aim of achieving data saturation. Interviews will be audio-recorded and transcribed verbatim. Transcripts will be analysed using framework analysis. Participants will be asked to report on their (a) communication experiences and preferences, (b) views on the influence of the AI-based DSS on the normative foundations of the use of AI in medical decision-making, focusing on agency along with trustworthiness, transparency and responsibility and (c) perceptions of the use of the AI-based DSS, as well as barriers and facilitators to its implementation into routine care.

ETHICS AND DISSEMINATION

Approval has been granted by the local ethics committee of Charité-Universitätsmedizin Berlin (EA1/177/23 on 08 August 2023). This research will be conducted in accordance with the principles of the Declaration of Helsinki (1996). The study findings will be used to develop communication guidance for physicians on how to introduce and sustainably implement AI-assisted SDM. The study results will also be used to develop lay language patient information on AI-assisted SDM. A broad dissemination strategy will help communicate the results of this research to a variety of target groups, including scientific and non-scientific audiences, to allow for a more informed discourse among different actors from policy, science and society on the role and impact of AI in physician-patient communication.

Linking clinical manifestations and causative organisms may provide clues for the treatment of peritoneal dialysis-associated peritonitis

INTRODUCTION

Different initial manifestations of peritoneal dialysis-associated peritonitis (PDAP) may depend on the type of pathogenic organism. We investigated the association between the clinical characteristics of PDAP and susceptibility to vancomycin and investigated the possibility of using vancomycin monotherapy alone as an initial treatment regimen for some PDAP patients to avoid unnecessary antibiotic exposure and secondary infection.

METHODS

Patients with culture-positive PDAP were retrospectively analyzed and divided into two groups: peritonitis with only cloudy effluent (PDAP-cloudy) or with cloudy effluent, abdominal pain and/or fever (PDAP-multi). The bacterial culture of PD effluent and antibiotic sensitivity test results were compared between groups. Logistic regression was used to investigate factors predicting susceptibility to vancomycin.

RESULTS

Of 162 episodes of peritonitis which had a positive bacterial culture of PD fluid, 30 peritonitis were in the PDAP-cloudy group, and 132 peritonitis were in the PDAP-multi group. Thirty (100%) peritonitis in the PDAP-cloudy group had gram-positive bacterial infections, which was significantly greater than that in the PDAP-multi group (51.5%) (P < 0.001). Twenty-nine (96.7%) peritonitis in the PDAP-cloudy group were susceptible to vancomycin, compared to 67 (50.8%) in the PDAP-multi group (P < 0.001). The specificity of PDAP-cloudy for vancomycin-sensitive peritonitis was 98.48%. Only one patient (3.3%) in the PDAP-cloudy group experienced vancomycin-resistant peritonitis caused by Enterococcus gallinarum, which could neither be covered by vancomycin nor by the initial antibiotic regimen recommended by the current ISPD guidelines. The presence of only cloudy effluent was an independent predictor of susceptibility to vancomycin according to multivariate analysis (OR = 27.678, 95% CI 3.191-240.103, p = 0.003), in addition to PD effluent WBC counts (OR = 0.988, 95% CI 0.980-0.996, p = 0.004), diabetes mellitus (OR = 3.646, 95% CI 1.580-8.416, p = 0.002), first episode peritonitis (OR = 0.447, 95% CI 0.207-0.962, p = 0.039) and residual renal creatinine clearance (OR = 0.956, 95% CI 0.918-0.995, p = 0.027). Addition of these characteristics increased the AUC to 0.813 (95% CI 0.0.749-0.878, P < 0.001). The specificity of presenting with only cloudy effluent for vancomycin-sensitive peritonitis was 98.48%.

CONCLUSIONS

Cloudy dialysate, as the only symptom at PDAP onset, was an independent predictor of vancomycin-sensitive PDAP, which is an important new insight that may guide the choice of initial antibiotic treatment.

Diagnostic Accuracy of MMP-8 and IL-6-Based Point-of-Care Testing to Detect Peritoneal Dialysis-Related Peritonitis: A Single-Center Experience

BACKGROUND

Peritoneal dialysis-related peritonitis (PDRP) is the most common complication of peritoneal dialysis (PD), which can lead to poor outcomes if not diagnosed and treated early. We aimed to investigate the diagnostic accuracy of MMP-8 and IL-6-based point-of-care tests (POCTs) in diagnosing PDRP in PD patients.

METHODS

This retrospective chart review study was conducted at a comprehensive kidney center in Qatar. It involved all adult PD patients who underwent PDRP from July 2018 to October 2019 and for whom MMP-8 and IL-6-based POCTs were used to diagnose presumptive peritonitis. Measures of diagnostic accuracy were computed. Peritoneal fluid effluent analysis was the reference standard.

RESULTS

We included 120 patients (68 [56.7%] females, ages 55.6 ± 15.6 years, treatment duration 39.5 ± 30.4 months [range: 5-142 months]). In this population, MMP-8 and IL-6-based POCTs yielded 100% in all dimensions of diagnostic accuracy (sensitivity, specificity, positive and negative predictive values).

CONCLUSIONS

MMP-8 and IL-6-based POCTs might be helpful in the early detection of PDRP. This monocentric observation requires further confirmation in a prospective multicentric setting.

Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause of sepsis is crucial, and identifying those at risk of complications and death is imperative for triaging treatment and resource allocation. Here, we explored the potential of explainable machine learning models to predict mortality and causative pathogen in sepsis patients. By using a modelling pipeline employing multiple feature selection algorithms, we demonstrate the feasibility of identifying integrative patterns from clinical parameters, plasma biomarkers, and extensive phenotyping of blood immune cells. While no single variable had sufficient predictive power, models that combined five and more features showed a macro area under the curve (AUC) of 0.85 to predict 90-day mortality after sepsis diagnosis, and a macro AUC of 0.86 to discriminate between Gram-positive and Gram-negative bacterial infections. Parameters associated with the cellular immune response contributed the most to models predictive of 90-day mortality, most notably, the proportion of T cells among PBMCs, together with expression of CXCR3 by CD4+ T cells and CD25 by mucosal-associated invariant T (MAIT) cells. Frequencies of Vδ2+ γδ T cells had the most profound impact on the prediction of Gram-negative infections, alongside other T-cell-related variables and total neutrophil count. Overall, our findings highlight the added value of measuring the proportion and activation patterns of conventional and unconventional T cells in the blood of sepsis patients in combination with other immunological, biochemical, and clinical parameters.

Correlating transcription and protein expression profiles of immune biomarkers following lipopolysaccharide exposure in lung epithelial cells

Universal and early recognition of pathogens occurs through recognition of evolutionarily conserved pathogen associated molecular patterns (PAMPs) by innate immune receptors and the consequent secretion of cytokines and chemokines. The intrinsic complexity of innate immune signaling and associated signal transduction challenges our ability to obtain physiologically relevant, reproducible and accurate data from experimental systems. One of the reasons for the discrepancy in observed data is the choice of measurement strategy. Immune signaling is regulated by the interplay between pathogen-derived molecules with host cells resulting in cellular expression changes. However, these cellular processes are often studied by the independent assessment of either the transcriptome or the proteome. Correlation between transcription and protein analysis is lacking in a variety of studies. In order to methodically evaluate the correlation between transcription and protein expression profiles associated with innate immune signaling, we measured cytokine and chemokine levels following exposure of human cells to the PAMP lipopolysaccharide (LPS) from the Gram-negative pathogen Pseudomonas aeruginosa. Expression of 84 messenger RNA (mRNA) transcripts and 69 proteins, including 35 overlapping targets, were measured in human lung epithelial cells. We evaluated 50 biological replicates to determine reproducibility of outcomes. Following pairwise normalization, 16 mRNA transcripts and 6 proteins were significantly upregulated following LPS exposure, while only five (CCL2, CSF3, CXCL5, CXCL8/IL8, and IL6) were upregulated in both transcriptomic and proteomic analysis. This lack of correlation between transcription and protein expression data may contribute to the discrepancy in the immune profiles reported in various studies. The use of multiomic assessments to achieve a systems-level understanding of immune signaling processes can result in the identification of host biomarker profiles for a variety of infectious diseases and facilitate countermeasure design and development.

Random forest can accurately predict the technique failure of peritoneal dialysis associated peritonitis patients

Instructions

Peritoneal dialysis associated peritonitis (PDAP) is a major cause of technique failure in peritoneal dialysis (PD) patients. The purpose of this study is to construct risk prediction models by multiple machine learning (ML) algorithms and select the best one to predict technique failure in PDAP patients accurately.

Methods

This retrospective cohort study included maintenance PD patients in our center from January 1, 2010 to December 31, 2021. The risk prediction models for technique failure were constructed based on five ML algorithms: random forest (RF), the least absolute shrinkage and selection operator (LASSO), decision tree, k nearest neighbor (KNN), and logistic regression (LR). The internal validation was conducted in the test cohort.

Results

Five hundred and eight episodes of peritonitis were included in this study. The technique failure accounted for 26.38%, and the mortality rate was 4.53%. There were resignificant statistical differences between technique failure group and technique survival group in multiple baseline characteristics. The RF prediction model is the best able to predict the technique failure in PDAP patients, with the accuracy of 93.70% and area under curve (AUC) of 0.916. The sensitivity and specificity of this model was 96.67 and 86.49%, respectively.

Conclusion

RF prediction model could accurately predict the technique failure of PDAP patients, which demonstrated excellent predictive performance and may assist in clinical decision making.

Machine learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

BACKGROUND

An appropriate prediction model for adverse prognosis before peritoneal dialysis (PD) is lacking. Thus, we retrospectively analysed patients who underwent PD to construct a predictive model for adverse prognoses using machine learning (ML).

METHODS

A retrospective analysis was conducted on 873 patients who underwent PD from August 2007 to December 2020. A total of 824 patients who met the inclusion criteria were included in the analysis. Five commonly used ML algorithms were used for the initial model training. By using the area under the curve (AUC) and accuracy (ACC), we ranked the indicators with the highest impact and displayed them using the values of Shapley additive explanation (SHAP) version 0.41.0. The top 20 indicators were selected to build a compact model that is conducive to clinical application. All model-building steps were implemented in Python 3.8.3.

RESULTS

At the end of follow-up, 353 patients withdrew from PD (converted to haemodialysis or died), and 471 patients continued receiving PD. In the complete model, the categorical boosting classifier (CatBoost) model exhibited the strongest performance (AUC = 0.80, 95% confidence interval [CI] = 0.76-0.83; ACC: 0.78, 95% CI = 0.72-0.83) and was selected for subsequent analysis. We reconstructed a compression model by extracting 20 key features ranked by the SHAP values, and the CatBoost model still showed the strongest performance (AUC = 0.79, ACC = 0.74).

CONCLUSIONS

The CatBoost model, which was built using the intelligent analysis technology of ML, demonstrated the best predictive performance. Therefore, our developed prediction model has potential value in patient screening before PD and hierarchical management after PD.

The Integration of Artificial Intelligence into Clinical Practice

The purpose of this literature review is to provide a fundamental synopsis of current research pertaining to artificial intelligence (AI) within the domain of clinical practice. Artificial intelligence has revolutionized the field of medicine and healthcare by providing innovative solutions to complex problems. One of the most important benefits of AI in clinical practice is its ability to investigate extensive volumes of data with efficiency and precision. This has led to the development of various applications that have improved patient outcomes and reduced the workload of healthcare professionals. AI can support doctors in making more accurate diagnoses and developing personalized treatment plans. Successful examples of AI applications are outlined for a series of medical specialties like cardiology, surgery, gastroenterology, pneumology, nephrology, urology, dermatology, orthopedics, neurology, gynecology, ophthalmology, pediatrics, hematology, and critically ill patients, as well as diagnostic methods. Special reference is made to legal and ethical considerations like accuracy, informed consent, privacy issues, data security, regulatory framework, product liability, explainability, and transparency. Finally, this review closes by critically appraising AI use in clinical practice and its future perspectives. However, it is also important to approach its development and implementation cautiously to ensure ethical considerations are met.

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.

Inflammatory biomarker signatures in post-surgical drain fluid may detect anastomotic leaks within 48 hours of colorectal resection

BACKGROUND

The optimal treatment of colorectal cancer is surgical resection and primary anastomosis. Anastomotic leak can affect up to 20% of patients and creates significant morbidity and mortality. Current diagnosis of a leak is based on clinical suspicion and subsequent radiology. Peritoneal biomarkers have shown diagnostic utility in other conditions and could be useful in providing earlier diagnosis. This pilot study was designed to assess the practical utility of peritoneal biomarkers after abdominal surgery utilising an automated immunoassay system in routine use for quantifying cytokines.

METHODS

Patients undergoing an anterior resection for a rectal cancer diagnosis were recruited at University Hospital of Wales, Cardiff between June 2019 and June 2021. A peritoneal drain was placed in the proximity of the anastomosis during surgery, and peritoneal fluid was collected at days 1 to 3 post-operatively, and analysed using the Siemens IMMULITE platform for interleukin (IL)-1β, IL-6, IL-10, CXCL8, tumour necrosis factor alpha (TNFα) and C-reactive protein (CRP).

RESULTS

A total of 42 patients were recruited (22M:20F, median age 65). Anastomotic leak was detected in four patients and a further five patients had other intra-abdominal complications. The IMMULITE platform was able to provide robust and reliable results from the analysis of the peritoneal fluid. A metric based on the combination of peritoneal IL-6 and CRP levels was able to accurately diagnose three anastomotic leaks, whilst correctly classifying all negative control patients including those with other complications.

CONCLUSIONS

This pilot study demonstrates that a simple immune signature in surgical drain fluid could accurately diagnose an anastomotic leak at 48 h postoperatively using instrumentation that is already widely available in hospital clinical laboratories.

A review of Spaulding's classification system for effective cleaning, disinfection and sterilization of reusable medical devices: Viewed through a modern-day lens that will inform and enable future sustainability

Despite advances in medicine and innovations in many underpinning fields including disease prevention and control, the Spaulding classification system, originally proposed in 1957, remains widely used for defining the disinfection and sterilization of contaminated re-usable medical devices and surgical instruments. Screening PubMed and Scopus databases using a PRISMA guiding framework generated 272 relevant publications that were used in this review. Findings revealed that there is a need to evolve how medical devices are designed, and processed by cleaning, disinfection (and/or sterilization) to mitigate patient risks, including acquiring an infection. This Spaulding Classification remains in use as it is logical, easily applied and understood by users (microbiologists, epidemiologists, manufacturers, industry) and by regulators. However, substantial changes have occurred over the past 65 years that challenge interpretation and application of this system that includes inter alia emergence of new pathogens (viruses, mycobacteria, protozoa, fungi), a greater understanding of innate and adaptive microbial tolerance to disinfection, toxicity risks, increased number of vulnerable patients and associated patient procedures, and greater complexity in design and use of medical devices. Common cited examples include endoscopes that enable non- or minimal invasive procedures but are highly sophisticated with various types of materials (polymers, electronic components etc), long narrow channels, right angle and heat-sensitive components and various accessories (e.g., values) that can be contaminated with high levels of microbial bioburden and patient tissues after use. Contaminated flexible duodenoscopes have been a source of several significant infection outbreaks, where at least 9 reported cases were caused by multidrug resistant organisms [MDROs] with no obvious breach in processing detected. Despite this, there is evidence of the lack of attention to cleaning and maintenance of these devices and associated equipment. Over the last few decades there is increasing genomic evidence of innate and adaptive resistance to chemical disinfectant methods along with adaptive tolerance to environmental stresses. To reduce these risks, it has been proposed to elevate classification of higher-risk flexible endoscopes (such as duodenoscopes) from semi-critical [contact with mucous membrane and intact skin] to critical use [contact with sterile tissue and blood] that entails a transition to using low-temperature sterilization modalities instead of routinely using high-level disinfection; thus, increasing the margin of safety for endoscope processing. This timely review addresses important issues surrounding use of the Spaulding classification system to meet modern-day needs. It specifically addresses the need for automated, robust cleaning and drying methods combined with using real-time monitoring of device processing. There is a need to understand entire end-to-end processing of devices instead of adopting silo approaches that in the future will be informed by artificial intelligence and deep-learning/machine learning. For example, combinational solutions that address the formation of complex biofilms that harbour pathogenic and opportunistic microorganisms on the surfaces of processed devices. Emerging trends are addressed including future sustainability for the medical devices sector that can be enabled via a new Quintuple Helix Hub approach that combines academia, industry, healthcare, regulators, and society to unlock real world solutions.

Relationship between serum iPTH and peritonitis episodes in patients undergoing continuous ambulatory peritoneal dialysis

Background

Peritonitis is considered as one of the most serious complications that cause hospitalization in patients undergoing continuous ambulatory peritoneal dialysis (CAPD). There is limited evidence on the impact of the parathyroid hormone (PTH) on the first peritoneal dialysis (PD)-associated peritonitis episode. We aimed to investigate the influence of serum intact parathyroid hormone (iPTH) on peritonitis in patients undergoing PD.

Methods

This was a retrospective cohort study. Patients undergoing initial CAPD from a single center in China were enrolled. The baseline characteristics and clinical information were recorded. The primary outcome of interest was the occurrence of the first PD-associated peritonitis episode. Five Cox proportional hazard models were constructed in each group set. In group set 1, all participants were divided into three subgroups by tertiles of the serum concentration of iPTH; in group set 2, all participants were divided into three subgroups based on the serum concentration of iPTH with 150 pg/ml interval (<150, 150-300, and >300 pg/ml). Hazard ratios and 95% confidence intervals (CIs) were calculated for each model. The multivariate linear regression analysis elimination procedure assessed the association between the clinical characteristics at baseline and the iPTH levels. Restricted cubic spline models were constructed, and stratified analyses were also conducted.

Results

A total of 582 patients undergoing initial PD (40% women; mean age, 45.1 ± 11.5 years) from a single center in China were recruited. The median follow-up duration was 25.3 months. Multivariate Cox regression analysis showed that, in the fully adjusted model, a higher serum iPTH level (tertile 3, iPTH >300 pg/ml) was significantly associated with a higher risk of PD-associated peritonitis at 3 years [tertile 3: hazard ratio (HR) = 1.53, 95%CI = 1.03-2.55, p = 0.03; iPTH > 300 pg/ml: HR = 1.57, 95%CI = 1.08-2.27, p = 0.02]. The hazard ratio for every 100 pg/ml increase in serum iPTH level was 1.12 (95%CI = 1.05-1.20, p < 0.01) in the total cohort when treating iPTH as a continuous variable.

Conclusions

An elevated iPTH level was significantly associated with an increased risk of peritonitis in patients undergoing CAPD.

Artificial intelligence in peritoneal dialysis: general overview

OBJECTIVE

This article is a general overview about artificial intelligence/machine learning (AI/ML) algorithms in the domain of peritoneal dialysis (PD).

METHODS

We searched studies that used AI/ML in PD, which were classified according to the type of algorithm and PD issue.

RESULTS

Studies were divided into (a) predialytic stratification, (b) peritoneal technique issues, (c) infections, and (d) complications prediction. Most of the studies were observational and majority of them were reported after 2010.

CONCLUSIONS

There is a number of studies proved that AI/ML algorithms can predict better than conventional statistical method and even nephrologists. However, the soundness of AI/ML algorithms in PD still requires large databases and interpretation by clinical experts. In the future, we hope that AI will facilitate the management of PD patients, thus increasing the quality of life and survival.

ISPD peritonitis guideline recommendations: 2022 update on prevention and treatment

Peritoneal dialysis (PD)-associated peritonitis is a serious complication of PD and prevention and treatment of such is important in reducing patient morbidity and mortality. The ISPD 2022 updated recommendations have revised and clarified definitions for refractory peritonitis, relapsing peritonitis, peritonitis-associated catheter removal, PD-associated haemodialysis transfer, peritonitis-associated death and peritonitis-associated hospitalisation. New peritonitis categories and outcomes including pre-PD peritonitis, enteric peritonitis, catheter-related peritonitis and medical cure are defined. The new targets recommended for overall peritonitis rate should be no more than 0.40 episodes per year at risk and the percentage of patients free of peritonitis per unit time should be targeted at >80% per year. Revised recommendations regarding management of contamination of PD systems, antibiotic prophylaxis for invasive procedures and PD training and reassessment are included. New recommendations regarding management of modifiable peritonitis risk factors like domestic pets, hypokalaemia and histamine-2 receptor antagonists are highlighted. Updated recommendations regarding empirical antibiotic selection and dosage of antibiotics and also treatment of peritonitis due to specific microorganisms are made with new recommendation regarding adjunctive oral N-acetylcysteine therapy for mitigating aminoglycoside ototoxicity. Areas for future research in prevention and treatment of PD-related peritonitis are suggested.

Recent advances in novel diagnostic testing for peritoneal dialysis-related peritonitis

Peritoneal dialysis-related peritonitis remains a significant complication and an important cause of technique failure. Based on current International Society for Peritoneal Dialysis guidelines, diagnosis of peritonitis is made when two of the three following criteria are met: 1) clinical features consistent with peritonitis; 2) dialysis effluent white blood cell count of >100 cells/μL; 3) positive effluent culture. However, early and accurate diagnosis can still be faulty, and emphasis has been placed on improving the timeliness and accuracy of diagnosis to facilitate early effective treatment. There have been advances in the novel diagnostic tests such as point-of-care molecular tests, genetics sequencing, mass spectrometry, and machine learning algorithm with immune fingerprinting. This article will discuss the latest evidence and updates of these tests in the management of peritoneal dialysis-related peritonitis.

Unconventional T cells and kidney disease

Unconventional T cells are a diverse and underappreciated group of relatively rare lymphocytes that are distinct from conventional CD4⁺ and CD8⁺ T cells, and that mainly recognize antigens in the absence of classical restriction through the major histocompatibility complex (MHC). These non-MHC-restricted T cells include mucosal-associated invariant T (MAIT) cells, natural killer T (NKT) cells, γδ T cells and other, often poorly defined, subsets. Depending on the physiological context, unconventional T cells may assume either protective or pathogenic roles in a range of inflammatory and autoimmune responses in the kidney. Accordingly, experimental models and clinical studies have revealed that certain unconventional T cells are potential therapeutic targets, as well as prognostic and diagnostic biomarkers. The responsiveness of human Vγ9Vδ2 T cells and MAIT cells to many microbial pathogens, for example, has implications for early diagnosis, risk stratification and targeted treatment of peritoneal dialysis-related peritonitis. The expansion of non-Vγ9Vδ2 γδ T cells during cytomegalovirus infection and their contribution to viral clearance suggest that these cells can be harnessed for immune monitoring and adoptive immunotherapy in kidney transplant recipients. In addition, populations of NKT, MAIT or γδ T cells are involved in the immunopathology of IgA nephropathy and in models of glomerulonephritis, ischaemia-reperfusion injury and kidney transplantation.

A Study of the Recent Trends of Immunology: Key Challenges, Domains, Applications, Datasets, and Future Directions

The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.

Peritoneal Dialysis Guidelines 2019 Part 1 (Position paper of the Japanese Society for Dialysis Therapy)

Approximately 10 years have passed since the Peritoneal Dialysis Guidelines were formulated in 2009. Much evidence has been reported during the succeeding years, which were not taken into consideration in the previous guidelines, e.g., the next peritoneal dialysis PD trial of encapsulating peritoneal sclerosis (EPS) in Japan, the significance of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs), the effects of icodextrin solution, new developments in peritoneal pathology, and a new international recommendation on a proposal for exit-site management. It is essential to incorporate these new developments into the new clinical practice guidelines. Meanwhile, the process of creating such guidelines has changed dramatically worldwide and differs from the process of creating what were “clinical practice guides.” For this revision, we not only conducted systematic reviews using global standard methods but also decided to adopt a two-part structure to create a reference tool, which could be used widely by the society’s members attending a variety of patients. Through a working group consensus, it was decided that Part 1 would present conventional descriptions and Part 2 would pose clinical questions (CQs) in a systematic review format. Thus, Part 1 vastly covers PD that would satisfy the requirements of the members of the Japanese Society for Dialysis Therapy (JSDT). This article is the duplicated publication from the Japanese version of the guidelines and has been reproduced with permission from the JSDT.

CytoPy: An autonomous cytometry analysis framework

Cytometry analysis has seen a considerable expansion in recent years in the maximum number of parameters that can be acquired in a single experiment. In response to this technological advance there has been an increased effort to develop new computational methodologies for handling high-dimensional single cell data acquired by flow or mass cytometry. Despite the success of numerous algorithms and published packages to replicate and outperform traditional manual analysis, widespread adoption of these techniques has yet to be realised in the field of immunology. Here we present CytoPy, a Python framework for automated analysis of cytometry data that integrates a document-based database for a data-centric and iterative analytical environment. In addition, our algorithm-agnostic design provides a platform for open-source cytometry bioinformatics in the Python ecosystem. We demonstrate the ability of CytoPy to phenotype T cell subsets in whole blood samples even in the presence of significant batch effects due to technical and user variation. The complete analytical pipeline was then used to immunophenotype the local inflammatory infiltrate in individuals with and without acute bacterial infection. CytoPy is open-source and licensed under the MIT license. CytoPy is available at https://github.com/burtonrj/CytoPy, with notebooks accompanying this manuscript (https://github.com/burtonrj/CytoPyManuscript) and software documentation at https://cytopy.readthedocs.io/.

Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning-Based Method to Predict Crucial Complication Phenotypes

BACKGROUND

Acute diseases present severe complications that develop rapidly, exhibit distinct phenotypes, and have profound effects on patient outcomes. Predictive analytics can enhance physicians' care and management of patients with acute diseases by predicting crucial complication phenotypes for a timely diagnosis and treatment. However, effective phenotype predictions require several challenges to be overcome. First, patient data collected in the early stages of an acute disease (eg, clinical data and laboratory results) are less informative for predicting phenotypic outcomes. Second, patient data are temporal and heterogeneous; for example, patients receive laboratory tests at different time intervals and frequencies. Third, imbalanced distributions of patient outcomes create additional complexity for predicting complication phenotypes.

OBJECTIVE

To predict crucial complication phenotypes among patients with acute diseases, we propose a novel, deep learning-based method that uses recurrent neural network-based sequence embedding to represent disease progression while considering temporal heterogeneities in patient data. Our method incorporates a latent regulator to alleviate data insufficiency constraints by accounting for the underlying mechanisms that are not observed in patient data. The proposed method also includes cost-sensitive learning to address imbalanced outcome distributions in patient data for improved predictions.

METHODS

From a major health care organization in Taiwan, we obtained a sample of 10,354 electronic health records that pertained to 6545 patients with peritonitis. The proposed method projects these temporal, heterogeneous, and clinical data into a substantially reduced feature space and then incorporates a latent regulator (latent parameter matrix) to obviate data insufficiencies and account for variations in phenotypic expressions. Moreover, our method employs cost-sensitive learning to further increase the predictive performance.

RESULTS

We evaluated the efficacy of the proposed method for predicting two hepatic complication phenotypes in patients with peritonitis: acute hepatic encephalopathy and hepatorenal syndrome. The following three benchmark techniques were evaluated: temporal multiple measurement case-based reasoning (MMCBR), temporal short long-term memory (T-SLTM) networks, and time fusion convolutional neural network (CNN). For acute hepatic encephalopathy predictions, our method attained an area under the curve (AUC) value of 0.82, which outperforms temporal MMCBR by 64%, T-SLTM by 26%, and time fusion CNN by 26%. For hepatorenal syndrome predictions, our method achieved an AUC value of 0.64, which is 29% better than that of temporal MMCBR (0.54). Overall, the evaluation results show that the proposed method significantly outperforms all the benchmarks, as measured by recall, F-measure, and AUC while maintaining comparable precision values.

CONCLUSIONS

The proposed method learns a short-term temporal representation from patient data to predict complication phenotypes and offers greater predictive utilities than prevalent data-driven techniques. This method is generalizable and can be applied to different acute disease (illness) scenarios that are characterized by insufficient patient clinical data availability, temporal heterogeneities, and imbalanced distributions of important patient outcomes.

Aberrant serum parathyroid hormone, calcium, and phosphorus as risk factors for peritonitis in peritoneal dialysis patients

Identifying modifiable risk factors of peritoneal dialysis (PD)-related peritonitis is of clinical importance in patient care. Mineral bone disease (MBD) has been associated with mortality and morbidity in end-stage kidney disease (ESKD) patients. However, its influence on PD related peritonitis due to altered host immunity remains elusive. This study investigated whether abnormal biomarkers of MBD are associated with the development of peritonitis in patients undergoing maintenance PD. We conducted a retrospective observational cohort study, analysing data derived from a nationwide dialysis registry database in Taiwan, from 2005 to 2012. A total of 5750 ESKD patients commencing PD therapy during this period were enrolled and followed up to 60 months or by the end of the study period. The patients were stratified based on their baseline serum parathyroid hormone (PTH) levels, calcium (Ca) levels or phosphorus (P) levels, respectively or in combinations. The primary outcome was the occurrence of first episode of peritonitis, and patient outcomes such as deaths, transfer to haemodialysis or receiving renal transplantation were censored. Peritonitis-free survival and the influence of PTH, Ca, P (individual or in combination) on the peritonitis occurrence were analysed. A total of 5750 PD patients was enrolled. Of them, 1611 patients experienced their first episode of peritonitis during the study period. Patients with low PTH, high Ca or low P levels, respectively or in combination, had the lowest peritonitis-free survival. After adjusting for age, sex and serum albumin levels, we found that the combinations of low PTH levels with either high Ca levels or low/normal P levels were significant risk factors of developing peritonitis. Abnormal mineral bone metabolism in maintenance PD patients with low serum PTH levels, in combination with either high Ca levels or low/normal P levels, could be novel risk factors of PD-related peritonitis.

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.

IL-17A as a Potential Therapeutic Target for Patients on Peritoneal Dialysis

Chronic kidney disease (CKD) is a health problem reaching epidemic proportions. There is no cure for CKD, and patients may progress to end-stage renal disease (ESRD). Peritoneal dialysis (PD) is a current replacement therapy option for ESRD patients until renal transplantation can be achieved. One important problem in long-term PD patients is peritoneal membrane failure. The mechanisms involved in peritoneal damage include activation of the inflammatory and immune responses, associated with submesothelial immune infiltrates, angiogenesis, loss of the mesothelial layer due to cell death and mesothelial to mesenchymal transition, and collagen accumulation in the submesothelial compact zone. These processes lead to fibrosis and loss of peritoneal membrane function. Peritoneal inflammation and membrane failure are strongly associated with additional problems in PD patients, mainly with a very high risk of cardiovascular disease. Among the inflammatory mediators involved in peritoneal damage, cytokine IL-17A has recently been proposed as a potential therapeutic target for chronic inflammatory diseases, including CKD. Although IL-17A is the hallmark cytokine of Th17 immune cells, many other cells can also produce or secrete IL-17A. In the peritoneum of PD patients, IL-17A-secreting cells comprise Th17 cells, γδ T cells, mast cells, and neutrophils. Experimental studies demonstrated that IL-17A blockade ameliorated peritoneal damage caused by exposure to PD fluids. This article provides a comprehensive review of recent advances on the role of IL-17A in peritoneal membrane injury during PD and other PD-associated complications.

Evaluation of a new rapid-diagnostic test for peritonitis in peritoneal dialysis: the PERIPLEX® device

In 2017, the British company MOLOGIC developed a new rapid-diagnostic test (PERIPLEX®) for the diagnosis of peritonitis in patients undergoing peritoneal dialysis. This single-use test is based on the detection in dialysate of two biomarkers of bacterial infection: Interleukin-6 (IL-6) and matrix metalloproteinase-8 (MMP-8). The test was evaluated in a prospective multicenter study including 10 centers from the RDPLF (French Language Peritoneal Dialysis Registry). A total of 184 tests were performed; 86 tests were negative and 98 were positive. 85 peritonitis were confirmed. There were no false-negatives, and 13 false-positives. Of the 13 false-positives, 7 of them were for sepsis without peritonitis, or peritoneal inflammation. The performance of the test is considered excellent: sensitivity 100%, specificity 86.9%, positive predictive value 86.7%, negative predictive value 100%. In this study, a negative test can formally rule out the diagnosis of peritonitis.

Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections

Sepsis is a high-mortality disease that is infected by bacteria, but pathogens in individual patients are difficult to diagnosis. Metabolomic changes triggered by microbial activity provide us with the possibility of accurately identifying infection. We adopted machine learning methods for training different classifiers with a clinical-metabolomic database from sepsis cases to identify the pathogen of sepsis. Records of clinical indicators and concentration of metabolites were obtained for each patient upon their arrival at the hospital. Machine learning algorithms were used in 100 patients with clear infection and corresponding 29 controls to select specific biosignatures to discriminate microorganism in septic patients. The sensitivity, specificity, and AUC value of clinical and metabolomic characteristics in predicting diagnostic outcomes were determined at admission. Our analyses demonstrate that the biosignatures selected by machine learning algorithms could have diagnostic value on the identification of infected patients and Gram-positive from Gram-negative; related AUC values were 0.94 ± 0.054 and 0.80 ± 0.085, respectively. Pathway and blood disease enrichment analyses of clinical and metabolomic biomarkers among infected patients showed that sepsis disease was accompanied by abnormal nitrogen metabolism, cell respiratory disorder, and renal or intestinal failure. The panel of selected clinical and metabolomic characteristics might be powerful biomarkers to discriminate patients with sepsis.

Vibrational Spectroscopy of Peritoneal Dialysis Effluent for Rapid Assessment of Patient Characteristics

Peritoneal dialysis (PD) offers specific advantages over hemodialysis, enabling increased autonomy of patients with end-stage renal disease, but PD-related complications need to be detected in a timely manner. Fourier transform infrared (FTIR) spectroscopy could provide rapid and essential insights into the patients' risk profiles via molecular fingerprinting of PD effluent, an abundant waste material that is rich in biological information. In this study, we measured FTIR spectroscopic profiles in PD effluent from patients taking part in a randomized controlled trial of alanyl-glutamine addition to the PD-fluid. Principal component analysis of FTIR spectra enabled us to differentiate between effluent samples from patients immediately after completion of instillation of the PD-fluid into the patients' cavity and 4 h later as well as between patients receiving PD-fluid supplemented with 8 mM alanyl-glutamine compared with control. Moreover, feasibility of FTIR spectroscopy coupled to supervised classification algorithms to predict patient-, PD-, as well as immune-associated parameters were investigated. PD modality (manual continuous ambulatory PD (CAPD) vs. cycler-assisted automated PD (APD)), residual urine output, ultrafiltration, transport parameters, and cytokine concentrations showed high predictive potential. This study provides proof-of-principle that molecular signatures determined by FTIR spectroscopy of PD effluent, combined with machine learning, are suitable for cost-effective, high-throughput diagnostic purposes in PD.

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.

Control of neutrophil influx during peritonitis by transcriptional cross-regulation of chemokine CXCL1 by IL-17 and IFN-γ

Neutrophil infiltration is a hallmark of peritoneal inflammation, but mechanisms regulating neutrophil recruitment in patients with peritoneal dialysis (PD)-related peritonitis are not fully defined. We examined 104 samples of PD effluent collected during acute peritonitis for correspondence between a broad range of soluble parameters and neutrophil counts. We observed an association between peritoneal IL-17 and neutrophil levels. This relationship was evident in effluent samples with low but not high IFN-γ levels, suggesting a differential effect of IFN-γ concentration on neutrophil infiltration. Surprisingly, there was no association of neutrophil numbers with the level of CXCL1, a key IL-17-induced neutrophil chemoattractant. We investigated therefore the production of CXCL1 by human peritoneal mesothelial cells (HPMCs) under in vitro conditions mimicking clinical peritonitis. Stimulation of HPMCs with IL-17 increased CXCL1 production through induction of transcription factor SP1 and activation of the SP1-binding region of the CXCL1 promoter. These effects were amplified by TNFα. In contrast, IFN-γ dose-dependently suppressed IL-17-induced SP1 activation and CXCL1 production through a transcriptional mechanism involving STAT1. The SP1-mediated induction of CXCL1 was also observed in HPMCs exposed to PD effluent collected during peritonitis and containing IL-17 and TNFα, but not IFN-γ. Supplementation of the effluent with IFN-γ led to a dose-dependent activation of STAT1 and a resultant inhibition of SP1-induced CXCL1 expression. Transmesothelial migration of neutrophils in vitro increased upon stimulation of HPMCs with IL-17 and was reduced by IFN-γ. In addition, HPMCs were capable of binding CXCL1 at their apical cell surface. These observations indicate that changes in relative peritoneal concentrations of IL-17 and IFN-γ can differently engage SP1-STAT1, impacting on mesothelial cell transcription of CXCL1, whose release and binding to HPMC surface may determine optimal neutrophil recruitment and retention during peritonitis. © 2020 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

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.

Measurement of innate immune response biomarkers in peritoneal dialysis effluent using a rapid diagnostic point-of-care device as a diagnostic indicator of peritonitis

Peritonitis is the commonest complication of peritoneal dialysis and a major reason for treatment failure. Current diagnosis is based on clinical symptoms, cloudy effluent and a dialysate white cell count (over 100 cells/μl). A rapid point-of-care diagnostic test would accelerate diagnosis and potentially improve outcomes from infection. Here, in a clinical audit project, we used PERiPLEX®, a point-of-care device which detects when levels of matrix metalloproteinase-8 and interleukin-6 are elevated above a threshold within minutes in dialysis effluent, to assess whether it could confirm or exclude peritonitis in 107 patients undergoing peritoneal dialysis. Mean patient age was 64.6 years with a median duration of peritoneal dialysis of 13.3 months (interquartile range 6.3 - 33.5 months). Presence of peritonitis was confirmed by clinical criteria. There were 49 positive tests of which 41 patients had peritonitis, three had other causes of intra-peritoneal inflammation, three had severe urosepsis and two patients required no treatment. Fifty-eight tests were negative with one patient having a false negative result. The positive predictive value of the test was 83.7% (95% confidence interval 72.8 - 90.8) and the negative predictive value was 98.3% (89.1 - 99.8). Sensitivity and specificity were 97.6% (87.4 - 99.9) and 87.7% (77.2 - 94.5) respectively. Thus, PERiPLEX® could be used as a rapid point-of-care test that can aid the diagnosis or exclusion of peritonitis with a high negative predictive value.

Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms

Women with uncomplicated urinary tract infection (UTI) symptoms are commonly treated with empirical antibiotics, resulting in overuse of antibiotics, which promotes antimicrobial resistance. Available diagnostic tools are either not cost-effective or diagnostically sub-optimal. Here, we identified clinical and urinary immunological predictors for UTI diagnosis. We explored 17 clinical and 42 immunological potential predictors for bacterial culture among women with uncomplicated UTI symptoms using random forest or support vector machine coupled with recursive feature elimination. Urine cloudiness was the best performing clinical predictor to rule out (negative likelihood ratio [LR−] = 0.4) and rule in (LR+ = 2.6) UTI. Using a more discriminatory scale to assess cloudiness (turbidity) increased the accuracy of UTI prediction further (LR+ = 4.4). Urinary levels of MMP9, NGAL, CXCL8 and IL-1β together had a higher LR+ (6.1) and similar LR− (0.4), compared to cloudiness. Varying the bacterial count thresholds for urine culture positivity did not alter best clinical predictor selection, but did affect the number of immunological predictors required for reaching an optimal prediction. We conclude that urine cloudiness is particularly helpful in ruling out negative UTI cases. The identified urinary biomarkers could be used to develop a point of care test for UTI but require further validation.

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

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

NK Cells in Ascites From Liver Disease Patients Display a Particular Phenotype and Take Part in Antibacterial Immune Response

Background and Aims: Ascites and spontaneous bacterial peritonitis (SBP) are frequent complications of liver cirrhosis. In spite of the clinical impact, knowledge about ascites as an immune cell compartment in liver disease is limited. Therefore, we analyzed NK cells in blood, ascites, and liver. Methods: Mononuclear cells from blood, ascites, and liver explants of patients with advanced liver disease were extracted by density gradient centrifugation. Phenotyping and analysis of functional responses were carried out using flow cytometry. Migratory potential was investigated with transwell chamber assays. NK cell metabolism was assessed by Seahorse technology. Results: NK cell frequency was increased in uninfected ascites compared to blood, but not to liver. Ascites NK cells were predominantly CD16positive. CD56bright ascites NK cells did not share the typical phenotype of their liver counterparts. In contrast to the inhibitory receptor NKG2A, expression of the activating receptor NKG2D was decreased on ascites and liver CD16positive NK cells. Ascites NK cells expressed higher levels of CXCR3 than blood or liver NK cells, corresponding to increased ascites levels of CXCL10. Blood NK cells migrated toward ascites. Stimulation of mononuclear cells with Escherichia coli led to downregulation of NKG2D expression and IL-12 and IL-18 mediated secretion of interferon-γ by ascites and liver, but not blood NK cells. In-vivo, ascites NK cells expressed higher levels of the activation marker CD69 and lower levels of NKG2D during SBP compared to uninfected ascites. Conclusion: Ascites NK cells display a particular phenotype and are implicated in local immune defense against translocating bacteria.

Neutrophil-derived miR-223 as local biomarker of bacterial peritonitis

Infection remains a major cause of morbidity, mortality and technique failure in patients with end stage kidney failure who receive peritoneal dialysis (PD). Recent research suggests that the early inflammatory response at the site of infection carries diagnostically relevant information, suggesting that organ and pathogen-specific "immune fingerprints" may guide targeted treatment decisions and allow patient stratification and risk prediction at the point of care. Here, we recorded microRNA profiles in the PD effluent of patients presenting with symptoms of acute peritonitis and show that elevated peritoneal miR-223 and reduced miR-31 levels were useful predictors of bacterial infection. Cell culture experiments indicated that miR-223 was predominantly produced by infiltrating immune cells (neutrophils, monocytes), while miR-31 was mainly derived from the local tissue (mesothelial cells, fibroblasts). miR-223 was found to be functionally stabilised in PD effluent from peritonitis patients, with a proportion likely to be incorporated into neutrophil-derived exosomes. Our study demonstrates that microRNAs are useful biomarkers of bacterial infection in PD-related peritonitis and have the potential to contribute to disease-specific immune fingerprints. Exosome-encapsulated microRNAs may have a functional role in intercellular communication between immune cells responding to the infection and the local tissue, to help clear the infection, resolve the inflammation and restore homeostasis.

An Equation Based on Fuzzy Mathematics to Assess the Timing of Haemodialysis Initiation

In order to develop an equation that integrates multiple clinical factors including signs and symptoms associated with uraemia to assess the initiation of dialysis, we conducted a retrospective cohort study including 25 haemodialysis centres in Mainland China. Patients with ESRD (n = 1281) who commenced haemodialysis from 2008 to 2011 were enrolled in the development cohort, whereas 504 patients who began haemodialysis between 2012 and 2013 were enrolled in the validation cohort comprised. An artificial neural network model was used to select variables, and a fuzzy neural network model was then constructed using factors affecting haemodialysis initiation as input variables and 3-year survival as the output variable. A logistic model was set up using the same variables. The equation’s performance was compared with that of the logistic model and conventional eGFR-based assessment. The area under the bootstrap-corrected receiver-operating characteristic curve of the equation was 0.70, and that of two conventional eGFR-based assessments were 0.57 and 0.54. In conclusion, the new equation based on Fuzzy mathematics, covering laboratory and clinical variables, is more suitable for assessing the timing of dialysis initiation in a Chinese ESRD population than eGFR, and may be a helpful tool to quantitatively evaluate the initiation of haemodialysis.

IL-17 in Peritoneal Dialysis-Associated Inflammation and Angiogenesis: Conclusions and Perspectives

Long-term peritoneal dialysis (PD) is associated with peritoneal membrane remodeling. This includes changes in peritoneal vasculature, which may ultimately lead to inadequate solute and water removal and treatment failure. The potential cause of such alterations is chronic inflammation induced by repeated episodes of infectious peritonitis and/or exposure to bioincompatible PD fluids. While these factors may jeopardize the peritoneal membrane integrity, it is not clear why adverse peritoneal remodeling develops only in some PD patients. Increasing evidence points to the differences that occur between patients in response to the same invading microorganism and/or the differences in the course of inflammatory reaction triggered by different species. Such differences may be related to the involvement of different inflammatory mediators. Here, we discuss the potential role of IL-17 in these processes with emphasis on its impact on peritoneal mesothelial cells and peritoneal vascularity.

Developing a Machine Learning System for Identification of Severe Hand, Foot, and Mouth Disease from Electronic Medical Record Data

Children of severe hand, foot, and mouth disease (HFMD) often present with same clinical features as those of mild HFMD during the early stage, yet later deteriorate rapidly with a fulminant disease course. Our goal was to: (1) develop a machine learning system to automatically identify cases with high risk of severe HFMD at the time of admission; (2) compare the effectiveness of the new system with the existing risk scoring system. Data on 2,532 HFMD children admitted between March 2012 and July 2015, were collected retrospectively from a medical center in China. By applying a holdout strategy and a 10-fold cross validation method, we developed four models with the random forest algorithm using different variable sets. The prediction system HFMD-RF based on the model of 16 variables from both the structured and unstructured data, achieved 0.824 sensitivity, 0.931 specificity, 0.916 accuracy, and 0.916 area under the curve in the independent test set. Most remarkably, HFMD-RF offers significant gains with respect to the commonly used pediatric critical illness score in clinical practice. As all the selected risk factors can be easily obtained, HFMD-RF might prove to be useful for reductions in mortality and complications of severe HFMD.

Onchocerca volvulus: The Road from Basic Biology to a Vaccine

Human onchocerciasis - commonly known as river blindness - is one of the most devastating yet neglected tropical diseases, leaving many millions in sub-Saharan Africa blind and/or with chronic disabilities. Attempts to eliminate onchocerciasis, primarily through the mass drug administration of ivermectin, remains challenging and has been heightened by the recent news that drug-resistant parasites are developing in some populations after years of drug treatment. Needed, and needed now, in the fight to eliminate onchocerciasis are new tools, such as preventive and therapeutic vaccines. This review summarizes the progress made to advance the onchocerciasis vaccine from the research laboratory into the clinic.