Using artificial intelligence algorithms to predict the overall survival of hemodialysis patients during the COVID-19 pandemic: A prospective cohort study.

BACKGROUND: Hemodialysis (HD) patients are a vulnerable population at high risk for severe complications from COVID-19. The impact of partial COVID-19 vaccination on the survival of HD patients remains uncertain. This prospective cohort study was designed to use artificial intelligence algorithms to predict the survival impact of partial COVID-19 vaccination in HD patients. METHODS: A cohort of 433 HD patients was used to develop machine-learning models based on a subset of clinical features assessed between July 1, 2021, and April 29, 2022. The patient cohort was randomly split into training (80%) and testing (20%) sets for model development and evaluation. Machine-learning models, including categorical boosting (CatBoost), light gradient boosting machines (LightGBM), RandomForest, and extreme gradient boosting models (XGBoost), were applied to evaluate their discriminative performance using the patient cohorts. RESULTS: Among these models, LightGBM achieved the highest F1 score of 0.95, followed by CatBoost, RandomForest, and XGBoost, with area under the receiver operating characteristic curve values of 0.94 on the testing dataset. The SHapley Additive explanation summary plot derived from the XGBoost model indicated that key features such as age, albumin, and vaccination details had a significant impact on survival. Furthermore, the fully vaccinated group exhibited higher levels of anti-spike (S) receptor-binding domain antibodies. CONCLUSION: This prospective cohort study involved using artificial intelligence algorithms to predict overall survival in HD patients during the COVID-19 pandemic. These predictive models assisted in identifying high-risk individuals and guiding vaccination strategies for HD patients, ultimately improving overall prognosis. Further research is warranted to validate and refine these predictive models in larger and more diverse populations of HD patients.

Survival benefit of a third dose of the COVID-19 vaccine among hemodialysis patients: A prospective cohort study.

BACKGROUND: Hemodialysis (HD) patients are particularly vulnerable to severe coronavirus disease 2019 (COVID-19) due to their immunocompromised state and comorbid conditions. Timely vaccination could be the most effective strategy to reduce morbidity and mortality. However, data on the survival benefit of the COVID-19 vaccine against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and death among HD patients are limited, especially during the Omicron-dominant period. METHODS: In this prospective hospital-based cohort study, we identified HD patients from July 1, 2021, to April 29, 2022. The patients were divided into fully vaccinated and partially vaccinated groups. We compared the humoral response, risk of developing SARS-CoV-2 infection, and all-cause mortality between the two groups. RESULTS: Among the 440 HD patients included, 152 patients were fully vaccinated, and 288 patients were partially vaccinated. Patients in the fully vaccinated group exhibited higher anti-spike protein receptor-binding domain (S protein RBD) antibody levels and lower risks of all-cause mortality (adjusted hazard ratio, 0.35; 95% confidence interval, 0.17-0.73; p = 0.005) than the partially vaccinated group. However, the risk for SARS-CoV-2 infection did not significantly differ between the two groups. Irrespective of the number of vaccinations, the risk of all-cause mortality was lower in patients with anti-S protein RBD antibody levels in the higher tertile. CONCLUSION: A third dose of the COVID-19 vaccine was associated with a decreased risk of all-cause mortality among HD patients during the Omicron-dominant period. A higher post-vaccination anti-S protein RBD antibody level was also associated with a lower risk of mortality.

Prediction of the risk of developing end-stage renal diseases in newly diagnosed type 2 diabetes mellitus using artificial intelligence algorithms.

OBJECTIVES: Type 2 diabetes mellitus (T2DM) imposes a great burden on healthcare systems, and these patients experience higher long-term risks for developing end-stage renal disease (ESRD). Managing diabetic nephropathy becomes more challenging when kidney function starts declining. Therefore, developing predictive models for the risk of developing ESRD in newly diagnosed T2DM patients may be helpful in clinical settings. METHODS: We established machine learning models constructed from a subset of clinical features collected from 53,477 newly diagnosed T2DM patients from January 2008 to December 2018 and then selected the best model. The cohort was divided, with 70% and 30% of patients randomly assigned to the training and testing sets, respectively. RESULTS: The discriminative ability of our machine learning models, including logistic regression, extra tree classifier, random forest, gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine were evaluated across the cohort. XGBoost yielded the highest area under the receiver operating characteristic curve (AUC) of 0.953, followed by extra tree and GBDT, with AUC values of 0.952 and 0.938 on the testing dataset. The SHapley Additive explanation summary plot in the XGBoost model illustrated that the top five important features included baseline serum creatinine, mean serum creatine within 1 year before the diagnosis of T2DM, high-sensitivity C-reactive protein, spot urine protein-to-creatinine ratio and female gender. CONCLUSIONS: Because our machine learning prediction models were based on routinely collected clinical features, they can be used as risk assessment tools for developing ESRD. By identifying high-risk patients, intervention strategies may be provided at an early stage.

The Associations between Erythropoietic Response with Inflammation Markers and Perfluorinated Chemicals in Hemodialysis Patients.

Erythropoiesis-stimulating agents (ESA) are used to treat anemia in hemodialysis (HD) patients. We investigated the role of inflammation and accumulation of environmental toxins (perfluorinated chemicals (PFCs), such as perfluorooctanoic acid and perfluorooctane sulfonate) in the erythropoietic response of HD patients who receive a fixed monthly continuous erythropoietin receptor activator (CERA) dosage. Forty-five patients underwent three successive phases of ESA treatment for two months each (phase one: 100 µg CERA once monthly; phase two: 50 µg CERA twice monthly; phase three: 100 µg CERA once monthly). Patient data were collected to determine the association of various factors with erythropoietic response (change in hematocrit). Liquid chromatography-tandem mass spectrometry was used to analyze perfluorinated chemicals. Twenty-eight patients exhibited a poor erythropoietic response that was significantly associated with: age > 80 years, initial hematocrit > 36%, glucose > 200 mg/dL, alanine aminotransferase > 21 U/L, c-reactive protein > 1 mg/dL, interleukin-6 > 10 ng/mL, lactate dehydrogenase ≤ 190 U/L, and chloride ≤ 93 mEq/L. There was also a borderline significant association between inflammation and PFCs, although PFCs failed to show any impact on ESA response. Age, glucose, chloride, liver function, and inflammation may be associated with cost-effective fixed CERA dosage administered at an increased frequency.

Far-Infrared Therapy Improves Arteriovenous Fistula Patency and Decreases Plasma Asymmetric Dimethylarginine in Patients with Advanced Diabetic Kidney Disease: A Prospective Randomized Controlled Trial.

Asymmetric dimethylarginine (ADMA) is an endogenous inhibitor of nitric oxide synthase and plays a significant role in the pathogenesis of arteriovenous fistula (AVF) dysfunction. The aim of this study is to evaluate the effect of far-infrared (FIR) therapy on the maturation and patency of newly-created AVFs in patients with advanced diabetic kidney disease (DKD) as well as the concurrent change in plasma ADMA. The study enrolled 144 participants with advanced DKD where 101 patients were randomly allocated to the FIR therapy group (N = 50) and control group (N = 51). Patients receiving FIR therapy had a decreased AVF failure rate within 12 months (16% versus 35.3%; p = 0.027); decreased incremental change of ADMA concentration at the 3rd and 12th month; increased AVF blood flow at the 1st, 3rd, and 12th month; increased 3-month physiologic maturation rate (88% versus 68.6%; p = 0.034); increased 1-year unassisted AVF patency rate (84% versus 64.7%; p = 0.017); and increased clinical AVF maturation rate within 12 months (84% versus 62.7%; p = 0.029) compared to the control group. The study demonstrates that FIR therapy can reduce the incremental changes in plasma ADMA concentration, which may be associated with the improvement of AVF prognosis in patients with advanced DKD.

Associations of atrial fibrillation with renal function decline in patients with chronic kidney disease.

BACKGROUND: Chronic kidney disease (CKD) is known to increase the risk of atrial fibrillation (AF) development, but the relationship between AF and subsequent renal function decline in patients with CKD is not well understood. In this study, we explored the role of AF on renal outcomes among patients with CKD. METHODS: In a retrospective hospital-based cohort study, we identified patients with CKD aged ≥20 years from 1 January 2008 to 31 December 2018. The patients were divided into AF and non-AF groups. We matched each patient with CKD and AF to two non-AF CKD controls according to propensity scores. The outcomes of interest included estimated glomerular filtration rate (eGFR) decline of ≥20%, ≥30%, ≥40% and ≥50%, and end-stage renal disease (ESRD). RESULTS: After propensity score matching, 6731 patients with AF and 13 462 matched controls were included in the analyses. Compared with the non-AF group, the AF group exhibited greater risks of eGFR decline ≥20% (HR 1.43; 95% CI 1.33 to 1.53), ≥30% (HR 1.50; 95% CI 1.36 to 1.66), ≥40% (HR 1.62; 95% CI 1.41 to 1.85) and ≥50% (HR 1.82; 95% CI 1.50 to 2.20), and ESRD (HR 1.22; 95% CI 1.12 to 1.34). Higher CHA2DS2-VASc scores were associated with greater risks of eGFR decline and ESRD. CONCLUSIONS: In patients with CKD, AF was associated with greater risks of subsequent renal function decline. CHA2DS2-VASc scores may be a useful risk stratification scheme for predicting the risk of renal function decline.

Associations of high anti-CMV IgG titer with renal function decline and allograft rejection in kidney transplant patients.

BACKGROUND: An anti-cytomegalovirus (CMV) immunoglobulin G (IgG) antibody is produced after primary CMV infection and generally persists after the primary infection. However, it is not well-known about the relationship between anti-CMV IgG titer and outcomes in kidney transplant recipients. We, therefore, aimed to explore the role of anti-CMV IgG titer on the risks of CMV disease development, allograft rejection, renal function decline, and mortality. METHODS: In a hospital-based study, we identified 179 CMV-seropositive kidney transplant recipients between January 2013 and December 2017. These patients were divided into low and high anti-CMV IgG titer groups, respectively. The cutoff level of anti-CMV IgG titer was determined by receiver operating characteristic curve analysis. The outcomes evaluated included CMV disease, decrease of ≥15% in estimated glomerular filtration rate (eGFR), biopsy-proven allograft rejection, and all-cause mortality. RESULTS: The high anti-CMV IgG titer group (≥846.2 AU/mL) exhibited a higher risk of CMV disease (adjusted hazard ratio [aHR], 3.77; 95% CI, 1.47-9.68; p = 0.006), eGFR decline ≥15% (aHR, 2.00; 95% CI, 1.19-3.35; p = 0.009), and renal allograft rejection (aHR, 2.95; 95% CI, 1.11-7.87; p = 0.030) than the low titer group (<846.2 AU/mL). CONCLUSION: In kidney transplant recipients, a high anti-CMV IgG titer was associated with higher risks for developing CMV disease, undergoing allograft rejection, and eGFR decline.

The Effect of Far-Infrared Therapy on the Peritoneal Membrane Transport Characteristics of Uremic Patients Undergoing Peritoneal Dialysis: An Open-Prospective Proof-of-Concept Study.

Long-term peritoneal dialysis (PD) can lead to detrimental changes in peritoneal membrane function, which may be related to the accumulation of glucose degradation products. A previous study demonstrated that 6 months of far-infrared (FIR) therapy may decrease glucose degradation products in PD dialysate. Due to limited literature on this matter, this study aims to investigate the effect of FIR therapy on the peritoneal membrane transport characteristics of PD patients. Patients were grouped according to baseline peritoneal transport status: lower transporters (low and low-average) and higher transporters (high-average and high). Both groups underwent 40 min of FIR therapy twice daily for 1 year. In lower transporters, FIR therapy increased weekly dialysate creatinine clearance (6.91 L/wk/1.73 m2; p = 0.04) and D/P creatinine (0.05; p = 0.01). In higher transporters, FIR therapy decreased D/P creatinine (-0.05; p = 0.01) and increased D/D0 glucose (0.05; p = 0.006). Fifty percent of high transporter patients shifted to high-average status after FIR therapy. FIR therapy may decrease D/P creatinine for patients in the higher transporter group and cause high transporters to shift to high-average status, which suggests the potential of FIR therapy in improving peritoneal membrane function in PD patients.

Long-term prognosis of vascular access in hemodialysis patients with systemic lupus erythematosus: a retrospective cohort study.

Patients with systemic lupus erythematosus (SLE) have a higher risk of vascular complications. This retrospective cohort study aimed to analyze the differences in the risk of arteriovenous fistula or graft (AVF/AVG) dysfunction in hemodialysis patients with and without SLE from Taiwan's National Health Insurance Database over a 10-year period. AVF/AVG dysfunction is defined as the occurrence of the first episode of intervention after vascular access creation. A total of 1366 HD patients with SLE had higher incidence rates of AVF/AVG dysfunction than 4098 non-SLE HD patients in the following 4 periods: (1) after 1 year (incidence rates = 15.21% and 13.01%, respectively; subdistribution hazard ratio (SHR) = 1.16; P = 0.007), (2) 1st-to-10th-year period (15.36% and 13.25%; SHR = 1.16; P = 0.007), (3) 5th-to-10th-year period (11.91% and 8.1%; SHR = 1.42; P = 0.003), and (4) overall period (23.53% and 21.66%; SHR = 1.09; P = 0.027). In conclusion, there were significantly higher incidence rates of AVF/AVG dysfunction in SLE patients during the long-term follow-up period. Vascular access function should be monitored regularly by clinical examinations, especially after 1 year and during 5 to 10 years, to improve AVF/AVG patency and dialysis adequacy in SLE patients undergoing maintenance hemodialysis.

The Effect of Far-Infrared Therapy on the Peritoneal Expression of Glucose Degradation Products in Diabetic Patients on Peritoneal Dialysis.

Peritoneal dialysis (PD) is a treatment modality for end-stage renal disease (ESRD) patients. Dextrose is a common osmotic agent used in PD solutions and its absorption may exacerbate diabetes mellitus, a common complication of ESRD. PD solutions also contain glucose degradation products (GDPs) that may lead to encapsulating peritoneal sclerosis (EPS), a severe complication of PD. A previous study showed that far-infrared (FIR) therapy improved a patient's gastrointestinal symptoms due to EPS. Due to limited literature on the matter, this study aims to investigate dialysate GDPs and peritoneal function in diabetic patients on PD. Thirty-one PD patients were enrolled and underwent 40 min of FIR therapy twice daily for six months. We demonstrated the effect of FIR therapy on the following: (1) decrease of methylglyoxal (p = 0.02), furfural (p = 0.005), and 5-hydroxymethylfurfural (p = 0.03), (2) increase of D/D0 glucose ratio (p = 0.03), and (3) decrease of potassium levels (p = 0.008) in both DM and non-DM patients, as well as (4) maintenance and increase of peritoneal Kt/V in DM and non-DM patients, respectively (p = 0.03). FIR therapy is a non-invasive intervention that can decrease dialysate GDPs in PD patients by improving peritoneal transport rate and solute removal clearance, while also maintaining dialysis adequacy.

Judicious use of sodium-glucose cotransporter 2 inhibitors in patients with diabetes on coronavirus-19 pandemic.

Sodium glucose cotransporter-2 inhibitors (SGLT2i), a novel antidiabetic drug blocks the reabsorption of glucose in proximal tubules of kidney, are demonstrated to have cardiovascular and renal benefits for people with diabetes. The benefits are associated with the significant increase of intrarenal angiotensin-converting enzyme II (ACE2) expression and blood volume contraction. However, the increased ACE2 may be detrimental to patients infected with the coronavirus infection 2019 (COVID-19), which is found to invade cells via the entry receptor of ACE2. Besides, an SGLT2i-induced natriuretic effect may also increase the risk of acute kidney injury and affect the hemodynamic stability during systemic infection disease. In this article, we explain the mechanisms why the use of SGLT2i in people with diabetes may lead to worse outcomes and suggest clinician to judiciously use it during COVID-19 pandemic.

Usefulness of the CHADS2 Score for Determining Risk of Seizure in Patients With Atrial Fibrillation.

Atrial fibrillation (AF) secondary to seizure has been described in case reports, but the association between AF and risk of seizure has never been evaluated in longitudinal studies. The objectives of this study were to investigate the role of AF on the risk of development of seizure and the usefulness of CHADS2 score for predicting the risk of seizure. Our analyses were conducted using information from a random sample of 1 million subjects enrolled in Taiwan National Health Insurance Research Database. A total of 11,552 subjects aged ≥18 years, comprising 5,776 subjects diagnosed with AF during the study period and 5,776 age and sex-matched subjects without AF were enrolled in our study. During the mean follow-up of 6.7 ± 3.3 years, seizure events occurred in 235 patients. In comparison, the AF group had a higher incidence rate of seizure occurrence (4.17 vs 1.90 per 1,000 person-years). Cox proportional hazard regression model analysis showed that development of AF was independently associated with a higher risk of developing future seizure (adjusted HR 2.30; 95% confidence interval 1.73 to 3.05). In multivariate Cox regression analysis adjusted for potentially confounding variables, a higher CHADS2 score was associated with a higher risk of seizure in a dose-dependent manner. AF may cause an ischemic stroke that subsequently leads to seizure, and present study further demonstrates that AF patients are associated with higher rate of subsequent seizure, even after adjusting for stroke. The CHADS2 score was found to be a useful scheme for predicting the risk of seizure occurrence.

Increased Circulating Visfatin Is Associated With Progression of Kidney Disease in Non-Diabetic Hypertensive Patients.

BACKGROUD: Declining renal function is an independent risk factor for all-cause mortality in cardiovascular disease. Visfatin has been described as a marker of inflammation and endothelial dysfunction, but whether circulating visfatin levels are predictive to a subsequent decline in renal function remains unclear. METHODS: In total, 200 nondiabetic, non-proteinuric hypertensive outpatients with initial serum creatinine (Scr) ≤1.5 mg/dl were enrolled. Plasma visfatin concentration and endothelial function estimated by brachial artery flow-mediated dilatation (FMD) were determined in the study subjects. The primary endpoints were the occurrence of renal events including doubling of Scr, 25% loss of glomerular filtration rate (GFR) from baseline values, and the occurrence of end-stage renal disease during follow-up. RESULTS: The mean annual rate of GFR decline (ΔGFR/y) was -1.26±2.76 ml/min/1.73 m(2) per year during follow-up (8.6±2.5 years). At baseline, plasma visfatin was negatively correlated with estimated GFR. In longitudinal analysis, the ΔGFR/y was correlated with visfatin, baseline GFR, FMD, systolic blood pressure, and fasting blood glucose (FBG). Multivariate analysis indicated that increased visfatin (r = -0.331, P <0.001), baseline GFR (r = -0.234, P = 0.001), FMD (r = 0.163, P = 0.015), and FBG (r = -0.160, P = 0.015) are independent predictors of ΔeGFR/y. Cox regression model analysis showed that visfatin (hazard ratio (HR), 1.09; 95% confidence interval (CI), 1.05-1.13, P <0.001), FBG (HR, 1.01; 95% CI, 1.00-1.02, P = 0.020), and FMD (HR, 0.87; 95% CI, 0.76-1.00, P = 0.049) were independently associated with the risk of developing future renal events. CONCLUSIONS: Increased circulating visfatin are associated with subsequent decline in renal function in nondiabetic hypertensive patients.