Purpose: Predictively diagnosing infectious diseases helps in providing better treatment and enhances the prevention and control of such diseases. This study uses actual data from a hospital. A multiple infectious disease diagnostic model (MIDDM) is designed for conducting multi-classification of infectious diseases so as to assist in clinical infectious-disease decision-making. Methods: Based on actual hospital medical records of infectious diseases from December 2012 to December 2020, a deep learning model for multi-classification research on infectious diseases is constructed. The data includes 20,620 cases covering seven types of infectious diseases, including outpatients and inpatients, of which training data accounted for 80%, i.e., 16,496 cases, and test data accounted for 20%, i.e., 4124 cases. Through the auto-encoder, data normalization and sparse data densification processing are carried out to improve the model training effect. A residual network and attention mechanism are introduced into the MIDDM model to improve the performance of the model. Result: MIDDM achieved improved prediction results in diagnosing seven kinds of infectious diseases. In the case of similar disease diagnosis characteristics and similar interference factors, the prediction accuracy of disease classification with more sample data is significantly higher than the prediction accuracy of disease classification with fewer sample data. For instance, the training data for viral hepatitis, influenza, and hand foot and mouth disease were 2954, 3924, and 3015 respectively and the corresponding test accuracy rates were 99.86%, 98.47%, and 97.31%. There is less training data for syphilis, infectious diarrhea, and measles, i.e., 1208, 575, and 190 respectively and the corresponding test accuracy rates were noticeably lower, i.e., 83.03%, 87.30%, and42.11%. We also compared the MIDDM model with the models used in other studies. Using the same input data, taking viral hepatitis as an example, the accuracy of MIDDM is 99.44%, which is significantly higher than that of XGBoost (96.19%), Decision tree (90.13%), Bayesian method (85.19%), and logistic regression (91.26%). Other diseases were also significantly better predicted by MIDDM than by these three models. Conclusion: The application of the MIDDM model to multi-class diagnosis and prediction of infectious diseases can improve the accuracy of infectious-disease diagnosis. However, these results need to be further confirmed via clinical randomized controlled trials.

Background: Modernizing medical education by using artificial intelligence and other new technologies to improve the clinical thinking ability of medical students is an important research topic in recent years. Prominent medical universities are actively conducting research and exploration in this area. In particular, given the shortage of human resources, the need to maintain social distancing to prevent the spread of the epidemics, and the increase in the cost of medical education, it is critical to harness online learning to promote medical education. A virtual case learning system that uses natural language processing technology to process and present a hospital’s real medical records and evaluate student responses can effectively improve medical students’ clinical thinking abilities. Objective: The purpose of this study is to develop a virtual case system, AIteach, based on actual complete hospital medical records and natural language processing technology, and achieve clinical thinking ability improvement through a contactless, self-service, trial-and-error system application. Methods: Case extraction is performed on a hospital’s case data center and the best-matching cases are produced through natural language processing, word segmentation, synonym conversion, and sorting. A standard clinical questioning data module, virtual case data module, and student learning difficulty module are established to achieve simulation. Students can view the objective examination and inspection data of actual cases, including details of the consultation and physical examination, and automatically provide their learning response via a multi-dimensional evaluation system. In order to assess the changes in students’ clinical thinking after using AIteach, 15 medical graduate students were subjected to two simulation tests before and after learning through the virtual case system. The tests, which included the full-process case examination of cases having the same difficulty level, examined core clinical thinking test points such as consultation, physical examination, and disposal, and generated multi-dimensional evaluation indicators (rigor, logic, system, agility, and knowledge expansion). Thus, a complete and credible evaluation system is developed. Results: The AIteach system used an internal and external double-cycle learning model. Students collect case information through online inquiries, physical examinations, and other means, analyze the information for feedback verification, and generate their detailed multi-dimensional clinical thinking after learning. The feedback report can be evaluated and its knowledge gaps analyzed. Such learning based on real cases is in line with traditional methods of disease diagnosis and treatment, and addresses the practical difficulties in reflecting actual disease progression while keeping pace with recent research. Test results regarding short-term learning showed that the average score (P < 0.01) increased from 69.87 to 85.6, the five indicators of clinical thinking evaluation improved, and there was obvious logical improvement, reaching 47%. Conclusion: By combining real cases and natural language processing technology, AIteach can provide medical students (including undergraduates and postgraduates) with an online learning tool for clinical thinking training. Virtual case learning helps students to cultivate clinical thinking abilities even in the absence of clinical tutor, such as during pandemics or natural disasters.

The 2022 Winter Olympics were held in the three competition zones of Beijing, Yanqing and Zhangjiakou, China. The venues of this Winter Olympics were scattered and the terrain was complex. Moreover, the medical resources of Hebei and Beijing were relatively unbalanced. In the medical security of major events, the connection between first aid and in-hospital processes is of the utmost importance to rescue quality. 5th generation mobile network (5G) applications in medical scenarios are on the rise. It would be of great relevance to fully use 5G’s low-latency and high-speed features to share the process information of patients, ambulance personnel, and the destination hospital’s rescue team at emergency scenes and in transportation, improving rescue efficiency. This paper proposes a system scheme of cross-institutional emergency health information sharing based on 5G and augmented reality wearable devices. It also integrates the construction method of monitoring and other sign data sharing, in addition to testing the proposed scheme’s service quality in 5G environments. In the deployment area of the 5G emergency medical rescue information sharing scheme for the Beijing Winter Olympic Games, we selected two designated medical support institutions for testing. The test adopted a combination of fixed-point and driving tests to experiment on the service data, voice service, and streaming media indicators. The 5G signal's coverage rate was close to 100%, the standalone connection's success rate was 100%, and the drop rate was 0. The average downlink rate of multiple scenarios was 620mbps, and the average uplink rate of 5G was over 71.8mbps, which is higher than the average 5G level in China. The downlink rate was more than 20 times larger than the 4th generation mobile network (4G) rate. This study’s proposed scheme demonstrates the importance of 5G applications in emergency response and support, in addition to providing a suitable scheme for the integration of 5G networks in the medical scene.

Background: Asthma is the world’s second most prevalent chronic respiratory disease. Current clinical decisions regarding hospitalization for adult asthma patients in emergency departments (EDs) primarily rely on presenting clinical status, acute exacerbation severity, therapeutic response and high-risk factors. Assessing the need for hospitalization of patients with complex comorbidities remains a significant challenge. Research Question: This study aims to develop models that integrate various environmental and clinical factors to predict the hospitalization of adult asthma patients in EDs and to interpret these models. Study Design and Methods: A retrospective analysis was conducted utilizing data from asthma patients at a single ED from 2016 to 2023; the data included demographics, vital signs, illness severity, laboratory test results, and comorbidities, along with environmental variables. Predictive models were constructed using the extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), support vector machine (SVM), logistic regression (LR), and random forest (RF). Area under the receiver operating characteristic curve (AUC), accuracy, and F1 score were the primary metrics used to assess model performance. Results: The analysis included 1140 ED visits. The median age was 51.0 years (interquartile range: 31.0 to 67.0 years), and 56.5% of the patients (644) were female. Overall, 21.8% of patients (249) required hospitalization after their ED visits. The AUC results for predicting hospitalization without external environmental factors were 0.8075 for XGBoost, 0.8233 for LightGBM, 0.7935 for SVM, 0.8033 for LR, and 0.8272 for RF. After integrating ambient air pollutant and meteorological features, the RF model consistently outperformed the other models, achieving an AUC of 0.8555. The most critical parameters for predicting hospitalization were found to be illness severity, oxygen saturation, age, and heart rate. Interpretation: Machine learning (ML) models based on clinical, meteorological, and air pollution data can rapidly and accurately predict hospitalization of adult asthma patients in EDs.

To improve the hospital's ability to proactively detect infectious diseases, a knowledge-based infectious disease monitoring and decision support system was established based on real medical records and knowledge rules. The effectiveness of the system was evaluated using interrupted time series analysis. In the system, a monitoring and alert rule library for infectious diseases was generated by combining infectious disease diagnosis guidelines with literature and a real medical record knowledge map. The system was integrated with the electronic medical record system, and doctors were provided with various types of real-time warning prompts when writing medical records. The effectiveness of the system's alerts was analyzed from the perspectives of false positive rates, rule accuracy, alert effectiveness, and missed case rates using interrupted time series analysis. Over a period of 12 months, the system analyzed 4,497,091 medical records, triggering a total of 12,027 monitoring alerts. Of these, 98.43% were clinically effective, while 1.56% were invalid alerts, mainly owing to the relatively rough rules generated by the guidelines leading to several false alarms. In addition, the effectiveness of the system's alerts, distribution of diagnosis times, and reporting efficiency of doctors were analyzed. 89.26% of infectious disease cases could be confirmed and reported by doctors within 5 min of receiving the alert, and 77.6% of doctors could complete the filling of 33 items of information within 2 min, which is a reduction in time compared to the past. The timely reminders from the system reduced the rate of missed cases by doctors; the analysis using interrupted time series method showed an average reduction of 4.4037% in the missed-case rate. This study proposed a knowledge-based infectious disease decision support system based on real medical records and knowledge rules, and its effectiveness was verified. The system improved the management of infectious diseases, increased the reliability of decision-making, and reduced the rate of underreporting.