Accurate identification of irreducible intussusception during air enema is crucial for optimizing enema strategies. Current methods are limited by subjective interpretation and inconsistent clinical criteria. We developed a deep learning (DL) framework to objectively predict irreducibility using air enema fluoroscopic images. In this retrospective study, a hybrid ensemble DL model was developed using fluoroscopic images acquired during air enema, comprising 770 irreducible and 1214 reducible cases. Model performance was evaluated on a real-world test set (46 irreducible vs. 802 reducible cases) and an external test set (9 irreducible vs. 101 reducible cases), with benchmarking against state-of-the-art techniques. The model’s performance was further compared with radiologists’ interpretations, and its ability to improve diagnostic accuracy was assessed. Performance was evaluated using receiver operating characteristic (ROC) analysis and confusion matrix-derived metrics. The proposed model achieved areas under the ROC curves (AUCs) of 0.89 (95

The accurate identification of children with refractory Mycoplasma pneumoniae pneumonia (RMPP) remains challenging. This study aimed to develop a transformer-based model utilizing clinically indicated chest computed tomography (CT) to stratify pediatric RMPP risk at a critical decision point. Non-contrast chest CT data from a multicenter retrospective cohort of 1224 pediatric patients with Mycoplasma pneumoniae pneumonia who underwent clinically indicated CT were used to develop a transformer-based deep learning framework (trans-DLF). The primary cohort comprised training (n = 506), validation (n = 140), and internal testing (n = 139) cohorts, with two independent external cohorts (n = 331 and n = 108) used to evaluate generalizability. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and compared against a three-dimensional convolutional neural network (3D-CNN), a clinical model, and a multimodal nomogram. Interpretability was examined using gradient-weighted class activation mapping (Grad-CAM). The median age was 6.83 years (interquartile range, 5.0–8.6 years), and 609 (49.8

Flexible bronchoscopy (FB) is recommended for pediatric Mycoplasma pneumoniae pneumonia (MPP) with persistent consolidation or atelectasis, though substantial heterogeneity in treatment effects exists. This study aimed to develop a causal forest-based predictive model to identify pediatric MPP patients most likely to benefit from FB. This retrospective two-center study enrolled pediatric MPP patients in derivation (n = 753) and validation (n = 139) cohorts. Clinical, laboratory, and AI-quantified computed tomography (CT) data were analyzed. Individual treatment effects (ITEs) were estimated using causal forest algorithms. FB-beneficial subgroups were defined using receiver operating characteristic (ROC) analysis of ITEs, with the varying treatment effect across the subgroups validated via multivariable linear regression. Subgroup characteristics, feature importance, and heatmap-based feature interactions were also analyzed. FB treatment significantly reduced total fever duration in identified FB-beneficial subgroups in both derivation (β = − 1.16, p < 0.001) and validation (β = − 0.68, p = 0.04) cohorts. These beneficial subgroups exhibited significantly higher consolidation/atelectasis volume (CAV), pneumonia attenuation (PA), and consolidation-to-pneumonia ratio (CAR) compared to non-beneficial groups (all p < 0.001). Heatmap analyses confirmed that increased CAV combined with elevated PA or lymphocyte counts could improve FB efficacy. This study developed and validated an individualized prediction model to identify pediatric MPP patients most likely to benefit from FB treatment. Our model may serve as a tool to support clinicians in optimizing FB utilization, potentially reducing unnecessary interventions and associated risks. An accessible online tool of this model facilitates practical clinical implementation.

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.

Background:Mycoplasma pneumoniae pneumonia (MPP) is a major cause of community-acquired pneumonia (CAP) in children, with some cases progressing to refractory MPP (RMPP). RMPP is associated with a hypercoagulable state and pulmonary embolism. This study aimed to investigate pulmonary microvascular changes in RMPP and evaluate the predictive value of pulmonary blood volume (PBV) parameters. Methods:A retrospective study using UV-Net-based pulmonary vascular analysis included 512 pediatric MPP patients in a cross-validation cohort and 124 pediatric MPP patients in an external testing cohort. Pulmonary blood vessels were segmented and classified by cross-sectional area into three blood-volume fractions: BV5%, representing the percentage of PBV contained in vessels with a cross-sectional area less than 5 mm2; BV5-10%, representing the percentage of PBV contained in vessels with a cross-sectional area between 5 and 10 mm2; and BV10%, representing the percentage of PBV contained in vessels with a cross-sectional area greater than 10 mm2. Logistic regression and extreme gradient boosting were used to analyze associations and predict RMPP. Model performance was assessed via receiver operating characteristic (ROC) curve analysis. Results:Patients with RMPP, compared to patients with non-RMPP, had a significantly lower BV5% (median: 58.50% vs. 60.63%, P=0.007) and higher BV10% (median: 20.90% vs. 19.39%, P=0.004). Multivariate analysis revealed BV5% as a protective predictor [odds ratio (OR) =0.70, P=0.005] and BV10% as a risk factor for RMPP (OR =1.49, P=0.002). Compared with the clinical-only model, the model incorporating these computed tomography (CT)-derived parameters significantly improved performance in the cross-validation cohort, demonstrating superiority in terms of area under the ROC curve (AUC) and other metrics (combined model: AUC =0.91, 95% CI: 0.89-0.94; clinical-only model: AUC =0.88, 95% CI: 0.86-0.91; P<0.001). In the external testing cohort, the combined model consistently outperformed the clinical-only model in accuracy, precision, specificity, and F1 score. Conclusions:Quantitative analysis revealed microvascular alterations in patients with RMPP. Integrating CT-derived biomarkers can enhance RMPP prediction and facilitate early intervention.

The last-minute cancellation of surgeries profoundly affects patients and their families. This research aimed to forecast these cancellations using EMR data and meteorological conditions at the time of the appointment, using a machine learning approach. We retrospectively gathered medical data from 13 440 pediatric patients slated for surgery from 2018 to 2021. Following data preprocessing, we utilized random forests, logistic regression, linear support vector machines, gradient boosting trees, and extreme gradient boosting trees to predict these abrupt cancellations. The efficacy of these models was assessed through performance metrics. The analysis revealed that key factors influencing last-minute cancellations included the impact of the coronavirus disease 2019 pandemic, average wind speed, average rainfall, preanesthetic assessments, and patient age. The extreme gradient boosting algorithm outperformed other models in predicting cancellations, boasting an area under the curve value of 0.923 and an accuracy of 0.841. This algorithm yielded superior sensitivity (0.840), precision (0.837), and F1 score (0.838) relative to the other models. These insights underscore the potential of machine learning, informed by EMRs and meteorological data, in forecasting last-minute surgical cancellations. The extreme gradient boosting algorithm holds promise for clinical deployment to curtail healthcare expenses and avert adverse patient-family experiences.

Alanine aminotransferase (ALT) is widely used to screen patients with hepatic diseases. However, the current reference ranges (< 50 U/L) were developed by laboratories and have not been validated in populations with a large number of healthy individuals. This study collected venous blood and anthropometric data from a total of 13,287 healthy children aged 3 months to 18 years who underwent routine physical examinations in the Department of Pediatric Healthcare. We applied the least mean square algorithm to establish age- and sex-related reference percentiles of serum levels of transaminases. For validation, we recruited 4276 children and adolescents with obesity/overweight who underwent evaluation and metabolic tests in the hospital. Using receiver operating characteristic curves, we determined age- and sex-specific upper limit percentiles of liver enzymes for fatty liver diseases. This study revealed a significant correlation between serum transaminase levels and age and sex (P < 0.01). These transaminase levels exhibited age- and sex-specific patterns. Among individuals in the non-alcoholic fatty liver disease (NAFLD) cohort, elevated ALT levels displayed a positive association with clinical markers of disease severity, including homeostatic model assessment of insulin resistance, waist–hip ratio, and serum uric acid levels (P < 0.01). According to the receiver operating characteristic curves, ALT levels at the 92.58th percentile for boys and the 92.07th percentile for girls yielded the highest accuracy and specificity. This study provides age- and sex-specific reference ranges for ALT, aspartate aminotransferase, and γ-glutamyltransferase in Chinese children and adolescents, making it the largest population study to date. Furthermore, the study establishes a precise upper limit for ALT levels, facilitating their use in NAFLD screening.

Background The COVID-19 pandemic has significantly altered the global health and medical landscape. In response to the outbreak, Chinese hospitals have established 24-hour fever clinics to serve patients with COVID-19. The emergence of these clinics and the impact of successive epidemics have led to a surge in visits, placing pressure on hospital resource allocation and scheduling. Therefore, accurate prediction of outpatient visits is essential for informed decision-making in hospital management. Objective Hourly visits to fever clinics can be characterized as a long-sequence time series in high frequency, which also exhibits distinct patterns due to the particularity of pediatric treatment behavior in an epidemic context. This study aimed to build models to forecast fever clinic visit with outstanding prediction accuracy and robust generalization in forecast horizons. In addition, this study hopes to provide a research paradigm for time-series forecasting problems, which involves an exploratory analysis revealing data patterns before model development. Methods An exploratory analysis, including graphical analysis, autocorrelation analysis, and seasonal-trend decomposition, was conducted to reveal the seasonality and structural patterns of the retrospective fever clinic visit data. The data were found to exhibit multiseasonality and nonlinearity. On the basis of these results, an ensemble of time-series analysis methods, including individual models and their combinations, was validated on the data set. Root mean square error and mean absolute error were used as accuracy metrics, with the cross-validation of rolling forecasting origin conducted across different forecast horizons. Results Hybrid models generally outperformed individual models across most forecast horizons. A novel model combination, the hybrid neural network autoregressive (NNAR)-seasonal and trend decomposition using Loess forecasting (STLF), was identified as the optimal model for our forecasting task, with the best performance in all accuracy metrics (root mean square error=20.1, mean absolute error=14.3) for the 15-days-ahead forecasts and an overall advantage for forecast horizons that were 1 to 30 days ahead. Conclusions Although forecast accuracy tends to decline with an increasing forecast horizon, the hybrid NNAR-STLF model is applicable for short-, medium-, and long-term forecasts owing to its ability to fit multiseasonality (captured by the STLF component) and nonlinearity (captured by the NNAR component). The model identified in this study is also applicable to hospitals in other regions with similar epidemic outpatient configurations or forecasting tasks whose data conform to long-sequence time series in high frequency exhibiting multiseasonal and nonlinear patterns. However, as external variables and disruptive events were not accounted for, the model performance declined slightly following changes in the COVID-19 containment policy in China. Future work may seek to improve accuracy by incorporating external variables that characterize moving events or other factors as well as by adding data from different organizations to enhance algorithm generalization.

Background:Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.Objective:In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.Methods:The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.Results:Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.Conclusions:This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Two-dimensional (2D) nanomaterials have been widely used in biomedical applications because of their biocompatibility. Considering the high risk of exposure of the circulatory system to Ti3C2Tx, we studied the cytocompatibility of Ti3C2Tx MXene with red blood cells (RBCs) and human umbilical vein endothelial cells (HUVECs) and showed that Ti3C2Tx had excellent compatibility with the two cell lines. Ti3C2Tx at a concentration as high as 200 μg/mL caused a negligible percent hemolysis of 0.8%. By contrast, at the same treatment concentration, graphene oxide (GO) caused a high percent hemolysis of 50.8%. Scanning electron microscopy revealed that RBC structures remained intact in the Ti3C2Tx treatment group, whereas those in the GO group completely deformed, sunk, and shrunk, which resulted in the release of cell contents. This difference can be largely ascribed to the distinct surficial properties of the two nanosheets. In specific, the fully covered surface-terminating -O and -OH groups leading to Ti3C2Tx had a very hydrophilic surface, thereby hindering its penetration into the highly hydrophobic interior of the cell membrane. However, the strong direct van der Waals attractions coordinated with hydrophobic interactions between the unoxidized regions of GO and the lipid hydrophobic tails can still damage the integrity of the cell membranes. In addition, the sharp and keen-edged corners of GO may also facilitate its relatively strong cell membrane damage effects than Ti3C2Tx. Thus, the excellent cell membrane compatibility of Ti3C2Tx nanosheets and their ultraweak capacity to provoke excessive ROS generation endowed them with much better compatibility with HUVECs than GO nanosheets. These results indicate that Ti3C2Tx has much better cytocompatibility than GO and provide a valuable reference for the future biomedical applications of Ti3C2Tx.

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.

Lung segmentation using computed tomography (CT) images is important for diagnosing various lung diseases. Currently, no lung segmentation method has been developed for assessing the CT images of preschool children, which may differ from those of adults due to (1) presence of artifacts caused by the shaking of children, (2) loss of a localized lung area due to a failure to hold their breath, and (3) a smaller CT chest area, compared with adults. To solve these unique problems, this study developed an automatic lung segmentation method by combining traditional imaging methods with ResUnet using the CT images of 60 children, aged 0-6 years. First, the CT images were cropped and zoomed through ecological operations to concentrate the segmentation task on the chest area. Then, a ResUnet model was used to improve the loss for lung segmentation, and case-based connected domain operations were performed to filter the segmentation results and improve segmentation accuracy. The proposed method demonstrated promising segmentation results on a test set of 12 cases, with average accuracy, Dice, precision, and recall of 0.9479, 0.9678, 0.9711, and 0.9715, respectively, which achieved the best performance relative to the other six models. This study shows that the proposed method can achieve good segmentation results in CT of preschool children, laying a good foundation for the diagnosis of children's lung diseases.

Background and Aims. Diagnosing pediatric intussusception from ultrasound images can be a difficult task in many primary care hospitals that lack experienced radiologists. To address this challenge, this study developed an artificial intelligence- (AI-) based system for automatic detection of “concentric circles” signs on ultrasound images, thereby improving the efficiency and accuracy of pediatric intussusception diagnosis. Methods. A total of 440 cases (373 pediatric intussusception and 67 normal cases) were retrospectively collected from Children’s Hospital affiliated to Zhejiang University School of Medicine from January 2020 to December 2020. An improved Faster RCNN deep learning framework was used to detect “concentric circle” signs. Finally, independent validation set was used to evaluate the performance of the developed AI tool. Results. The data of pediatric intussusception were divided into a training set and validation set according to the ratio of 8 : 2, with training set (298 pediatric intussusception) and validation set (75 pediatric intussusception and 67 normal cases). In the “concentric circle” detection model, the detection rate, recall, specificity, and F1 score assessed by the validation set were 92.8%, 95.0%, 92.2%, and 86.4%, respectively. Pediatric intussusception was classified by “concentric circle” signs, and the accuracy, recall, specificity, and F1 score were 93.0%, 92.0%, 94.1%, and 93.2% on the validation set, respectively. Conclusion. The model established in this paper can realize the automatic detection of “concentric circle” signs in the ultrasound images of abdominal intussusception in children; the AI tool can improve the diagnosis speed of pediatric intussusception. It is necessary to further develop an artificial intelligence system for real-time detection of “concentric circles” in ultrasound images for the judgment of children with intussusception.

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.

Coronary artery damage left by Kawasaki disease persist for a long time, and long-term monitoring is necessary. With the help of hospital information system, an outpatient clinical pathway management system for Kawasaki disease was designed. The system has the functions of path setting, doctor workstation path, scientific research statistical analysis, patient appointment reminding, etc., which can meet the needs of clinical treatment and scientific research of Kawasaki disease. However, the utilization rate of the system and the refinement level of the system operation need to be further improved, which can be continuously improved from two aspects of system support and clinical management.

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.

Chronic diseases for children pose serious challenges from a health management perspective. When not implemented in a well-designed manner, an inefficient management platform can have a significant negative impact on patients and the utilization of health care resources. Innovations of recent years in information technology, artificial intelligence and machine learning provide possibilities to design and implement knowledge-based systems and platforms that follow-up, monitor and advise child patients with a chronic disease in an automated manner. In this article we propose the Artificial Intelligence Chronic Management System that combines artificial intelligence, knowledge graph, big data and internet of things in a platform to offer an optimized solution from the perspective of treatment and utilization of resources. The system includes patient and hospital clients, data storage and analytic tools for decision support relying on AI-based services. We illustrate the functionality of the system through different situations frequently occurring in pediatric wards. To assess the feasibility of the AI component, we utilize real life health care data from a hospital in China to develop a classification model for patients with asthma. To provide a more qualitative assessment at the same time, we discuss how the Artificial Intelligence Chronic Management System conforms to the requirements set forth by the standard Chronic Care Model.

Background:Due to the phenotypic similarities among different pediatric respiratory diseases with chronic cough, primary doctors often misdiagnose and the misuse of examinations is prevalent. In the pre-diagnosis stage, the patients' chief complaints and other information in the electronic medical record (EMR) provide a powerful reference for respiratory experts to make preliminary disease judgment and examination plan. In this paper, we proposed an intelligent prediagnosis system to predict disease diagnosis and recommend examinations based on EMR text.Methods:We examined the clinical notes of 178,293 children with chronic cough symptoms from retrospective EMR data. The dataset is split into 7:3 for training and testing. From the testing set, we also extract 5% of samples for validation. We proposed a medical-semantic-aware convolution neural network (MSCNN) framework that can accomplish two downstream tasks from the same medical language model through transfer learning. First, a medical language model based on the word2vec algorithm was built to generate embeddings for the text data. Then, text convolutional neural network (TextCNN) was used to build models for disease prediction and examination recommendation.Results:We implemented 5 algorithms for disease prediction. In the disease prediction task, our algorithm outperformed the baseline methods on all metrics, with a top-1 accuracy (AC) of 0.68 and a top-3 AC of 0.923 on the testing set. By adding data enhancement, the top-3 AC reached 0.926. In the examination recommendation task, the overall AC on the testing set was 0.93 and the macro average (MA) F1-score was 0.88. The average area under the curve (AUC) on the training set was 0.97 while on the testing set it was 0.86.Conclusions:We constructed an intelligent prediagnosis system with an MSCNN framework that can predict diseases and make examination recommendations based on EMR data. Our approach achieved good results on a retrospective clinical dataset and thus has great potential for the application of automated diagnosis assist in clinical practice during pre-diagnosis stage, which will provide help for primary level doctors or doctors in basic-level hospitals. Due to the generality of the proposed framework, it can be straight forwardly extended to prediagnosis for other diseases.

Respiratory diseases, including asthma, bronchitis, pneumonia, and upper respiratory tract infection (RTI), are among the most common diseases in clinics. The similarities among the symptoms of these diseases precludes prompt diagnosis upon the patients' arrival. In pediatrics, the patients' limited ability in expressing their situation makes precise diagnosis even harder. This becomes worse in primary hospitals, where the lack of medical imaging devices and the doctors' limited experience further increase the difficulty of distinguishing among similar diseases. In this paper, a pediatric fine-grained diagnosis-assistant system is proposed to provide prompt and precise diagnosis using solely clinical notes upon admission, which would assist clinicians without changing the diagnostic process. The proposed system consists of two stages: a test result structuralization stage and a disease identification stage. The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage. A novel deep learning algorithm was developed for the disease identification stage, where techniques including adaptive feature infusion and multi-modal attentive fusion were introduced to fuse structured and text data together. Clinical notes from over 12000 patients with respiratory diseases were used to train a deep learning model, and clinical notes from a non-overlapping set of about 1800 patients were used to evaluate the performance of the trained model. The average precisions (AP) for pneumonia, RTI, bronchitis and asthma are 0.878, 0.857, 0.714, and 0.825, respectively, achieving a mean AP (mAP) of 0.819.