Enhanced Attention Mechanism with Long Short-Term Memory based Automatic Chronic Kidney Disease Classification Using ECG Signals

Chronic kidney disease (CKD) is a global disease that is harder to treat at a later stage. Therefore, early diagnosis and monitoring of CKD are crucial. T cell immunoglobulin and mucin domain molecule 3 (Tim-3) is a negative regulator of the T cell responses and it is involved in the immunomodulation of kidney disease. To date, only a small number of reports regarding serum soluble Tim-3 (sTim-3) in CKD are available. In the present study, the serum levels of sTim-3 in patients with CKD at different stages and the levels of sTim-3 in the early diagnosis and monitoring of CKD were analyzed. A highly sensitive time-resolved fluorescence immunoassay was performed to quantify sTim-3 levels in 318 patients with CKD and 114 healthy individuals. The serum levels of sTim-3 in patients with CKD (33.47±20.77 ng/ml) were significantly higher than those in the healthy individuals group (8.32±3.23 ng/ml; P<0.0001). As CKD progressed from stage G1 to G5, the serum sTim-3 level gradually increased (P<0.0001). A cut-off value of 13.63 ng/ml for the sTim-3 concentration was effective in diagnosing patients with CKD (area under the receiver operating characteristic curve, 0.9176; sensitivity, 79.87%; specificity, 96.49%). At this critical value, the positive detection rate of CKD in the early stages (G1 + G2), G3, G4 and G5 was 55.70, 77.78, 84.44 and 92.86%, respectively. In conclusion, the serum sTim-3 levels in patients with CKD were significantly higher than those in the healthy individuals group. As CKD progressed from G1 to G5, the serum sTim-3 concentration gradually increased, facilitating the monitoring of the progression of CKD. In addition, serum sTim-3 had an auxiliary effect that was useful in the early diagnosis of CKD. The positive detection rate of CKD in the early stages was 55.70%, which can assist other clinically common kidney disease indicators.

Background and Aims Chronic kidney disease (CKD), affecting 6–10% of adults, often progresses silently until advanced stages, resulting in frequent underdiagnosis and inadequate management. To compare diagnosed, proxy-diagnosed, and undiagnosed CKD patients in terms of prevalence, assessment, nephroprotective treatment, healthcare utilization, and mortality. Method A retrospective observational study using Region Halland's healthcare data included adults meeting the confirmed CKD criteria defined by Kidney Disease: Improving Global Outcomes (KDIGO) from January–December 2019. Participants were classified into three groups: ICD-coded CKD (diagnosed CKD), CKD-related diagnoses (proxy-diagnosed CKD), and those meeting CKD criteria without an ICD diagnosis (undiagnosed CKD). Results Among 20488 CKD patients, 21% had an ICD-documented diagnosed CKD, 18% had a proxy-diagnosed CKD, and 61% were undiagnosed CKD. The mean ages were 76.4 years for diagnosed CKD, 62.4 years for proxy-diagnosed CKD, and 81.8 years for undiagnosed CKD (P &amp;lt; 0.001). Blood pressure follow-up rates were 88% for diagnosed, 67% for proxy-diagnosed, and 80% for undiagnosed, while glucose testing rates were 83%, 69%, and 76%, respectively. eGFR testing rates were 73%, 53%, and 66%. Urine albumin-creatinine ratio (UACR) testing rates were 25% in the overall population, 45% among individuals with diagnosed CKD, and 19% in both the undiagnosed CKD and proxy-diagnosed CKD groups. Renin-angiotensin system inhibitors were used in 45% of the cohort: 51% in diagnosed CKD, 28% in proxy-diagnosed CKD, and 47% in undiagnosed CKD. The relative risk of hospitalization, adjusted for age and comorbidities, was 2.71 (CI: 2.59–2.84) for patients with diagnosed CKD and 1.38 (CI: 1.31–1.46) for those with proxy-diagnosed CKD. The adjusted all-cause mortality hazard ratios were 2.22 (CI: 1.95–2.52) for CKD-diagnosed patients and 1.31 (CI: 1.08–1.60) for those with a proxy-diagnosed CKD. Conclusion The study highlights gaps in CKD diagnosis and management, with many patients remaining undiagnosed despite meeting CKD criteria. Diagnosed CKD patients received better follow-up but faced higher risks of hospitalization and mortality due to more complex comorbidities and more advanced CKD. Proxy-diagnosed CKD were common and associated with suboptimal management. These findings emphasize the need for consistent and accurate CKD identification to improve outcomes and optimize care.

BackgroundThe effectiveness of identifying and monitoring early-stage chronic kidney disease (CKD) is not fully recognised. This study quantified people with undiagnosed CKD among the middle-aged Japanese population and clarified potential...

LC-QQQ-MS routine analysis method for new biomarker quantification in plasma aimed at early chronic kidney disease diagnosis

Early detection of chronic kidney disease using eurygasters optimization algorithm with ensemble deep learning approach

POSTER PRESENTATIONS

Perceived knowledge among patients cared for by nephrologists about chronic kidney disease and end-stage renal disease therapies

Chronic kidney disease (CKD) affects 6-10% of adults and often remains undiagnosed until advanced stages, leading to inadequate management. This study compared diagnosed, proxy-diagnosed, and undiagnosed CKD patients regarding prevalence, clinical assessment, nephroprotective treatment, healthcare utilization, and mortality. This retrospective observational study analyzed Region Halland's healthcare data for adults meeting KDIGO CKD-confirmed criteria for the year 2019. Patients were categorized as diagnosed CKD (ICD-coded), proxy-diagnosed CKD (CKD-related diagnoses), or undiagnosed CKD (meeting CKD criteria without an ICD CKD diagnosis). Of 20,488 CKD patients, 21% had diagnosed CKD, 18% proxy-diagnosed CKD, and 61% undiagnosed CKD. Mean ages were 76.4, 62.4, and 81.8 years, respectively (p < 0.001). Blood pressure follow-up was carried out in diagnosed CKD (88%) versus 67% and 80% in the proxy-diagnosed and undiagnosed groups. eGFR was tested in 66% overall (73% diagnosed, 53% proxy-diagnosed, 66% undiagnosed), while urine albumin-to-creatinine ratio (UACR) testing was performed in 27% overall (50%, 20%, and 21%, respectively). Renin-angiotensin system inhibitors were prescribed to 45% overall (51%, 28%, and 47%, respectively). The adjusted hospitalization risk was 2.71 (CI: 2.59-2.84) in diagnosed CKD and 1.38 (CI: 1.31-1.46) in proxy-diagnosed CKD. Adjusted all-cause mortality hazard ratios were 2.22 (CI: 1.95-2.52) and 1.31 (CI: 1.08-1.60), respectively. Stratified sensitivity analyses by CKD stage confirmed these associations, though the strength varied. Patients with complex comorbidities, more advanced CKD, and frequent hospitalizations are more likely to be diagnosed with CKDand receive better follow-up care. Proxy-diagnosed CKD was common and associated with suboptimal management. These findings emphasize the need for consistent and accurate CKD identification to improve outcomes and optimize care.

Tracking Acoustic and Electrophysiological Changes Associated with CKD-induced Cardiac and Valvular Remodeling in a Mouse Model

Introduction: Chronic Kidney Disease (CKD) is a serious public health problem, affecting about 10% of the world's population. It is characterized by progressive and irreversible loss of kidney function, often caused by diabetes mellitus and hypertension. Early diagnosis of CKD is essential to slow its progression, improve patients' quality of life, and reduce treatment costs. Markers such as glomerular filtration rate (GFR) and albuminuria are critical for early detection. Methods: A comprehensive literature review was conducted on advances in early diagnosis and continuous monitoring of CKD. The search included studies published between 2013 and 2023, indexed in the PubMed, Lilacs, and SciELO databases, using terms such as "Chronic Kidney Disease management", "early diagnosis", and "continuous monitoring". 20 articles were selected after applying strict inclusion and exclusion criteria, with the final analysis of the full texts. Results: The analysis of the selected studies highlighted the importance of solid protocols for early diagnosis and continuous monitoring in the management of CKD. The introduction of new biomarkers, such as Leucine-Rich α-2-Glycoprotein 1 (LRG1), complements traditional methods, offering more accurate detection of CKD. In addition, remote monitoring via telemedicine has been shown to be effective in reducing hospitalizations and improving treatment adherence, particularly in patients on home dialysis. The combination of these strategies not only improves patients' clinical outcomes, but also reduces the financial burden on health systems. Conclusion: The review highlighted the need for robust protocols for early diagnosis and continuous monitoring in the management of CKD. The integration of new biomarkers and telemedicine technologies represents a significant advance, allowing for more effective and economically viable interventions. Such practices can improve patients' quality of life and provide a more sustainable approach to health systems, aligning with public health objectives.

Cardiorenal syndrome and death risk in patients with heart failure or chronic kidney disease: an unmet cardiorenal need?

Background and Aims With an estimated global prevalence of 10% or more, chronic kidney disease (CKD) and its associated complications constitute a major challenge for healthcare systems worldwide, which is worsened by the burden of undiagnosed CKD. Early diagnosis of CKD followed by guideline-recommended interventions can improve patient outcomes, particularly by delaying or preventing progression to kidney failure. This may result in a reduction in the costs associated with managing CKD. Elevated albuminuria is a strong predictor of risk of complications and death in patients with CKD, and measurement of urinary albumin-to-creatinine ratio (UACR) is an important diagnostic and prognostic tool. However, adherence to screening recommendations is suboptimal in routine care. Inside CKD aims to model the global clinical and economic burden of CKD using country-specific, patient-level microsimulation models. We used the Inside CKD microsimulation to model the potential clinical and economic impacts of routine UACR measurement with appropriate intervention in primary care settings in UK patients aged 45 years and over. This analysis is being expanded to further European countries. Method We used the Inside CKD microsimulation to model the clinical and economic impacts of measuring UACR with subsequent appropriate intervention during routine primary care visits in all individuals aged 45 years and over, versus current practice (i.e. screening in patients with diabetes, hypertension or cardiovascular disease). The model covers the period 2020–2025. First, a virtual population representing the general population of the UK was constructed using data from the 2016 Health Survey for England, covering demographics, prevalence of CKD and comorbidities (type 2 diabetes, uncontrolled hypertension and heart failure) and incidence of complications (heart failure, myocardial infarction, stroke and acute kidney injury). The model also included parameters relating to the direct and indirect costs associated with CKD (e.g. cost of renal replacement therapy), the proportion of patients who visit a primary care physician at least once a year, the proportion of patients who agree to UACR measurements, and the diagnostic sensitivity and specificity of UACR measurements. Results Preliminary results from the UK show that over the 2020–2025 period, routinely measuring UACR in all patients aged 45 years and over during primary care visits could prevent progression to CKD stages 3b–5 in approximately 327 000 patients, compared with current clinical practice, with a linear increase in the cumulative number of prevented cases over the 5 years (Figure). Associated savings in costs related to the management of CKD and its complications are projected to be approximately £300M in 2025, corresponding to a 1.9% reduction from current clinical practice. Conclusion Preliminary results from this Inside CKD microsimulation model show that implementation of routine measurement of UACR in primary care settings in the UK could prevent a substantial number of patients progressing to CKD stages 3b–5 and has the potential to reduce the associated healthcare-related costs considerably. This analysis is being extended to other European countries.

Background: Early recognition of chronic kidney disease (CKD) is crucial to slow its progression, yet underdiagnosis remains high. This study assesses prevalence of and factors associated with undiagnosed stage 3 CKD in patients with pre-existing type 2 diabetes (T2D) . Methods: REVEAL-CKD is a multi-national secondary data study. Data were extracted from THIN (Cegedim Health Data, France) and Disease Analyzer (IQVIA, Germany) . Patients were aged ≥18 years with 2 consecutive estimated glomerular filtration rate (eGFR) results 30-59 mL/min/1.73 m2 recorded 90-730 days apart in 2015-2021. T2D was identified by a diagnosis code before 2nd eGFR. Patients with no CKD code before 1st eGFR and ≤6 months after 2nd eGFR were considered undiagnosed. Results: The cohorts included 3,532 patients with T2D and stage 3 CKD in France and 6,935 in Germany. In both cohorts, undiagnosed CKD was high (94% and 74%, respectively) , and was greater in those aged ≥65 years and in females. In patients with additional pre-existing comorbidities undiagnosed CKD remained high, ranging between 65% - 96% (Table 1) . Conclusion: A high prevalence of undiagnosed CKD in patients with T2D was observed for France and Germany. Older patients and females were particularly vulnerable to undiagnosed CKD. Considerable opportunities exist to increase early identification and proactive management of CKD to slow progression and improve outcomes. Disclosure M.P. Schneider: Consultant; AstraZeneca. J.B. Virgitti: Advisory Panel; AstraZeneca, Lilly, Novo Nordisk. E. Peach: Employee; AstraZeneca. Stock/Shareholder; AstraZeneca. S. Barone: Employee; AstraZeneca. M. Arnold: Employee; AstraZeneca. N. Tangri: Consultant; AstraZeneca, Bayer AG, Boehringer Ingelheim International GmbH, Janssen Pharmaceuticals, Inc., Otsuka America Pharmaceutical, Inc., Pulsedata, Renibus, Tricida, Inc. Stock/Shareholder; Clinpredict, Klinrisk.

Chronic kidney disease (CKD) is a global health burden that affects approximately 10% of the adult population in the world. It is also recognized as the top 20 causes of death worldwide. Unfortunately, there is no cure for CKD however, it is possible to slow down its progression and mollify the damage by early diagnosis of the disease. Due to a limited number of nephrologists, the early diagnosis of CKD is often not possible for most of the people. Therefore the use of modern computer-aided methods is necessary to aid the traditional CKD diagnosis system to be more efficient and accurate. In this research, our primary focus was to apply 3 modern machine learning techniques namely logistic regression, feedforward neural networks and wide & deep learning to diagnose CKD as well as finding the best performing technique by evaluating their diagnosis performance. To evaluate their performance, f1-score, precision, recall and AUC score was used for logistic regression and an additional loss score was considered for the feedforward neural networks and wide & deep model. We found the feedforward neural network as the best performing technique for CKD diagnosis with 0.99 f1-score, 0.97 precision, 0.99 recall and 0.99 AUC score. Logistic regression produced the lowest result among all and the wide & deep learning with a larger number of hidden layers and neurons found to be effective for larger datasets.

Background and Aims With an estimated global prevalence of 10%, chronic kidney disease (CKD) and its associated complications place a substantial strain on healthcare systems worldwide, which is compounded by the burden of undiagnosed CKD. Early CKD diagnosis followed by guideline-recommended interventions can improve patient outcomes and reduce associated healthcare-related costs, particularly by delaying or preventing the development of complications and progression to kidney failure. Urinary albumin-to-creatinine ratio (UACR) can be used to screen for CKD, but adherence to screening recommendations is suboptimal in routine care. Inside CKD aims to model the global clinical and economic burden of CKD using country-specific, patient-level microsimulation models. We used the Inside CKD microsimulation to model the potential clinical and economic impacts of routine measurement of UACR followed by appropriate intervention in patients aged 45 years and over in the US and Canada. Method The Inside CKD microsimulation model was used to model the clinical and economic impacts associated with measurement of UACR with subsequent appropriate intervention during routine primary care visits versus current practice in individuals aged 45 years and over. The model covers the period 2020–2025. In preliminary analyses, virtual populations representing the general populations of the US and Canada were constructed using published country-specific data, including demographics, prevalence of CKD and comorbidities (type 2 diabetes, uncontrolled hypertension and heart failure), incidence of complications (heart failure, myocardial infarction, stroke and acute kidney injury) and costs associated with CKD. The model also included parameters relating to the proportion of patients who visit a primary care physician at least once a year, the proportion of patients who agreed to UACR measurements, and the diagnostic sensitivity and specificity of UACR measurements. The modelling is being expanded to additional countries in the Americas and the Asia-Pacific region. Results Preliminary results from the US and Canada show that over the 2020–2025 period routine measurement of UACR during primary care visits followed by appropriate intervention could prevent progression to CKD stages 3b–5 in approximately 1.3M patients in the US and 160 000 in Canada, compared with current clinical practice, with linear increases in the cumulative numbers of prevented cases (Figure). Associated savings in healthcare costs in 2025 are projected to be approximately US$16B in the US and C$2.5B in Canada, corresponding to a reduction in cost for that year of 4.4% and 7.4%, respectively, compared with current clinical practice. Conclusion Preliminary results from the Inside CKD microsimulation model in the US and Canada show that routine measurement of UACR with subsequent intervention in primary care would prevent progression to CKD stages 3b–5 in a substantial number of patients compared with current screening practices, and could therefore decrease associated healthcare costs considerably. This analysis is being extended to further countries in the Americas and the Asia-Pacific region.