UNASSIGNED: Predicting hypoglycemia while maintaining a low false alarm rate is a challenge for the wide adoption of continuous glucose monitoring (CGM) devices in diabetes management. One small study suggested that a deep learning model based on the long short-term memory (LSTM) network had better performance in hypoglycemia prediction than traditional machine learning algorithms in European patients with type 1 diabetes. However, given that many well-recognized deep learning models perform poorly outside the training setting, it remains unclear whether the LSTM model could be generalized to different populations or patients with other diabetes subtypes.
UNASSIGNED: The aim of this study was to validate LSTM hypoglycemia prediction models in more diverse populations and across a wide spectrum of patients with different subtypes of diabetes.
UNASSIGNED: We assembled two large data sets of patients with type 1 and type 2 diabetes. The primary data set including CGM data from 192 Chinese patients with diabetes was used to develop the LSTM, support vector machine (SVM), and random forest (RF) models for hypoglycemia prediction with a prediction horizon of 30 minutes. Hypoglycemia was categorized into mild (glucose=54-70 mg/dL) and severe (glucose<54 mg/dL) levels. The validation data set of 427 patients of European-American ancestry in the United States was used to validate the models and examine their generalizations. The predictive performance of the models was evaluated according to the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).
UNASSIGNED: For the difficult-to-predict mild hypoglycemia events, the LSTM model consistently achieved AUC values greater than 97% in the primary data set, with a less than 3% AUC reduction in the validation data set, indicating that the model was robust and generalizable across populations. AUC values above 93% were also achieved when the LSTM model was applied to both type 1 and type 2 diabetes in the validation data set, further strengthening the generalizability of the model. Under different satisfactory levels of sensitivity for mild and severe hypoglycemia prediction, the LSTM model achieved higher specificity than the SVM and RF models, thereby reducing false alarms.
UNASSIGNED: Our results demonstrate that the LSTM model is robust for hypoglycemia prediction and is generalizable across populations or diabetes subtypes. Given its additional advantage of false-alarm reduction, the LSTM model is a strong candidate to be widely implemented in future CGM devices for hypoglycemia prediction.

BACKGROUND: The high prevalence of mental illness is a critical social problem. The limited availability of mental health services is a major factor that exacerbates this problem. One solution is to deliver cognitive behavioral therapy (CBT) using an embodied conversational agent (ECA). ECAs make it possible to provide health care without location or time constraints. One of the techniques used in CBT is Socratic questioning, which guides users to correct negative thoughts. The effectiveness of this approach depends on a therapist\'s skill to adapt to the user\'s mood or distress level. However, current ECAs do not possess this skill. Therefore, it is essential to implement this adaptation ability to the ECAs.
OBJECTIVE: This study aims to develop and evaluate a method that automatically adapts the number of Socratic questions based on the level of detected psychological distress during a CBT session with an ECA. We hypothesize that this adaptive approach to selecting the number of questions will lower psychological distress, reduce negative emotional states, and produce more substantial cognitive changes compared with a random number of questions.
METHODS: In this study, which envisions health care support in daily life, we recruited participants aged from 18 to 65 years for an experiment that involved 2 different conditions: an ECA that adapts a number of questions based on psychological distress detection or an ECA that only asked a random number of questions. The participants were assigned to 1 of the 2 conditions, experienced a single CBT session with an ECA, and completed questionnaires before and after the session.
RESULTS: The participants completed the experiment. There were slight differences in sex, age, and preexperimental psychological distress levels between the 2 conditions. The adapted number of questions condition showed significantly lower psychological distress than the random number of questions condition after the session. We also found a significant difference in the cognitive change when the number of questions was adapted based on the detected distress level, compared with when the number of questions was fewer than what was appropriate for the level of distress detected.
CONCLUSIONS: The results show that an ECA adapting the number of Socratic questions based on detected distress levels increases the effectiveness of CBT. Participants who received an adaptive number of questions experienced greater reductions in distress than those who received a random number of questions. In addition, the participants showed a greater amount of cognitive change when the number of questions matched the detected distress level. This suggests that adapting the question quantity based on distress level detection can improve the results of CBT delivered by an ECA. These results illustrate the advantages of ECAs, paving the way for mental health care that is more tailored and effective.

Introduction: The acquisition of blood lactate concentration (BLC) during exercise is beneficial for endurance training, yet a convenient method to measure it remains unavailable. BLC and electrocardiogram (ECG) both exhibit variations with changes in exercise intensity and duration. In this study, we hypothesized that BLC during exercise can be predicted using ECG data. Methods: Thirty-one healthy participants underwent four cardiopulmonary exercise tests, including one incremental test and three constant work rate (CWR) tests at low, moderate, and high intensity. Venous blood samples were obtained immediately after each CWR test to measure BLC. A mathematical model was constructed using 31 trios of CWR tests, which utilized a residual network combined with long short-term memory to analyze every beat of lead II ECG waveform as 2D images. An artificial neural network was used to analyze variables such as the RR interval, age, sex, and body mass index. Results: The standard deviation of the fitting error was 0.12 mmol/L for low and moderate intensities, and 0.19 mmol/L for high intensity. Weighting analysis demonstrated that ECG data, including every beat of ECG waveform and RR interval, contribute predominantly. Conclusion: By employing 2D convolution and artificial neural network-based methods, BLC during exercise can be accurately estimated non-invasively using ECG data, which has potential applications in exercise training.

BACKGROUND: Although prior research has identified multiple risk factors for diabetic ketoacidosis (DKA), clinicians continue to lack clinic-ready models to predict dangerous and costly episodes of DKA. We asked whether we could apply deep learning, specifically the use of a long short-term memory (LSTM) model, to accurately predict the 180-day risk of DKA-related hospitalization for youth with type 1 diabetes (T1D).
OBJECTIVE: We aimed to describe the development of an LSTM model to predict the 180-day risk of DKA-related hospitalization for youth with T1D.
METHODS: We used 17 consecutive calendar quarters of clinical data (January 10, 2016, to March 18, 2020) for 1745 youths aged 8 to 18 years with T1D from a pediatric diabetes clinic network in the Midwestern United States. The input data included demographics, discrete clinical observations (laboratory results, vital signs, anthropometric measures, diagnosis, and procedure codes), medications, visit counts by type of encounter, number of historic DKA episodes, number of days since last DKA admission, patient-reported outcomes (answers to clinic intake questions), and data features derived from diabetes- and nondiabetes-related clinical notes via natural language processing. We trained the model using input data from quarters 1 to 7 (n=1377), validated it using input from quarters 3 to 9 in a partial out-of-sample (OOS-P; n=1505) cohort, and further validated it in a full out-of-sample (OOS-F; n=354) cohort with input from quarters 10 to 15.
RESULTS: DKA admissions occurred at a rate of 5% per 180-days in both out-of-sample cohorts. In the OOS-P and OOS-F cohorts, the median age was 13.7 (IQR 11.3-15.8) years and 13.1 (IQR 10.7-15.5) years; median glycated hemoglobin levels at enrollment were 8.6% (IQR 7.6%-9.8%) and 8.1% (IQR 6.9%-9.5%); recall was 33% (26/80) and 50% (9/18) for the top-ranked 5% of youth with T1D; and 14.15% (213/1505) and 12.7% (45/354) had prior DKA admissions (after the T1D diagnosis), respectively. For lists rank ordered by the probability of hospitalization, precision increased from 33% to 56% to 100% for positions 1 to 80, 1 to 25, and 1 to 10 in the OOS-P cohort and from 50% to 60% to 80% for positions 1 to 18, 1 to 10, and 1 to 5 in the OOS-F cohort, respectively.
CONCLUSIONS: The proposed LSTM model for predicting 180-day DKA-related hospitalization was valid in this sample. Future research should evaluate model validity in multiple populations and settings to account for health inequities that may be present in different segments of the population (eg, racially or socioeconomically diverse cohorts). Rank ordering youth by probability of DKA-related hospitalization will allow clinics to identify the most at-risk youth. The clinical implication of this is that clinics may then create and evaluate novel preventive interventions based on available resources.

Cardiovascular disease is the leading cause of death worldwide, accounting for 48.0% of all deaths in Europe and 34.3% in the United States. Studies have shown that arterial stiffness takes precedence over vascular structural changes and is therefore considered to be an independent predictor of many cardiovascular diseases. At the same time, the characteristics of Korotkoff signal is related to vascular compliance. The purpose of this study is to explore the feasibility of detecting vascular stiffness based on the characteristics of Korotkoff signal. First, the Korotkoff signals of normal and stiff vessels were collected and preprocessed. Then the scattering features of Korotkoff signal were extracted by wavelet scattering network. Next, the long short-term memory (LSTM) network was established as a classification model to classify the normal and stiff vessels according to the scattering features. Finally, the performance of the classification model was evaluated by some parameters, such as accuracy, sensitivity, and specificity. In this study, 97 cases of Korotkoff signal were collected, including 47 cases from normal vessels and 50 cases from stiff vessels, which were divided into training set and test set according to the ratio of 8 : 2. The accuracy, sensitivity and specificity of the final classification model was 86.4%, 92.3% and 77.8%, respectively. At present, non-invasive screening method for vascular stiffness is very limited. The results of this study show that the characteristics of Korotkoff signal are affected by vascular compliance, and it is feasible to use the characteristics of Korotkoff signal to detect vascular stiffness. This study might be providing a new idea for non-invasive detection of vascular stiffness.
血管硬化是心血管疾病的独立预测因子，柯氏音的特征与血管顺应性密切相关。本研究的目的是探究基于柯氏音信号的特征进行血管硬化检测的可行性。分别采集正常血管和硬化血管的柯氏音信号，并进行预处理，利用小波散射网络对柯氏音信号进行散射特征提取，搭建长短期记忆网络（LSTM）作为分类模型，对散射特征进行分类，评估 LSTM 分类模型的性能。本研究共有 97 例柯氏音信号数据，其中血管硬化组为 50 例，血管正常组为 47 例，按照 8∶2 的比例划分为训练集和测试集。最终分类模型的准确率为 86.4%，敏感度为 92.3%，特异性为 77.8%。研究结果表明，柯氏音信号的特征受到血管顺应性的影响，利用柯氏音信号的特征进行血管硬化的检测是可行的，本研究为无创血管硬化检测提供了一种新的思路。.

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG acquisition device (Max30101 photonic sensor) was utilized to (1) capture PPG signals and (2) wirelessly transmit data sets. In contrast to traditional feature engineering machine learning classification schemes, this study preprocessed raw data and applied a deep learning algorithm (LSTM-Attention) directly to extract deeper correlations between these raw datasets. The Long Short-Term Memory (LSTM) model underlying a gate mechanism and memory unit enables it to handle long sequence data more effectively, avoiding gradient disappearance and possessing the ability to solve long-term dependencies. To enhance the correlation between distant sampling points, an attention mechanism was introduced to capture more data change features than a separate LSTM model. A protocol with 15 healthy volunteers and 15 hypertension patients was implemented to obtain these datasets. The processed result demonstrates that the proposed model could present satisfactory performance (accuracy: 0.991; precision: 0.989; recall: 0.993; F1-score: 0.991). The model we proposed also demonstrated superior performance compared to related studies. The outcome indicates the proposed method could effectively diagnose and identify hypertension; thus, a paradigm to cost-effectively screen hypertension could rapidly be established using wearable smart devices.

The use of models capable of forecasting the production of photovoltaic (PV) energy is essential to guarantee the best possible integration of this energy source into traditional distribution grids. Long Short-Term Memory networks (LSTMs) are commonly used for this purpose, but their use may not be the better option due to their great computational complexity and slower inference and training time. Thus, in this work, we seek to evaluate the use of neural networks MLPs (Multilayer Perceptron), Recurrent Neural Networks (RNNs), and LSTMs, for the forecast of 5 min of photovoltaic energy production. Each iteration of the predictions uses the last 120 min of data collected from the PV system (power, irradiation, and PV cell temperature), measured from 2019 to mid-2022 in Maceió (Brazil). In addition, Bayesian hyperparameters optimization was used to obtain the best of each model and compare them on an equal footing. Results showed that the MLP performs satisfactorily, requiring much less time to train and forecast, indicating that they can be a better option when dealing with a very short-term forecast in specific contexts, for example, in systems with little computational resources.

Type 1 diabetes (T1D) outcome prediction plays a vital role in identifying novel risk factors, ensuring early patient care and designing cohort studies. TEDDY is a longitudinal cohort study that collects a vast amount of multi-omics and clinical data from its participants to explore the progression and markers of T1D. However, missing data in the omics profiles make the outcome prediction a difficult task. TEDDY collected time series gene expression for less than 6% of enrolled participants. Additionally, for the participants whose gene expressions are collected, 79% time steps are missing. This study introduces an advanced bioinformatics framework for gene expression imputation and islet autoimmunity (IA) prediction. The imputation model generates synthetic data for participants with partially or entirely missing gene expression. The prediction model integrates the synthetic gene expression with other risk factors to achieve better predictive performance. Comprehensive experiments on TEDDY datasets show that: (1) Our pipeline can effectively integrate synthetic gene expression with family history, HLA genotype and SNPs to better predict IA status at 2 years (sensitivity 0.622, AUC 0.715) compared with the individual datasets and state-of-the-art results in the literature (AUC 0.682). (2) The synthetic gene expression contains predictive signals as strong as the true gene expression, reducing reliance on expensive and long-term longitudinal data collection. (3) Time series gene expression is crucial to the proposed improvement and shows significantly better predictive ability than cross-sectional gene expression. (4) Our pipeline is robust to limited data availability. Availability: Code is available at https://github.com/compbiolabucf/TEDDY.

The growing number of depressive people and the overload in primary care services make it necessary to identify depressive states with easily accessible biomarkers such as mobile electroencephalography (EEG). Some studies have addressed this issue by collecting and analyzing EEG resting state in a search of appropriate features and classification methods. Traditionally, EEG resting state classification methods for depression were mainly based on linear or a combination of linear and non-linear features. We hypothesize that participants with ongoing depressive states differ from controls in complex patterns of brain dynamics that can be captured in EEG resting state data, using only nonlinear measures on a few electrodes, making it possible to develop cheap and wearable devices that could be even monitored through smartphones. To validate such a perspective, a resting-state EEG study was conducted with 50 participants, half with depressive state (DEP) and half controls (CTL). A data-driven approach was applied to select the most appropriate time window and electrodes for the EEG analyses, as suggested by Giacometti⁠, as well as the most efficient nonlinear features and classifiers, to distinguish between CTL and DEP participants. Nonlinear features showing temporo-spatial and spectral complexity were selected. The results confirmed that computing nonlinear features from a few selected electrodes in a 15 s time window are sufficient to classify DEP and CTL participants accurately. Finally, after training and testing internally the classifier, the trained machine was applied to EEG resting state data (CTL and DEP) from a publicly available database, validating the capacity of generalization of the classifier with data from different equipment, population, and environment obtaining an accuracy near 100%.

Real-time prediction of the state of the river itself and the degree of its benefit to the people is the leading way to achieve human-water harmony. Using the indicator scoring method as the evaluation method, we used the river evaluation data and results with time series characteristics as features and labels and applied the concept of transfer learning to Long Short-Term Memory to establish six subsystems, including water safety, water quality, economic contribution, water ecology, water management and water culture, to conduct a real-time rolling evaluation simulation study on the degree of river happiness in the Jiangsu section of the Huaihe River Basin in China. The empirical results show that the maximum Root Mean Square Error (RMSE) of the training set and test set of each system is 0.0226, and the lowest coefficient of determination R2 is 0.9011, which proves that the model fits well, according to which the relevant data of the watershed in June 2022 are brought in, and the evaluation result is obtained as 89.77 points. The overall trend is good, but a certain tendency to fall back at the level of economic contribution can be found, and the reasons are analyzed objectively.