Early risk assessment and prediction model for osteoporosis based on traditional Chinese medicine syndromes.

Objective: To evaluate the risk factors of osteoporosis and establish a risk prediction model based on routine clinical information and traditional Chinese medicine (TCM) syndromes. Methods: Adults aged 30-82 who lived in 12 grass-roots communities or rural towns in Shanghai, Jilin Province, and Jiangsu Province from December 2019 to January 2022 through a multi-stage sampling method were included in this study. The risk factors and risk prediction of osteoporosis in women and men were explored and established by univariate analysis and multivariate logistic regression model. ROC curve and Hosmer-Lemeshow goodness-of-fit test were used to evaluate the prediction model. Results: A total of 3000 subjects including 2243 females (75 %) and 757 males (25 %) were included in this study. The logistic prediction model of osteoporosis in women was Logit (P) = -2.946 + 0.960 (age ≥50 years old) + 0.633 (BMI ≥24 kg/m2) - 0.545 (daily exposure to sunlight >30 min) + 0.519 (no intake of dairy products) + 0.827 (coronary heart disease) + 0.383 (lumbar disc herniation) + 0.654 (no intake of calcium tablets and vitamin D) - 0.509 (insomnia) + 0.580 (flushed face and congested eyes) + 1.194 (thready and rapid pulse) + 1.309 (sunken and slow pulse). The logistic prediction model of osteoporosis in men was Logit (P) = -1.152-0.644 (daily exposure to sunlight >30 min) + 0.975 (no intake of calcium tablets and vitamin D) - 0.488 (insomnia). The area under the ROC curve (AUC) of female and male osteoporosis prediction models was 0.743 and 0.679, respectively. The Hosmer-Lemeshow goodness-of-fit test was >0.5. Conclusions: There are some significant differences in risk factors between female and male patients with osteoporosis. The risk of osteoporosis are found to be associated with TCM syndromes, and osteoporosis risk prediction models based on routine clinical information and TCM syndrome is effective.

Zero-Material Cost Production of Soil-Coated Fabrics with Underwater Superoleophobicity for Antifouling Oil/Water Separation.

Soil-coated fabrics were fabricated by scrape-coating of soil slurry onto cotton fabrics. The raw materials, soil, and cotton fabrics were, respectively, obtained from farmland and waste bed sheets, making the method a zero-material cost way to produce superwetting membrane. The superhydrophilic/underwater superoleophobic soil-coated fabrics exhibit high efficiency (>99%), ultra-high flux (~45,000 L m-2 h-1), and excellent antifouling behavior for separating water from various oils driven by gravity. The simple fabrication and superior performance suggest that the soil-coated fabric could be a promising candidate as a filtration membrane for practical applications in industrial oily wastewater and oil spill treatments.

Artificial Intelligence-Based Psoriasis Severity Assessment: Real-world Study and Application.

BACKGROUND: Psoriasis is one of the most frequent inflammatory skin conditions and could be treated via tele-dermatology, provided that the current lack of reliable tools for objective severity assessments is overcome. Psoriasis Area and Severity Index (PASI) has a prominent level of subjectivity and is rarely used in real practice, although it is the most widely accepted metric for measuring psoriasis severity currently. OBJECTIVE: This study aimed to develop an image-artificial intelligence (AI)-based validated system for severity assessment with the explicit intention of facilitating long-term management of patients with psoriasis. METHODS: A deep learning system was trained to estimate the PASI score by using 14,096 images from 2367 patients with psoriasis. We used 1962 patients from January 2015 to April 2021 to train the model and the other 405 patients from May 2021 to July 2021 to validate it. A multiview feature enhancement block was designed to combine vision features from different perspectives to better simulate the visual diagnostic method in clinical practice. A classification header along with a regression header was simultaneously applied to generate PASI scores, and an extra cross-teacher header after these 2 headers was designed to revise their output. The mean average error (MAE) was used as the metric to evaluate the accuracy of the predicted PASI score. By making the model minimize the MAE value, the model becomes closer to the target value. Then, the proposed model was compared with 43 experienced dermatologists. Finally, the proposed model was deployed into an app named SkinTeller on the WeChat platform. RESULTS: The proposed image-AI-based PASI-estimating model outperformed the average performance of 43 experienced dermatologists with a 33.2% performance gain in the overall PASI score. The model achieved the smallest MAE of 2.05 at 3 input images by the ablation experiment. In other words, for the task of psoriasis severity assessment, the severity score predicted by our model was close to the PASI score diagnosed by experienced dermatologists. The SkinTeller app has been used 3369 times for PASI scoring in 1497 patients from 18 hospitals, and its excellent performance was confirmed by a feedback survey of 43 dermatologist users. CONCLUSIONS: An image-AI-based psoriasis severity assessment model has been proposed to automatically calculate PASI scores in an efficient, objective, and accurate manner. The SkinTeller app may be a promising alternative for dermatologists' accurate assessment in the real world and chronic disease self-management in patients with psoriasis.

Comparative analysis of instantaneous wave-free ratio and quantitative real-time myocardial contrast echocardiography for the assessment of myocardial perfusion.

Background and hypothesis: The field of coronary artery physiology is developing rapidly and changing the practice of interventional cardiology. A new functional evaluation technique using the instantaneous wave-free ratio (iFR) has become an alternative to fractional flow reserve. Future research studies need to determine whether physiological indicators play a role in evaluating myocardial perfusion in the catheter room. Materials and methods: Thirty-eight patients scheduled for coronary angiography and iFR evaluation underwent a real-time myocardial contrast echocardiography (RT-MCE) examination at rest. The myocardial perfusion parameters (A, ß, and A × ß) on the myocardial perfusion curve were quantitatively analyzed using Q-Lab software. Coronary angiography and iFR assessment were completed within 1 week after the RT-MCE examination in all patients. Correlation analysis was used to identify iFR- and MCE-related indicators. The sensitivity and specificity of iFR in the quantitative detection of coronary microcirculation were obtained. Results: The correlation coefficients between iFR and A, ß, and A × ß were 0.81, 0.66, and 0.82, respectively. The cut-off value for iFR was 0.85 for microvascular ischemia detection, while the sensitivity and specificity for the diagnosis of myocardial perfusion were 90.7 and 89.9%, respectively. The receiver operating characteristic (ROC) curve area for iFR was 0.946 in the segments related to myocardial blood flow. Conclusion: The iFR is an effective tool for detecting myocardial microcirculation perfusion, with satisfactory diagnostic performance and a demonstrated role in physiological indices used for the perfusion assessment.

Dilemma and Solution of Copyright Justice System for Health Short Video under Network Big Data Environment Monitoring.

Short videos have quickly taken over the mobile screens of network users and established themselves as one of the most significant social platforms in the "Internet+era" as a new carrier of social culture. Short films have the qualities of high participation, strong engagement, high real-time, and quick propagation, which satisfy the needs of Internet users in interpersonal communication and reading or enjoyment in leisure time. This is against the backdrop of network big data environment monitoring. Based on this, the paper defines the fair use system of short video copyright, elaborates on its concept, examines the system's challenges and potential fixes in the context of networks, and develops a model for short video repeat detection using local key points. According to the experimental findings, this algorithm's short video repetition detection accuracy rate can reach 95.8%, and its recall rate can reach 94.5%. For the development of the fair use system of short video copyright in the current network environment, the video in some complex scenes can achieve good detection performance, which establishes a good data analysis foundation and provides a significant amount of assistance for the system to escape its predicament.

A Deep Learning-Based Method for Automatic Assessment of Stomatal Index in Wheat Microscopic Images of Leaf Epidermis.

The stomatal index of the leaf is the ratio of the number of stomata to the total number of stomata and epidermal cells. Comparing with the stomatal density, the stomatal index is relatively constant in environmental conditions and the age of the leaf and, therefore, of diagnostic characteristics for a given genotype or species. Traditional assessment methods involve manual counting of the number of stomata and epidermal cells in microphotographs, which is labor-intensive and time-consuming. Although several automatic measurement algorithms of stomatal density have been proposed, no stomatal index pipelines are currently available. The main aim of this research is to develop an automated stomatal index measurement pipeline. The proposed method employed Faster regions with convolutional neural networks (R-CNN) and U-Net and image-processing techniques to count stomata and epidermal cells, and subsequently calculate the stomatal index. To improve the labeling speed, a semi-automatic strategy was employed for epidermal cell annotation in each micrograph. Benchmarking the pipeline on 1,000 microscopic images of leaf epidermis in the wheat dataset (Triticum aestivum L.), the average counting accuracies of 98.03 and 95.03% for stomata and epidermal cells, respectively, and the final measurement accuracy of the stomatal index of 95.35% was achieved. R 2 values between automatic and manual measurement of stomata, epidermal cells, and stomatal index were 0.995, 0.983, and 0.895, respectively. The average running time (ART) for the entire pipeline could be as short as 0.32 s per microphotograph. The proposed pipeline also achieved a good transferability on the other families of the plant using transfer learning, with the mean counting accuracies of 94.36 and 91.13% for stomata and epidermal cells and the stomatal index accuracy of 89.38% in seven families of the plant. The pipeline is an automatic, rapid, and accurate tool for the stomatal index measurement, enabling high-throughput phenotyping, and facilitating further understanding of the stomatal and epidermal development for the plant physiology community. To the best of our knowledge, this is the first deep learning-based microphotograph analysis pipeline for stomatal index assessment.

Real-time burn depth assessment using artificial networks: a large-scale, multicentre study.

INTRODUCTION: Early judgment of the depth of burns is very important for the accurate formulation of treatment plans. In medical imaging the application of Artificial Intelligence has the potential for serving as a very experienced assistant to improve early clinical diagnosis. Due to lack of large volume of a particular feature, there has been almost no progress in burn field. METHODS: 484 early wound images are collected on patients who discharged home after a burn injury in 48 h, from five different levels of hospitals in Hunan Province China. According to actual healing time, all images are manually annotated by five professional burn surgeons and divided into three sets which are shallow(0-10 days), moderate(11-20 days) and deep(more than 21 days or skin graft healing). These ROIs were further divided into 5637 patches sizes 224 × 224 pixels, of which 1733 shallow, 1804 moderate, and 2100 deep. We used transfer learning suing a Pre-trained ResNet50 model and the ratio of all images is 7:1.5:1.5 for training:validation:test. RESULTS: A novel artificial burn depth recognition model based on convolutional neural network was established and the diagnostic accuracy of the three types of burns is about 80%. DISCUSSION: The actual healing time can be used to deduce the depth of burn involvement. The artificial burn depth recognition model can accurately infer healing time and burn depth of the patient, which is expected to be used for auxiliary diagnosis improvement.

Assessing the Risk for Development of Deep Vein Thrombosis among Chinese Patients using the 2010 Caprini Risk Assessment Model: A Prospective Multicenter Study.

AIM: We sought to validate the 2010 Caprini risk assessment model (RAM) in risk stratification for deep vein thrombosis (DVT) prophylaxis among Chinese bedridden patients. METHODS: We performed a prospective study in 25 hospitals in China over 9 months. Patients were risk-stratified using the 2010 Caprini RAM. RESULTS: We included a total 24,524 patients. Fresh DVT was found in 221 patients, with overall incidence of DVT 0.9%. We found a correlation of DVT incidence with Caprini score according to risk stratification (χ2 =196.308, P＜0.001). Patients in the low-risk and moderate-risk groups had DVT incidence ＜0.5%. More than half of patients with DVT were in the highest risk group. Compared with the low-risk group, risk was 2.10-fold greater in the moderate-risk group, 3.34-fold greater in the high-risk group, and 16.12-fold greater in the highest-risk group with Caprini scores ≥ 9. The area under the receiver operating characteristic curve was 0.74 (95% confidence interval, 0.71-0.78; P＜0.01) for all patients. A Caprini score of ≥ 5 points was considered the criterion of a reliably increased risk of DVT in surgical patients with standard thromboprophylaxis. Predicting DVT using a cumulative risk score ≥ 4 is recommended for nonsurgical patients. CONCLUSIONS: Our study suggested that the 2010 Caprini RAM can be effectively used to stratify hospitalized Chinese patients into DVT risk categories, based on individual risk factors. Classification of the highest risk levels using a cumulative risk score ≥ 4 and ≥ 5 provides significantly greater clinical information in nonsurgical and surgical patients, respectively.

Recovery Degree of the Natural Flow Regimes and the Corresponding Economic Costs for Reservoir Operation in Fish Spawning Seasons.

The construction of large-scale reservoirs alters the natural flow process downstream and inevitably affects the aquatic organism. Current studies have verified that flow regimes play an important role in fish spawning stimulus. Recovery of the flow regimes may be incompatible with the economic benefit, mainly referring to hydropower generation. In this study, multiple models are established to study the relationship between the recovery degree of the natural flow regimes and the cost of the hydropower generation in spawning season for different hydrological years. The flow regimes are first quantitatively described by three characteristic parameters including the number of floods, the average duration of each flood, and the daily increment of the natural flow. The model for ecological operation needs to approach these characteristics as close as possible, while the model for economic benefit is set to generate power as much as possible. The ecological flow constraint is also considered to shape the flow process pattern. The proposed methodology is applied on the upper reaches of the Yellow River, where a large-scale reservoir is under planning. Different schemes are compared for different hydrological years to answer the question that to what extent can we recover the flow regime by reservoir operation, and how much the corresponding economic cost is.

[Spatial Distribution and Risk Assessment of Heavy Metal Contamination in Surface Farmland Soil Around a Lead and Zinc Smelter].

Surface farmland soil samples were collected from 135 different sites in a 64 km2 area around a lead and zinc smelter in Jiaozuo City, China. The concentration of the selected heavy metals (Cu, Zn, Pb, Cr, Cd, Ni, V, and Co) was analyzed and the spatial distribution of these heavy metals in the farmland was determined using the kriging interpolation technique (ArcGis 10.1). The enrichment factor, potential ecological risk model, and potential health risk model were used to assess the contamination level and potential risk of heavy metals in farmland surface soil. The results show that the average contents of Cd, Pb, Cr, and Zn in farmland soil are higher than the background content of these metals in the Henan Province and the average content of Cd is 2.8 times higher than that of class Ⅱ of the environmental quality standard for soils in China (GB 15618-1995). The heavy metal contamination in the west of the study area is higher than that in the east and the soil around the lead and zinc smelter (within 3 km) is severely contaminated with Pb and Cd, which is consistent with the location of the industries causing the pollution. The enrichment factors show that the soil is severely contaminated with Cd; partial sampling points are seriously contaminated with Pb, Cu, and Zn; the Cr and Co pollution is small; and Ni and V are almost not affected by human activities. The results of the risk assessment indicate that Cd poses serious ecological and health risks, Pb and Cu pose serious ecological risks, and Cr poses a serious cancer risk.

A "building block" approach to the new influenza A virus entry inhibitors with reduced cellular toxicities.

Influenza A virus (IAV) is a severe worldwide threat to public health and economic development that results in the emergence of drug-resistant or highly virulent strains. Therefore, it is imperative to develop potent anti-IAV drugs with different modes of action to currently available drugs. Herein, we show a new class of antiviral peptides generated by conjugating two known short antiviral peptides: part-1 (named Jp with the sequence of ARLPR) and part-2 (named Hp with the sequence of KKWK). The new peptides were thus created by hybridization of these two domains at C- and N- termini, respectively. The anti-IAV screening results identified that C20-Jp-Hp was the most potent peptide with IC50 value of 0.53 µM against A/Puerto Rico/8/34 (H1N1) strain. Interestingly, these new peptides display lower toxicities toward mammalian cells and higher therapeutic indices than their prototypes. In addition, the mechanism of action of C20-Jp-Hp was extensively investigated.