Pattern recognition and prognostic analysis of longitudinal blood pressure records in hemodialysis treatment based on a convolutional neural network

Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study

BACKGROUND

Early identification of mental disorder symptoms is crucial for timely treatment and reduction of recurring symptoms and disabilities. A tool to help individuals recognize warning signs is important. We posit that such a tool would have to rely on longitudinal analysis of patterns and trends in the individual's daily activities and mood, which can now be captured through data from wearable activity trackers, speech recordings from mobile devices, and the individual's own description of their mental state. In this paper, we describe such a tool developed by our team to detect early signs of depression, anxiety, and stress.

OBJECTIVE

This study aims to examine three questions about the effectiveness of machine learning models constructed based on multimodal data from wearables, speech, and self-reports: (1) How does speech about issues of personal context differ from speech while reading a neutral text, what type of speech data are more helpful in detecting mental health indicators, and how is the quality of the machine learning models influenced by multilanguage data? (2) Does accuracy improve with longitudinal data collection and how, and what are the most important features? and (3) How do personalized machine learning models compare against population-level models?

METHODS

We collect longitudinal data to aid machine learning in accurately identifying patterns of mental disorder symptoms. We developed an app that collects voice, physiological, and activity data. Physiological and activity data are provided by a variety of off-the-shelf fitness trackers, that record steps, active minutes, duration of sleeping stages (rapid eye movement, deep, and light sleep), calories consumed, distance walked, heart rate, and speed. We also collect voice recordings of users reading specific texts and answering open-ended questions chosen randomly from a set of questions without repetition. Finally, the app collects users' answers to the Depression, Anxiety, and Stress Scale. The collected data from wearable devices and voice recordings will be used to train machine learning models to predict the levels of anxiety, stress, and depression in participants.

RESULTS

The study is ongoing, and data collection will be completed by November 2023. We expect to recruit at least 50 participants attending 2 major universities (in Canada and Mexico) fluent in English or Spanish. The study will include participants aged between 18 and 35 years, with no communication disorders, acute neurological diseases, or history of brain damage. Data collection complied with ethical and privacy requirements.

CONCLUSIONS

The study aims to advance personalized machine learning for mental health; generate a data set to predict Depression, Anxiety, and Stress Scale results; and deploy a framework for early detection of depression, anxiety, and stress. Our long-term goal is to develop a noninvasive and objective method for collecting mental health data and promptly detecting mental disorder symptoms.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/48210.

Time-series deep survival prediction for hemodialysis patients using an attention-based Bi-GRU network

BACKGROUND AND OBJECTIVE

The number of end-stage renal disease (ESRD) patients treated with hemodialysis (HD) has significantly increased, but the prognosis remains poor. Time-series features have been included in only a few studies to predict HD patient survival, and how to utilize such features effectively remains unclear. This article aims to develop a more accurate, interpretable, and clinically practical personalized survival prediction model for HD patients.

METHODS

This study proposed and evaluated an attention-based Bi-GRU network using time-series features for survival prediction. A distance-based loss function was proposed to improve performance. We used data from 1232 ESRD patients who received regular hemodialysis treatment for ≥ 3 months from 2007 to 2016 at the First Affiliated Hospital of Zhejiang University. The proposed model was compared with representative sequence modeling deep learning architectures and existing survival analysis methods in terms of the C-index and IBS value. Post hoc tests were used to test statistical significance. The attention map was used to assess feature importance over time. The impact of time-series changes on survival was investigated after controlling initial values (using BMI as an example).

RESULTS

The proposed method outperformed other sequence modeling architectures and the state-of-the-art survival analysis approaches in terms of the C-index and the integrated Brier score (IBS) value. Our method achieved a C-index of 0.7680 (95% confidence intervals [CI]: 0.7645, 0.7716) and an IBS of 0.1302 (95% confidence intervals [CI]: 0.1292, 0.1313), showing an improvement of up to 5.4% in terms of the C-index and a decrease of 3.2% in terms of the IBS value. The addition of the distance-based loss function improved the performance. The predicted risk and actual risk levels closely agreed. This study also found that even after controlling the initial body mass index (BMI) values, different 3-month BMI trends could produce different survival outcomes.

CONCLUSIONS

This study proposed a more effective and interpretable method to use time-series information in survival analysis. The proposed method may help promote personalized medicine and improve patient prognosis.

Automated ECG classification using a non-local convolutional block attention module

BACKGROUND AND OBJECTIVE

Recent advances in deep learning have been applied to ECG detection and obtained great success. The spatial and temporal information from ECG signals is fused by combining convolutional neural networks (CNN) with recurrent neural network (RNN). However, these networks ignore the different contribution of local and global segments of a feature map extracted from the ECG and the correlation relationship between the above two segments. To address this issue, a novel convolutional neural network with non-local convolutional block attention module(NCBAM) is proposed to automatically classify ECG heartbeats.

METHODS

Our proposed method consists of a 33-layer CNN architecture followed by a NCBAM module. Initially, preprocessed electrocardiogram (ECG) signals are fed into the CNN architecture to extract the spatial and channel features. Further, long-range dependencies of representative features along spatial and channel axis are captured by non-local attention. Finally, the spatial, channel and temporal information of ECG are fused by a learned matrix. The learned matrix is to mine rich relationship information across the above three types of information to make up for the different contribution.

RESULTS AND CONCLUSION

The proposed method achieves an average F1 score of 0.9664 on MIT-BIH arrhythmia database, as well as AUC of 0.9314 and F_max of 0.8507 on PTB-XL ECG database. Compared with the state-of-the-art attention mechanism based on the same public database, NCBAM achieves an obvious improvement in classifying ECG heartbeats. The results demonstrate the proposed method is reliable and efficient for ECG beat classification.

Deep Learning Model for Real-Time Prediction of Intradialytic Hypotension

BACKGROUND AND OBJECTIVES

Intradialytic hypotension has high clinical significance. However, predicting it using conventional statistical models may be difficult because several factors have interactive and complex effects on the risk. Herein, we applied a deep learning model (recurrent neural network) to predict the risk of intradialytic hypotension using a timestamp-bearing dataset.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

We obtained 261,647 hemodialysis sessions with 1,600,531 independent timestamps (i.e., time-varying vital signs) and randomly divided them into training (70%), validation (5%), calibration (5%), and testing (20%) sets. Intradialytic hypotension was defined when nadir systolic BP was <90 mm Hg (termed intradialytic hypotension 1) or when a decrease in systolic BP ≥20 mm Hg and/or a decrease in mean arterial pressure ≥10 mm Hg on the basis of the initial BPs (termed intradialytic hypotension 2) or prediction time BPs (termed intradialytic hypotension 3) occurred within 1 hour. The area under the receiver operating characteristic curves, the area under the precision-recall curves, and F1 scores obtained using the recurrent neural network model were compared with those obtained using multilayer perceptron, Light Gradient Boosting Machine, and logistic regression models.

RESULTS

The recurrent neural network model for predicting intradialytic hypotension 1 achieved an area under the receiver operating characteristic curve of 0.94 (95% confidence intervals, 0.94 to 0.94), which was higher than those obtained using the other models (P<0.001). The recurrent neural network model for predicting intradialytic hypotension 2 and intradialytic hypotension 3 achieved area under the receiver operating characteristic curves of 0.87 (interquartile range, 0.87-0.87) and 0.79 (interquartile range, 0.79-0.79), respectively, which were also higher than those obtained using the other models (P≤0.001). The area under the precision-recall curve and F1 score were higher using the recurrent neural network model than they were using the other models. The recurrent neural network models for intradialytic hypotension were highly calibrated.

CONCLUSIONS

Our deep learning model can be used to predict the real-time risk of intradialytic hypotension.

Comparison of Combined Hemodialysis and Hemoperfusion with Hemoperfusion Alone in 106 Patients with Diabetic Ketoacidosis and Acute Renal Failure: A Retrospective Study from a Single Center in China

Background

Acute kidney injury with acute renal failure is associated with severe diabetic ketoacidosis. This retrospective study was conducted at a single center in China and aimed to compare combined hemodialysis and hemoperfusion (hemodialysis+hemoperfusion) with hemoperfusion alone in 106 patients with diabetic ketoacidosis and acute renal failure.

Material/Methods

The 106 patients were divided into 2 groups according to different dialysis programs, with 53 cases in each group. Hemodialysis was performed using a single-pass 4008S FX8 HeLix-One hollow fiber hemodialyzer (Fresenius Medical Care, St. Wendel, Germany). Hemoperfusion was performed using HA130 resin adsorbents.

Results

There were no significant differences in terms of sex, age, duration of diabetes, A1c, pH, and admission blood glucose between the 2 groups (P=0.54, 0.564, 0.53, 0.78, 0.82, 0.51). There were no significant differences in fasting blood glucose, blood urea nitrogen, osmotic pressure, and creatinine between the 2 groups before treatment (P=0.146, 0.978, 0.786, 0.983). After treatment, blood urea nitrogen and creatinine in the dual-treatment group were lower than in the control group, and the osmotic pressure was higher than that in the control group (P=0.000, 0.000, 0.000). The dual-treatment group experienced a lower prevalence of dizziness (5.7%), anemia (7.5%), bone pain (7.5%), hypertension (3.8%), and pruritus (5.7%) than the control group (P<0.05).

Conclusions

Compared with hemoperfusion alone, hemodialysis+hemoperfusion significantly reduced pruritus and anemia, improved renal function, and was associated with significantly fewer adverse events in patients with diabetic ketoacidosis and acute renal failure.