Automated machine learning in nanotoxicity assessment: A comparative study of predictive model performance.

Computational modeling has earned significant interest as an alternative to animal testing of toxicity assessment. However, the process of selecting an appropriate algorithm and fine-tuning hyperparameters for the developing of optimized models takes considerable time, expertise, and an intensive search. The recent emergence of automated machine learning (autoML) approaches, available as user-friendly platforms, has proven beneficial for individuals with limited knowledge in ML-based predictive model development. These autoML platforms automate crucial steps in model development, including data preprocessing, algorithm selection, and hyperparameter tuning. In this study, we used seven previously published and publicly available datasets for oxides and metals to develop nanotoxicity prediction models. AutoML platforms, namely Vertex AI, Azure, and Dataiku, were employed and performance measures such as accuracy, F1 score, precision, and recall for these autoML-based models were then compared with those of conventional ML-based models. The results demonstrated clearly that the autoML platforms produced more reliable nanotoxicity prediction models, outperforming those built with conventional ML algorithms. While none of the three autoML platforms significantly outperformed the others, distinctions exist among them in terms of the available options for choosing technical features throughout the model development steps. This allows users to select an autoML platform that aligns with their knowledge of predictive model development and its technical features. Additionally, prediction models constructed from datasets with better data quality displayed, enhanced performance than those built from datasets with lower data quality, indicating that future studies with high-quality datasets can further improve the performance of those autoML-based prediction models.

How the digital infrastructure construction affects urban carbon emissions-A quasi-natural experiment from the "Broadband China" policy.

The global emphasis on informatization and low-carbon development is growing. Using staggered Difference-In-Differences (DID) methodology, this research examines the impact of digital infrastructure development on urban carbon dioxide emissions and explores its underlying causal mechanisms. Drawing from a comprehensive 2009-2019 panel dataset of 240 Chinese cities, the study employs the "Broadband China" policy as a reliable proxy for digital infrastructure construction (DIC). The findings indicate that DIC effectively reduces urban carbon dioxide emissions, fostering sustainable low-carbon regional economic development. The results withstand robustness tests, revealing heterogeneous effects, with coastal cities and those with stronger environmental regulations experiencing more significant reductions. The study suggests that upgrading industrial structure and enhancing green innovation capacity are effective methods for DIC to mitigate urban carbon emissions. The paper concludes with policy recommendations, emphasizing leveraging policy dividends, addressing regional disparities, and adopting a multi-path development approach. Providing new insights and empirical data, this research contributes to understanding the relationship between DIC and urban carbon emissions, offering policy guidance for China's carbon reduction efforts and strategic objectives of carbon peaking and neutrality.

[Clinical comprehensive evaluation of Ruyi Zhenbao Pills in treatment of osteoarthritis].

This study evaluated the clinical effectiveness of Ruyi Zhenbao Pills in the treatment of osteoarthritis, aiming to clarify its clinical advantages and promote rational drug use and related policy transformation. Following the relevant standards in Guidelines for the Comprehensive Evaluation of Drugs in Clinical Practice and Technical Specifications for the Clinical Comprehensive Evaluation of Chinese Patent Medicine, comprehensive research and related data on Ruyi Zhenbao Pills in the treatment of osteoarthritis were collected in the dimensions of safety, effectiveness, economy, innovation, suitability, accessibility, and traditional Chinese medicine(TCM) cha-racteristics(referred to as the "6+1" dimensions). Through evidence-based medicine, questionnaire surveys, health technology assessment, pharmacoeconomic evaluation, and other methods, a multi-criteria decision analysis(MCDA) model and CSC v2.0 software were used to comprehensively evaluate the clinical value of Ruyi Zhenbao Pills. Spontaneous reporting system data on adverse reactions and literature data indicate that the adverse reactions of Ruyi Zhenbao Pills are mostly general adverse reactions, with no reports of se-rious adverse reactions. The known risks are small, and its safety is rated as class A. It has been shown to effectively relieve joint pain and restore joint function in the treatment of osteoarthritis. However, more high-quality, large-sample randomized controlled trials are needed to further validate its effectiveness, which is rated as class B. There is evidence supporting its economic viability, and its economic is rated as class B. It demonstrates good clinical innovation, innovative enterprise service system, and industrial innovation, and innovation is rated as class A. Medical professionals and patients have a favorable perception of the suitability of Ruyi Zhenbao Pills, and further improvement can be made in terms of convenience of administration and promotion to facilitate rational drug use by healthcare professionals and patients. Suitability is rated as class B. The drug has a favorable price level, availability, and affordability, and accessibility is rated as class A. Ruyi Zhenbao Pills are a classic Tibetan medicinal prescription with excellent TCM theoretical characteristics. However, further research is needed on its use in human studies. TCM characteristics are rated as class B. Based on the evaluation results of the "6+1" dimensions, the comprehensive clinical evaluation is rated as grade B. Ruyi Zhenbao Pills have good clinical value in the treatment of osteoarthritis, and it is recommended to undergo the necessary procedures for conditional transformation into a policy for the management of essential clinical drugs.

Learning Hand Kinematics for Parkinson's Disease Assessment Using a Multimodal Sensor Glove.

Hand dysfunctions in Parkinson's disease include rigidity, muscle weakness, and tremor, which can severely affect the patient's daily life. Herein, a multimodal sensor glove is developed for quantifying the severity of Parkinson's disease symptoms in patients' hands while assessing the hands' multifunctionality. Toward signal processing, various algorithms are used to quantify and analyze each signal: Exponentially Weighted Average algorithm and Kalman filter are used to filter out noise, normalization to process bending signals, K-Means Cluster Analysis to classify muscle strength grades, and Back Propagation Neural Network to identify and classify tremor signals with an accuracy of 95.83%. Given the compelling features, the flexibility, muscle strength, and stability assessed by the glove and the clinical observations are proved to be highly consistent with Kappa values of 0.833, 0.867, and 0.937, respectively. The intraclass correlation coefficients obtained by reliability evaluation experiments for the three assessments are greater than 0.9, indicating that the system is reliable. The glove can be applied to assist in formulating targeted rehabilitation treatments and improve hand recovery efficiency.

Assessment on the declining degree of farmland shelter forest in a desert oasis based on LiDAR and hyperspectrum imagery.

We examined the growth decline and health status of farmland protective forest belt (Populus alba var. pyramidalis and Populus simonii shelterbelts) in Ulanbuh Desert Oasis by using airborne hyperspectral and ground-based LiDAR to collect the hyperspectral images and point cloud data of the whole forest belt respectively. Through correlation analysis and stepwise regression analysis, we constructed the evaluation model of the decline degree of farmland protection forest with the spectral differential value, vegetation index, and forest structure parameters as independent variables and the tree canopy dead branch index of the field survey as dependent variables. We further tested the accuracy of the model. The results showed that the evaluation accuracy of the decline degree of P. alba var. pyramidalis and P. simonii by LiDAR method was better than that by hyperspectral method, and that the evaluation accuracy of the combined LiDAR and hyperspectral method was the highest. Using the LiDAR method, hyperspectral method, the combined method, the optimal model of P. alba var. pyramidalis was all light gradient boosting machine model, with the overall classification accuracy being 0.75, 0.68, 0.80, and Kappa coefficient being 0.58, 0.43, 0.66, respectively. The optimal model of P. simonii was random forest model, random forest model, and multilayer perceptron model, with the overall classification accuracy being 0.76, 0.62, 0.81, and Kappa coefficient being 0.60, 0.34, 0.71, respectively. This research method could accurately check and monitor the decline of plantations.

Bridging gaps to universal palliative care access in Chile: serious health-related suffering and the cost of expanding the package of care services.

Background: The Lancet Commission on Palliative Care (PC) and Pain Relief quantified the burden of serious health-related suffering (SHS), proposing an Essential Package of PC (EPPC) to narrow the global PC divide. We applied the EPPC framework to analyze PC access in Chile, identify gaps in coverage, and provide recommendations to improve PC access. Methods: Total SHS and population in need of PC was estimated using official 2019 government data. We differentiated between cancer and non-cancer related SHS given guaranteed Chilean PC coverage for cancer. We calculated differences between the Chilean PC package and the Lancet Commission EPPC to estimate the cost of expanding to achieve national coverage of palliative care. Findings: In 2019, nearly 105,000 decedent and non-decedent Chileans experienced SHS with a lower-bound estimate of 12.1 million days and an upper-bound estimate of 42.4 million days of SHS. Each individual experienced between 116 and 520 days of SHS per year. People living with a cancer diagnosis had PC access with financial protection, accounting for almost 42% of patients in need. People with non-cancer diagnoses-about 61 thousand patients-lacked PC coverage. Expanding coverage of the EPPC for all patients in need would cost just above $123 million USD, equivalent to 0.47% of Chilean National Health Expenditure. Interpretation: Achieving universal PC access is urgent and feasible for Chile, classified as a high-income country. Expanding PC services and coverage to the EPPC standard are affordable and critical health system responses to ensuring financial protection for patients with SHS. In Chile, this requires closing large gaps in PC coverage pertaining to patients with non-cancer conditions and treatment of symptoms that go beyond pain. Our research provides an empirical approach for applying the Lancet Commission SHS framework to estimate the cost of achieving national universal PC access anchored in a package of health care services. Funding: This research was partially funded by the Chilean Government through the Fondo Nacional de Ciencia y Tecnología (Fondecyt Regular) grant number 1201721, the U.S. Cancer Pain Relief Committee grant AWD-003806 awarded to the University of Miami and by the University of Miami Institute for Advanced Study of the Americas. We acknowledge NIH/NCI award P30CA008748.

Are you more risk-seeking when helping others? Effects of situational urgency and peer presence on prosocial risky behavior.

Introduction: Prosocial risky behavior (PRB) proposes that individuals take risks for others' benefits or social welfare, and that this may involve trade-offs between risk and social preferences. However, little is known about the underlying cognitive mechanisms of risk-seeking or aversion during PRB. Methods: This study adopted the dilemma-priming paradigm to examine the interaction between the risk levels of personal cost and situational urgency on PRB (Experiment 1, N = 88), and it further uncovered the modulation of the risk levels of failure (Experiment 2, N = 65) and peer presence (Experiment 3, N = 80) when helping others. Results: In Experiment 1, the participants involved in risky dilemmas made more altruistic choices for strangers in urgent situations compared to those for strangers in non-urgent situations. However, increasing the risk levels of personal cost decreased the frequencies of help offered to strangers in urgent situations. Experiment 2 further established that, similar to the risk of personal cost, increasing the risk levels of failure when helping others also decreased the frequencies of help offered to strangers in urgent situations. Furthermore, in dilemmas involving a low-risk personal cost, Experiment 3 showed that peer presence encouraged the participants to make more altruistic choices when providing help to strangers in non-urgent situations. Discussion: Individuals demonstrate obvious risk-seeking behavior when helping others and that both non-urgent situations and peer presence weaken the effect of increased risk aversion on PRB in a limited manner.

The Economic Value of Health Benefits Associated with Urban Park Investment.

The allocation of resources towards the development and enhancement of urban parks offers an effective strategy for promoting and improving the health and well-being of urban populations. Investments in urban parks can result in a multitude of health benefits. The increased usage of greenspace by park users has been linked to positive physical and mental health outcomes. Additionally, the expansion of greenspace in urban areas can mitigate harmful impacts from air pollutants, heat, noise, and climate-related health risks. While the health benefits attributed to urban parks and greenspaces are well documented, few studies have measured the economic value of these benefits. This study applied a novel ecohealth economic valuation framework to quantify and estimate the potential economic value of health benefits attributed to the development of a proposed park in the downtown core of Peterborough, Canada. The results indicated that development of the small urban park will result in annual benefits of CAD 133,000 per year, including CAD 109,877 in the avoided economic burden of physical inactivity, CAD 23,084 in health savings associated with improved mental health, and CAD 127 in health savings attributed to better air quality. When including the economic value of higher life satisfaction, the economic benefit is more than CAD 4 million per year. The study demonstrates the value of developing and enhancing urban parks as a strategy to improve population health and well-being, and as a means of cost savings to the medical system.

[Guideline for clinical comprehensive evaluation of Chinese patent medicine (2022 version)].

Currently,the research or publications related to the clinical comprehensive evaluation of Chinese patent medicine are increasing,which attracts the broad attention of all circles. According to the completed clinical evaluation report on Chinese patent medicine,there are still practical problems and technical difficulties such as unclear responsibility of the evaluation organization,unclear evaluation subject,miscellaneous evaluation objects,and incomplete and nonstandard evaluation process. In terms of evaluation standards and specifications,there are different types of specifications or guidelines with different emphases issued by different academic groups or relevant institutions. The professional guideline is required to guide the standardized and efficient clinical comprehensive evaluation of Chinese patent medicine and further improve the authority and quality of evaluation. In combination with the characteristics of Chinese patent medicine and the latest research achievement at home and abroad,the detailed specifications were formulated from six aspects including design,theme selection,content and index,outcome,application and appraisal,and quality control. The guideline was developed based on the guideline development requirements of China Assoication of Chinese medicine. After several rounds of expert consensus and public consultation,the current version of the guideline has been developed.

Perceived Constraints on Active Recreational Sport Participation among Residents in Urban China.

Recreational sport participation is an important pathway to improving the quality of life. While facilities for recreational sports are provided in many urban areas in China, how urban residents might be aware of or use these facilities for recreational sport participation is still a vague notion in the literature. This study explored the linkages between perceived leisure constraints and active participation in recreational sports among urban residents. We collected data samples from 2901 urban residents in China to identify their perceived constraints and the effects of the perceived constraints on active recreational sport participation by structural equation models. Five perceived constraints of active recreational sport participation were identified: intrapersonal, interpersonal, environmental condition, facility-service management, and leisure opportunity constraints. More specifically, leisure opportunity, intrapersonal, facility-service management, and interpersonal constraints were the four most important constraints limiting active recreational sport participation of urban residents. Theoretical and practical implications to facilitate the active recreational sport participation of Chinese urban residents were discussed.

[Effects of different long-term fertilization patterns on net carbon sink effect and economic benefits in double cropping rice paddy ecosystem in southern China]. / 长期不同施肥模式对南方双季稻田生态系统净碳汇效应和经济收益的影响.

There is close relationship between fertilizer managements and net carbon (C) sink effect, economic benefits in rice paddy ecosystem. Based on a long-term (35-year) field experiment, we analyzed the effects of different fertilization patterns on soil C sequestration rate, C density of topsoil, annual C balance, and economic benefits in the double cropping rice paddy in southern China. There were four fertilization treatments, chemical fertilizer alone (MF), rice straw and chemical fertilizer (RF), 30% organic manure and 70% chemical fertilizer (OM), and without any fertilizer input as a control (CK). The results showed that soil C pool in the double cropping rice paddy field under different fertilization treatments changed from 216.02 to 866.74 kg·hm-2·a-1, and soil C pool under OM treatment were significantly higher than that of MF, RF and CK. The soil C sequestration rates in the double cropping rice paddy field under different fertilization treatments ranged from 51.5 to 650.7 kg·hm-2·a-1, and that of C density of topsoil was from 55.64 to 78.42 t·hm-2. The order of soil C sequestration rates and C density of topsoil was OM>RF>MF>CK. The change range of C adsorption in the double cropping rice paddy field ecosystem was from 4.42 to 9.32 t C·hm-2·a-1, with an order of OM>RF>MF>CK. Compared with the MF treatment, soil net C sink under OM and RF treatments increased by 27.6% and 13.6%, respectively. The change range of C cost material input ranged from 1.49 to 2.17 t C·hm-2·a-1, and that of annual economic benefits was from 1.30×103 to 7.83×103 yuan·hm-2·a-1 with an order of RF>OM>MF>CK. The net income of economic benefits of OM, RF and MF treatments were significantly higher than that of CK. Generally, soil C sequestration rate, C sink effect and annual economic benefits were increased by the long-term application of organic manure and rice straw returning together with chemical fertilizer, which could increase soil organic carbon storage in the double cropping rice paddy field of southern China.

Do socio-economic factors matter? A comprehensive evaluation of tourism eco-efficiency determinants in China based on the Geographical Detector Model.

Constructed on the total-factor analysis framework, this paper develops a comprehensive evaluation system and adopts the Super-SBM model to both analyze and enunciate the characteristics of tourism eco-efficiency in China during 2000-2017. This paper also identifies the determinants associated with spatial differentiation of tourism eco-efficiency by employing a novel geographical technique, namely the Geographical Detector Model. The results indicate that the tourism eco-efficiency exhibits great potential for growth. Besides, pure technical efficiency drives the optimized development of eco-efficiency. Also, there is significant spatial variations in eco-efficiency across different provinces and regions in China. Urbanization contributes to tourism eco-efficiency remarkably, followed by openness, technical level, economic scale, industrial structure, capital effect, environmental regulation, and tourism growth. The relational interrelations of tourism eco-efficiency determinants are the bi-enhancement and the nonlinear-enhancement interactions. The implications of research findings are discussed and may be applied to a multitude of corporate environmental-economic management scenarios.

[Clinical comprehensive evaluation of Chinese patent medicine based on EVIDEM].

The clinical comprehensive evaluation of Chinese patent medicine is an important direction in the evaluation of traditional Chinese medicine(TCM), which positively promotes the development of TCM industry. The evaluation system of Chinese patent medicine is helpful to comprehensively evaluate the clinical value of different Chinese patent medicine in the same category, different dosage forms, and specifications, from different manufacturers on the basis of evidence and value. The establishment of a scientific and reasonable comprehensive evaluation index system for Chinese patent medicine is an important prerequisite to ensure clinical value. However, there has been neither a recognized systematic review on the clinical comprehensive evaluation of Chinese patent medicine nor a methodological system used for reference. The evidence and value: impact on decision-making(EVIDEM), developed by the international research team, is used to evaluate the comprehensive value of medical interventions. EVIDEM provides a methodological tool for scientific decision-making to evaluate evidence and value for health technologies on the basis of the multi-criteria decision analysis(MCDA) model and health technology assessment(HTA). Based on the ongoing EVIDEM research, the present study put forward that EVIDEM-based clinical comprehensive evaluation of Chinese patent medicine consisted of four aspects, seven modules, and ten steps, which is expected to references and practical experience for the follow-up comprehensive evaluation of Chinese patent medicine in the TCM field.

Atom- and step-economic 1,3-thiosulfonylation of activated allenes with thiosulfonates to access vinyl sulfones/sulfides.

A new type of organocatalyzed 1,3-thiosulfonylation has been developed to straightforwardly access highly functionalized vinyl sulfones, which features mild conditions, atom- and step-economy, practicability, conciseness, and environmental friendliness. Moreover, these valuable products can be transformed to vinyl sulfides via a base-promoted isomerization. The versatile route can efficiently and rapidly introduce SCD3 groups with excellent levels of deuterium content (>99% D) by utilizing our newly developed SCD3 reagents. Gram-scale operations and further transformations are smoothly carried out, providing promising applications for drug discovery.

Quantitative probabilistic assessment of caffeine intake from tea in Chinese adult consumers based on nationwide caffeine content determination and tea consumption survey.

Caffeine has known effects on the central nervous and cardiovascular systems. An intake up to 400 mg/day does not give rise to health concerns. Tea, a major source of caffeine, is highly consumed in China. However, the potential health risk of caffeine from tea has not been well evaluated. The present study assessed caffeine intake levels from tea for Chinese adult consumers. We collected 1,398 samples of green, black, dark, jasmine, oolong, white, and yellow tea from 17 provinces. The caffeine content was determined by HPLC. The average contents were 27 (oolong tea) - 43 (yellow tea) mg/g. The leaching rate of caffeine into the water was about 100%. Tea consumption data were from the National Beverage Consumption Survey 2013-2014. Monte Carlo simulations were applied to estimate the distribution of caffeine intake. The average caffeine intake from tea was 180 mg/day of all consumers. Green, dark, and black tea were the primary sources. Males (197 mg/day) consumed more caffeine than females (136 mg/day) on average, but females older than 71 years had the highest intake level (259 mg/day) among all subgroups. Over 90% of Chinese adult tea drinkers have caffeine intake under 400 mg/day.

Perceived participation and autonomy structural relationships among related factors in patients with stroke and hypertension in China: A ISM model approach.

Aims: To explore the structural relationship between perceived participation and autonomy among older adults with stroke and hypertension in home and community-based services (HCBSs) in the eastern coastal region of China. Design: An explorative cross-sectional study. Methods: From July to September 2021, a total of 714 respondents were reported to have stroke and hypertension, and their information was used in the analysis of this study. A multiple linear regression analysis was used to explore the factors influencing factors older adults' perceived participation and autonomy. Using the ISM model, we analyzed the factors affecting social participation in patients with stroke and hypertension and explained the logical relationships and hierarchy among the factors. Results: The mean score of perceived participation was 58.34 ± 27.57. Age, marital status, health insurance, living status, number of children, chronic diseases, sleep time, frequency of outings, and health utility value were significant factors affecting perceived participation and autonomy with stroke and hypertension patients. Among them, health insurance is the direct factor on the surface, age, number of children, chronic diseases, sleep time, frequency of outings, and health utility value are the intermediate indirect factors, and marital status and living status are the deep-rooted factors. Conclusion: By the study that the hierarchical structure provides a visualization of interrelationships and interdependences among the influencing factors of perceived participation and autonomy. It also may be a significant complement to traditional variable-entered approaches and construct an optimized multidimensional perspective of participation and autonomy. Future research should focus on optimizing the living environment of older adults with stroke and hypertension to explore the model of rehabilitative intervention and help patients successfully reintegrate into their families/societies.

Extubation in the operating room results in fewer composite mechanical ventilation-related adverse outcomes in patients after liver transplantation: a retrospective cohort study.

BACKGROUND: To investigate the effect of extubation in the operating room (OR) on mechanical ventilation-related adverse outcomes in patients who undergo liver transplantation. METHODS: Patients who underwent liver transplantation between January 2016 and December 2019 were included. According to the timing of extubation, patients were divided into OR extubation group and intensive care unit (ICU) extubation group. The propensity score was used to match OR extubation group and ICU extubation group at a 1:2 ratio by demographical and clinical covariates. The primary outcome was a composite of mechanical ventilation-related adverse outcomes, including 30-day all-cause mortality, in-hospital acute kidney injury (stage 2 or 3), and in-hospital moderate to severe pulmonary complications. Secondary outcomes included in-hospital moderate to severe infectious complications, unplanned reintubation rates, ICU and postoperative hospital lengths of stay, and total hospital cost. RESULTS: A total of 438 patients were enrolled. After propensity score matching, 94 patients were in OR extubation group and 148 patients were in ICU extubation group. Incidence of the composite mechanical ventilation-related adverse outcomes was significantly lower in OR extubation group than ICU extubation group, even after adjusting for confounding factors (19.1% vs. 31.8%; Odds Ratio, 0.509; 95% Confidence Index [CI], 0.274-0.946; P=0.031). The duration of ICU stay was much shorter in OR extubation group than ICU extubation group (median 4, Interquartile range [IQR] (3 ~ 6) vs. median 6, IQR (4 ~ 8); P<0.001). Meanwhile, extubation in the OR led to a significant reduction of total hospital cost compared with extubation in the ICU (median 3.9, IQR (3.5 ~ 4.6) 10000 US dollars vs. median 4.1, IQR (3.8 ~ 5.1) 10000 US dollars; P=0.021). However, there were no statistically significant differences in moderate to severe infectious complications, unplanned reintubation rates, and the length of postoperative hospital stay between groups. CONCLUSIONS: Among patients who underwent liver transplantation, extubation in the OR compared with extubation in the ICU, significantly reduced the primary composite outcome of 30-day all-cause mortality, in-hospital acute kidney injury (stage 2 or 3), or in-hospital moderate to severe pulmonary complications. TRIAL REGISTRATION: The trial was registered at www.clinicaltrials.gov with registration number NCT04261816. Retrospectively registered on 1st February 2020.

Automated Assessment of Neonatal Endotracheal Intubation Measured by a Virtual Reality Simulation System.

Manual assessment from experts in neonatal endotracheal intubation (ETI) training is a time-consuming and tedious process. Such subjective, highly variable, and resource-intensive assessment method may not only introduce inter-rater/intra-rater variability, but also represent a serious limitation in many large-scale training programs. Moreover, poor visualization during the procedure prevents instructors from observing the events occurring within the manikin or the patient, which introduces an additional source of error into the assessment. In this paper, we propose a physics-based virtual reality (VR) ETI simulation system that captures the entire motions of the laryngoscope and the endotracheal tube (ETT) in relation to the internal anatomy of the virtual patient. Our system provides a complete visualization of the procedure, offering instructors with comprehensive information for accurate assessment. More importantly, an interpretable machine learning algorithm was developed to automatically assess the ETI performance by training on the performance parameters extracted from the motions and the scores rated by experts. Our results show that the leave-one-out-cross-validation (LOOCV) classification accuracy of the automated assessment algorithm is 80%, which indicates that our system can reliably conduct a consistent and standardized assessment for ETI training.

Automated Assessment System for Neonatal Endotracheal Intubation Using Dilated Convolutional Neural Network.

Neonatal endotracheal intubation (ETI) is an important, complex resuscitation skill, which requires a significant amount of practice to master. Current ETI practice is conducted on the physical manikin and relies on the expert instructors' assessment. Since the training opportunities are limited by the availability of expert instructors, an automatic assessment model is highly desirable. However, automating ETI assessment is challenging due to the complexity of identifying crucial features, providing accurate evaluations and offering valuable feedback to trainees. In this paper, we propose a dilated Convolutional Neural Network (CNN) based ETI assessment model, which can automatically provide an overall score and performance feedback to pediatric trainees. The proposed assessment model takes the captured kinematic multivariate time-series (MTS) data from the manikin-based augmented ETI system that we developed, automatically extracts the crucial features of captured data, and eventually provides an overall score as output. Furthermore, the visualization based on the class activation mapping (CAM) can automatically identify the motions that have significant impact on the overall score, thus providing useful feedback to trainees. Our model can achieve 92.2% average classification accuracy using the Leave-One-Out-Cross-Validation (LOOCV).

Assessment of the Learning Curve of Supercapsular Percutaneously Assisted Total Hip Arthroplasty in an Asian Population.

The supercapsular percutaneously assisted total hip (SuperPATH) approach is a microinvasive approach that was developed to minimize surgical disruption of soft tissue during routine total hip arthroplasty (THA). This study was aimed at assessing early outcomes and learning curves of the SuperPATH approach in one Chinese hospital's experience. Early outcomes of the first consecutive 78 SuperPATH cases (80 hips) performed by the same surgeon were evaluated. The patients were divided into 4 groups according to the surgical order. The incision, intraoperative blood loss, hospital stay, Harris hip score, and complication occurrence in each group were evaluated. Learning curves were assessed using operative time and intraoperative blood loss as surrogates. The operation time and intraoperative blood loss of groups A and B were more than those of groups C and D, and the difference was statistically significant (P < 0.05); however, there was no statistically significant difference between the two groups (group A vs. group B, P = 0.426; group A vs. group B, P = 0.426). There was no statistically significant difference in terms of incision length and hospital stay, and Harris hip score at the last follow-up was increased with statistically significant difference when compared with that preoperatively among the 4 groups. One case of periprosthetic fracture occurred in group A. No other complication, such as joint dislocation, sciatic nerve injury, prosthesis loosening, periprosthetic infection, and deep vein thromboembolism, occurred in the 4 groups. In summary, for surgeons who are familiar with the standard posterolateral approach, they could achieve more familiarity with SuperPATH after 40 cases of surgery.