The missing values widely existing in multivariate time series significantly hinder accurate forecasting efforts. Existing multivariate time series forecasting methods predominantly learn the interrelations between complete historical and future time series data, thus failing to accommodate the prevalent instances of missing values within these time series data. In this paper, we propose a novel forecasting model, named Enter, which integrates two key modules, i.e., missing-aware pre-training (MAP) and incomplete time series forecasting (ITF), to forecast incomplete multivariate time series effectively and efficiently in an end-to-end manner. Specifically, MAP introduces a missing-aware Transformer to pre-train the forecasting model by learning the underlying data distribution from incomplete historical multivariate time series. ITF fine-tunes this pre-trained model with a cross attention mechanism to robustly forecast future time series without error accumulation by leveraging all observed elements within the historical multivariate time series. Extensive experiments on four real-world multivariate time series datasets and a publicly available incomplete meteorological dataset demonstrate that, compared with the state-of-the-art methods, Enter yields over a more than 21% accuracy gain. It accelerates the training process up to two orders of magnitude faster.

This study presents a novel diagnostic approach that integrates hyperspectral imaging (HSI) with deep learning to discriminate among dermatitis, actinic keratosis (AK), and seborrheic keratosis (SK). We evaluated 60 intraoperative clinical specimens and achieved 93% accuracy, 91% sensitivity, and 95% specificity in three-class classification. A Savitzky-Golay filter was applied to the raw spectra to enhance the signal-to-noise ratio and data fidelity, while first-derivative spectral analysis enabled the model to capture subtle biochemical and morphological differences among lesions. Our results demonstrate that the combined HSI-deep-learning framework can accelerate dermatologic diagnosis and reduce error rates. This methodology not only provides a robust tool for clinical decision support in dermatology but also holds promise for wider adoption across medical imaging workflows. Future work will focus on scalability, cost-benefit optimization, and seamless integration with existing diagnostic platforms.

Background:There is a challenge of in diagnostic testing of pneumonia in children, especially severe pneumonia. Thus, developing an auxiliary diagnostic model to help identify severe pneumonia in pediatric patients at an early stage would be highly valuable to address the issues. To overcome the issue of privacy protection, we applied a privacy-preserving machine learning framework to build a multicenter diagnostic model based on federated learning technology. Methods:Based on Arya, a novel privacy computing platform developed by Hangzhou Healink Technology Corporation, several privacy-preserving federated learning models were developed using datasets from one, two, or four medical centers. A total of 5,091 records were included in this multicenter retrospective study, with 2,484 pediatric patients with severe pneumonia and 2,607 with common pneumonia. Among the records, 80% were used in model training for the diagnosis of severe pneumonia, with 11 common indicators, including white blood cell count (WBC), high-sensitivity C-reactive protein (hs-CRP), hemoglobin (Hb), platelet count (PLT), lymphocyte percentage (L%), monocyte percentage (M%), neutrophil percentage (N%), prothrombin time (PT), alanine aminotransferase (ALT), aspartate aminotransferase (AST), and lactic dehydrogenase (LDH), while the other 20% records were used for model efficacy evaluation. During the process, the original data were stored in the individual hospitals without transmission. Results:Based on privacy-preserving federated learning technology, the developed models provided reliable diagnostic efficacy for severe pneumonia. Among these models, the four-center model achieved the highest diagnostic efficacy (95.10% sensitivity, 82.70% specificity, and 85.80% accuracy). Although the two-center models achieved a relatively low diagnostic efficacy, they still surpassed the diagnostic efficacy of the single-center model (88.10% sensitivity, 74.60% specificity, and 81.00% accuracy). Conclusions:Privacy-preserving federated learning technology can facilitate the performance of multicenter studies and was used to develop a high-performance diagnostic model for severe pneumonia in pediatric patients, which can benefit doctors and patients as an auxiliary diagnostic tool.

We investigated the outcomes of extremely low birth weight (ELBW) infants who underwent intestinal enterostomy. This retrospective study included ELBW infants who were hospitalized from January 1, 2019, to December 31, 2023, and underwent enterostomy. Data regarding demographic information, complications, and outcomes were collected. In total, 52 ELBW infants who underwent enterostomy were enrolled. Among them, 30 (57.7

Kawasaki disease (KD) is a syndrome of acute systemic vasculitis commonly observed in children. Due to its unclear pathogenesis and the lack of specific diagnostic markers, it is prone to being confused with other diseases that exhibit similar symptoms, making early and accurate diagnosis challenging. This study aimed to develop an interpretable machine learning (ML) diagnostic model for KD. We collected demographic and laboratory data from 3650 patients (2299 with KD, 1351 with similar symptoms but different diseases) and employed 10 ML algorithms to construct the diagnostic model. Diagnostic performance was evaluated using several metrics, including area under the receiver-operating characteristic curve (AUC). Additionally, the shapley additive explanations (SHAP) method was employed to select important features and explain the final model. Using the Streamlit framework, we converted the model into a user-friendly web application to enhance its practicality in clinical settings. Among the 10 ML algorithms, XGBoost demonstrates the best diagnostic performance, achieving an AUC of 0.9833. SHAP analysis revealed that features, including age in months, fibrinogen, and human interferon gamma, are important for diagnosis. When relying on the top 10 most important features, the model’s AUC remains at 0.9757. The proposed model can assist clinicians in making early and accurate diagnoses of KD. Furthermore, its interpretability enhances model transparency, facilitating clinicians’ understanding of prediction reliability.

Developmental Dysplasia of the Hip (DDH) stands as one of the preeminent hip disorders prevalent in pediatric orthopedics. Automated diagnostic instruments, driven by artificial intelligence methodologies, are capable of providing substantial assistance to clinicians in the diagnosis of DDH. We have developed a dataset designated as Multitasking DDH (MTDDH), which is composed of two sub-datasets. Dataset 1 encompasses 1,250 pelvic X-ray images, with annotations demarcating four discrete regions for the evaluation of pelvic X-ray quality, in tandem with eight pivotal points serving as support for DDH diagnosis. Dataset 2 contains 906 pelvic X-ray images, and each image has been annotated with eight key points for assisting in the diagnosis of DDH. Notably, MTDDH represents the pioneering dataset engineered for the comprehensive evaluation of pelvic X-ray quality while concurrently offering the most exhaustive set of eight key points to bolster DDH diagnosis, thus fulfilling the exigency for enhanced diagnostic precision. Ultimately, we presented the elaborate process of constructing the MTDDH and furnished a concise introduction regarding its application.

Background: Atopic dermatitis (AD) is a chronic, recurrent inflammatory disease associated with an unbalanced immune response in the upper layers of the skin tissue, mostly starting in childhood. As important factors in gene expression regulation, polymorphisms in interleukin (IL)-17A and IL-17F may be associated with the susceptibility and severity of AD. Methods: Blood samples and clinical information were obtained from 132 patients with AD and 100 healthy children. Using multiplex polymerase chain reaction and next-generation sequencing, five potential single-nucleotide polymorphisms (SNPs) of IL-17A and IL-17F were genotyped in all participants. The relationship between SNPs and susceptibility to or severity of AD was examined by analyzing haplotypes and genetic models. Results: The IL-17A rs3819025 polymorphism was substantially associated with higher AD risk in both the allele model (p = 0.03; odds ratio [OR] = 1.76; confidence interval [CI]: 1.05-2.95) and the dominant model (p = 0.04, OR = 1.85; CI: 1.03-3.33). There was no correlation between AD susceptibility and the IL-17A (rs2275913 and rs4711998) or IL-17F (rs763780 and rs12203736) SNPs (all p > 0.05). Additionally, the five IL-17A and IL-17F SNPs did not significantly differ across the mild-to-moderate and severe subgroups (all p > 0.05). Conclusions: The IL-17A/rs3819025 polymorphism was linked to the development of AD, whereas the IL-17F polymorphism was unrelated to the susceptibility to and severity of AD. The IL-17A polymorphism may provide valuable information to speculate on the susceptibility to AD in Chinese Han children.

Objective While current multimodal approaches in the diagnosis and severity assessment of pneumonia demonstrate remarkable performance, they frequently overlook the issue of modality absence—a common challenge in clinical practice. Thus, we present the robust multimodal transformer (RMT) model, crafted to bridge this gap. The RMT model aims to enhance diagnosis and severity assessment accuracy in situations with incomplete data, thereby ensuring it meets the complex needs of real-world clinical settings. Method The RMT model leverages multimodal data, integrating X-ray images and clinical text data through a sophisticated AI-driven framework. It employs a Transformer-based architecture, enhanced by multi-task learning and mask attention mechanism. This approach aims to optimize the model’s performance across different modalities, particularly under conditions of modality absence. Results The RMT model demonstrates superior performance over traditional diagnostic methods and baseline models in accuracy, precision, sensitivity, and specificity. In tests involving various scenarios, including single-modal and multimodal tasks, the model shows remarkable robustness in handling incomplete data. Its effectiveness is further validated through extensive comparative analysis and ablation studies. Conclusion The RMT model represents a substantial advancement in pediatric pneumonia severity assessment. It successfully harnesses multimodal data and advanced AI techniques to improve assessment precision. While the RMT model sets a new precedent in AI applications in medical diagnostics, the development of a comprehensive pediatric pneumonia dataset marks a pivotal contribution, providing a robust foundation for future research.

OBJECTIVE:Gene expression profiling techniques measure the transcription of thousands of genes in a parallel manner. With more and more hepatocellular carcinoma (HCC) transcriptomic data becoming available, the high-throughput data provides an unprecedented opportunity to discover HCC diagnostic biomarkers. In this work, we propose a bioinformatics method based on dynamic network entropy analysis, called DNEA, to identify potential pathway biomarkers for HCC occurrence and development by integrating transcriptome and interactome. METHODS:We firstly collect the pathways documented in different knowledge-bases and then impose the genome-wide human transcriptomic data of multistage cancerous tissues during the development and progression of HCC. After linking the gene sets of pathways into individual connected networks, we map the corresponding gene expression information onto these pathways. The dynamic network entropy of individual pathways is calculated to evaluate its activities and dysfunctionalities during the disease occurrence and development. We use the overall significant difference in the entropic dynamics during the time course to prioritize distinctive pathways during disease progression. Then machine learning classification methods are employed to screen out pathway biomarkers with the classification ability to distinguish different-stage samples of HCC progression. RESULTS:Pathway biomarkers discovered based on DNEA demonstrate good classification performance in measuring HCC progression. The classification accuracy is as follows: DNA replication pathway (mean AUC = 0.82, 20 genes) from KEGG, FMLP pathway (mean AUC = 0.84, 14 genes) from BioCarta, and downstream signaling of activated FGFR pathway (mean AUC = 0.80, 15 genes) from Reactome. At the same time, previous studies have shown that these genes and pathways screened are closely related to the occurrence and development of HCC in terms of oncogenesis dysfunctions. CONCLUSIONS:Our method for cancer biomarker discovery based on dynamic network entropy analysis is effective and efficient in identifying pathway biomarkers related to the progression of complex diseases.

Background and Aims: Neonatal necrotizing enterocolitis (NEC) is a common life-threatening gastrointestinal disease in newborns. Abdominal X-rays (AXRs) is an important basis for diagnosing NEC and determining the need for surgical treatment. Computer-aided diagnosis (CAD) is extensively utilized in the clinical diagnosis of numerous diseases. Nevertheless, the efficacy of CAD for NEC has not been widely validated. Methods: We proposed for the first time a two-stage multimodal classification method for NEC based on AXRs data. The objective is to achieve early diagnosis of NEC and determine the optimal timing for surgical intervention. This method addresses the problem of insufficient labeled data through transfer learning and introduces coordinate attention to enhance the accuracy of target region localization and identification, thereby improving the capability of image feature extraction. Results: In total, the dataset was sourced from 2 children’s hospital consisted of 3,176 AXRs from 845 newborns diagnosed with NEC. Additionally, there were 1,825 AXRs from 470 newborns without NEC. The task for determining whether newborns has NEC achieved an accuracy of 97.49%, recall of 97.44%, precision of 83.09%, F1-score of 98.02% and AUC of 99.68%. Similarly, for the task of identifying if NEC patients require surgery, the accuracy, recall, precision, and F1-score were 78.96%, 81.50%, 80.30%, 80.89%, and 84.49% respectively. Our method performed better than the four commonly used baseline methods in the two-stage NEC diagnosis task. Conclusions: We have introduced a novel two-stage diagnostic model for NEC in newborns, which can rapidly and accurately identify NEC patients and determine if surgery is necessary.

目的/意义 通过儿童多学科联合会诊平台,优化会诊预约方式,规范会诊流程,推动医疗科研创新,提升儿科区域医疗服务能力.方法/过程 以浙江大学医学院附属儿童医院为多学科会诊服务中心,以杭州市滨江区3 家社区医院为分中心构建多渠道预约、多形式开展、多学科联合的智能儿科会诊管理平台.结果/结论 医院多学科智能儿科会诊有利于复杂疑难疾病诊治,实现区域儿科医疗资源整合、医院服务模式优化和医疗科研创新,构筑医患和谐共赢新生态.

分析以咳嗽为第一主诉的儿童疾病背景及其医疗数据应用情况和发展困境,结合联邦学习技术提出多中心横向联邦学习的数据安全共享框架,介绍3类联邦学习基础概念,从框架实施目的、系统架构组成、应用流程以及系统优点等方面详细阐述模型框架及构建路径.

目的 新生儿坏死性小肠结肠炎(Necrotizing Enterocolitis,NEC)是新生儿常见的危及生命的胃肠道疾病,建立新生儿NEC专病平台,对病情的诊疗以及科学研究均具有重要意义.方法 以三甲儿童医院为研究背景,依托医院现有临床数据,开展专病平台建设需求调研,实现临床数据的分层管理,开发影像标注功能.结果 建立了包含2225例患儿诊疗信息的新生儿NEC专病平台,实现了620例患儿腹部平片的标注,初步满足临床科研需求.结论 新生儿NEC专病平台有益于提升医生诊疗效率,充分挖掘高质量诊疗数据临床与科研价值.

Neonatal necrotizing enterocolitis is a severe neonatal intestinal disease. Timely identification of surgical indications is essential for newborns in order to seek the best time for treatment and improve prognosis. This paper attempts to establish an algorithm model based on multimodal clinical data to determine the features of surgical indications and construct an auxiliary diagnosis model. The proposed algorithm adds hypergraph constraints on the two modal data based on Joint Nonnegative Matrix Factorization (JNMF), aiming to mine the higher-order correlations of the two data features. In addition, the adjacency matrix of the two kinds of data is used as a network regularization constraint to prevent overfitting. Orthogonal and L1-norm regulations were introduced to avoid feature redundancy and perform feature selection, respectively, and confirmed 14 clinical features. Finally, we used three classifiers, random forest, support vector machine, and logistic regression, to perform binary classification of patients requiring surgery. The results show that when the features selected by the proposed algorithm model are classified by random forest, the area under the ROC curve is 0.8, which has high prediction accuracy.

With the continuous development and improvement of artificial intelligence technology, machine learning technology has also been extensively developed, which has promoted the development of computer vision, image processing, natural language processing, and other fields. Purpose. This article aims to apply the image processing technology based on machine learning in the detection of childhood diseases and propose the application of image processing technology to the detection of childhood diseases. This article introduces machine learning, image recognition technology, and related algorithms in detail and experiments on image recognition technology based on machine learning. The experimental results show that image recognition technology based on machine learning can well identify white blood cells that are difficult to distinguish with the naked eye, with a recognition rate of up to 90%. Applying image recognition technology based on machine learning in disease diagnosis has greatly improved the level of medical diagnosis.

Neonatal necrotizing enterocolitis is a severe neonatal intestinal disease. Timely, the identification of surgical indications is essential for newborns to seek the best time for treatment and improve prognosis. This paper attempts to establish an algorithm model based on multi-modal clinical data to determine the features of surgical indications and construct an auxiliary diagnosis model. The proposed algorithm adds hypergraph constraints on the two modal data based on Joint Non-negative Matrix Factorization, aiming to mine the higher-order correlations of the two data features. In addition, the adjacency matrix of the two kinds of data is used as a network regularization constraint to prevent overfitting. Orthogonal and L-1-norm regulations were introduced to avoid feature redundancy and perform feature selection, respectively, and confirmed 14 clinical features. Finally, we used three classifiers, random forest, support vector machine, and logistic regression, to perform binary classification of patients requiring surgery. The results show that when the features selected by the proposed algorithm model are classified by random forest, the area under the ROC curve is 0.8, which has high prediction accuracy.

Background: Multicenter clinical research faces many challenges, including how to quantitatively evaluate the data contribution of each research center. However, few data pricing model meets the requirements to the scenario. Thus, a suitable mechanism to measure the data value for clinical research is required.Methods: Extensive documents were acquired and analyzed, including a rare disease list from the National Health Commission, data structures of the electronic medical records (EMR) system, diagnosis-related groups (DRGs) regulations from the Health Commission of Zhejiang Province, and the Clinical Service Price List of Zhejiang Province. Nine senior experts were invited as consultants from hospital and enterprises with professional field of clinical research, data governance, and health economics. After brainstorming and expert evaluation, seven data attributes were identified as the main factors affecting the value of medical data. Different weights were assigned for each attribute based on its influence on data value. Each attribute was quantized to an index based on proposed algorithms. The data value models for chronic diseases and other diseases were distinguished given the different sensitivity of data timeliness. A simulation system using blockchain and federated learning techniques was constructed to verify the data pricing model in the scenario of clinical research.Results: A comprehensive clinical data pricing model is proposed and the simulation of three research centers with 50 million real clinical data entries was conducted to verify its effectiveness. It demonstrates that the proposed model can compute medical data value quantitatively.Conclusions: Quantitative evaluation of the value of medical data for multicenter clinical research based on the proposed data pricing model works well in simulation. This model will be improved by real-world applications in the near future.

Background Developmental dysplasia of the hip (DDH) is a common orthopedic disease in children. In clinical surgery, it is essential to quickly and accurately locate the exact position of the lesion, and there are still some controversies relating to DDH status. We adopt artificial intelligence (AI) to solve the above problems. Methods In this paper, automatic DDH measurements and classifications were achieved using a three-stage pipeline. In the first stage, we used Mask-RCNN to detect the local features of the image and segment the bony pelvis, including the ilium, pubis, ischium, and femoral heads. For the second stage, local image patches focused on semantically related areas for DDH landmarks were extracted by high-resolution network (HRNet). In the third stage, some radiographic results are obtained. In the above process, we used 1,265 patient x-ray samples as the training set and 133 samples from two other medical institutions as the verification set. The results of AI were compared with three orthopedic surgeons for reliability and time consumption. Results AI-aided diagnostic system's Tönnis and International Hip Dysplasia Institute (IHDI) classification accuracies for both hips ranged from 0.86 to 0.95. The measurements of numerical indices showed that there was no statistically significant difference between surgeons and AI. Tönnis and IHDI indicators were similar across the AI system, intermediate surgeon, and junior surgeon. Among some objective interpretation indicators, such as acetabular index and CE angle, there were good stability and consistency among the four observers. Intraclass consistency of acetabular index and CE angle among surgeons was 0.79–0.98, while AI was 1.00. The measurement time required by AI was significantly less than that of the doctors. Conclusion The AI-aided diagnosis system can quickly and automatically measure important parameters and improve the quality of clinical diagnosis and screening referral process with a convenient and efficient way.

随着城市大脑跨部门协同的"超级应用"层出不穷,与城市大脑高效对接日渐成为医疗机构数据管理部门需要认真思考的课题.本文探索建立一套新的医疗数据治理体系,在保障数据安全的前提下实现与城市大脑无缝对接.通过对医疗机构和院外数据进行归集,并按照城市大脑五层数据模型进行治理,形成数据中心.研究结果显示,经过治理的医疗数据平台包含了医疗机构、学校、教育局、社发局等多家单位,有效实现了多跨协同.由此,基于城市大脑数据模型的数据治理体系为医疗机构提供了一种新的数据治理方式,为跨部门数据协同开发奠定了坚实的基础.

目的:为提高儿童常见皮肤病人工智能辅助诊断模型准确率,需要对收集的影像进行标注.本文提出一套儿童常见皮肤病影像标注平台,为后续临床研究提供强有力的支撑.方法:运用VUE、Spring Boot和Canvas等技术研发一套适合儿童皮肤科医生使用的影像标注系统.结果:使用研发的影像标注系统完成了儿童常见皮肤病近8000张影像的标注工作.结论:本系统满足临床科研影像标注需求,符合皮肤科医生使用习惯,具有很好的推广前景.