Beyond playing games: nephrologist vs machine in pediatric dialysis prescribing

Bedside sonographic assessments for predicting predialysis fluid overload in children with end-stage kidney disease

Although the number of studies evaluating methods to predict fluid overload is increasing, the assessment of fluid status in children on dialysis is still fraught with inaccuracies. We aimed to evaluate the predictive capability of lung ultrasounds and the inferior vena cava collapsibility index (cIVC) in predialysis overhydration in children with end-stage kidney disease. Ten children with end-stage kidney disease who were on an intermittent hemodialysis program were included. The hydration status of the patients was clinically evaluated. Moreover, 30 predialysis and 30 postdialysis lung ultrasound, cIVC, and bioimpedance spectroscopy (BIS) measurements were performed. The median age of the participants was 14 (IQR, 13-15) years, and two (20%) were male. There was a strong positive correlation between the predialysis total number of B-lines and predialysis fluid overload (r=0.764, p<0.001). Additionally, there was a moderate negative correlation between predialysis cIVC and predialysis fluid overload (r=-0.599, p=0.002). Although the moderate correlation was determined between the postdialysis fluid overload and total number of B-lines, no correlation was determined using cIVC. Receiver operating characteristic curves demonstrated that the total number of B-lines and cIVC could successfully predict the predialysis fluid overload (relative hydration >7% derived from the BIS; AUROC 0.82 and 0.80, respectively). When both evaluations were combined, if either the total number of B-lines or the cIVC was outside the corresponding cutoff range (>10.5 and ≤23.5, respectively), it was detected in 16 out of 17 sessions (sensitivity 94%). If either one was outside the corresponding cutoff range (total number of B-lines >10.5 and cIVC ≤18.2), the severe predialysis fluid overload was predicted successfully in all eight (100%) sessions. Conclusion: Randomized controlled studies are needed to prove the reliability of the combined use of lung ultrasounds and cIVC in the assessment of predialysis fluid overload. What is Known: • The association of chronic fluid overload with increased morbidity and mortality raises the need for optimal determination of fluid overload in pediatric patients who are dialysis-dependent at a young age. • The linear correlation between the total number of B-lines on lung ultrasound images and fluid overload by weight has been shown. What is New: • This study evaluates the lung ultrasound and inferior vena cava collapsibility index combined in predicting fluid overload in dialytic children. • If either the total number of B-lines or the cIVC was outside the corresponding cutoff range (>10.5 and cIVC ≤18.2, respectively), the severe predialysis fluid overload was predicted successfully in all eight (100%) sessions.

Machine learning in nephrology: scratching the surface

Machine learning shows enormous potential in facilitating decision-making regarding kidney diseases. With the development of data preservation and processing, as well as the advancement of machine learning algorithms, machine learning is expected to make remarkable breakthroughs in nephrology. Machine learning models have yielded many preliminaries to moderate and several excellent achievements in the fields, including analysis of renal pathological images, diagnosis and prognosis of chronic kidney diseases and acute kidney injury, as well as management of dialysis treatments. However, it is just scratching the surface of the field; at the same time, machine learning and its applications in renal diseases are facing a number of challenges. In this review, we discuss the application status, challenges and future prospects of machine learning in nephrology to help people further understand and improve the capacity for prediction, detection, and care quality in kidney diseases.

Using Artificial Intelligence Resources in Dialysis and Kidney Transplant Patients: A Literature Review

BACKGROUND

The purpose of this review is to depict current research and impact of artificial intelligence/machine learning (AI/ML) algorithms on dialysis and kidney transplantation. Published studies were presented from two points of view: What medical aspects were covered? What AI/ML algorithms have been used?

METHODS

We searched four electronic databases or studies that used AI/ML in hemodialysis (HD), peritoneal dialysis (PD), and kidney transplantation (KT). Sixty-nine studies were split into three categories: AI/ML and HD, PD, and KT, respectively. We identified 43 trials in the first group, 8 in the second, and 18 in the third. Then, studies were classified according to the type of algorithm.

RESULTS

AI and HD trials covered: (a) dialysis service management, (b) dialysis procedure, (c) anemia management, (d) hormonal/dietary issues, and (e) arteriovenous fistula assessment. PD studies were divided into (a) peritoneal technique issues, (b) infections, and (c) cardiovascular event prediction. AI in transplantation studies were allocated into (a) management systems (ML used as pretransplant organ-matching tools), (b) predicting graft rejection, (c) tacrolimus therapy modulation, and (d) dietary issues.

CONCLUSIONS

Although guidelines are reluctant to recommend AI implementation in daily practice, there is plenty of evidence that AI/ML algorithms can predict better than nephrologists: volumes, Kt/V, and hypotension or cardiovascular events during dialysis. Altogether, these trials report a robust impact of AI/ML on quality of life and survival in G5D/T patients. In the coming years, one would probably witness the emergence of AI/ML devices that facilitate the management of dialysis patients, thus increasing the quality of life and survival.

Effect of hemodialysis on impedance cardiography (electrical velocimetry) parameters in children

BACKGROUND

Pediatric hemodialysis (HD) patients have a high incidence of cardiovascular morbidity and mortality. The study aim was to investigate whether impedance cardiography (electrical velocimetry, EV) is suitable as a hemodynamic trend monitoring tool in pediatric patients during HD.

METHODS

Measurements by EV were obtained before, during, and after HD in a prospective single-center pediatric observational study. In total, 54 dialysis cycles in four different pediatric patients with end-stage kidney disease on chronic HD were included. EV parameters analyzed were heart rate (HR), stroke volume (SV), stroke volume index (SI), cardiac output (CO), cardiac index (CI), thoracic fluid content (TFC), index of contractility (ICON), stroke volume variation (SVV), variation of ICON (VIC), R-R interval (TRR), pre-ejection period (PEP), left ventricular ejection time (LVET), and systolic time ration (STR). Systemic vascular resistance index (SVRI) was calculated.

RESULTS

EV did measure significant changes in cardiovascular parameters associated with HD. The following parameters increased after HD: HR (9%), SVV (19%), VIC (33%), PEP (8%), and STR (18%). A decrease after HD was measured in SV (18%), SI (18%), CO (10%), CI (10%), TFC (10%), ICON (7%), TRR (7%), LVET (8%), and LVET (8%). SVRI was not affected by HD. The changes were correlated to ultrafiltration. HD cycles without fluid withdrawal also altered cardiovascular parameters.

CONCLUSIONS

Pediatric HD with and without fluid withdrawal changes hemodynamic EV monitoring parameters. Possibly EV may be useful to optimize HD management in pediatric patients.