Antibody drugs targeting SARS-CoV-2: Time for a rethink?

The coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) heavily burdens human health. Multiple neutralizing antibodies (nAbs) have been issued for emergency use or tested for treating infected patients in the clinic. However, SARS-CoV-2 variants of concern (VOC) carrying mutations reduce the effectiveness of nAbs by preventing neutralization. Uncoding the mutation profile and immune evasion mechanism of SARS-CoV-2 can improve the outcome of Ab-mediated therapies. In this review, we first outline the development status of anti-SARS-CoV-2 Ab drugs and provide an overview of SARS-CoV-2 variants and their prevalence. We next focus on the failure causes of anti-SARS-CoV-2 Ab drugs and rethink the design strategy for developing new Ab drugs against COVID-19. This review provides updated information for the development of therapeutic Ab drugs against SARS-CoV-2 variants.

Nomogram-based risk assessment model for left ventricular hypertrophy in patients with essential hypertension: Incorporating clinical characteristics and biomarkers.

Left ventricular hypertrophy (LVH) is a hypertensive heart disease that significantly escalates the risk of clinical cardiovascular events. Its etiology potentially incorporates various clinical attributes such as gender, age, and renal function. From mechanistic perspective, the remodeling process of LVH can trigger increment in certain biomarkers, notably sST2 and NT-proBNP. This multicenter, retrospective study aimed to construct an LVH risk assessment model and identify the risk factors. A total of 417 patients with essential hypertension (EH), including 214 males and 203 females aged 31-80 years, were enrolled in this study; of these, 161 (38.6%) were diagnosed with LVH. Based on variables demonstrating significant disparities between the LVH and Non-LVH groups, three multivariate stepwise logistic regression models were constructed for risk assessment: the "Clinical characteristics" model, the "Biomarkers" model (each based on their respective variables), and the "Clinical characteristics + Biomarkers" model, which amalgamated both sets of variables. The results revealed that the "Clinical characteristics + Biomarkers" model surpassed the baseline models in performance (AUC values of the "Clinical characteristics + Biomarkers" model, the "Biomarkers" model, and the "Clinical characteristics" model were .83, .75, and .74, respectively; P < .0001 for both comparisons). The optimized model suggested that being female (OR: 4.26, P <.001), being overweight (OR: 1.88, p = .02) or obese (OR: 2.36, p = .02), duration of hypertension (OR: 1.04, P = .04), grade III hypertension (OR: 2.12, P < .001), and sST2 (log-transformed, OR: 1.14, P < .001) were risk factors, while eGFR acted as a protective factor (OR: .98, P = .01). These findings suggest that the integration of clinical characteristics and biomarkers can enhance the performance of LVH risk assessment.

A bibliometric analysis of worldwide cancer research using machine learning methods.

With the progress and development of computer technology, applying machine learning methods to cancer research has become an important research field. To analyze the most recent research status and trends, main research topics, topic evolutions, research collaborations, and potential directions of this research field, this study conducts a bibliometric analysis on 6206 research articles worldwide collected from PubMed between 2011 and 2021 concerning cancer research using machine learning methods. Python is used as a tool for bibliometric analysis, Gephi is used for social network analysis, and the Latent Dirichlet Allocation model is used for topic modeling. The trend analysis of articles not only reflects the innovative research at the intersection of machine learning and cancer but also demonstrates its vigorous development and increasing impacts. In terms of journals, Nature Communications is the most influential journal and Scientific Reports is the most prolific one. The United States and Harvard University have contributed the most to cancer research using machine learning methods. As for the research topic, "Support Vector Machine," "classification," and "deep learning" have been the core focuses of the research field. Findings are helpful for scholars and related practitioners to better understand the development status and trends of cancer research using machine learning methods, as well as to have a deeper understanding of research hotspots.

Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources.

With the rapid development of artificial intelligence (AI) technologies, and the large amount of pharmacovigilance-related data stored in an electronic manner, data-driven automatic methods need to be urgently applied to all aspects of pharmacovigilance to assist healthcare professionals. However, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings. Analyzing challenges and solutions for AI-based pharmacovigilance in resource-limited settings can improve pharmacovigilance frameworks and capabilities in these settings. In this review, we summarize the challenges into four categories: establishing a database for an AI-based pharmacovigilance system, lack of human resources, weak AI technology and insufficient government support. This study also discusses possible solutions and future perspectives on AI-based pharmacovigilance in resource-limited settings.

Health Natural Language Processing: Methodology Development and Applications.

With the rapid growth of information technology, the necessity for processing substantial amounts of health data using advanced information technologies is increasing. A large amount of valuable data exists in natural text such as diagnosis text, discharge summaries, online health discussions, and eligibility criteria of clinical trials. Health natural language processing, as an interdisciplinary field of natural language processing and health care, plays a substantial role in a wide scope of both methodology development and applications. This editorial shares the most recent methodology innovations of health natural language processing and applications in the medical domain published in this JMIR Medical Informatics special theme issue entitled "Health Natural Language Processing: Methodology Development and Applications".

Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning.

BACKGROUND: Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. METHODS: An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. RESULTS: Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. CONCLUSIONS: A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Risk Interval of Complete Blood Counts May be Closely Associated with Bone Mineral Density in the Elderly Chinese Population.

BACKGROUND: Accumulating research suggests that hematopoiesis and bone metabolism are interconnected. Several studies have investigated the partial indexes of peripheral blood counts related to bone mineral density (BMD). The aim of this study was to investigate the associations between all of the parameters, especially the risk interval of complete blood counts (CBC) and BMD in a sample of elderly subjects aged >70 years. METHODS: Three hundred and eighty-six subjects aged > 70 years in our hospital were enrolled in a cross-sectional study and underwent BMD measurement along with a CBC test. Patients were divided into two groups: "at least osteopenia" (T-score < -1) and a normal group (T-score ≥ -1). The clinicopathological characteristics, CBC parameters, and BMD were analyzed between the two groups. We performed a supervised discretization (using a conditional inference tree algorithm) to find the risk interval for the continuous variables, especially for CBC parameters, and bootstrap multivariable logistic regression to estimate the odds of CBC parameters associated with BMD. RESULTS: A total of 248 subjects were included in the study and divided into the normal (n = 43) and "at least osteopenia" groups (n = 205). Subjects in the "at least osteopenia" group had varying degrees of decreases in white blood cell (WBC) count, red blood cell (RBC) count, hemoglobin (Hb), mean corpuscular hemoglobin concentration (MCHC), hematocrit (HCT), platelet volume distribution width (PDW) mean platelet volume (MPV), eosinophils, and lymphocytes, and had increases in platelets (PLTs). MCHC, WBC, RBC, PDW, MPV, Hb, and lymphocytes were successfully divided into two (low and high) intervals. Bootstrap logistic regression showed that low levels of body mass index (BMI) [(11.88, 23.53); OR: 4.07; p < 0.0001], lymphocytes [(0.54, 2.3); OR: 3.95; p < 0.0001] and PDW [(8.5, 12.7); OR: 2.44; p < 0.0001] along with being female and older age [(72, 97); OR: 2.16; p < 0.0001] were significantly associated with BMD as risk factors. CONCLUSIONS: The elderly with BMD loss tended to show an abnormal sign in the CBC test. Low levels of lymphocytes and PDW may contribute to the evaluation of osteoporosis risk in the elderly. Bone remodeling and hematopoiesis may have stronger associations and interactions than has been previously recognized.

The comparison of extraction methods of ganjiang decoction based on fingerprint, quantitative analysis and pharmacodynamics.

BACKGROUND: Ulcerative colitis (UC) is a chronic nonspecific inflammatory disease of the colon and rectum with unknown etiology, and its symptoms include bloody diarrhea, abdominal pain, and hematochezia. Traditional Chinese medicine compound has a good therapeutic, multi-target effect on UC. Ganjiang decoction (GD), which is a traditional classic prescription in China, contains Zingiberis Rhizoma, Angelicae Sinensis Radix, Coptidis Rhizoma, Phellodendri Chinensis Cortex, Sanguisorbae Radix, Granati Pericarpium, and Asini Corii Colla and could be used to treat symptoms of UC. This study aimed to conduct a preliminary study before GD colon-targeted preparation, to explore the relationship between extraction method and efficacy of GD. METHODS: High-performance liquid chromatography (HPLC) was used for the fingerprinting of five preparation methods of GD. HPLC and gas chromatography were used to quantitatively analyze the important chemical components of GD and compare their differences. Mice with UC induced by dextran sulphate sodium salt received the extracts from the five preparation methods of GD via gavage. Disease activity index (DAI) score, colonic length, relative weight of spleen, pathological analysis results, inflammatory factors, therapeutic effect of the five preparation methods of GD, and their relationship with extraction process were compared. RESULTS: Cluster analysis revealed that the content of the components extracted by traditional extraction methods was significantly different from the other four methods. The third and fifth preparation methods extracted Coptidis Rhizoma and Phellodendri Chinensis Cortex with 50% ethanol to obtain more alkaloids. In the fourth and fifth methods, more volatile oils were detected by adding Zingiberis Rhizoma and Angelicae Sinensis Radix fine powder. According to DAI score, colonic length, relative weight of spleen, pathological analysis results, and inflammatory factors, the third method showed a good therapeutic effect, while the fifth method had the best therapeutic effect. CONCLUSIONS: The results showed that the difference of the five extracts of GD in the efficacy of DSS-induced UC in mice was closely related to the extraction method. Our study improved the extraction process of GD and provided a foundation for the process of enteric-soluble preparations and a new idea for traditional Chinese medicine compound preparation.