Volume Balance in Chronic Kidney Disease: Evaluation Methodologies and Innovation Opportunities

Porta, Edoardo La; Lanino, Luca; Calatroni, Marta; Caramella, Elena; Avella, Alessandro; Quinn, Caroline; Faragli, Alessandro; Estienne, Luca; Alogna, Alessio; Esposito, Pasquale

doi:10.1159/000515172

Cited by 6 publications

(11 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…La Porta E et al used a 34-layer deep convolutional neural network trained on a dataset of 9123 ECG recordings from approximately 40,000 patients to achieve the classification of 15 rhythm types. From the above studies, it can be seen that, with the continuous development of deep learning, the use of deep learning methods in the medical field to mine the deep information of medical data and assist doctors in diagnosis and treatment has become a hot spot at home and abroad [ 17 ].…”

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence-Based Echocardiographic Left Atrial Volume Measurement with Pulmonary Vein Comparison

Zhu

Fan

Liu

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

This paper combines echocardiographic signal processing and artificial intelligence technology to propose a deep neural network model adapted to echocardiographic signals to achieve left atrial volume measurement and automatic assessment of pulmonary veins efficiently and quickly. Based on the echocardiographic signal generation mechanism and detection method, an experimental scheme for the echocardiographic signal acquisition was designed. The echocardiographic signal data of healthy subjects were measured in four different experimental states, and a database of left atrial volume measurements and pulmonary veins was constructed. Combining the correspondence between ECG signals and echocardiographic signals in the time domain, a series of preprocessing such as denoising, feature point localization, and segmentation of the cardiac cycle was realized by wavelet transform and threshold method to complete the data collection. This paper proposes a comparative model based on artificial intelligence, adapts to the characteristics of one-dimensional time-series echocardiographic signals, automatically extracts the deep features of echocardiographic signals, effectively reduces the subjective influence of manual feature selection, and realizes the automatic classification and evaluation of human left atrial volume measurement and pulmonary veins under different states. The experimental results show that the proposed BP neural network model has good adaptability and classification performance in the tasks of LV volume measurement and pulmonary vein automatic classification evaluation and achieves an average test accuracy of over 96.58%. The average root-mean-square error percentage of signal compression is only 0.65% by extracting the coding features of the original echocardiographic signal through the convolutional autoencoder, which completes the signal compression with low loss. Comparing the training time and classification accuracy of the LSTM network with the original signal and encoded features, the experimental results show that the AI model can greatly reduce the model training time cost and achieve an average accuracy of 97.97% in the test set and increase the real-time performance of the left atrial volume measurement and pulmonary vein evaluation as well as the security of the data transmission process, which is very important for the comparison of left atrial volume measurement and pulmonary vein. It is of great practical importance to compare left atrial volume measurements with pulmonary veins.

show abstract

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence-Based Echocardiographic Left Atrial Volume Measurement with Pulmonary Vein Comparison

Zhu

Fan

Liu

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Reducing the symptom burden and achieving maximal functional and social rehabilitation is the overarching priority of all HD patients [7]. If during HD too much fluid (below the dry weight) is removed, or too rapidly, a patient may experience extracellular volume (EV) depletion causing intradialytic hypotension and its related symptomatology (i.e., dizziness, cramps, nausea, cold extremities, tachycardia, arrhythmia) [29]. In more severe cases (i.e., hypovolemic shock or cardiac events), interventions involving medical resuscitation and/or hospitalization are necessary [30].…”

Section: Morbidity and Hrqolmentioning

confidence: 99%

“…Clinical Manifestations (Abnormalities) of Sodium-Fluid Imbalance in HD Intradialytic Hypotension and Hypovolemia Intradialytic hypotension (IDH) is a frequent complication (20%) of chronic HD and attributed essentially to rapid ultrafiltration [29,73]. The discontinuous and brief nature of HD therapies requires high ultrafiltration rates to reach dry weight that leads to hypovolemia and results in hypotensive episodes, limiting fluid removal and BP control [84].…”

Section: Current Modes Of Hemodialysis Delivery Aggravate Sodium-flui...mentioning

confidence: 99%

See 1 more Smart Citation

Personalized Management of Sodium and Volume Imbalance in Hemodialysis to Mitigate High Costs of Hospitalization

Hornig¹,

Canaud²,

Bowry³

2023

Blood Purif

View full text Add to dashboard Cite

The primary objective of hemodialysis (HD) is lowering concentrations of organic uremic toxins that accumulate in blood in end-stage kidney disease (ESKD) and redress imbalances of inorganic compounds in particular sodium and water. Removal by ultrafiltration of excess fluid that has accumulated during the dialysis-free interval is a vital aspect of each HD session. Most HD patients are volume overloaded, with ∼25% of patients having severe (>2.5 L) fluid overload (FO). The potentially serious complications of FO contribute to the high cardiovascular morbidity and mortality observed in the HD population. Weekly cycles imposed by the schedule of HD treatments create a deleterious and unphysiological “tide phenomenon” marked by sodium-volume overload (loading) and depletion (unloading). Fluid overload-related hospitalizations are frequent and costly, with average cost estimates of $ 6,372 per episode, amounting to some $ 266 million total costs over a 2-year period in a US dialysis population. Various strategies (e.g., dry weight management or use of fluids with different sodium concentrations) have been attempted to rectify FO in HD patients but have met with limited success largely due to imprecise and cumbersome, or costly, approaches. In recent years, conductivity-based technologies have been refined to actively restore sodium and fluid imbalance and maintain the predialysis plasma sodium set point (plasma tonicity) of each patient. By automatically controlling the dialysate-plasma sodium gradient based on the specific patient needs throughout a session, an individualized sodium dialysate prescription can be delivered. Maintaining precise sodium mass balance helps better control of blood pressure, reduces FO, and thus tends to prevent hospitalization for congestive heart failure. We present the case for personalized salt and fluid management via a machine-integrated sodium management tool. Results from proof-of-principle clinical trials indicate that the tool enables individualized sodium-fluid volume control during each HD session. Its application in routine clinical practice has the potential to mitigate the substantial economic burden of hospitalizations attributed to volume overload complications in HD. Additionally, such a tool would contribute toward reduced symptomology and dialysis-induced multiorgan damage in HD patients and to improving their treatment perception and quality of life which matters most to patients.

show abstract

“…This workup may include devices or equipment, such as ultrasound evaluation of the lungs or inferior vena cava. Physical examination, with or without ancillary ultrasound, presents low accuracy in detecting fluid overload 9 …”

Section: Introductionmentioning

confidence: 99%

Incidence of hospital admissions in bioimpedance‐guided fluid management among maintenance hemodialysis patients—Results of a randomized controlled trial

Stigger

Ribeiro

Cordeiro

et al. 2023

Hemodialysis International

View full text Add to dashboard Cite

Introduction: Hemodialysis is life-sustaining in kidney failure. However, proper regulation of body fluids depends on an accurate estimate of target weight. This trial aims to compare clinical endpoints between target weight estimation guided by bioimpedance spectroscopy and usual care in hemodialysis patients. Methods: This is an open-label, parallel-group, controlled trial that randomized, through a table of random numbers, adult patients on maintenance hemodialysis to target weight estimation based on monthly clinical evaluation alone or added to evaluation by bioimpedance twice a year. The primary outcome was survival, and the secondary outcomes were the rate of hospital admissions, change in blood pressure (BP), and antihypertensive drugs load.Participants were followed for 2 years. Survival analysis was performed using Kaplan-Meier estimator and Log-rank test, and hospital admissions were analyzed by the incidence-rate ratio.Findings: One hundred and ten patients were randomized to the usual care (52) or bioimpedance (58) groups, with a mean age of 57.4 (15.4) years, 64 (58%) males. There was no difference between the groups at baseline. Survival was not significantly different between groups (log-rank test p = 0.68), but the trial was underpowered for this outcome. There was also no difference between the groups in the change in systolic or diastolic BP or in the number of antihypertensive drugs being used. The incidence rate of hospital admissions was 3.1 and 2.1 per person-year in usual care and bioimpedance groups, respectively, with a time-adjusted incidence rate ratio of 1.48 (95% CI: 1.20-1.82, p = 0.0001) and attributable fraction of risk among exposed individuals of 0.32 (95% CI: 0.17-0.45).Discussion: The inclusion of bioimpedance data to guide the estimation of target weight in hemodialysis patients had no detectable impact on survival or BP control, but significantly reduced the incidence rate of hospital admissions.The study was registered at ClinicalTrials.gov Identifier: NCT05272800.

show abstract

Volume Balance in Chronic Kidney Disease: Evaluation Methodologies and Innovation Opportunities

Cited by 6 publications

References 121 publications

Artificial Intelligence-Based Echocardiographic Left Atrial Volume Measurement with Pulmonary Vein Comparison

Artificial Intelligence-Based Echocardiographic Left Atrial Volume Measurement with Pulmonary Vein Comparison

Personalized Management of Sodium and Volume Imbalance in Hemodialysis to Mitigate High Costs of Hospitalization

Incidence of hospital admissions in bioimpedance‐guided fluid management among maintenance hemodialysis patients—Results of a randomized controlled trial

Contact Info

Product

Resources

About