Seasonal variation and predictors of intradialytic hypotension

Recurrent Intradialytic Hypotension, Associated Risk Factors, and Outcomes in Northern Tanzania: A Retrospective Cohort Study

Background and Aims

Intradialytic hypotension (IDH) is a common phenomenon during hemodialysis (HD), with profound complications and all-cause mortality. Data on IHD is scarce in Sub-Saharan Africa. The study aimed to evaluate the incidence, risk factors, and outcome associated with recurrent IDH among patients on maintenance HD.

Methods

This was a retrospective cohort study conducted at the Kilimanjaro Christian Medical Centre HD unit between August 1, 2021 and July 31, 2022. In the study, 39 met the inclusion criteria, and a total of 4706 HD sessions were analyzed. The predictor was the occurrence of recurrent IDH. The outcomes were mortality from IDH, hospital admission due to IDH, and termination of the respective HD session. Descriptive statistics for categorical and continuous variables. A χ 2 test was used to identify associations, and the receiver operating characteristics curve was used to determine the cutoff threshold for different parameters in determining risk factors for recurrent IDH.

Results

The incidence of IDH was 4.35%; 46.3% of these IDH episodes were recurrent. Risk of IDH was higher in patients with pre-dialytic serum inorganic phosphate levels > 1.8 mmol/L (RR: 2.33, 95% CI: 1.02-5.35, p < 0.001) with a predicted threshold of 1.27 mmol/L by ROC curve (AUC 0.618, CI: 0.541-0.694, sensitivity 60%, specificity 40%), among males (aRR: 9.65, CI: 2.27-40.85, p = 0.002). A systolic blood pressure of < 140 mmHg had a significant protective effect (aRR: 0.34, CI: 0.17-0.69, p = 0.003).

Conclusion

Recurrent IDH is more common in males, among patients with hyperphosphatemia, and shows seasonal variations. Systolic blood pressure of < 140 mmHg confers a protective effect against recurrent IDH.

Intradialytic Hypotension Frequency Prediction Using Generalizable Neighborhood Reasoning on Temporal Patient Knowledge Graph

Intradialytic hypotension (IDH) is a common complication among hemodialysis patients, adversely affecting quality of life and elevating mortality risk. IDH prediction enables physicians to take proactive measures, effectively reducing its occurrence. However, most prediction works rely on machine learning models, with a focus on real-time or session-level IDH. Hemodialysis patient data is multi-type and temporal, necessitating research on patient condition representation and temporal information utilization. Knowledge graphs (KGs) offer flexible data modeling and encompass rich structured information. This study represents patients using KGs and reason on graph structures to predict IDH. To study monthly IDH and utilize temporal information, a temporal patient KG is constructed. Patient KGs are first built at the monthly granularity based on data of 532 patients between January 2017 and August 2022. Six sequential monthly KGs are then combined into an observation window, resulting in a temporal KG dataset of 15,807 independent windows from 458 patients. The aim of this study is to utilize information from multiple months within a window to predict frequent IDH in the last month. However, the characteristics of IDH scenario and generalizability requirement pose challenges for the application of general KG reasoning models. Therefore, we adopt neighborhood-based KG reasoning and devise a visible feature guided patient-centric graph convolution to obtain patients' generalizable representations. Finally, patient representations in a window are fused using a sequential model, and processed by a prediction MLP to obtain the prediction results. Compared to 7 classic machine learning models, our model demonstrates superior performance in comprehensive metrics such as accuracy and F1 score.

Multilayer Perceptron-Based Real-Time Intradialytic Hypotension Prediction Using Patient Baseline Information and Heart-Rate Variation

Intradialytic hypotension (IDH) is a common side effect that occurs during hemodialysis and poses a great risk for dialysis patients. Many studies have been conducted so far to predict IDH, but most of these could not be applied in real-time because they used only underlying patient information or static patient disease information. In this study, we propose a multilayer perceptron (MP)-based IDH prediction model using heart rate (HR) information corresponding to time-series information and static data of patients. This study aimed to validate whether HR differences and HR slope information affect real-time IDH prediction in patients undergoing hemodialysis. Clinical data were collected from 80 hemodialysis patients from 9 September to 17 October 2020, in the artificial kidney room at Yeungnam University Medical Center (YUMC), Daegu, South Korea. The patients typically underwent hemodialysis 12 times during this period, 1 to 2 h per session. Therefore, the HR difference and HR slope information within up to 1 h before IDH occurrence were used as time-series input data for the MP model. Among the MP models using the number and data length of different hidden layers, the model using 60 min of data before the occurrence of two layers and IDH showed maximum performance, with an accuracy of 81.5%, a true positive rate of 73.8%, and positive predictive value of 87.3%. This study aimed to predict IDH in real-time by continuously supplying HR information to MP models along with static data such as age, diabetes, hypertension, and ultrafiltration. The current MP model was implemented using relatively limited parameters; however, its performance may be further improved by adding additional parameters in the future, further enabling real-time IDH prediction to play a supporting role for medical staff.