Live-donor kidney transplant outcome prediction (L-TOP) using artificial intelligence.

Outcome prediction for live-donor kidney transplantation improves clinical and patient decisions and donor selection. However, the concurrently used models are of limited discriminative or calibration power and there is a critical need to improve the selection process. We aimed to assess the value of various artificial intelligence (AI) algorithms to improve the risk stratification index. We evaluated pre-transplant variables among 66 914 live-donor kidney transplants (performed between 01/12/2007-01/06/2021) from the United Network of Organ Sharing database, randomized into training (80%) and test (20%) sets. The primary outcome measure was death-censored graft survival. We tested four machine learning models for discrimination (time-dependent concordance index, CTD, and area under the ROC curve) and calibration (integrated Brier score, IBS). We used decision curve analysis to assess the potential clinical utility. Among the models, the deep Cox mixture model showed the best discriminative performance (AUC = 0.70, 0.68, and 0.68 at 5, 10, and 13 years post-transplant, respectively). CTD reached 0.70, 0.67, and 0.66 at 5, 10, and 13 years post-transplant. The IBS score was 0.09, indicating good calibration. In comparison, applying the Living Kidney Donor Profile Index (LKDPI) on the same cohort produced a CTD of 0.56 and an AUC of 0.55-0.58 only. Decision curve analysis showed an additional net benefit compared to the LKDPI, 'Treat all' and 'Treat None' approaches. Our AI-based deep Cox mixture model, termed Live-Donor Kidney Transplant Outcome Prediction outperforms existing prediction models, including the LKDPI, with the potential to improve decisions for optimum live donor selection by ranking potential transplant pairs based on graft survival. This model could be adopted to improve the outcomes of paired exchange programs.

Magnesium Is a Vital Ion in the Body-It Is Time to Consider Its Supplementation on a Routine Basis.

The importance of maintaining proper magnesium intake and total body magnesium content in preserving human health remains underappreciated among medical professionals and laymen. This review aimed to show the importance of hypomagnesemia as a modifiable risk factor for developing disease processes. We searched the PubMed database and Google Scholar using the keywords 'magnesium', 'diabetes', 'cardiovascular disease', 'respiratory disease', 'immune system', 'inflammation', 'autoimmune disease', 'neurology', 'psychiatry', 'cognitive function', 'cancer', and 'vascular calcification'. In multiple contexts of the search terms, all reviews, animal experiments, and human observational data indicated that magnesium deficiency can lead to or contribute to developing many disease states. The conclusions of several in-depth reviews support our working hypothesis that magnesium and its supplementation are often undervalued and underutilized. Although much research has confirmed the importance of proper magnesium supply and tissue levels, simple and inexpensive magnesium supplementation has not yet been sufficiently recognized or promoted.

Deceased-Donor Kidney Transplant Outcome Prediction Using Artificial Intelligence to Aid Decision-Making in Kidney Allocation.

In kidney transplantation, pairing recipients with the highest longevity with low-risk allografts to optimize graft-donor survival is a complex challenge. Current risk prediction models exhibit limited discriminative and calibration capabilities and have not been compared to modern decision-assisting tools. We aimed to develop a highly accurate risk-stratification index using artificial intelligence (AI) techniques. Using data from the UNOS database (156,749 deceased kidney transplants, 2007-2021), we randomly divided transplants into training (80%) and validation (20%) sets. The primary measure was death-censored graft survival. Four machine learning models were assessed for calibration (integrated Brier score [IBS]) and discrimination (time-dependent concordance [CTD] index), compared with existing models. We conducted decision curve analysis and external validation using UK Transplant data. The Deep Cox mixture model showed the best discriminative performance (area under the curve [AUC] = 0.66, 0.67, and 0.68 at 6, 9, and 12 years post-transplant), with CTD at 0.66. Calibration was adequate (IBS = 0.12), while the kidney donor profile index (KDPI) model had lower CTD (0.59) and AUC (0.60). AI-based D-TOP outperformed the KDPI in evaluating transplant pairs based on graft survival, potentially enhancing deceased donor selection. Advanced computing is poised to influence kidney allocation schemes.

Artificial intelligence and machine learning trends in kidney care.

BACKGROUND: The integration of artificial intelligence (AI) and machine learning (ML) in kidney care has seen a significant rise in recent years. This study specifically analyzed AI and ML research publications related to kidney care to identify leading authors, institutions, and countries in this area. It aimed to examine publication trends and patterns, and to explore the impact of collaborative efforts on citation metrics. METHODS: The study used the Science Citation Index Expanded (SCI-EXPANDED) of Clarivate Analytics Web of Science Core Collection to search for AI and machine learning publications related to nephrology from 1992 to 2021. The authors used quotation marks and Boolean operator "or" to search for keywords in the title, abstract, author keywords, and Keywords Plus. In addition, the 'front page' filter was applied. A total of 5425 documents were identified and analyzed. RESULTS: The results showed that articles represent 75% of the analyzed documents, with an average author to publications ratio of 7.4 and an average number of citations per publication in 2021 of 18. English articles had a higher citation rate than non-English articles. The USA dominated in all publication indicators, followed by China. Notably, the research also showed that collaborative efforts tend to result in higher citation rates. A significant portion of the publications were found in urology journals, emphasizing the broader scope of kidney care beyond traditional nephrology. CONCLUSIONS: The findings underscore the importance of AI and ML in enhancing kidney care, offering a roadmap for future research and implementation in this expanding field.

Susac Syndrome and Role of Therapeutic Plasma Exchange: A Case Report.

Susac syndrome is a relatively uncommon autoimmune disease that predominantly affects young females, with the highest incidence between the third and fourth decade of life, presenting classically with encephalopathy, various CNS dysfunctions, visual impairment due to retinal artery occlusion, and hearing loss. Despite treatment options, such as glucocorticoid steroids, intravenous immunoglobulin, methotrexate, azathioprine, mycophenolate mofetil, or rituximab, some patients with Susac syndrome remain refractory to therapy. We present a case report of a 38-year-old female with refractory Susac syndrome who was treated successfully with plasmapheresis.

A bibliometric analysis of publications in Renal Failure in the last three decades.

Publications in Renal Failure in Science Citation Index Expanded (SCI-EXPANDED) between 1992 and 2021 were analyzed. Six publication indicators: total, independent, collaborative, first author, corresponding author, and single author publications as well as their related citation indicators, were used to compare performances of countries, institutes, and authors. Comparison of the highly cited papers and journal's impact factor (IF) contributors was discussed. In addition, the main research topics in the journal were presented. Results show that China published the most total articles and reviews, as well as the first-author papers and corresponding-author papers in the journal. The Chang Gung Memorial Hospital in Taiwan ranked the top in five publication indicators: total, single-institution, inter-institutionally collaborative, first author, and corresponding-author papers. A low percentage of productive authors emerged as a journal IF contributor. Similarly, only a limited relationship between highly cited papers and IF contributing papers was found. Publications related to hemodialysis, chronic kidney disease, and acute kidney injury were the most popular topic, while meta-analysis was new focus in the last decade in the journal.

Prevention of Intradialytic Hypotension in Hemodialysis Patients: Current Challenges and Future Prospects.

Intradialytic hypotension, defined as rapid decrease in systolic blood pressure of greater than or equal to 20 mmHg or in mean arterial pressure of greater than or equal to 10 mmHg that results in end-organ ischemia and requires countermeasures such as ultrafiltration reduction or saline infusion to increase blood pressure to improve patient's symptoms, is a known complication of hemodialysis and is associated with several potential adverse outcomes. Its pathogenesis is complex and involves both patient-related factors such as age and comorbidities, as well as factors related to the dialysis prescription itself. Key factors include the need for volume removal during hemodialysis and a suboptimal vascular response which compromises the ability to compensate for acute intravascular volume loss. Inadequate vascular refill, incorrect assessment or unaccounted changes of target weight, acute illnesses and medication interference are further potential contributors. Intradialytic hypotension can lead to compromised tissue perfusion and end-organ damage, both acutely and over time, resulting in repetitive injuries. To address these problems, a careful assessment of subjective symptoms, minimizing interdialytic weight gains, individualizing dialysis prescription and adjusting the dialysis procedure based on patients' risk factors can mitigate negative outcomes.

A Critical Reassessment of the Kidney Risk Caused by Tetrastarch Products in the Perioperative and Intensive Care Environments.

Purpose: To reassess the results of former meta-analyses focusing on the relationship between novel HES preparations (130/0.4 and 130/0.42) and acute kidney injury. Previous meta-analyses are based on studies referring to partially or fully unpublished data or data from abstracts only. Methods: The studies included in the former meta-analyses were scrutinized by the authors independently. We completed a critical analysis of the literature, including the strengths, weaknesses and modifiers of the studies when assessing products, formulations and outcomes. Results: Both the published large studies and meta-analyses show significant bias in the context of the deleterious effect of 6% 130/0.4-0.42 HES. Without (1) detailed hemodynamic data, (2) the exclusion of other nephrotoxic events and (3) a properly performed evaluation of the dose-effect relationship, the AKI-inducing property of 6% HES 130/0.4 or 0.42 should not be considered as evidence. The administration of HES is safe and effective if the recommended dose is respected. Conclusions: Our review suggests that there is questionable evidence for the deteriorating renal effect of these products. Further well-designed, randomized and controlled trials are needed. Additionally, conclusions formulated for resource-rich environments should not be extended to more resource-scarce environments without proper qualifiers provided.

The Importance of the Nephrologist in the Treatment of the Diuretic-Resistant Heart Failure.

Heart failure is not only a global problem but also significantly limits the life prospects of these patients. The epidemiology and presentation of heart failure are intensively researched topics in cardiology. The risk factors leading to heart failure are well known; however, the real challenge is to provide effective treatments. A vicious cycle develops in heart failure of all etiologies, sooner or later compromising both cardiac and kidney functions simultaneously. This can explain the repeated hospital admissions due to decompensation and the significantly reduced quality of life. Moreover, diuretic-refractory heart failure represents a distinct challenge due to repeated hospital admissions and increased mortality. In our narrative review, we wanted to draw attention to nephrology treatment options for severe diuretic-resistant heart failure. The incremental value of peritoneal dialysis in severe heart failure and the feasibility of percutaneous peritoneal dialysis catheter insertion have been well known for many years. In contrast, the science and narrative of acute peritoneal dialysis in diuretic-resistant heart failure remains underrepresented. We believe that nephrologists are uniquely positioned to help these patients by providing acute peritoneal dialysis to reduce hospitalization dependency and increase their quality of life.

Outcomes of thymoglobulin versus basiliximab induction therapies in living donor kidney transplant recipients with mild to moderate immunological risk - a retrospective analysis of UNOS database.

INTRODUCTION: The aim of this study is to assess the outcomes of different induction therapies among mild to moderate immunological risk kidney transplants in the era tacrolimus and mycophenolate-derivate based maintenance. METHODS: This was a retrospective cohort study using data from the United States Organ Procurement and Transplantation Network among mild to moderate immunological risk living-donor KTRs, defined as having first transplant and panel reactive antibodies less than 20% but with two HLA-DR mismatches. KTRs were divided into two groups based on induction therapy with either thymoglobulin or basiliximab. Instrumental variable regression models were used to assess the effect of induction therapy on acute rejection episodes, serum creatinine levels and graft survival. RESULTS: Of the entire cohort, 788 patients received basiliximab while 1727 patients received thymoglobulin induction. There were no significant differences between basiliximab versus thymoglobulin induction in acute rejection episodes at one-year post-transplant (coefficient= -0.229, p value = .106), serum creatinine levels at one-year post-transplant (coefficient= -0.024, p value = .128) or death-censored graft survival (coefficient: - <0.001, p value = .201). CONCLUSION: This study showed no significant difference in acute rejection episodes or graft survival when using thymoglobulin or basiliximab in mild to moderate immunological risk living donor KTRs, maintained on tacrolimus and mycophenolate-based immunosuppressive regimen.

Outcomes of Remote Patient Monitoring in Peritoneal Dialysis: A Meta-Analysis and Review of Practical Implications for COVID-19 Epidemics.

The present study seeks to determine clinical outcomes associated with remote patient monitoring of peritoneal dialysis (RPM-PD), with potential implications during COVID-19 outbreaks. We performed a systematic review in the PubMed, Embase, and Cochrane databases. We combined all study-specific estimates using the inverse-variant weighted averages of logarithmic relative risk (RR) in the random-effects models. Confidence interval (CI) including the value of 1 was used as evidence to produce a statistically significant estimate. Twenty-two studies were included in our meta-analysis. Quantitative analysis demonstrated that RPM-PD patients had lower rates of technique failure (log RR = -0.32; 95% CI, -0.59 to -0.04), lower hospitalization rates (standardized mean difference = -0.84; 95% CI, -1.24 to -0.45), and lower mortality rates (log RR = -0.26; 95% CI, -0.44 to -0.08) compared with traditional PD monitoring. RPM-PD has better outcomes in multiple spheres of outcomes when compared with conventional monitoring and likely increases system resilience during disruptions of healthcare operations.

Hypomagnesemia as a Risk Factor and Accelerator for Vascular Aging in Diabetes Mellitus and Chronic Kidney Disease.

The age-old axiom that one is as old as his or her vessels are, calls for ongoing critical re-examination of modifiable risk factors of accelerated vascular ageing in chronic kidney diseases. Attempts to modulate vascular risk with cholesterol-lowering agents have largely failed in advanced chronic kidney disease (CKD). In addition to nitrogen waste products, many pathological biochemical processes also play a role in vascular calcification in chronic kidney damage. Magnesium, a cation vital for the body, may substantially reduce cardiovascular diseases' risk and progression. This narrative review aimed to address the relationship between hypomagnesemia and vascular calcification, which promotes further cardiovascular complications in diabetes, aging, and CKD. Articles with predefined keywords were searched for in the PubMed and Google Scholar databases with specific inclusion and exclusion criteria. We hypothesized that a decrease in serum magnesium levels contributes to increased vascular calcification and thereby increases cardiovascular mortality. In summary, based on existing evidence in the literature, it appears that simple and inexpensive oral magnesium supplementation may reduce the cardiovascular mortality of patients who are already severely affected by such diseases; in this context, the concept of 'normal' vs. 'ideal' serum magnesium levels should be carefully re-examined.

Pneumoperitoneum and Acute Kidney Injury-An Integrative Clinical Concept Review.

An increased intraabdominal pressure, particularly when occurring during periods of hemodynamic instability or fluid overload, is regarded as a major contributor to acute kidney injury (AKI) in intensive care units. During abdominal laparoscopic procedures, intraoperative insufflation pressures up to 15 mmHg are applied, to enable visualization and surgical manipulation but with the potential to compromise net renal perfusion. Despite the widely acknowledged renal arterial autoregulation, net arterial perfusion pressure is known to be narrow, and the effective renal medullary perfusion is disproportionately impacted by venous and lymphatic congestion. At present, the potential risk factors, mitigators and risk-stratification of AKI during surgical pneumoperitoneum formation received relatively limited attention among nephrologists and represent an opportunity to look beyond mere blood pressure and intake-output balances. Careful charting and reporting duration and extent of surgical pneumoperitoneum represents an opportunity for anesthesia teams to better communicate intraoperative factors affecting renal outcomes for the postoperative clinical teams. In this current article, the authors are integrating preclinical data and clinical experience to provide a better understanding to optimize renal perfusion during surgeries. Future studies should carefully consider intrabdominal insufflation pressure as a key variable when assessing outcomes and blood pressure goals in these settings.

A Critical Review of Medication Adherence in Hypertension: Barriers and Facilitators Clinicians Should Consider.

Hypertension is a global public health problem, and its prevalence is increasing worldwide. Impacting all human societies and socioeconomic strata, it remains the major modifiable risk factor for global burden of cardiovascular disease all-cause mortality and the leading cause of loss of disability-adjusted life years. Despite increased awareness, the rate of blood pressure control remains unsatisfactory, particularly in low- to middle-income countries. Apparent treatment-resistant hypertension is associated with worse adverse health outcomes. It includes both true resistant and pseudo-resistant hypertension, which requires out-of-office blood pressure monitoring to exclude white-coat effect and confirmation of adherence to the agreed recommended antihypertensive therapy. The depth of medication non-adherence remains poorly recognized among medical practitioners, thus presenting an underestimated modifiable risk factor. Medication non-adherence is a complex and multidimensional variable with three quantifiable phases: initiation, implementation, and discontinuation, collectively called persistence. Non-adherence can be both intentional and non-intentional and usually involves several interconnected factors. Persistence declines over time in the treatment of chronic diseases like hypertension. The risk is higher in patients with new diagnosis, poor insurance status, polypharmacy, and multiple comorbidities, particularly psychiatric disorders. The World Health Organization divides the contributing factors impacting adherence into five categories. Screening and detection for medication non-adherence are challenging due to its dynamic nature and potential white-coat effect. Easy-to-conduct screening methods have low reliability and validity, whereas more reliable and valid methods are costly and difficult to perform. Medication non-adherence is associated with poor clinical outcome and potential negative impact on health-care costs. Evaluation of adherence should become an integral part of assessment of patients treated for hypertension. Medication adherence can significantly improve with a patient-centered approach, non-judgmental communication skills, and collaborative multidisciplinary management, including engagement of the patients in their care by self-blood pressure monitoring.

Real-world characteristics, modern antidiabetic treatment patterns, and comorbidities of patients with type 2 diabetes in central and Eastern Europe: retrospective cross-sectional and longitudinal evaluations in the CORDIALLY® study.

BACKGROUND: Guidelines from 2016 onwards recommend early use of SGLT2i or GLP-1 RA for patients with type 2 diabetes (T2D) and cardiovascular disease (CVD), to reduce CV events and mortality. Many eligible patients are not treated accordingly, although data are lacking for Central and Eastern Europe (CEE). METHODS: The CORDIALLY non-interventional study evaluated the real-world characteristics, modern antidiabetic treatment patterns, and the prevalence of CVD and chronic kidney disease (CKD) in adults with T2D at nonhospital-based practices in CEE. Data were retrospectively collated by medical chart review for patients initiating empagliflozin, another SGLT2i, DPP4i, or GLP-1 RA in autumn 2018. All data were analysed cross-sectionally, except for discontinuations assessed 1 year ± 2 months after initiation. RESULTS: Patients (N = 4055) were enrolled by diabetologists (56.7%), endocrinologists (40.7%), or cardiologists (2.5%). Empagliflozin (48.5%) was the most prescribed medication among SGLT2i, DPP4i, and GLP-1 RA; > 3 times more patients were prescribed empagliflozin than other SGLT2i (10 times more by cardiologists). Overall, 36.6% of patients had diagnosed CVD. Despite guidelines recommending SGLT2i or GLP-1 RA, 26.8% of patients with CVD received DPP4i. Patients initiating DPP4i were older (mean 66.4 years) than with SGLT2i (62.4 years) or GLP-1 RA (58.3 years). CKD prevalence differed by physician assessment (14.5%) or based on eGFR and UACR (27.9%). Many patients with CKD (≥ 41%) received DPP4i, despite guidelines recommending SGLT2is owing to their renal benefits. 1 year ± 2-months after initiation, 10.0% (7.9-12.3%) of patients had discontinued study medication: 23.7-45.0% due to 'financial burden of co-payment', 0-1.9% due to adverse events (no patients discontinued DPP4i due to adverse events). Treatment guidelines were 'highly relevant' for a greater proportion of cardiologists (79.4%) and endocrinologists (72.9%) than diabetologists (56.9%), and ≤ 20% of physicians consulted other physicians when choosing and discontinuing treatments. CONCLUSIONS: In CORDIALLY, significant proportions of patients with T2D and CVD/CKD who initiated modern antidiabetic medication in CEE in autumn 2018 were not treated with cardioprotective T2D medications. Use of DPP4i instead of SGLT2i or GLP-1 RA may be related to lack of affordable access, the perceived safety of these medications, lack of adherence to the latest treatment guidelines, and lack of collaboration between physicians. Thus, many patients with T2D and comorbidities may develop preventable complications or die prematurely. Trial registration NCT03807440.