Intradialytic Hypotension and Newly Recognized Peripheral Artery Disease in Patients Receiving Hemodialysis

Personalized prediction of intradialytic hypotension in clinical practice: Development and evaluation of a novel AI dashboard incorporating risk factors from previous and current dialysis sessions

BACKGROUND

Intradialytic hypotension (IDH) is one of the most common and critical complications of hemodialysis. Despite many proven factors associated with IDH, accurately predicting it before it occurs for individual patients during dialysis sessions remains a challenge.

PURPOSE

To establish artificial intelligence (AI) predictive models for IDH, which consider risk factors from previous and ongoing dialysis to optimize model performance. We then implement a novel digital dashboard with the best model for continuous monitoring of patients' status undergoing hemodialysis. The AI dashboard can display the real-time probability of IDH for each patient in the hemodialysis center providing an objective reference for care members for monitoring IDH and treating it in advance.

METHODS

Eight machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Light Gradient Boosting Machine (LightGBM), Multilayer Perception (MLP), eXtreme Gradient Boosting (XGBoost), and NaiveBayes, were used to establish the predictive model of IDH to determine if the patient will acquire IDH within 60 min. In addition to real-time features, we incorporated several features sourced from previous dialysis sessions to improve the model's performance. The electronic medical records of patients who had undergone hemodialysis at Chi Mei Medical Center between September 1, 2020 and December 31, 2020 were included in this research. Impact evaluation of AI assistance was conducted by IDH rate.

RESULTS

The results showed that the XGBoost model had the best performance (accuracy: 0.858, sensitivity: 0.858, specificity: 0.858, area under the curve: 0.936) and was chosen for AI dashboard implementation. The care members were delighted with the dashboard providing real-time scientific probabilities for IDH risk and historic predictive records in a graphic style. Other valuable functions were appended in the dashboard as well. Impact evaluation indicated a significant decrease in IDH rate after the application of AI assistance.

CONCLUSION

This AI dashboard provides high-quality results in IDH risk prediction during hemodialysis. High-risk patients for IDH will be recognized 60 min earlier, promoting individualized preventive interventions as part of the treatment plan. Our approachis believed to promise an excellent way for IDH management.

Efficacy and safety of ultrafiltration combined with haemodialysis in patients with uraemia who cannot tolerate dialysis because of hypotension

OBJECTIVE

To evaluate the efficacy and safety of ultrafiltration (UF) combined with haemodialysis (HD) sequential therapy in patients with intradialytic hypotension (IDH) and water retention.

METHODS

A total of 53 uraemia patients with IDH who could not tolerate dehydration and significant water and sodium retention (net weight gain of more than 4 kg) were randomly divided into control group (28 cases) and treatment group (25 cases). After adjusting dialysis parameters (blood pump speed and excessive filtration), HD was tried again in the control group, and UF combined with HD was given sequential treatment in the treatment group. Outcome measures included efficacy measures (duration of treatment, total water removal, weight loss, dyspnoea score and left ventricular ejection fraction) and safety measures (heart rate, blood pressure, IDH incidence, bleeding and thromboembolic events).

RESULTS

In terms of efficacy indicators, In the sequential treatment group, the duration of treatment (740 ± 168 min vs. 380 ± 94 min, p < 0.05), total water removal (5280 ± 968 mL vs. 2980 ± 765 mL, p < 0.05) and the weight loss (2756 ± 537 g vs. 1421 ± 362 g, p < 0.05) was significantly higher than that of control group. Postoperative dyspnoea score (1.92 ± 0.400 vs. 3.32 ± 0.476, p < 0.05), left ventricular ejection fraction (LVEF; 49.25 ± 3.76 vs. 56.46 ± 4.42, p < 0.05) was significantly improved compared with that before treatment, and the difference was statistically significant. In control group, dyspnoea score (1.89 ± 0.416 vs. 1.82 ± 0.390, p > 0.05) and left ventricular ejection fraction (49.04 ± 6.72 vs. 48.61 ± 7.12, p > 0.05) were slightly improved after treatment, but there was no statistical significance. In terms of safety indicators, patients in the control group were prone to significant blood pressure fluctuation during treatment, and the incidence of IDH was significantly higher than that in the treatment group (75% vs. 0%, p < 0.01), the difference was statistically significant, while the other safety indicators (heart rate change, bleeding and thromboembolic events) showed no statistically significant difference between the two groups.

CONCLUSIONS

Compared with conventional HD, UF combined with HD can safely and effectively reduce water retention in patients with uraemia while avoiding IDH.

Impact of frequent intradialytic hypotension on quality of life in patients undergoing hemodialysis

BACKGROUND

Intradialytic hypotension (IDH) is frequently accompanied by symptoms of nausea, dizziness, fatigue, muscle spasm, and arrhythmia, which can adversely impact the daily lives of patients who undergo hemodialysis and may lead to decreased quality of life (QoL). This study employed the KDQOL™-36 scale to evaluate the impact of frequent IDH, based on the definition determined by predialysis blood pressure (BP) and nadir systolic blood pressure (SBP) thresholds, on the QoL of patients.

METHODS

This is a single center retrospective cohort study involving 160 hemodialysis patients. We enrolled adult patients with uremia who received routine hemodialysis (4 h/time, 3 times/week) from October 1, 2019, to September 30, 2021. Frequent IDH was defined as an absolute nadir SBP < 90 mmHg occurring in no less than 30% of hemodialysis sessions when predialysis SBP < 159 mmHg (or < 100 mmHg when predialysis BP ≥ 160 mmHg).The differences between patients with and without frequent IDH were compared using the independent t test, Kruskal‒Wallis test, or chi-square test. The primary visit was at month 36, and the remaining visits were exploratory outcomes.

RESULTS

Compared to patients with infrequent IDH at baseline, those with frequent IDH had significantly lower scores on the symptoms and discomfort of kidney disease dimension at all follow-up points (P < 0.05). The symptoms and discomfort of kidney disease dimension were worse in patients with frequent IDH. Those with frequent IDH had a significantly poorer QoL regarding the dimensions of symptoms and discomfort of kidney disease and the impact of kidney disease on life.

CONCLUSIONS

The findings of the study suggest an association between frequent IDH and QoL dimensions of symptoms and discomfort of kidney disease and the impact of kidney disease on life dimension under the definition of frequent IDH.

Intradialytic hypotension and objectively measured physical activity among patients on hemodialysis

BACKGROUND

Intradialytic hypotension is related to patient-reported outcomes such as post-dialysis fatigue, but its impact on physical activity has not been fully studied. We aimed to examine the relationship between intradialytic blood pressure (BP) and objectively measured physical activity.

METHODS

In this cross-sectional study, 192 hemodialysis patients underwent 4 weeks of physical activity measurement using triaxial accelerometers to measure step counts and moderate-to-vigorous physical activity (MVPA). Intradialytic BP parameters (pre-dialysis BP, post-dialysis BP, nadir BP, and fall in BP) were measured during all dialysis sessions. Mixed-effects linear regression models were used to analyze associations between intradialytic BP parameters and physical activity (1) after dialysis sessions on dialysis days and (2) on the following non-dialysis days.

RESULTS

The mean age of the patients was 71 years, and 47% had diabetes mellitus. Valid physical activity data were obtained in a total of 1938 dialysis days and 2629 non dialysis days. Lower nadir diastolic BP was significantly associated with lower step counts and shorter moderate-to-vigorous physical activity not only on dialysis days but also on the following non-dialysis days. Nadir diastolic BP showed a higher discrimination capacity for physical inactivity, defined as a step count < 4000 on non-dialysis days, than the other BP parameters. The optimal cutoff point of nadir diastolic BP for discriminating physical inactivity was 68 mmHg; its sensitivity and specificity were 66% and 67%, respectively.

CONCLUSIONS

Lower nadir diastolic BP was strongly associated with lower physical activity on both dialysis and non-dialysis days. Nadir diastolic BP may be a predictor for physical inactivity.