Dysfunctional Beliefs and Attitudes about Sleep-6 (DBAS-6): Data-driven shortened version from a machine learning approach.

BACKGROUND: The Dysfunctional Beliefs and Attitudes about Sleep Scale (DBAS-16) is a widely used self-report instrument for identifying sleep-related cognition. However, its length can be cumbersome in clinical practice. This study aims to develop a data-driven shortened version of the DBAS-16 that efficiently predicts the DBAS-16 total score among the general population. METHODS: We collected 1000 responses to the DBAS-16 from the general population through three separate surveys, each focusing on different aspects of insomnia severity and related factors. Using Exploratory Factor Analysis (EFA) on the survey responses, we grouped DBAS-16 items based on response pattern similarities. The most representative item from each group, showing the highest regression performance with eXtreme Gradient Boosting (XGBoost) in predicting the DBAS-16 total score, was selected to create a shortened version of the DBAS-16. RESULTS: Through EFA and XGBoost, we categorized the DBAS-16 items into six distinct groups. Selecting one item from each group, based on the highest coefficient of determination R2 values in predicting the DBAS-16 total score. After measuring the R2 values for all possible combinations of six items, items 4, 5, 7, 11, 13, and 15 were chosen, exhibiting the highest R2 value. Based on these six items, we developed the DBAS-6, a data-driven shortened version of the DBAS-16. The DBAS-6 exhibited outstanding predictive ability, achieving the highest R2 value of 0.90 for predicting the DBAS-16 total score, surpassing that of a previously developed shortened version. Notably, the DBAS-6 efficiently encapsulates the core aspects of the DBAS-16 and demonstrates robust predictive power over heterogeneous test data samples with distinct statistical characteristics from the training data. CONCLUSION: With its concise format and high predictive accuracy, the DBAS-6 offers a practical tool for assessing dysfunctional beliefs about sleep in clinical settings.

Data-driven shortened Insomnia Severity Index (ISI): a machine learning approach.

BACKGROUND: The Insomnia Severity Index (ISI) is a widely used questionnaire with seven items for identifying the risk of insomnia disorder. Although the ISI is still short, more shortened versions are emerging for repeated monitoring in routine clinical settings. In this study, we aimed to develop a data-driven shortened version of the ISI that accurately predicts the severity level of insomnia disorder. METHODS: We collected a sample of 800 responses from the EMBRAIN survey system. Based on the responses, seven items were grouped based on the similarity of their response using exploratory factor analysis (EFA). The most representative item within each group was selected by using eXtreme Gradient Boosting (XGBoost). RESULTS: Based on the selected three key items, maintenance of sleep, interference with daily function, and concerns about sleep problems, we developed a data-driven shortened questionnaire of ISI, ISI-3 m (machine learning). ISI-3 m achieved the highest coefficient of determination ( R 2 = 0.910 ) for the ISI score prediction task and the accuracy of 0.965, precision of 0.841, and recall of 0.838 for the multiclass-classification task, outperforming four previous versions of the shortened ISI. CONCLUSION: As ISI-3 m is a highly accurate shortened version of the ISI, it allows clinicians to efficiently screen for insomnia and observe variations in the condition throughout the treatment process. Furthermore, the framework based on the combination of EFA and XGBoost developed in this study can be utilized to develop data-driven shortened versions of the other questionnaires.

Density physics-informed neural networks reveal sources of cell heterogeneity in signal transduction.

The transduction time between signal initiation and final response provides valuable information on the underlying signaling pathway, including its speed and precision. Furthermore, multi-modality in a transduction-time distribution indicates that the response is regulated by multiple pathways with different transduction speeds. Here, we developed a method called density physics-informed neural networks (Density-PINNs) to infer the transduction-time distribution from measurable final stress response time traces. We applied Density-PINNs to single-cell gene expression data from sixteen promoters regulated by unknown pathways in response to antibiotic stresses. We found that promoters with slower signaling initiation and transduction exhibit larger cell-to-cell heterogeneity in response intensity. However, this heterogeneity was greatly reduced when the response was regulated by slow and fast pathways together. This suggests a strategy for identifying effective signaling pathways for consistent cellular responses to disease treatments. Density-PINNs can also be applied to understand other time delay systems, including infectious diseases.

Machine Learning-Based COVID-19 Patients Triage Algorithm Using Patient-Generated Health Data from Nationwide Multicenter Database.

INTRODUCTION: A prompt severity assessment model of patients with confirmed infectious diseases could enable efficient diagnosis while alleviating burden on the medical system. This study aims to develop a SARS-CoV-2 severity assessment model and establish a medical system that allows patients to check the severity of their cases and informs them to visit the appropriate clinic center on the basis of past treatment data of other patients with similar severity levels. METHODS: This paper provides the development processes of a severity assessment model using machine learning techniques and its application on SARS-CoV-2-infected patients. The proposed model is trained on a nationwide data set provided by a Korean government agency and only requires patients' basic personal data, allowing them to judge the severity of their own cases. After modeling, the boosting-based decision tree model was selected as the classifier while mortality rate was interpreted as the probability score. The data set was collected from all Korean citizens with confirmed COVID-19 between February 2020 and July 2021 (N = 149,471). RESULTS: The experiments achieved high model performance with an approximate precision of 0.923 and area under the curve of receiver operating characteristic (AUROC) score of 0.950 [95% tolerance interval (TI) 0.940-0.958, 95% confidence interval (CI) 0.949-0.950]. Moreover, our experiments identified the most important variables affecting the severity in the model via sensitivity analysis. CONCLUSION: A prompt severity assessment model for managing infectious people has been attained through using a nationwide data set. It has demonstrated its superior performance by surpassing that of conventional risk assessments. With the model's high performance and easily accessible features, the triage algorithm is expected to be particularly useful when patients monitor their health status by themselves through smartphone applications.

Real-World Implications of a Rapidly Responsive COVID-19 Spread Model with Time-Dependent Parameters via Deep Learning: Model Development and Validation.

BACKGROUND: The COVID-19 pandemic has caused major disruptions worldwide since March 2020. The experience of the 1918 influenza pandemic demonstrated that decreases in the infection rates of COVID-19 do not guarantee continuity of the trend. OBJECTIVE: The aim of this study was to develop a precise spread model of COVID-19 with time-dependent parameters via deep learning to respond promptly to the dynamic situation of the outbreak and proactively minimize damage. METHODS: In this study, we investigated a mathematical model with time-dependent parameters via deep learning based on forward-inverse problems. We used data from the Korea Centers for Disease Control and Prevention (KCDC) and the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University for Korea and the other countries, respectively. Because the data consist of confirmed, recovered, and deceased cases, we selected the susceptible-infected-recovered (SIR) model and found approximated solutions as well as model parameters. Specifically, we applied fully connected neural networks to the solutions and parameters and designed suitable loss functions. RESULTS: We developed an entirely new SIR model with time-dependent parameters via deep learning methods. Furthermore, we validated the model with the conventional Runge-Kutta fourth order model to confirm its convergent nature. In addition, we evaluated our model based on the real-world situation reported from the KCDC, the Korean government, and news media. We also crossvalidated our model using data from the CSSE for Italy, Sweden, and the United States. CONCLUSIONS: The methodology and new model of this study could be employed for short-term prediction of COVID-19, which could help the government prepare for a new outbreak. In addition, from the perspective of measuring medical resources, our model has powerful strength because it assumes all the parameters as time-dependent, which reflects the exact status of viral spread.

Trend to equilibrium for the kinetic Fokker-Planck equation via the neural network approach.

The issue of the relaxation to equilibrium has been at the core of the kinetic theory of rarefied gas dynamics. In the paper, we introduce the Deep Neural Network (DNN) approximated solutions to the kinetic Fokker-Planck equation in a bounded interval and study the large-time asymptotic behavior of the solutions and other physically relevant macroscopic quantities. We impose the varied types of boundary conditions including the inflow-type and the reflection-type boundaries as well as the varied diffusion and friction coefficients and study the boundary effects on the asymptotic behaviors. These include the predictions on the large-time behaviors of the pointwise values of the particle distribution and the macroscopic physical quantities including the total kinetic energy, the entropy, and the free energy. We also provide the theoretical supports for the pointwise convergence of the neural network solutions to the a priori analytic solutions. We use the library PyTorch, the activation function tanh between layers, and the Adam optimizer for the Deep Learning algorithm.