Quantitative assessment of corneal elasticity distribution after FS-LASIK using optical coherence elastography.

Quantifying corneal elasticity after femtosecond laser-assisted in situ keratomileusis (FS-LASIK) procedure plays an important role in improving surgical safety and quality, since some latent complications may occur ascribing to changes in postoperative corneal biomechanics. Nevertheless, it is suggested that current research has been severely constrained due to the lack of an accurate quantification method to obtain postoperative corneal elasticity distribution. In this paper, an acoustic radiation force optical coherence elastography system combined with the improved phase velocity algorithm was utilized to realize elasticity distribution images of the in vivo rabbit cornea after FS-LASIK under various intraocular pressure levels. As a result, elasticity variations within and between the regions of interest could be identified precisely. This is the first time that elasticity imaging of in vivo cornea after FS-LASIK surgery was demonstrated, and the results suggested that this technology may hold promise in further exploring corneal biomechanical properties after refractive surgery.

The Expression of LDL-R in CD8+ T Cells Serves as an Early Assessment Parameter for the Production of TCR-T Cells.

BACKGROUND/AIM: The quantity and the phenotypes of desired T cell receptor engineered T (TCR-T) cells in the final cell product determine their in vivo anti-tumor efficacy. Optimization of key steps in the TCR-T cell production process, such as T cell activation, has been shown to improve cell quality. MATERIALS AND METHODS: Using a modified TCR (mTCR) derived from mice transducing PBMCs, we assessed the proportions of low-density lipoprotein receptor (LDL-R) and mTCR expressing cells under the various activation conditions of CD3/CD28-Dynabeads or OKT3 via flow cytometry. RESULTS: We demonstrate that the proportion of T cells expressing LDL-R post activation is positively correlated with the percentage of mTCR+CD8+ T cells with their less differentiated subtypes in the final product. In addition, we show that shifting the CD3/CD28-Dynabeads activation duration from a typical 48 h to 24 h can significantly increase the production of the desired mTCR+CD8+ T cells. Importantly, the percentages of TCR-T cells with less-differentiated phenotypes, namely mTCR central memory T cells (TCM), were found to be preserved with markedly higher efficiency when T cell activation was optimized. CONCLUSION: Our findings suggest that the proportion of LDL-R+ T cells may serve as an early assessment parameter for evaluating TCR-T cell quality, possibly facilitating the functional and economical improvement of current adoptive therapy.

Assessment of surface ozone production in Qinghai, China with satellite-constrained VOCs and NOx emissions.

The implementation of the western development strategy of China and the migration of air pollutants from eastern China might lead to a rapid increase in volatile organic compounds (VOCs) concentrations in the Qinghai-Tibet Plateau (QTP) and an amplified role of Nitrogen Oxides (NOx) in ozone (O3) pollution. Qinghai province, situated on the northeast of the QTP, had fewer human activities compared to eastern China, while ozone pollution worsened over the years. To better capture recent emission trends and improve the accuracy of O3 simulation in Qinghai, this study proposed a top-down method, which combined the air quality modeling system RAMS-CMAQ, with formaldehyde (HCHO) and nitrogen dioxide (NO2) columns derived from TROPOMI as the constraints to improve the emission estimates of VOCs and NOx in July 2020, respectively. Through a series of sensitivity experiments, better quantified emission estimates of VOCs and NOx were obtained to be 1.33 and 0.34 Tg/yr, 2.5 and 2.1 times larger than the bottom-up ones. The results demonstrated the effectiveness of the top-down method and satellite observations constraints in improving VOCs and NOx emission estimates, resulting in a reduction in the differences between the observed and modeled HCHO and NO2 columns to 0.7 and 0.2 × 1015 molec/cm2, respectively. As a result, the simulated maximum daily 8-h average (MDA8) O3 concentrations increased from 58.9 to 81.6 µg/m3, which were closer to observations (85.4 µg/m3), the normalized mean bias (NMB) and normalized mean error (NME) values of hourly O3 concentrations changed from -24.7 % to -2.9 % and from 29.9 % to 22.3 %, respectively. This study showed the potential of top-down estimates to aide in the development of emission scenarios, which were critical for accurately simulating the O3 pollution and pollution control policy studies.

How to understand high global food price? Using SHAP to interpret machine learning algorithm.

The global food prices have surged to historical highs, and there is no consensus on the reasons behind this round of price increases in academia. Based on theoretical analysis, this study uses monthly data from January 2000 to May 2022 and machine learning models to examine the root causes of that period's global food price surge and global food security situation. The results show that: Firstly, the increase in the supply of US dollars and the rise in oil prices during pandemic are the two most important variables affecting food prices. The unlimited quantitative easing monetary policy of the US dollar is the primary factor driving the global food price surge, and the alternating impact of oil prices and excessive US dollar liquidity are key features of the surge. Secondly, in the context of the global food shortage, the impact of food production reduction and demand growth expectations on food prices will further increase. Thirdly, attention should be paid to potential agricultural import supply chain risks arising from international uncertainty factors such as the ongoing Russia-Ukraine conflict. The Russian-Ukrainian conflict has profoundly impacted the global agricultural supply chain, and crude oil and fertilizers have gradually become the main driving force behind the rise in food prices.

Risk assessment and stratification of mild cognitive impairment among the Chinese elderly: attention to modifiable risk factors.

BACKGROUND: The early identification of individuals at risk of mild cognitive impairment (MCI) has major public health implications for Alzheimer's disease prevention. OBJECTIVE: This study aims to develop and validate a risk assessment tool for MCI with a focus on modifiable factors and a suggested risk stratification strategy. METHODS: Modifiable risk factors were selected from recent reviews, and risk scores were obtained from the literature or calculated based on the Rothman-Keller model. Simulated data of 10 000 subjects with the exposure rates of the selected factors were generated, and the risk stratifications were determined by the theoretical incidences of MCI. The performance of the tool was verified using cross-sectional and longitudinal datasets from a population-based Chinese elderly cohort. RESULTS: Nine modifiable risk factors (social isolation, less education, hypertension, hyperlipidaemia, diabetes, smoking, drinking, physical inactivity and depression) were selected for the predictive model. The area under the curve (AUC) was 0.71 in the training set and 0.72 in the validation set for the cross-sectional dataset. The AUCs were 0.70 and 0.64 in the training and validation sets, respectively, for the longitudinal dataset. A combined risk score of 0.95 and 1.86 was used as the threshold to categorise MCI risk as 'low', 'moderate' and 'high'. CONCLUSION: A risk assessment tool for MCI with appropriate accuracy was developed in this study, and risk stratification thresholds were also suggested. The tool might have significant public health implications for the primary prevention of MCI in elderly individuals in China.

Impacts of the zero mark-up policy on hospitalization expenses of T2DM and cholecystolithiasis inpatients in SC province, western China: an interrupted time series analysis.

Background: Since 2009, a series of ambitious health system reforms have been launched in China, including the zero mark-up drug policy (ZMDP); the policy was intended to reduce substantial medicine expenses for patients by abolishing the 15% mark-up on drugs. This study aims to evaluate the impacts of ZMDP on medical expenditures from the perspective of disease burden disparities in western China. Method: Two typical diseases including Type 2 diabetes mellitus (T2DM) in internal medicine and cholecystolithiasis (CS) in surgery were selected from medical records in a large tertiary level-A hospital in SC Province. The monthly average medical expenses of patients from May 2015 to August 2018 were extracted to construct an interrupted time series (ITS) model to evaluate the impact of policy implementation on the economic burden. Results: A total of 5,764 cases were enrolled in our study. The medicine expenses for T2DM patients maintained a negative trend both before and after the intervention of ZMDP. It had declined by 74.3 CNY (P < 0.001) per month on average in the pre-policy period and subsequently dropped to 704.4 CNY (P = 0.028) immediately after the policy. The level change of hospitalization expenses was insignificant (P = 0.197), with a reduction of 677.7 CNY after the policy, while the post-policy long-term trend was significantly increased by 97.7 CNY (P = 0.035) per month contrasted with the pre-policy period. In addition, the anesthesia expenses of T2DM patients had a significant increase in the level under the impact of the policy. In comparison, the medicine expenses of CS patients significantly decreased by 1,014.2 CNY (P < 0.001) after the policy, while the total hospitalization expenses had no significant change in level and slope under the influence of ZMDP. Furthermore, the expenses of surgery and anesthesia for CS patients significantly increased by 320.9 CNY and 331.4 CNY immediately after the policy intervention. Conclusion: Our study indicated that the ZMDP has been an effective intervention to reduce the excessive medicine expenses for both researched medical and surgical diseases, but failed to show any long-term advantage. Moreover, the policy has no significant impact on relieving the overall hospitalization burden for either condition.

Clinical expert consensus on the assessment and protection of pancreatic islet ß-cell function in type 2 diabetes mellitus.

Islet ß-cell dysfunction is a basic pathophysiological characteristic of type 2 diabetes mellitus (T2DM). Appropriate assessment of islet ß-cell function is beneficial to better management of T2DM. Protecting islet ß-cell function is vital to delay the progress of type 2 diabetes mellitus. Therefore, the Pancreatic Islet ß-cell Expert Panel of the Chinese Diabetes Society and Endocrinology Society of Jiangsu Medical Association organized experts to draft the "Clinical expert consensus on the assessment and protection of pancreatic islet ß-cell function in type 2 diabetes mellitus." This consensus suggests that ß-cell function can be clinically assessed using blood glucose-based methods or methods that combine blood glucose and endogenous insulin or C-peptide levels. Some measures, including weight loss and early and sustained euglycemia control, could effectively protect islet ß-cell function, and some newly developed drugs, such as Sodium-glucose cotransporter-2 inhibitor and Glucagon-like peptide-1 receptor agonists, could improve islet ß-cell function, independent of glycemic control.

Versatile, facile and low-cost single-cell isolation, culture and sequencing by optical tweezer-assisted pool-screening.

Real-time image-based sorting of target cells in a precisely indexed manner is desirable for sequencing or cultivating individual human or microbial cells directly from clinical or environmental samples; however, the versatility of existing methods is limited as they are usually not broadly applicable to all cell sizes. Here, an optical tweezer-assisted pool-screening and single-cell isolation (OPSI) system is established for precise, indexed isolation of individual bacterial, yeast or human-cancer cells. A controllable static flow field that acts as a cell pool is achieved in a microfluidics chip, to enable precise and ready screening of cells of 1 to 40 µm in size by bright-field, fluorescence, or Raman imaging. The target cell is then captured by a 1064 nm optical tweezer and deposited as one-cell-harboring nanoliter microdroplets in a one-cell-one-tube manner. For bacterial, yeast and human cells, OPSI achieves a >99.7% target-cell sorting purity and a 10-fold elevated speed of 10-20 cells per min. Moreover, OPSI-based one-cell RNA-seq of human cancer cells yields high quality and reproducible single-cell transcriptome profiles. The versatility, facileness, flexibility, modularized design, and low cost of OPSI suggest its broad applications for image-based sorting of target cells.

Business Model Innovation Paths of Manufacturing Oriented towards Green Development in Digital Economy.

China's manufacturing industry has been confronted with the issue of extensive development with high input, high consumption, and high emissions for a long time, and its green development is the key to reaching carbon neutrality in China. Under the digital economy, business model innovation is the fundamental means of the green development of manufacturing enterprises. Four representative listed companies in China's manufacturing were selected as typical cases for the case study. Through open, axial, and selective coding that is based on proceduralized grounded theory, this study profoundly explores business model innovation paths of the manufacturing industry oriented towards green development in the digital economy following the research logic of "green development orientation-business model innovation process-business model innovation result". Moreover, this study further compares the differences among paths and discusses each path's effectiveness and applicable conditions. Results show that: (1) Four green business model innovation paths are revealed based on the four green development orientations: efficiency-oriented path, value-oriented path, user-oriented path, and ecology-oriented path. (2) Different enterprises pursue distinct business model innovation paths. The scientific premise for enterprises to opt for the optimal innovation path is the matching of upgrading demands, existing conditions, and path characteristics. Ultimately, the following policy implications are offered: First, promote the green innovation of business models in the manufacturing industry. Second, consider enterprises' heterogeneity and implement differentiated support policies. This study can serve as theoretical support and decision-making reference for business model innovation and green development in manufacturing enterprises.

Efficacy, safety, and cost-effectiveness analysis of aflibercept in metastatic colorectal cancer: A rapid health technology assessment.

Background: Metastatic colorectal cancer (mCRC) imposes a heavy tumor burden worldwide due to limited availability of therapeutic drugs. Aflibercept, a kind of recombinant protein of the anti-vascular endothelial growth factor (VEGF) family, has been approved in clinical application among mCRC patients since 2012. A comprehensive analysis of the efficacy, safety, and cost-effectiveness of aflibercept in mCRC treatment is necessary. Objective: To evaluate the efficacy, safety, and cost-effectiveness of aflibercept for the treatment of mCRC in order to provide a decision-making reference for the selection of targeted drugs for second-line treatment of mCRC in Hong Kong, Macao, and Taiwan regions of China and the selection of new drugs for medical institutions in these regions. Methods: A systematic retrieve on databases including PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang, and Weipu, as well as relevant websites and databases of health technology assessment including the National Institute of Health and Clinical Optimization, Centre for Evaluation and Communication at the University of York, and the Canadian Agency for Medicines and Health Technology, was conducted. The literature was screened according to the inclusion and exclusion criteria, and data were extracted and analyzed by two authors, while the quality of the literature was assessed. Results: Finally, we included two HTA reports, 11 systematic reviews/meta-analyses, and two cost-effectiveness studies in the rapid health technology assessment. For mCRC patients receiving second-line treatment, aflibercept combined with FOLFIRI significantly increased progression-free survival (PFS) and overall survival (OS) and the objective response rate (ORR) also improved, compared with folinic acid + fluorouracil + irinotecan (FOLFIRI). In terms of safety, mCRC patients who received aflibercept combined with FOLFIRI therapy had a higher incidence of grade 3-4 adverse events than those who received FOLFIRI alone, including anti-VEGF-related adverse events (hypertension, hemorrhagic events, and proteinuria) and chemotherapy-related adverse events (diarrhea, weakness, stomatitis, hand-foot syndrome, neutropenia, and thrombocytopenia). In terms of cost-effectiveness, two economic studies conducted in the United Kingdom and Japan, respectively, found that compared with FOLFIRI, aflibercept combined with FOLFIRI had no cost-effectiveness advantage in mCRC patients receiving second-line treatment. Conclusion: Compared with FOLFIRI treatment, aflibercept combined with FOLFIRI for the second-line treatment of mCRC patients has better efficacy, worse safety, and is not cost-effective. More high-quality clinical studies are required for further exploration of aflibercept's clinical value. Medical institutions in Hong Kong, Macao, and Taiwan regions of China should be cautious when using or introducing aflibercept plus FOLFIRI as a mCRC treatment.

Long-term trends in the burden of inflammatory bowel disease in China over three decades: A joinpoint regression and age-period-cohort analysis based on GBD 2019.

Background: To study the corresponding strategies to control inflammatory bowel disease (IBD), a comprehensive assessment of the disease burden is required. Herein, we present long-term trends in the burden of IBD in China over the last three decades, as well as its epidemiological features. Methods: We characterized the burden of IBD in China using the GBD 2019 methods and results, based on prevalence, incidence, mortality, years lost (YLLs), years lived with disability (YLDs), and disability-adjusted life years (DALYs) estimated using the DisMod-MR 2-1. We also used joinpoint and age-period-cohort (apc) analysis methods to interpret IBD epidemiological characteristics and compare them to global prevalence trends. Results: The age-standardized incidence and mortality rates in both sexes changed from 1.47 (95% CI: 1.24, 1.74) to 3.01 (95% CI: 2.59, 3.50) and from 0.86 (95% CI: 0.59, 1.16) to 0.30 (95% CI: 0.24, 0.35) per 100,000 people in China from 1990 to 2019. The age-standardized DALY rate in China decreased from 24.47 (95% CI: 17.88, 30.19) per 100,000 people in 1990 to 13.10 (95% CI: 10.29, 16.31) per 100,000 people in 2019. The average annual percentage change (AAPC) in age-standardized incidence, prevalence, and mortality rates for IBD in China were 2.51 (95% CI: 2.44, 2.57), 2.53 (95% CI: 2.41, 2.66), and -3.62 (95% CI: -3.85, -3.39). The effects of age, period, and cohort on incidence and mortality rates differed. Conclusions: The increasing age-standardized prevalence rates are contributed to by the reduction in age-standardized mortality rates and DALYs, compounded by the rise in the age-standardized incidence rates between 1990 and 2019 in China. The burden of IBD in China will be a major public health challenge, given the country's large population base and aging population.

Quantitative Assessment of Biomechanical Properties of the Human Keratoconus Cornea Using Acoustic Radiation Force Optical Coherence Elastography.

Purpose: Quantification of biomechanical properties of keratoconus (KC) corneas has great significance for early diagnosis and treatment of KC, but the corresponding clinical measurement remains challenging. Here, we developed an acoustic radiation force (ARF) optical coherence elastography technique and explored its potential for evaluating biomechanical properties of KC corneas. Methods: An ARF system was used to induce the tissue deformation, which was detected by an optical coherence tomography system, and thus the localized point-by-point Young's modulus measurements were achieved. Then, two healthy rabbit eyes were imaged to test the system, after which the human keratoconus cornea was evaluated by using the same method. Three regions were selected for biomechanics analysis: the conical region, the transitional region, and the peripheral region. Results: Young's moduli of transitional region ranged from 53.3 to 58.5 kPa. The corresponding values for the peripheral region were determined to be 58.6 kPa and 63.2 kPa, respectively. Young's moduli of the conical region were gradually increased by 18.3% from the center to the periphery, resulting in the minimum and maximum values of 44.9 kPa and 53.1 kPa, respectively. Furthermore, Young's moduli of the anterior and posterior of the center were determined to be 44.9 kPa and 50.7 kPa, respectively. Conclusions: Differences in biomechanical properties between the three regions and slight variations within the conical region were clearly distinguished. Biomechanical weakening of the keratoconus cornea was mainly localized in the conical region, especially in the vertex position. Translational Relevance: The system may provide a promising clinical tool for the noninvasive evaluation of local corneal biomechanics and thus may have potential applications in early keratoconus detection with further optimization.

Research on Rice Yield Prediction Model Based on Deep Learning.

Food is the paramount necessity of the people. With the progress of society and the improvement of social welfare system, the living standards of people all over the world are constantly improving. The development of medical industry improves people's health level constantly, and the world population is constantly climbing to a new peak. With the continuous development of deep learning in recent years, its advantages are constantly displayed, especially in the aspect of image recognition and processing, it drives into the distance. Thanks to the superiority of deep learning in image processing, the combination of remote sensing images and deep learning has attracted more attention. To simulate the four key factors of rice yield, this article tries a regression model with a combination of various characteristic independent variables. In this article, the selection of the best linear and nonlinear regression models is discussed, the prediction performance and significance of each regression model are analyzed, and some thoughts are given on estimation of actual rice yield.

An analysis of coupling coordination relationship between regional economy and transportation: empirical evidence from China.

The increasing discrepancy between a regional economy and transportation imposes higher requirements for their coordinated development. This paper utilized the coupling coordination degree (CCD) model and entropy method (EM) to quantitatively study the coupling coordination state between regional economy and transportation and its spatial distribution of 30 provinces in China from 2004 to 2017. The results show the following: (1) The comprehensive level of regional economy and transportation development in China has shown a growing trend, and the development of regional economy is faster than that of the transportation. (2) The CCD between regional economy and transportation in China is changing from incoordination to high-level coordination. The imbalance of CCD levels among the regions studied varies significantly. The CCD in the eastern regions is slightly higher than that in the central, western, and northeast regions. (3) In the region with a higher CCD, the discrepancy between the development of regional economy and transportation is higher than that in other regions. Moreover, suggestions are provided to promote the coordinated development from a regional perspective. This study provides references to policymakers to help them properly plan and design transportation systems while considering the regional economy, thus stimulating the coordinated and sustainable development between regional economy and transportation.

Role of Reputation in Sustainable Performance of Online Crowdsourcing Vendors: An Explanation From Transaction Cost Theory.

This study reveals a new finding on the impact of reputation growth on crowdsourcing vendors' sustainable performance in different modes of markets using fixed-effect panel data regression models. To this end, we extract data from a large Chinese crowdsourcing platform named zbj.com for the period of 2012-2014, which was a key stage for the establishment of market diversification. Based on different transaction modes, the study divides the markets on the crowdsourcing platform into task-based market (TBM) and employment market (EPM). By applying the multiple framework, the empirical results exhibit a negative and significant effect of vendors' reputation on participation rate (PR) in TBM and EPM. At the same time, reputation also has a consistent effect on vendors' revenue share (RS) of each market. Moreover, this study shows that the significant reputation impact on PR and RS of EPM will be, respectively, weakened and strengthened in fixed-price mode and customized mode when vendors participate more in large-scale projects. The findings suggest that the growth of reputation will promote market transfer of vendors, that is, showing different sustainability in different markets, which will lead to uneven development of the crowdsourcing markets. By adopting the perspective of transaction cost theory (TCT), this study elaborates and analyses these phenomena and derives corresponding policy implications.

The Structural Characteristics of Economic Network and Efficiency of Health Care in China.

With the rapid development of the economy of China, the interactivity between provinces and the mobility of the population is increasing. Some patients who could have received the same treatment in their residential areas still choose to receive services in areas with higher economic development and concentrated high-quality medical resources, resulting in a huge waste of medical resources. Blindly increasing medical resources everywhere does not necessarily increase the output effectively. In this study, the data envelopment analysis (DEA) model, social network analysis (SNA), cluster analysis, and regression analysis are used to analyze the structural characteristics of the economic network structure and efficiency of health care in China. The results show that indegree and eigenvector centrality have a significant positive correlation with the efficiency of health care, and the clustering coefficient has a significant negative correlation with the efficiency of health care in China. This study uses a k-means algorithm to classify 31 provinces into three groups and extract their characteristics. As for the supply of health care resources, the government should command and dispatch the resources in the whole country through a top-down design based on the characteristics of each province.

High-Resolution Full-3D Specimen Imaging for Lumpectomy Margin Assessment in Breast Cancer.

BACKGROUND: Two-dimensional (2D) specimen radiography (SR) and tomosynthesis (DBT) for breast cancer yield data that lack high-depth resolution. A volumetric specimen imager (VSI) was developed to provide full-3D and thin-slice cross-sectional visualization at a 360° view angle. The purpose of this prospective trial was to compare VSI, 2D SR, and DBT interpretation of lumpectomy margin status with the final pathologic margin status of breast lumpectomy specimens. METHODS: The study enrolled 200 cases from two institutions. After standard imaging and interpretation was performed, the main lumpectomy specimen was imaged with the VSI device. Image interpretation was performed by three radiologists after surgery based on VSI, 2D SR, and DBT. A receiver operating characteristic (ROC) curve was created for each method. The area under the curve (AUC) was computed to characterize the performance of the imaging method interpreted by each user. RESULTS: From 200 lesions, 1200 margins were interpreted. The AUC values of VSI for the three radiologists were respectively 0.91, 0.90, and 0.94, showing relative improvement over the AUCs of 2D SR by 54%, 13%, and 40% and DBT by 32% and 11%, respectively. The VSI has sensitivity ranging from 91 to 94%, specificity ranging from 81 to 85%, a positive predictive value ranging from 25 to 30%, and a negative predicative value of 99%. CONCLUSIONS: The ROC curves of the VSI were higher than those of the other specimen imaging methods. Full-3D specimen imaging can improve the correlation between the main lumpectomy specimen margin status and surgical pathology. The findings from this study suggest that using the VSI device for intraoperative margin assessment could further reduce the re-excision rates for women with malignant disease.

ECG quality assessment based on hand-crafted statistics and deep-learned S-transform spectrogram features.

Background and Objective Electrocardiogram (ECG) quality assessment is significant for automatic diagnosis of cardiovascular disease and reducing the massive workload of reviewing continuous ECGs. Hence, how to design an appropriate algorithm for objectively evaluating the multi-lead ECG recordings is particularly important. Despite the deep learning methods performing well in many fields, as a data-driven method, it may not be entirely suitable for ECG analysis due to the difficulty in obtaining sufficient data and the low signal-to-noise ratio of ECG recordings. In this study, with the aim of providing an accurate and automatic ECG quality assessment scheme, we propose an innovative ECG quality assessment algorithm based on hand-crafted statistical features and deep-learned spectral features. Methods In this paper, a novel approach, combining the deep-learned Stockwell transform (S-Transform) spectrogram features and hand-crafted statistical features, is proposed for ECG quality assessment. Firstly, a double-input convolutional neural network (CNN) is established. Then, the S-Transform with a novel online augmentation scheme is performed on the multi-lead raw ECG signal received from one input layer to obtain proper time-frequency representation. After that, the CNN with three convolutional layers is employed to extract robust deep-learned features automatically. Simultaneously, the hand-crafted statistical features, including lead-fall, baseline drift, and R peak features, are calculated and fed into another input layer for feature fusion training. Finally, the deep-learned and hand-crafted features are concatenated and further fused by a fully connected layer for quality classification. Furthermore, a log-odds analysis scheme combining with a gradient-based method can localize the abnormal zone in time, frequency, and spatial domains. Results and Conclusion Our proposed method is evaluated on a publicly available database with 10-fold cross-validation. The experimental results demonstrate that the proposed assessment algorithm reached a mean accuracy of 93.09%, a mean F1-score of 0.8472, and a sensitivity of 0.9767. Moreover, comprehensive experiments indicate that the fusion of CNN features and statistical features has complementary advantages and ideal interpretability, achieving end-to-end multi-lead ECG assessment with satisfying performance.

Improving Ki67 assessment concordance by the use of an artificial intelligence-empowered microscope: a multi-institutional ring study.

AIMS: The nuclear proliferation biomarker Ki67 plays potential prognostic and predictive roles in breast cancer treatment. However, the lack of interpathologist consistency in Ki67 assessment limits the clinical use of Ki67. The aim of this article was to report a solution utilising an artificial intelligence (AI)-empowered microscope to improve Ki67 scoring concordance. METHODS AND RESULTS: We developed an AI-empowered microscope in which the conventional microscope was equipped with AI algorithms, and AI results were provided to pathologists in real time through augmented reality. We recruited 30 pathologists with various experience levels from five institutes to assess the Ki67 labelling index on 100 Ki67-stained slides from invasive breast cancer patients. In the first round, pathologists conducted visual assessment on a conventional microscope; in the second round, they were assisted with reference cards; and in the third round, they were assisted with an AI-empowered microscope. Experienced pathologists had better reproducibility and accuracy [intraclass correlation coefficient (ICC) = 0.864, mean error = 8.25%] than inexperienced pathologists (ICC = 0.807, mean error = 11.0%) in visual assessment. Moreover, with reference cards, inexperienced pathologists (ICC = 0.836, mean error = 10.7%) and experienced pathologists (ICC = 0.875, mean error = 7.56%) improved their reproducibility and accuracy. Finally, both experienced pathologists (ICC = 0.937, mean error = 4.36%) and inexperienced pathologists (ICC = 0.923, mean error = 4.71%) improved the reproducibility and accuracy significantly with the AI-empowered microscope. CONCLUSION: The AI-empowered microscope allows seamless integration of the AI solution into the clinical workflow, and helps pathologists to obtain higher consistency and accuracy for Ki67 assessment.