Patients with chronic kidney disease (CKD) may progress to end-stage renal disease (ESRD) or die from other causes during long-term follow-up, making it essential to properly account for competing risks in prognostic modeling. However, most existing CKD prediction models rely on hazard-based measures, which primarily reflect relative effects, lack clinical interpretability, and cannot directly quantify survival time lost due to disease progression or death. To address this limitation, we adopted the restricted mean time lost (RMTL), an absolute and intuitive measure of survival time loss, and developed a dynamic prediction model under competing risks. Given the rich time-dependent covariate information in longitudinal CKD data and the clinical need for patients to understand their disease progression at different stages, we developed a dynamic RMTL prediction model that incorporates the landmark approach. The model captures how covariate effects evolve over time, offering insights into the dynamic impact of clinical variables, and enables individualized prediction of survival time loss over a future window from any given prediction time point. We evaluated its statistical properties through Monte Carlo simulations and demonstrated its practical utility using CKD patient data from the AASK cohort. The results showed that the proposed model yields accurate and robust estimates, captures time-varying covariate effects, and outperforms conventional static models in predictive performance. By quantifying survival time loss under competing risks, the dynamic RMTL model offers clinically interpretable and individualized risk estimates, supporting personalized risk assessment and intervention planning in chronic disease management.

The widespread presence of oceanic internal waves (IWs) across continental shelves, straits, and islands has been confirmed using multiple satellite payloads, including optical and synthetic aperture radar (SAR) sensors. However, the efficiency and accuracy of IWs detection are severely limited by the cloud contamination of optical images and the availability of SAR data. In other words, although IWs can be observed by multiple sensors, achieving full-time coverage remains challenging. The SAR altimeter (SRAL), characterized by high spatial resolution and continuous observation capability, holds substantial potential for IWs detection. Consequently, this study proposes a deep-learning-based method, named the IWs detection network (IWD-Net), to detect IWs from SRAL data. The IWD-Net is trained and tested in the Andaman Sea, achieving a detection precision of 96.2%. In addition, the model is subsequently applied to the South China Sea (SCS), where the detection precision of 94.9% reconfirms its robustness and reliability in detecting IWs. Statistical results indicate that the IWs detection efficiency using altimeter data improves by 227% compared to SAR and optical sensors combined. Finally, spatiotemporal analysis reveals that IWs are primarily concentrated in the western Luzon Strait and the Sulu Sea, but the seasonal variations of IWs in these two regions exhibit opposite trends: IWs are more active in summer/autumn within the western Luzon Strait, whereas IWs are more active in late winter/early spring within the Sulu Sea. These findings highlight the potential of altimeter data to fill gaps in IWs observations and enhance our understanding of ocean dynamics.

The echo signal received by ionosonde contains both ordinary wave (O-wave) and extraordinary wave (X-wave), and its separation result directly determines the accuracy of mode discrimination and ionospheric parameter inversion, which is of great significance to ionospheric research. The separation of O-wave and X-wave is exceptionally complex due to environmental noise, instrumental thermal noise, external interference, and the time-varying dispersion properties of the ionosphere itself. In this article, a method for separating O-wave and X-wave of ionosonde based on dual-channel phase difference statistics is proposed, which uses constant false alarm rate (CFAR) detection to extract the vertical ionospheric measurement echo signals and dynamically calculates the compensated phases of O-wave and X-wave separations at each frequency, achieving the robust and effective separation of O-wave and X-wave. The results of the measured data show that: 1) this method dynamically calculates the phase compensated for O-wave and X-wave separation by considering the variation of the compensation phase with frequency and time, through real-time statistics of the phase difference in the echo signal; 2) it compensates for the amplitude difference between the two channels and the signal-to-noise ratio of the separated O-wave and X-wave is improved; 3) it exhibits strong robustness and is suitable for vertical ionospheric signals in various modes; and 4) it demonstrates good performance, with the accuracy of O-wave and X-wave separation reaching 98.64%, which is 21.37% higher than the traditional dual-channel phase compensation methods.

The accuracy of O/X mode separation in vertical ionograms directly determines the quality of pattern discrimination results and metrics, which is of great significance to ionospheric research. It is extremely complicated to separate the O/X mode of the vertical ionograms because of the environmental noise, interference, and the time-varying dispersion characteristics of the ionosphere itself. In this article, we propose a method for separating the O/X mode signal in vertical ionograms based on an improved U-shaped encoder–decoder network, named vertical ionogram separation U-shaped network (VIS-UNet). Our model is based on the encoder–decoder architecture. It introduces the residual convolution to avoid network performance degradation and utilizes the attention module to improve the attention of the signal characteristic. In addition, we design an adaptive loss function to expedite the convergent speed of the model. Experimental results show that our model performs better than the baselines for the task of the O/X mode signal separation: 1) the method in this article has low requirements on the vertical ionospheric sounding system and the ionograms obtained by the single-channel vertical ionospheric sounding system can realize the separation of O/X mode signal at the pixel level; 2) it has strong universality and is insensitive to the signal integrity and the ionospheric pattern of the vertical ionograms; and 3) it performs better for the separation task. The mean intersection over union (MIOU) of the O/X mode separation task reaches 91.97% and the performance is significantly improved compared with the existing methods.

In the field of clinical chronic diseases, common prediction results (such as survival rate) and effect size hazard ratio (HR) are relative indicators, resulting in more abstract information. However, clinicians and patients are more interested in simple and intuitive concepts of (survival) time, such as how long a patient may live or how much longer a patient in a treatment group will live. In addition, due to the long follow-up time, resulting in generation of longitudinal time-dependent covariate information, patients are interested in how long they will survive at each follow-up visit. In this study, based on a time scale indicator-restricted mean survival time (RMST)-we proposed a dynamic RMST prediction model by considering longitudinal time-dependent covariates and utilizing joint model techniques. The model can describe the change trajectory of longitudinal time-dependent covariates and predict the average survival times of patients at different time points (such as follow-up visits). Simulation studies through Monte Carlo cross-validation showed that the dynamic RMST prediction model was superior to the static RMST model. In addition, the dynamic RMST prediction model was applied to a primary biliary cirrhosis (PBC) population to dynamically predict the average survival times of the patients, and the average C-index of the internal validation of the model reached 0.81, which was better than that of the static RMST regression. Therefore, the proposed dynamic RMST prediction model has better performance in prediction and can provide a scientific basis for clinicians and patients to make clinical decisions.