Purpose: Traditional craniofacial phenotyping of obstructive sleep apnea (OSA) relies on predefined anatomical hypotheses, often yielding incomplete assessments. This study aimed to apply multiple explainable deep learning (DL) approaches to explore novel craniofacial phenotypes. Patients and Methods: A multimodal DL model was trained using frontal and lateral facial images, lateral cephalograms, and demographic data from 130 participants (65 OSA patients diagnosed by overnight polysomnography, and 65 age-and sex-matched controls). Explainability analysis of the model's prediction was conducted in a subset of 56 participants per group using average face analysis, feature importance analysis, and gradient-weighted class activation mapping (Grad-CAM). Targeted measurements were then performed on the identified non-traditional regions to validate morphological differences. Results: The model achieved an area under the curve of 0.87. The explainability analysis identified not only anatomical structures that have been confirmed to predict OSA (such as the mandible, chin, and hyoid regions), but also the middle and upper facial third (e.g. the forehead, eyebrows, and upper eyelids), which has not been fully emphasized in previous studies. Targeted measurements confirmed a significantly smaller inter-eyebrow distance, increased frontal protrusion (p < 0.001) and frontal sinus area (p < 0.001) in OSA patients. Conclusion: Explainable DL expanded OSA-related craniofacial phenotypes. Future studies are needed to validate these upper-face traits in larger cohorts and clarify their relevance to OSA subtyping and mechanisms.

Analysis of transient performance of patient flow in hospitals is critical for healthcare delivery, which could offer valuable insights into building and environmental design, medical resource allocation, and traffic planning. Despite extensive research on hospital operation management, effective analytical models to study dynamic behaviors of patient flow remain scarce. Due to the time-varying and stochastic features in patient arrivals and care services, transient modeling, rather than steady-state analysis, could provide insights into short-term system dynamics, which is strongly needed, but the study is limited. To bridge this gap, this study introduces a dynamic queueing network model to analyze the transient performance of patient flow, under the scenario of a large public hospital. Specifically, the transient behavior of patient service processes, characterized by multiple units with complex structures, is analyzed using a history-buffer-based iterative method derived from dynamic equations. To address cumulative errors in long-term analysis, a real-time correction method is proposed. Extensive numerical experiments demonstrate that the proposed approach can provide transient estimation of patient flow with acceptable accuracy. In addition, the influence of parameter settings and system properties are investigated. Such a model provides an effective analytical tool for real-time management to improve care delivery.

ObjectiveThe objective of this study was to investigate the effectiveness of a machine learning algorithm in diagnosing OSA in children based on clinical features that can be obtained in nonnocturnal and nonmedical environments.Patients and methodsThis study was conducted at Beijing Children's Hospital from April 2018 to October 2019. The participants in this study were 2464 children aged 3–18 suspected of having OSA who underwent clinical data collection and polysomnography(PSG). Participants’ data were randomly divided into a training set and a testing set at a ratio of 8:2. The elastic net algorithm was used for feature selection to simplify the model. Stratified 10-fold cross-validation was repeated five times to ensure the robustness of the results.ResultsFeature selection using Elastic Net resulted in 47 features for AHI ≥5 and 31 features for AHI ≥10 being retained. The machine learning model using these selected features achieved an average AUC of 0.73 for AHI ≥5 and 0.78 for AHI ≥10 when tested externally, outperforming models based on PSG questionnaire features. Linear Discriminant Analysis using the selected features identified OSA with a sensitivity of 44% and specificity of 90%, providing a feasible clinical alternative to PSG for stratifying OSA severity.ConclusionsThis study shows that a machine learning model based on children's clinical features effectively identifies OSA in children. Establishing a machine learning screening model based on the clinical features of the target population may be a feasible clinical alternative to nocturnal OSA sleep diagnosis.

ObjectiveThe appropriate use of statins plays a vital role in reducing the risk of atherosclerotic cardiovascular disease (ASCVD). However, due to changes in diet and lifestyle, there has been a significant increase in the number of individuals with high cholesterol levels. Therefore, it is crucial to ensure the rational use of statins. Adverse reactions associated with statins, including liver enzyme abnormalities and statin-associated muscle symptoms (SAMS), have impacted their widespread utilization. In this study, we aimed to develop a predictive model for statin efficacy and safety based on real-world clinical data using machine learning techniques.MethodsWe employed various data preprocessing techniques, such as improved random forest imputation and Borderline SMOTE oversampling, to handle the dataset. Boruta method was utilized for feature selection, and the dataset was divided into training and testing sets in a 7:3 ratio. Five algorithms, including logistic regression, naive Bayes, decision tree, random forest, and gradient boosting decision tree, were used to construct the predictive models. Ten-fold cross-validation and bootstrapping sampling were performed for internal and external validation. Additionally, SHAP (SHapley Additive exPlanations) was employed for feature interpretability. Ultimately, an accessible web-based platform for predicting statin efficacy and safety was established based on the optimal predictive model.ResultsThe random forest algorithm exhibited the best performance among the five algorithms. The predictive models for LDL-C target attainment (AUC = 0.883, Accuracy = 0.868, Precision = 0.858, Recall = 0.863, F1 = 0.860, AUPRC = 0.906, MCC = 0.761), liver enzyme abnormalities (AUC = 0.964, Accuracy = 0.964, Precision = 0.967, Recall = 0.963, F1 = 0.965, AUPRC = 0.978, MCC = 0.938), and muscle pain/Creatine kinase (CK) abnormalities (AUC = 0.981, Accuracy = 0.980, Precision = 0.987, Recall = 0.975, F1 = 0.981, AUPRC = 0.987, MCC = 0.965) demonstrated favorable performance. The most important features of LDL-C target attainment prediction model was cerebral infarction, TG, PLT and HDL. The most important features of liver enzyme abnormalities model was CRP, CK and number of oral medications. Similarly, AST, ALT, PLT and number of oral medications were found to be important features for muscle pain/CK abnormalities. Based on the best-performing predictive model, a user-friendly web application was designed and implemented.ConclusionThis study presented a machine learning-based predictive model for statin efficacy and safety. The platform developed can assist in guiding statin therapy decisions and optimizing treatment strategies. Further research and application of the model are warranted to improve the utilization of statin therapy.

The early detection accuracy of early gastric cancer (EGC) determines the choice of the optimal treatment strategy and the related medical expenses. We aimed to develop a simple, affordable, and time-saving diagnostic model using six machine learning (ML) algorithms for the diagnosis of EGC. It is based on the endoscopy-based Kyoto classification score obtained after the completion of endoscopy and other clinical features obtained after medical consultation. We retrospectively evaluated 1999 patients who underwent gastrointestinal endoscopy at the China Beijing Hospital. Of these, 203 subjects were diagnosed with EGC. The data were randomly divided into training and test sets (ratio 4:1). We constructed six ML models, and the developed models were evaluated on the testing set. This procedure was repeated five times. The Kolmogorov–Arnold Networks (KANs) model achieved the best performance (mean AUC value: 0.76; mean balanced accuracy: 70.96%; mean precision: 58.91%; mean recall: 70.96%; mean false positive rate: 26.11%; mean false negative rate: 31.96%; and mean F1 score value: 58.46). The endoscopy-based Kyoto classification score was the most important feature with the highest feature importance score. The results suggest that the KAN model, the optimal ML model in this study, has the potential to identify EGC patients, which may result in a reduction in both the time cost and medical expenses in clinical practice.

To reduce energy consumption, green hospitals have received increasing research attention. In this letter, a patient flow prediction-based approach is introduced to control air conditioning system for energy savings in green hospitals. The patient occupancy in various hospital units is predicted through a discrete-event simulation model. Control policies are developed by using the predicted information to adjust parameters of a thermal model for fresh air and cooling load in air conditioning systems. It is shown that such an approach can lead to significant energy savings in hospitals.

ObjectiveTo develop clinical nurse⁃patient communication knowledge，attitude and practice questionnaire， and to test its reliability and validity.MethodsBased on the theory of knowledge，attitude and practice，clinical nurse⁃patient communication knowledge，attitude and practice questionnaire was compiled through literature analysis，semi⁃structured interview and expert consultation.A total of 200 clinical nurses from tertiary grade A hospitals in Jiangsu Province were selected to test the reliability and validity.ResultsThe clinical nurse⁃patient communication knowledge，attitude and practice questionnaire included three dimensions with knowledge，attitude and practice，involving 25 items.The overall Cronbach's α coefficient of the scale was 0.864，and Cronbach's α coefficients of each dimension were 0.817，0.917，and 0.943.The item⁃content validity index（I⁃CVI） ranged from 0.82 to 1.00，and scale⁃content validity index（S⁃CVI） was 0.95.The exploratory factor analysis（EFA） extracted three common factors，and the cumulative variance contribution rate was 62.308%.ConclusionThe clinical nurse⁃patient communication knowledge，attitude and practice questionnaire had good reliability and validity，and could be used as an effective tool to investigate the knowledge，attitude and practice of clinical nurse⁃patient communication.

目的 探索真实世界大样本儿童病例注射用尖吻蝮蛇不良反应主动监测方法,以期为儿童病例注射用尖吻蝮蛇血凝酶不良反应的揭示和挖掘提供支持.方法 利用实体识别技术对 2014 年2月25日至 2021年1月8日首都儿科研究所住院并使用注射用尖吻蝮蛇血凝酶的35 720儿童病例进行回顾性不良反应主动监测,采用查准率(precision,P)、查全率(recall,R)和F1值 3个指标来评估实验结果.结果 经过 3轮分析,查准率、查全率和F1值 3个指标均达到了100%.结论 应用自然语言处理技术可以用于真实世界大样本儿童病例注射用尖吻蝮蛇血凝酶不良反应监测.

Gastric cancer is one of the most common malignant tumors of the digestive system. Although gastroscopy can effectively detect early cancers, manual identification and diagnosis is time-consuming and laborious, and the false-negative rate is as high as 4.6-25.8%. Early gastric cancer lesion areas can be detected and segmented using deep learning techniques. We collected and organized 12665 eligible gastroscopy images, and cropped and expanded the original dataset after labeling by professional doctors, and finally obtained 19673 images for model training. We propose ResMSE Net and DWFF Net and apply these two networks to Mask R-CNN to obtain a new model: Mask R-CNN With R-D Net. On the same standard dataset, the mAP@[IoU=0.5] and ACC values of the Mask R-CNN With R-D Net model achieve respectively 45.37% and 67.74%, which are improved by 5.83% and 9.08%, respectively, compared with the original model. In our experiments, we found that Mask R-CNN With R-D Net is difficult to detect targets that are extremely similar to the background, which is the direction of our future work. Secondly, we hope to minimize the number of model parameters and make the model more lightweight under the premise of ensuring accuracy, so that the model can be embedded into gastroscopy detection equipment for real-time detection.

As the medical aesthetic market is growing rapidly in China, orthodontic treatment is becoming very common among the adolescent population. However, there are countless doctor-patient disputes due to treatment results that do not meet patients' expectations, so there is an urgent need for a method to predict treatment results. With the development of artificial intelligence technology, generative adversarial network has provided us with a new way of thinking. The purpose of this paper is to accurately predict the face of patients after orthodontic treatment by using generative adversarial network. Therefore, we designed an evaluation index to reflect the difference between the algorithm predicted image and the patient's real image. After that, we designed a network based on Encoder-Decoder architecture to transform the vectors in StyleGAN latent space. Finally, we carried out experiments to verify the effectiveness of the evaluation index design and the advantages of the algorithm.

OBJECTIVES:This study aimed to develop a fully automated artificial intelligence-aided cervical vertebral maturation (CVM) classification method based on convolutional neural networks (CNNs) to provide an auxiliary diagnosis for orthodontists.METHODS:This study consisted of cephalometric images from patients aged between 5 and 18 years. After grouping them into six cervical stages (CSs) by orthodontists, a data set was constructed for analyzing CVM using CNNs. The data set was divided into training, validation, and test sets in the ratio of 70, 15, and 15%. Four CNN models namely, VGG16, GoogLeNet, DenseNet161, and ResNet152 were selected as the candidate models. After training and validation, the models were evaluated to determine which of them is most suitable for CVM analysis. Heat maps were analyzed for a deeper understanding of what the CNNs had learned.RESULTS:The final classification accuracy ranking was ResNet152>DenseNet161>GoogLeNet>VGG16, as evaluated on the test set. ResNet152 proved to be the best model among the four models for CVM classification with a weighted κ of 0.826, an average AUC of 0.933 and total accuracy of 67.06%. The F1 score rank for each subgroup was: CS6>CS1>CS4>CS5>CS3>CS2. The area of the third (C3) and fourth (C4) cervical vertebrae were activated when CNNs were assessing the images.CONCLUSION:CNN models proved to be a convenient, fast and reliable method for CVM analysis. CNN models have the potential to provide automatic auxiliary diagnostic tools in the future.

Objective We aim to investigate the application and accuracy of artificial intelligence (AI) methods for automated medical literature screening for systematic reviews. Materials and Methods We systematically searched PubMed, Embase, and IEEE Xplore Digital Library to identify potentially relevant studies. We included studies in automated literature screening that reported study question, source of dataset, and developed algorithm models for literature screening. The literature screening results by human investigators were considered to be the reference standard. Quantitative synthesis of the accuracy was conducted using a bivariate model. Results Eighty-six studies were included in our systematic review and 17 studies were further included for meta-analysis. The combined recall, specificity, and precision were 0.928 [95% confidence interval (CI), 0.878-0.958], 0.647 (95% CI, 0.442-0.809), and 0.200 (95% CI, 0.135-0.287) when achieving maximized recall, but were 0.708 (95% CI, 0.570-0.816), 0.921 (95% CI, 0.824-0.967), and 0.461 (95% CI, 0.375-0.549) when achieving maximized precision in the AI models. No significant difference was found in recall among subgroup analyses including the algorithms, the number of screened literatures, and the fraction of included literatures. Discussion and Conclusion This systematic review and meta-analysis study showed that the recall is more important than the specificity or precision in literature screening, and a recall over 0.95 should be prioritized. We recommend to report the effectiveness indices of automatic algorithms separately. At the current stage manual literature screening is still indispensable for medical systematic reviews.

Bronchiectasis can cause pulmonary ventilation dysfunction, which will bring huge social and economic burden. Deep learning methods are rarely used in the detection and classification of bronchiectasis. Current studies on bronchiectasis mainly focus on high resolution CT (HRCT), ignoring the more common low-dose CT (LDCT). Methodologically, existing studies do not use an authoritative standard to classify the severity of bronchiectasis. In effect, the accuracy of detection and classification needs to be improved for practical application. According to the above problems, we adopt LDCT data, contrast two deep learning models for the detection and classification of bronchiectasis effect, then we use dilated convolution to promote deep learning model for detection and classification of bronchiectasis. Finally, we developed an automatic detection and scoring system for bronchiectasis combining with authoritative scoring standards. According to the experiments that the detection rate of bronchiectasis in LDCT images by our developed bronchiectasis detection and scoring system can reach 91.0

Abstract Purpose: The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay the diagnosis. With the widespread use of Artificial Intelligence, quick identification with simple clinical information and image recognition pointing at craniofacial features might be a useful tool for self-helped screening of OSA. Methods: The subjects suspected of OSA receiving sleep examination and frontal photographing were consecutively recruited. Sixty-eight points were labelled with automated identification. An optimized model with facial features and basic clinical information was established and ten-folds cross-validation was performed. Area under the receiver operating characteristic curve (AUC) was calculated to evaluate the model’s performance using sleep monitoring as the reference standard. Results: A total of 653 subjects (77.2% males, 55.3% OSA) were analyzed. CATBOOST was the most suitable algorithm for OSA classification with a sensitivity, specificity, accuracy and AUC of 0.75, 0.66, 0.71 and 0.76 respectively (P<0.05), which was better than STOP-Bang questionnaire, NoSAS scores and Epworth scale. And its advantage was more robust in the prediction of supine sleep apnea with a sensitivity of 0.94. Witnessed apnea by sleep partner was the most powerful variable and followed by body mass index, neck circumference, facial parameters and hypertension. Conclusion: OSA could be identified by a machine-learning derived model with automatic recognition of facial photo for Chinese adults, which may facilitate screening of suspected subjects in a simple and quick manner by mobile application. Clinical trial registration Chinese Clinical Trial Registry: No. ChiCTR-ROC-17011027 (http://chictr.org.cn.)

Operating room (OR) is one of the most critical units in a hospital. Managing surgical processes in ORs for better utilization of medical resources, safe delivery of surgical cases, improving patient outcome, and reducing cost, is of significant importance. In this paper, a discrete-event simulation model of OR workflow in a Tertiary A hospital in Beijing, China, is developed. The model is validated by comparing with three-month data collected in the hospital. Using this model, the impacts of OR capacity, resource level, design and operation policies are investigated.

(1) Background: The present study aims to evaluate and compare the model performances of different convolutional neural networks (CNNs) used for classifying sagittal skeletal patterns. (2) Methods: A total of 2432 lateral cephalometric radiographs were collected. They were labeled as Class I, Class II, and Class III patterns, according to their ANB angles and Wits values. The radiographs were randomly divided into the training, validation, and test sets in the ratio of 70%:15%:15%. Four different CNNs, namely VGG16, GoogLeNet, ResNet152, and DenseNet161, were trained, and their model performances were compared. (3) Results: The accuracy of the four CNNs was ranked as follows: DenseNet161 > ResNet152 > VGG16 > GoogLeNet. DenseNet161 had the highest accuracy, while GoogLeNet possessed the smallest model size and fastest inference speed. The CNNs showed better capabilities for identifying Class III patterns, followed by Classes II and I. Most of the samples that were misclassified by the CNNs were boundary cases. The activation area confirmed the CNNs without overfitting and indicated that artificial intelligence could recognize the compensatory dental features in the anterior region of the jaws and lips. (4) Conclusions: CNNs can quickly and effectively assist orthodontists in the diagnosis of sagittal skeletal classification patterns.

运动协调障碍是儿童生长发育过程中的一种高发问题,严重影响儿童身心健康并对成年后的远期健康造成多种不良影响.随着人工智能的发展,可利用计算机视觉领域的人体姿态估计和动作识别技术辅助诊断这类疾病,有利于提升医疗普惠程度和医疗效率,对缓解医疗资源不足有着重要意义.报告了儿童运动协调障碍AI诊断系统的研究现状,介绍了儿童运动协调障碍的临床诊断方式,并基于此提出了计算机辅助诊断该类疾病的诊断技术路线,总结了人体姿态估计和动作识别任务的深度学习方法,分析了目前主流使用的人体姿态估计与动作识别任务评估指标与其对应数据集,讨论了其应用于计算机辅助诊断的问题及挑战.

胃癌是全世界癌症死亡的第三大主要原因,胃癌的早期检测会对胃癌患者的后期治疗起到至关重要的作用.随着人工智能的发展,可以利用计算机视觉领域的机器学习模型辅助检测早期胃癌,有研究发现一些计算机辅助诊断模型的筛查率接近甚至高于医生.利用计算机辅助诊断可以及早发现胃癌以减少胃癌患者的后期治疗成本.报告了基于机器学习在胃镜下早期胃癌辅助诊断的研究现状,介绍了胃镜下早期胃癌的临床诊断方式,并基于此提出了计算机辅助诊断该疾病的技术路线,分析了不同诊断技术路线的研究特点,为计算机辅助诊断早期胃癌提供不同的切入点.总结了用于早期胃癌检测的机器学习、深度学习、目标检测模型,讨论了其应用于计算机辅助诊断的问题及挑战.

支气管扩张症是一种常见的慢性呼吸道疾病,严重影响患者的生活质量,带来了沉重的社会经济负担.随着人工智能的发展,可利用计算机视觉领域的目标检测技术辅助诊断这类疾病.报告了支气管扩张症人工智能诊断系统的研究现状,介绍了支气管扩张症的临床诊断方式,并基于此提出了计算机辅助诊断该类疾病的诊断技术路线,总结了CT影像噪声抑制、肺实质提取、肺叶分割的传统和深度学习方法,针对支气管扩张金标准数据集匮乏的问题,从两个方面综述了目标检测应用于计算机辅助诊断的问题及挑战,详细比较了不同算法的特点和适用场景.最后讨论了未来可能的发展趋势.