Privacy-preserving medical decision support for kidney disease requires localized deployment of large language models (LLMs) while maintaining clinical reasoning capabilities. Current solutions face three challenges: 1) Cloud-based LLMs pose data security risks; 2) Local model deployment demands technical expertise; 3) General LLMs lack mechanisms to integrate medical knowledge. Retrieval-augmented systems also struggle with medical document processing and clinical usability. We developed KidneyTalk-open, a desktop system integrating three technical components: 1) No-code deployment of state-of-the-art (SOTA) open-source LLMs (such as DeepSeek-r1, Qwen2.5) via local inference engine; 2) Medical document processing pipeline combining context-aware chunking and intelligent filtering; 3) Adaptive Retrieval and Augmentation Pipeline (AddRep) employing agents collaboration for improving the recall rate of medical documents. A graphical interface was designed to enable clinicians to manage medical documents and conduct AI-powered consultations without technical expertise. Experimental validation on 1,455 challenging nephrology exam questions demonstrates AddRep's effectiveness: achieving 29.1% accuracy (+8.1% over baseline) with intelligent knowledge integration, while maintaining robustness through 4.9% rejection rate to suppress hallucinations. Comparative case studies with the mainstream products (AnythingLLM, Chatbox, GPT4ALL) demonstrate KidneyTalk-open's superior performance in real clinical query. KidneyTalk-open represents the first no-code medical LLM system enabling secure documentation-enhanced medical Q&A on desktop. Its designs establishes a new framework for privacy-sensitive clinical AI applications. The system significantly lowers technical barriers while improving evidence traceability, enabling more medical staff or patients to use SOTA open-source LLMs conveniently.

Background: Chronic kidney disease (CKD), a progressive disease with high morbidity and mortality, has become a significant global public health problem. At present, most of the models used for predicting the progression of CKD are static models. We aim to develop a dynamic kidney failure prediction model based on deep learning (KFDeep) for CKD patients, utilizing all available data on common clinical indicators from real-world Electronic Health Records (EHRs) to provide real-time predictions. Findings: A retrospective cohort of 4,587 patients from EHRs of Yinzhou, China, is used as the development dataset (2,752 patients for training, 917 patients for validation) and internal validation dataset (917 patients), while a prospective cohort of 934 patients from the Peking University First Hospital CKD cohort (PKUFH cohort) is used as the external validation dataset. The AUROC of the KFDeep model reaches 0.946 (95\% CI: 0.922-0.970) on the internal validation dataset and 0.805 (95\% CI: 0.763-0.847) on the external validation dataset, both surpassing existing models. The KFDeep model demonstrates stable performance in simulated dynamic scenarios, with the AUROC progressively increasing over time. Both the calibration curve and decision curve analyses confirm that the model is unbiased and safe for practical use, while the SHAP analysis and hidden layer clustering results align with established medical knowledge. Interpretation: The KFDeep model built from real-world EHRs enhances the prediction accuracy of kidney failure without increasing clinical examination costs and can be easily integrated into existing hospital systems, providing physicians with a continuously updated decision-support tool due to its dynamic design.

Unsupervised/self-supervised time series representation learning is a challenging problem because of its complex dynamics and sparse annotations. Existing works mainly adopt the framework of contrastive learning with the time-based augmentation techniques to sample positives and negatives for contrastive training. Nevertheless, they mostly use segment-level augmentation derived from time slicing, which may bring about sampling bias and incorrect optimization with false negatives due to the loss of global context. Besides, they all pay no attention to incorporate the spectral information in feature representation. In this paper, we propose a unified framework, namely Bilinear Temporal-Spectral Fusion (BTSF). Specifically, we firstly utilize the instance-level augmentation with a simple dropout on the entire time series for maximally capturing long-term dependencies. We devise a novel iterative bilinear temporal-spectral fusion to explicitly encode the affinities of abundant time-frequency pairs, and iteratively refines representations in a fusion-and-squeeze manner with Spectrum-to-Time (S2T) and Time-to-Spectrum (T2S) Aggregation modules. We firstly conducts downstream evaluations on three major tasks for time series including classification, forecasting and anomaly detection. Experimental results shows that our BTSF consistently significantly outperforms the state-of-the-art methods.

Few-shot Time Series Classification (few-shot TSC) is a challenging problem in time series analysis. It is more difficult to classify when time series of the same class are not completely consistent in spectral domain or time series of different classes are partly consistent in spectral domain. To address this problem, we propose a novel method named Spectral Propagation Graph Network (SPGN) to explicitly model and propagate the spectrum-wise relations between different time series with graph network. To the best of our knowledge, SPGN is the first to utilize spectral comparisons in different intervals and involve spectral propagation across all time series with graph networks for few-shot TSC. SPGN first uses bandpass filter to expand time series in spectral domain for calculating spectrum-wise relations between time series. Equipped with graph networks, SPGN then integrates spectral relations with label information to make spectral propagation. The further study conveys the bi-directional effect between spectral relations acquisition and spectral propagation. We conduct extensive experiments on few-shot TSC benchmarks. SPGN outperforms state-of-the-art results by a large margin in 4% 13%.