Health Care Science最新文献

Automated labelling of radiology reports using natural language processing allows for the labelling of ground truth for large datasets of radiological studies that are required for training of computer vision models. This paper explains the necessary data preprocessing steps, reviews the main methods for automated labelling and compares their performance. There are four main methods of automated labelling, namely: (1) rules-based text-matching algorithms, (2) conventional machine learning models, (3) neural network models and (4) Bidirectional Encoder Representations from Transformers (BERT) models. Rules-based labellers perform a brute force search against manually curated keywords and are able to achieve high F1 scores. However, they require proper handling of negative words. Machine learning models require preprocessing that involves tokenization and vectorization of text into numerical vectors. Multilabel classification approaches are required in labelling radiology reports and conventional models can achieve good performance if they have large enough training sets. Deep learning models make use of connected neural networks, often a long short-term memory network, and are similarly able to achieve good performance if trained on a large data set. BERT is a transformer-based model that utilizes attention. Pretrained BERT models only require fine-tuning with small data sets. In particular, domain-specific BERT models can achieve superior performance compared with the other methods for automated labelling.

Langya Henipavirus (LayV) is a zoonotic virus that has recently re-emerged in Eastern China. There is limited data available on the global prevalence, mortality, and morbidity of LayV. The majority of cases have been reported in two provinces in China (Shandong and Henan). Between 2018 and 2022, 35 individuals were diagnosed with the LayV infection in these regions. This novel ribonucleic acid virus attacks animals (including goats, dogs, and shrews) and can potentially spread to humans. The Henipavirus genus is a Paramyxoviridae family member that can be spread through animal-human contact with no established human-to-human transmission yet [1].

There are several disease spectra associated with LayV, including fever, fatigue, nausea, vomiting, cough, and headache. Furthermore, 34% of patients had elevated liver function tests, and 8% had impaired kidney function [2]. Henipaviruses are biosafety level 4 microbes that have the potential to sicken both humans and animals severely [1]. One of its species, the Nipah virus, can cause serious infection in the presence of acute respiratory infection and fatal encephalitis, with a case fatality rate ranging from 40% to 75% [3].

Currently, Henipavirus is not treatable with medications or protected against by vaccinations; thus, the treatment for human infection is mainly supportive, like other viruses including during the current COVID-19 pandemic. The need of raising public understanding of many elements of emerging viruses cannot be overstated, for scientists to continue to monitor the emergence of zoonotic diseases, and to practice rigorous personal hygiene due to a potentially lethal consequence of the virus spread [4].

With any emerging virus, it is important to have full genome detection, determine the mode and risk of transmission, and study possible therapeutics and preventive therapies for regional preparedness. LayV is a newly discovered member of the Henipavirus family, which also includes Nipah and Hendra viruses. It is important to consider the potential challenges that Henipaviruses, including LayV, may pose to the global healthcare system [1]. Some potential challenges include limited diagnostic and surveillance tools, high fatality rates, zoonotic transmission, potential for person-to-person transmission, and lack of awareness and preparedness among healthcare providers and public health officials.

The incidence of zoonotic viral infections in South Asia is multifaceted and versatile: diseases that are old, emergent, re-emerging, and those that have just been found. They all coexist and interplay in unique ways that we are still learning more about. South Asia is frequently believed to be a crucial hotspot for zoonotic spread to humans. Human behavior, large human and animal demographic density, intense animal-human interaction, multiple live animal marketplaces, urbanization, deforesta

At the end of 2019, He Jiankui was sentenced to 3 years in prison for “illegal medical practices”. The Ministry of Science and Technology and the National Health Commission of P.R. China have banned him from engaging in any work related to reproductive science such as in vitro fertilization, and prohibited him from conducting further research in genetic editing.

On November 24, 2022, He Jiankui announced on his personal Weibo account for the establishment of the He Jiankui Laboratory in Beijing's Daxing district, and extensively promoted his rare disease research plan through social media and the press, calling it a “new starting point, a new journey”.

On February 13, 2023, Nature News reported that He Jiankui participated in an online exchange event organized by the University of Kent in the United Kingdom, focusing on life ethics regulation. Many scholars were disappointed with his speech, which they believed was “a publicity stunt” that only “left the impression of a salesperson” [1]. Similar disappointment and criticism were expressed by the Chinese academic community toward He Jiankui's speech.

On March 2, 2023, a Conference on “Challenges and Responses to Ethical Governance of Science and Technology” was held in Beijing. The Conference was organized jointly by Center for Ethics and Morality, People's University of China, Beijing Institute of Stem Cell and Regenerative Medicine, and Center for Bioethics, Chinese Academy of Medical Sciences/Peking Union Medical College. Over 200 scholars from all over the country attended the conference.

Xiaomei Zhai: Conceptualization (lead); resources (lead); writing—original draft (lead).

The author declares no conflict of interest.

The author has nothing to report. No patient was involved in the present study.

Not applicable.

To further improve the diagnosis and treatment of COVID-19, the National Health Commission of People's Republic of China and the National Administration of Traditional Chinese Medicine convened a group of experts to revise the relevant content of the Diagnosis and Treatment Protocol for COVID-19 Patients (Trial Version 9) and developed the Diagnosis and Treatment Protocol for COVID-19 Patients (Trial Version 10), summarizing the etiological characteristics, epidemiological characteristics, prevention, clinical features, diagnosis, clinical classification, population with high risk of severe/critical illnesses, early warning predictors for severe/critical illnesses, differential diagnosis, case identification and reporting, treatment, nursing, control of nosocomial infection in medical institutions, and discharge criteria for inpatients.

Electrocardiography (ECG) abnormalities are evaluated through several automatic detection methods. Primarily, real-world ECG data are digital signals those are stored in the form of images in hospitals. Also, the existing automated detection technique eliminates the cardiac pattern that is abnormal and it is difficult to multiple abnormalities at some instances. To address those issues in this paper conventional ECG image automated techniques CardioLabelNet model is proposed. The proposed model incorporates two stages for image abnormality detection. At first fuzzy membership is performed in the image for computation of uncertainty. In second stage, classification is performed for computation of abnormal activity. The proposed CardioLabelNet collect ECG image data set for the uncertainty estimation while taking the account of various image classes which includes the global and local entropy of image pixels. For each waveform, uncertainties are calculated on the basis of global entropy. The computation of uncertainty in the images is performed with the fuzzy membership function. The spatial likelihood estimation of a fuzzy weighted membership function is used to calculate local entropy. Upon completion of fuzzification, classification is performed for the detection of normal and abnormal patterns in the ECG signal images. Through integration of stacked architecture model classification is performed for ECG images. The proffered algorithm performance is calculated in terms of accuracy for segmentation, Dice similarity coefficient, and partition entropy. Additionally, classification parameters accuracy sensitivity, specificity, and AUC are evaluated. The proposed approach outperforms the existing methodology, according to the results of a comparative analysis.