Latest Issue
Volume 37 ， Issue 3 ， 2022
-
Abstract：Objective To explore the semi-supervised learning (SSL) algorithm for long-tail endoscopic image classification with limited annotations. Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir, the largest gastrointestinal public dataset with 23 diverse classes. Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling. After splitting the training dataset and the test dataset at a ratio of 4:1, we sampled 20%, 50%, and 100% labeled training data to test the classification with limited annotations. Results The classification performance was evaluated by micro-average and macro-average evaluation metrics, with the Mathews correlation coefficient (MCC) as the overall evaluation. SSL algorithm improved the classification performance, with MCC increasing from 0.8761 to 0.8850, from 0.8983 to 0.8994, and from 0.9075 to 0.9095 with 20%, 50%, and 100% ratio of labeled training data, respectively. With a 20% ratio of labeled training data, SSL improved both the micro-average and macro-average classification performance; while for the ratio of 50% and 100%, SSL improved the micro-average performance but hurt macro-average performance. Through analyzing the confusion matrix and labeling bias in each class, we found that the pseudo-based SSL algorithm exacerbated the classifier’s preference for the head class, resulting in improved performance in the head class and degenerated performance in the tail class. Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification, especially when the labeled data is extremely limited, which may benefit the building of assisted diagnosis systems for low-volume hospitals. However, the pseudo-labeling strategy may amplify the effect of class imbalance, which hurts the classification performance for the tail class.Keywords：endoscopic image;artificial intelligence;semi-supervised learning;long-tail distribution;image classification24|307|0Updated：2024-04-10 -
Abstract：Objective To forecast the future burden and its attributable risk factors of infective endocarditis (IE). Method We analyzed the disease burden of IE and its risk factors from 1990 to 2019 using the Global Burden of Disease 2019 database and projected the disease burden from 2020 to 2030 using a Bayesian age-period-cohort model. Results By 2030, the incidence of IE will increase uncontrollably on a global scale, with developed countries having the largest number of cases and developing countries experiencing the fastest growth. The affected population will be predominantly males, but the gender gap will narrow. The elderly in high-income countries will bear the greatest burden, with a gradual shift to middle-income countries. The incidence of IE in countries with middle/high-middle social-demographic indicators (SDI) will surpass that of high SDI countries. In China, the incidence rate and the number of IE will reach 18.07 per 100,000 and 451,596 in 2030, respectively. IE-associated deaths and heart failure will continue to impose a significant burden on society, the burden on women will increase and surpass that on men, and the elderly in high-SDI countries will bear the heaviest burden. High systolic blood pressure has become the primary risk factor for IE-related death. Conclusions This study provides comprehensive analyses of the disease burden and risk factors of IE worldwide over the next decade. The IE-associated incidence will increase in the future and the death and heart failure burden will not be appropriately controlled. Gender, age, regional, and country heterogeneity should be taken seriously to facilitate in making effective strategies for lowering the IE disease burden.Keywords：infective endocarditis;disease burden;risk factors;Bayesian age-period-cohort model;projection38|518|0Updated：2024-04-10 -
Abstract：Objective Traditional Chinese medicine (TCM) prescriptions have been used to cure diseases in China for thousands of years, in which many TCM herbs have no definite common quantity. Some key TCM herbs are commonly used and thus deserve in-depth investigations based on a more acceptable classification method. This study analyzes whether TCM prescriptions follow Zipf’s law and attempts to obtain the thresholds of key TCM herbs based on the application of Zipf’s law. Methods A total of 84,418 TCM prescriptions were collected and standardized. We tested whether Zipf’s law and Zipf’s distribution fit the Chinese herb distributions. A linear fitting experiment was performed to verify the relationship between the frequency distribution and frequency of TCM herbs. Results The distribution of TCM herbs in TCM prescriptions conformed to Zipf’s law. Accordingly, the thresholds were obtained for the key TCM herbs. Conclusion The distribution of TCM herbs in TCM prescriptions follows Zipf’s law.Keywords：Zipf’s law;traditional Chinese medicine;prescriptions;herb15|181|0Updated：2024-04-10 -
Abstract：Objective To compare the performance of five machine learning models and SAPS II score in predicting the 30-day mortality amongst patients with sepsis. Methods The sepsis patient-related data were extracted from the MIMIC-IV database. Clinical features were generated and selected by mutual information and grid search. Logistic regression, Random forest, LightGBM, XGBoost, and other machine learning models were constructed to predict the mortality probability. Five measurements including accuracy, precision, recall, F1 score, and area under curve (AUC) were acquired for model evaluation. An external validation was implemented to avoid conclusion bias. Results LightGBM outperformed other methods, achieving the highest AUC (0.900), accuracy (0.808), and precision (0.559). All machine learning models performed better than SAPS II score (AUC=0.748). LightGBM achieved 0.883 in AUC in the external data validation. Conclusions The machine learning models are more effective in predicting the 30-day mortality of patients with sepsis than the traditional SAPS II score.Keywords：MIMIC-IV;sepsis;machine learning;risk prediction59|1248|0Updated：2024-04-10 -
Abstract：Objective To build a prostate cancer (PCa) risk prediction model based on common clinical indicators to provide a theoretical basis for the diagnosis and treatment of PCa and to evaluate the value of artificial intelligence (AI) technology under healthcare data platforms. Methods After preprocessing of the data from Population Health Data Archive, smuothly clipped absolute deviation (SCAD) was used to select features. Random forest (RF), support vector machine (SVM), back propagation neural network (BP), and convolutional neural network (CNN) were used to predict the risk of PCa, among which BP and CNN were used on the enhanced data by SMOTE. The performances of models were compared using area under the curve (AUC) of the receiving operating characteristic curve. After the optimal model was selected, we used the Shiny to develop an online calculator for PCa risk prediction based on predictive indicators. Results Inorganic phosphorus, triglycerides, and calcium were closely related to PCa in addition to the volume of fragmented tissue and free prostate-specific antigen (PSA). Among the four models, RF had the best performance in predicting PCa (accuracy: 96.80%; AUC: 0.975, 95% CI: 0.964-0.986). Followed by BP (accuracy: 85.36%; AUC: 0.892, 95% CI: 0.849-0.934) and SVM (accuracy: 82.67%; AUC: 0.824, 95% CI: 0.805-0.844). CNN performed worse (accuracy: 72.37%; AUC: 0.724, 95% CI: 0.670-0.779). An online platform for PCa risk prediction was developed based on the RF model and the predictive indicators. Conclusions This study revealed the application value of traditional machine learning and deep learning models in disease risk prediction under healthcare data platform, proposed new ideas for PCa risk prediction in patients suspected for PCa and had undergone core needle biopsy. Besides, the online calculation may enhance the practicability of AI prediction technology and facilitate medical diagnosis.Keywords：prostate cancer;random forest;support vector machine;back-propagation neural network;convolutional neural network59|675|0Updated：2024-04-10 -
Abstract：Objective In recent years, many studies have reported that air pollution is a risk factor for type 2 diabetes mellitus (T2DM). The aim of this systematic review and meta-analysis is to summarize the evidence about the association between exposure to air pollution and T2DM in developing countries. Methods The databases, including PubMed, EMBASE and Web of Science, were systematically searched for studies published up to 31 March 2022. Studies about the association between air pollution and T2DM prevalence or incidence in developing countries were included. The odds ratio (OR) was used as effect estimate. We synthesized the included studies in the meta-analysis. Results We included 8 cross-sectional studies and 8 cohort studies, all conducted in developing countries. Meta-analysis of 8 studies on PM2.5 (particulate matter ≤ 2.5 μm in diameter) showed that T2DM prevalence was significantly associated with PM2.5 exposure (OR=1.12; 95% CI: 1.07, 1.17; P<0.001). The association between air pollutants and T2DM incidence was not estimated due to the limited relevant studies. Conclusions The exposure to PM2.5 would be positively associated with an increased prevalence of T2DM in developing countries. Some effective measures should be taken to reduce air pollutant exposure in people who are vulnerable to diabetes.Keywords：Air pollutants;PM2.5;type 2 diabetes mellitus26|588|1Updated：2024-04-10
Scientific Data Sharing and Reuse:Original Article
- Abstract：The past twenty years have seen the increasingly important role of ontology in traditional Chinese medicine (TCM). However, the development of TCM ontology faces many challenges. Since the epistemologies dramatically differ between TCM and contemporary biomedicine, it is hard to apply the existing top-level ontology mechanically. “Data silos” are widely present in the currently available terminology standards, term sets, and ontologies. The formal representation of ontology needs to be further improved in TCM. Therefore, we propose a unified basic semantic framework of TCM based on in-depth theoretical research on the existing top-level ontology and a re-study of important concepts in TCM. Under such a framework, ontologies in TCM sub-domains should be built collaboratively and be represented formally in a common format. Besides, extensive cooperation should be encouraged by establishing ontology research communities to promote ontology peer review and reuse.Keywords：ontology;traditional Chinese medicine;top-level ontology;domain ontology;semantic standard39|491|0Updated：2024-04-10
Scientific Data Sharing and Reuse:Perspective
- Abstract：This data article describes the dataset from a national cross-sectional questionnaire survey on Chinese internal migrants in 2017. The survey was part of the Chinese Migrants Dynamic Survey, which is an annually conducted large-scale national questionnaire survey on internal migrants. The respondents in the described dataset were migrants and registered local residents aged over 15 years old. A multistage stratified probability-proportional-to-size (PPS) sampling method based on the 2016 annual report data of China Migrant Population was adopted. The questionnaire was designed to collect demographic information of respondents and their family members, intention of migration or settlement, health status, health services accessibility, social integration, and epidemic influencing factors of common diseases, including hypertension, type 2 diabetes, diarrhea, fever, rash, icterus, conjunctival redness, cold, and other illnesses or injuries. The sample population in this survey include 13,998 internal migrants and 14,000 registered local residents from eight domestic cities / prefecture / districts across China. It is the most widely covering and highly representative dataset on common diseases and influencing factors of internal migrants in China. The dataset can be used to study common diseases and influencing factors among floating Chinese population. It provides data support for government to improve healthcare accessibility and the equity of public health services for internal migrants in China.Keywords：health services;floating population;population survey;common diseases;influencing factors;China29|253|0Updated：2024-04-10
Scientific Data Sharing and Reuse:Data Article
- Abstract：Focusing on the reform initiatives of Chinese Academy of Medical Sciences (CAMS) & Peking Union Medical College (PUMC) in medical scientific and technological innovation from perspectives of deepening the reform and optimizing the ecosystem of science and technology innovation, this article summarizes the highlights of CAMS & PUMC’s efforts in safeguarding people’s health and promoting the Healthy China 2030 strategy through scientific and technological innovation in the fields including basic research, disease prevention and treatment, and medical technology in the past ten years. These achievements embody the endeavors and responsibility of CAMS & PUMC in realizing self-reliance and self-improvement of Chinese medical science and technology and highlight its contributions to the development of medical science and technology of China.Keywords：Chinese Academy of Medical Sciences;Peking Union Medical College;medical health;scientific and technological innovation;ten years20|200|0Updated：2024-04-10
-
Abstract：Blood loss and blood transfusion requirement are important quality control indicators of cardiovascular surgery and cardiovascular anesthesia. Patient blood management (PBM) is an evidence-based, multidisciplinary approach to optimizing the care of patients who may need transfusion, which encompasses anemia management, hemodilution, cell salvage, hemostatic treatment, and other approaches to reducing bleeding and minimizing blood transfusion. PBM in cardiovascular surgery is a “team sport” that involves cardiac and vascular surgeons, anesthesiologists, perfusionist, intensivists, and other health care providers. The current work provides an overview of evidence and practice of PBM at Fuwai Hospital. Implementation of PBM should also take local resource availability and cost-effectiveness of different devices, drugs, technologies, and techniques into consideration.Keywords：bleeding;blood transfusion;blood management;cardiovascular surgery;anesthesia38|1565|1Updated：2024-04-10
All for People’s Health——Our Decade:Special Reports
- Abstract：Based on the macroanalysis of the unbalanced development of the “demand side” and the “supply side” of clinical medicine in China, this paper elucidates the stakeholders, resources, and ecosystem of the strategic scientific and technological capacity-building and calls for a larger coverage, smoother supply chain, and more sustainable ecosystem to ensure the development of clinical medicine. Furthermore, focusing on the establishment and development of clinical reproductive health in China, the authors introduce the strategic scientific and technological capacity-building of reproductive medicine in Peking University Third Hospital, with an attempt to inform similar efforts in other fields and even the whole clinical medicine in China.Keywords：reproductive medicine;clinical medicine;capacity-building;scientific and technological progress19|174|0Updated：2024-04-10
Think Tank Forum
-
Abstract：Wnt5a is a secreted Wnt ligand that plays a critical role in cellular pathways and inflammatory diseases. The WNT5A gene encodes two protein isoforms, Wnt5a-long and Wnt5a-short, which differ based on different promoter methylation and have distinct functions. However, the mechanisms of the promoter methylation are unclear. Depending on the extent of promoter methylation, Wnt5a exerts both anti-inflammatory and pro-inflammatory effects in inflammatory diseases, which may be involved in different Wnt5a isoforms. Therefore, the Wnt5a isoforms may be potential diagnostic markers for inflammatory diseases and the mechanisms of the WNT5A gene promoter methylation need to be further investigated.Keywords：Wnt5a;inflammatory diseases;promoter methylation69|796|0Updated：2024-04-10 -
Abstract：Myocardial perfusion imaging (MPI) is valuable for the diagnosis, prognosis, and management of coronary artery disease (CAD). The most commonly used pharmacologic stress agents at present are vasodilators and adrenergic agents. However, these agents have contraindications and may cause adverse effects in some patients. Thus, other stress agents feasible for more patients are required. Higenamine (HG) is a β-adrenergic receptor agonist currently approved for clinical trials as a stress agent for myocardial infarction. It also has a promising value in MPI for the detection of CAD in preclinical and clinical studies. This review summarizes the application of HG on MPI, including its mechanism of action, stress protocol, efficacy, and safety.Keywords：coronary artery disease;higenamine;myocardial perfusion imaging;stress agent20|403|0Updated：2024-04-10
Review
-
Abstract：The research and development of penicillin started with difficulty before 1949 and achieved certain results. In 1951, after the founding of the People’s Republic of China, Zhang Weishen, as the only Chinese scientist who had been trained and worked in a penicillin research and development center in the United States for many years, overcame many difficulties and returned to China. In 1953, with the efforts of Zhang Weishen and his colleagues, China realized the industrialized production of penicillin, alleviating the urgent needs of the masses. Antibiotics has also become the first discipline to achieve major scientific and technological achievements after the founding of the New China. In the mid-1950s, the technical breakthrough in the localization of lactose substitutes marked the localization of the raw materials of the penicillin-producing culture medium, which paved the way for the industrialized production of penicillin with Chinese characteristics. Antibiotics have become one of the most widely used and affordable drugs for hundreds of millions of patients in China, and China has since ended the humiliating history of the “Sick Man of East Asia”.Keywords：penicillin;antibiotics;research and development;industrial production;Zhang Weishen37|186|0Updated：2024-04-10
Historical Traces of Medicine
- © 2024 Chinese Academy of Medical Sciences 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0