RESUMO
The classifier of support vector machine (SVM) learning for assessing the quality of arteriovenous fistulae (AVFs) in hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor device is presented in this work. In clinical practice, there are two important indices for assessing the quality of AVF: the blood flow volume (BFV) and the degree of stenosis (DOS). In hospitals, the BFV and DOS of AVFs are nowadays assessed using an ultrasound Doppler machine, which is bulky, expensive, hard to use, and time consuming. In this study, a newly-developed PPG sensor device was utilized to provide patients and doctors with an inexpensive and small-sized solution for ubiquitous AVF assessment. The readout in this sensor was custom-designed to increase the signal-to-noise ratio (SNR) and reduce the environment interference via maximizing successfully the full dynamic range of measured PPG entering an analog-digital converter (ADC) and effective filtering techniques. With quality PPG measurements obtained, machine learning classifiers including SVM were adopted to assess AVF quality, where the input features are determined based on optical Beer-Lambert's law and hemodynamic model, to ensure all the necessary features are considered. Finally, the clinical experiment results showed that the proposed PPG sensor device successfully achieved an accuracy of 87.84% based on SVM analysis in assessing DOS at AVF, while an accuracy of 88.61% was achieved for assessing BFV at AVF.
Assuntos
Fístula Arteriovenosa/diagnóstico por imagem , Falência Renal Crônica/patologia , Aprendizado de Máquina , Fotopletismografia/métodos , Fluxo Sanguíneo Regional/fisiologia , Fístula Arteriovenosa/classificação , Constrição Patológica/classificação , Constrição Patológica/patologia , Hemodinâmica , Humanos , Falência Renal Crônica/complicações , Fotopletismografia/instrumentação , Razão Sinal-RuídoRESUMO
BACKGROUND: The importance of identifying mortality biomarkers in chronic kidney disease (CKD), and especially in patients treated with hemodialysis (HD), has become evident. In addition to being a marker of tubulointerstitial injury, plasma kidney injury molecule-1 (KIM-1) has been mentioned in regard to HD patients as a risk marker for cardiovascular (CV) mortality and coronary artery calcification. The aim of this study was to assess the level of plasma KIM-1 as a marker of cardiovascular disease (CVD) and mortality in CKD5-HD patients (patients with CKD stage G5D treated with hemodialysis). METHODS: We conducted a prospective case-control study that included 63 CKD5-HD patients (HD for 1-5 years) followed up for 48 months and a control group consisting of 52 non-dialysis patients diagnosed with CKD stages G1-G5 (ND-CKD). All patients had a CVD baseline assessment including medical history, echocardiography, and electrocardiography (ECG). Circulating plasma KIM-1 levels were determined with single-molecule counting immunoassay technology using an enzyme-linked immunosorbent assay. We obtained the following parameters: serum creatinine and urea; the inflammation markers CRP (C-reactive protein) and IL-6 (interleukin-6); and the anemia markers complete blood count, serum ferritin, and transferrin saturation (TSAT). RESULTS: The mean plasma KIM-1 level was 403.8 ± 546.8 pg/mL, showing a statistically significant correlation with inflammation (CRP, R = 0.28, p = 0.02; IL-6, R = 0.36, p = 0.005) and with anemia (hematocrit, R = -0.5, p = -0.0316; hemoglobin (Hb), R = -0.5, p = 0.02). We found that patients with left ventricular hypertrophy (LVH) on echocardiography (59.7%) had significantly lower mean levels of plasma KIM-1 than patients from the control group (155.51 vs. 432.12 pg/mL; p = 0.026). Regarding the patients' follow-up, we assessed all-cause mortality as an endpoint. After 24 months of follow-up, we found a mortality rate of 22.23%, while after 48 months, the mortality rate was 50.73%. A plasma KIM-1 level < 82.98 pg/mL was significantly associated with decreased survival in hemodialysis patients (p < 0.001). CONCLUSIONS: In patients treated with hemodialysis, low levels of plasma KIM-1 were associated with cardiovascular changes and an increased risk of mortality. Plasma KIM-1 levels were significantly higher in HD patients compared to ND-CKD patients.
RESUMO
BACKGROUND: Protein-energy loss and inflammation are the main risk factors in the occurrence of complications in hemodialysis patients. The Prognostic Inflammatory and Nutritional Index (PINI) is a simple, inexpensive test to identify the early onset of inflammation and malnutrition in hemodialysis patients, critically ill subjects and those with malignancies. METHODS: A systemic review of English literature was conducted on the topic published between 1985 and 2022. A focused and sensitive search strategy was applied to the PUBMED database to identify relevant scientific articles in English. Once articles were identified, a detailed quality and bias assessment was performed. Two independent researchers analyzed the detailed data extraction. RESULTS: PINI proved to be a sensitive, powerful, low-cost and simple test. PINI has been useful in assessing evolution and prognostics in clinical care, with values above one being associated with a high risk of mortality and morbidity. It is useful in cases with surgical and postoperative complications, long hospitalization, as well as increased associated expenses. CONCLUSIONS: This is the first review of the literature on the above-mentioned topic (PINI) and is a valuable candidate for validating prognosis in patients with different pathologies.
RESUMO
OBJECTIVES: Aim of the present study was to investigate serum concentration of leptin and its association with values of body mass index (BMI), C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR) in hemodialysis (HD) patients. METHODS: This cross-sectional study included 60 HD patients (34 male, 26 female) and 30 age- and sex-matched (4 males, 26 females) apparently healthy subjects. Serum leptin concentration was determined by an enzyme-linked immunosorbent assay (ELISA). Serum CRP concentration was measured by means of particle-enhanced immunonephelometry. ESR value was determined by Western Green method. BMI was calculated as weight (kg) divided by height squared (m(2)). RESULTS: Results have shown that median serum leptin concentration (30.65 ng/mL; 12.48-86.40 ng/mL) was statistically significantly higher in HD patients compared to median serum leptin concentration (15.75 ng/mL; 9.15-30.65 ng/mL) in the control group of healthy subjects (p<0.05). Likewise, median serum CRP concentration (5.5 mg/L; 1.93-8.9 mg/L) and median ESR value (57.5 mm/h; 40.5-77.0 mm/h) were significantly higher in HD patients compared to median serum CRP concentration (0.8 mg/L; 0.38-1.43 mg/L) (p<0.001) and median ESR value (10.0 mm/h; 6.5-14.0 mm/h) (p<0.001) determined in the control group. Statistically significant positive correlation was found between BMI values and serum leptin concentration in HD patients (rho=0.434; p<0.001). Positive, although not significant, correlation was observed between serum CRP and leptin levels in HD patients (rho=0.171; p>0.05). Negative correlation between ESR values and serum leptin concentrations in HD patients was determined but it was not statistically significant (rho= -0.029; p>0.05). CONCLUSIONS: Increased serum concentration of leptin as pro-inflammatory cytokine as well as elevated serum values of CRP and ESR indicate presence of systemic micro inflammation in HD patients. Results of the present study point to possible use of serum leptin concentration as an indicator of nutritional status in HD patients based on observed significant positive correlation between serum leptin concentrations and BMI values. However, absence of significant association between serum leptin and CRP levels as well as between serum leptin concentrations and ESR values in HD patients requires further investigation and clarification.