Background and Aims The vascular access of choice for hemodialysis patients is the arteriovenous fistula (AVF). There is a high rate of early primary failure and loss of primary AVF patency. Monitoring of vascular access is essential for early diagnosis of complications and prolonging survival. Models based on Artificial Intelligence (AI) and Machine Learning (ML) can be used for this. Method Retrospective descriptive study of the Vascular Doppler Ultrasound (VDU) in adults carried out since January 2019 to January 2022 in our AVF follow-up nephrology clinic. We analyze the results and create AI-based AVF underdevelopment prediction models. We included clinical, demographic and ultrasound variables. Patients were undergoing AVF post-surgery follow-up (VDU by protocol at 3-4 weeks after AVF surgery) or were referred to the clinic with signs of AVF dysfunction. The insufficient development of the vascular access is established as an objective variable. SPSS 20 Statistical Package. Automated Learning Analysis (ML) with Orange ML and BigML. Results 243 VDU were performed. Of the total, 139 (57%) were follow-up post-surgical VDU per protocol and 104 (43%) were AVF dysfunction VDU. Using supervised ML Analysis techniques with random sampling of 80% of the instances for Training and 20% for Test, we obtain prediction models for the underdevelopment (UD) attribute of FAV: Decision tree algorithm, Area under the curve (AUC) 89%, Classification accuracy (CA) 90%, Precision 90%. Random Forest Algorithm (RF) (AUC) 95%, (CA) 86%, Accuracy 81%. Near Neighbor Algorithm (K-NN) (AUC) 88%, CA 82%, Accuracy 78%. Convolutional Neural Networks (NNC) (AUC) 82%, CA 74%, Accuracy 60%. Algorithm with unsupervised technique of clustering in k-Means 3 clusters are obtained. The variables that best correlate with the objective variable are access flow, vein diameter, resistance index (RI) proximal, (RI) distal, and diameter of the anastomosis. Conclusion The vascular ultrasound systematized by the nephrologist facilitates the early diagnosis of complications that lead to early intervention. Analysis of the data with techniques (ML) can facilitate early diagnosis AVF poor development requiring close monitoring or intervention. The development of a nephrology clinic for monitoring vascular access could avoid invasive and unnecessary procedures for the patient.

Background and Aims Kidney injury is a common complication in multiple myeloma (MM) and it has a negative prognostic implication. Most common cause of Acute Kidney Injury (AKI) in these patients is Light chain Cast Nephropathy, where free light chains precipitate in the tubules and bind with uromodulin, turning into intratubular casts that obstruct the tubules and also promote local giant cell reaction and interstitial inflammation and fibrosis. Free light chains (FLCs) can also damage the kidneys due to direct tubular toxicity when excessive amounts are reabsorbed by the proximal tubules. Targeted therapy to reduce FLC load can help recover renal function. Both total reduction and reduction speed are relevant for prognosis. FLC removal through extracorporeal techniques can be used as an adjuvant therapy, having an important part on the evolution of the disease. We gathered data from our experience treating MM patients with AKI with HFR-supra hemodialysis (HD) and analized the evolution and possible influence of this technique on renal recovery. Method This is an observational retrospective study. We included all patients with a diagnosis of multiple myeloma and acute kidney injury who received HFR-Supra hemodialysis in between years 2016-2022 in Hospital Virgen Macarena (Seville). We initially performed 6-10 daily HFR-Supra HD sessions and then modulated the frequency based on renal response (if renal replacement therapy had to be continued they underwent a usual hemodialysis regime 3 days a week). We continued these sessions until renal recovery was achieved or free light chain levels were reduced in agreement with the Hematology team. Measurement of pre and post dialysis FLCs was made always at first and last session and at least once in between, depending on the total number of sessions. Results 12 patients, with mean age at diagnosis 63.6 (43-86) years, presented with AKI stage KDIGO 3. 1 of them was oliguric. Median serum creatinine at diagnosis was 4.4 mg/dL [2,2-17], mean proteinuria was 4,1g/24 h [0,7-8,7] and 66,7% had positive Bence Jones proteinuria (mean 2,3g/24 h). 2 of the patients had previous chronic kidney disease stage 3a. All of them were diagnosed with Light Chain Multiple Myeloma (75% kappa, mean 10346 mg/L; 25% lambda, mean 5990 mg/L). Mean clonal bone marrow plasma cell was 20,7% [2-55]. According to the Revised International Staging System (R-ISS), 25% were stage 2 and 75% were stage 3. Renal biopsy was performed in 4 patients, all showed evidence of Cast Nephropathy. The indication for starting HFR-Supra HD was FLC removal in 9 patients, need of renal replacement therapy in 1 and both in 2 patients. We have experience in our center with using this therapy as an adyuvant treatment and often we start the technique in patients who present with AKI but would not necessarily have immediate need for renal replacement therapy. The goal is to remove FLCs and avoid further damage to the kidney tissue. Out of the 12 patients, 9 were able so stop dialysis (75%). They received a mean number of 12,4 [3-41] sessions in 3,7 [0,2-25] months). Free light chain removal per session was 24% on average [5-43%]. All of them were started on bortezomib-dexamethasone regime as initial chemotherapy for MM. As per renal recovery, at 3 months 33,3% achieved complete response, 11,1% partial response and 55,6% minimal response. At 1 year, 42,9% achieved complete response, 14,3% partial response and 42,9% minimal response. One-year survival rate was 91,7% (1 patient died from respiratory sepsis less than 1 month after diagnosis). Conclusion HFR-Supra hemodialyisis achieved a 24% free light chain removal per session on average. After presenting severe AKI (KDIGO 3), almost 43% of patients who received this adyuvant therapy obtained full renal recovery at 1 year and in 75% of patients withdrawal from hemodialysis was possible. 1 year survival was 91,7%.

No abstract

No abstract

Background and Aims Hyperkalemia constitutes an electrolyte imbalance that frequently appears in patients with Chronic Renal Disease (CKD) and is related to an increase in morbidity and mortality. Today, computerization of laboratory systems allows us to have access to these data to analyze the real prevalence of hyperkalemia in these patients, which we currently do not know. Our purpose is to analyze the frequency and characteristics of nephrologic patients with hyperkalemia and identify the most prevalent areas. Method Using a coding established by the laboratory, we have selected all patients with potassium greater than 5.5 mEq / l in analytics requested by any nephrologist of our hospital during the months of January to March 2019. It was established as mild hyperkalemia values up to 5.5mEq / l, and up to 6.5 mEq / l, severe hyperkalemia. We retrospectively analyzed the characteristics of these patients and the prevalence according to etiology and units within our service, relating potassium levels to the prescription of hyperkalemiant or related drugs. Results After analyzing the data, using as a reference the total number of patients seen in each area, we obtain an estimated total prevalence of 3.5% (86/2480). We found a distribution by sex with a predominance of men (56%), with a mean age of 62 years. The highest prevalence is obtained in the Hemodialysis unit (39.8%), followed by Peritoneal Dialysis (11%), Transplantation (5%), Hospitalization (4.3%), Interconsultations (3.8%), ERCA (2.7%) and External Consultations (0.6%). 65% had moderate hyperkalemia (defined as potassium levels of 5.5-6.5 mEq / l). Regarding the etiology of CKD, the most prevalent were: Vascular (29.2%), Diabetic (20.7%), Glomerular (19.5%) and Interstitial (14.6%). These etiologies also coincide with higher mean potassium levels, although without significant differences. There is also an increase in potassium levels the lower the glomerular filtration rate. However, when performing linear regression analysis we found no significant differences. Analyzing the drugs, it should be noted that the patients with the highest potassium levels were those taking anticoagulants, anticalcineurinics or resins (mean 6.17 mEq / l), finding significant differences only with the resins. In addition, most did not take ACE inhibitors, ARA-II or Beta blockers. Conclusion The prevalence of hyperkalemia in our population represents 3.5%. Being in most cases mild-moderate. The prevalence of hyperkalemia is higher in protein and kidney nephropathies and vascular nephropathies, probably associated with increased use of antiproteinuric drugs with hyperkalemic effect. Hyperkalemia is more prevalent in patients in patients undergoing renal replacement therapy reaching 40% in hemodialysis. The prevalence in CKD has been lower than expected, possibly in relation to greater patient awareness and adherence to the indications. Despite not finding a significant relationship, (due to the size of the sample) there is a relationship with the prescription of hyperkalemiant drugs. Resin prescription does not correct hyperkalemia