Analysis of false reasons based on the artificial intelligence RRCART model to identify frozen sections of lymph nodes in breast cancer.

BACKGROUND: Breast cancer is the most common malignant tumor in the world. Intraoperative frozen section of sentinel lymph nodes is an important basis for determining whether axillary lymph node dissection is required for breast cancer surgery. We propose an RRCART model based on a deep-learning network to identify metastases in 2362 frozen sections and count the wrongly identified sections and the associated reasons. The purpose is to summarize the factors that affect the accuracy of the artificial intelligence model and propose corresponding solutions. METHODS: We took the pathological diagnosis of senior pathologists as the gold standard and identified errors. The pathologists and artificial intelligence engineers jointly read the images and heatmaps to determine the locations of the identified errors on sections, and the pathologists found the reasons (false reasons) for the errors. Through NVivo 12 Plus, qualitative analysis of word frequency analysis and nodal analysis was performed on the error reasons, and the top-down error reason framework of "artificial intelligence RRCART model to identify frozen sections of breast cancer lymph nodes" was constructed based on the importance of false reasons. RESULTS: There were 101 incorrectly identified sections in 2362 slides, including 42 false negatives and 59 false positives. Through NVivo 12 Plus software, the error causes were node-coded, and finally, 2 parent nodes (high-frequency error, low-frequency error) and 5 child nodes (section quality, normal lymph node structure, secondary reaction of lymph nodes, micrometastasis, and special growth pattern of tumor) were obtained; among them, the error of highest frequency was that caused by normal lymph node structure, with a total of 45 cases (44.55%), followed by micrometastasis, which occurred in 30 cases (29.70%). CONCLUSIONS: The causes of identification errors in examination of sentinel lymph node frozen sections by artificial intelligence are, in descending order of influence, normal lymph node structure, micrometastases, section quality, special tumor growth patterns and secondary lymph node reactions. In this study, by constructing an artificial intelligence model to identify the error causes of frozen sections of lymph nodes in breast cancer and by analyzing the model in detail, we found that poor quality of slices was the preproblem of many identification errors, which can lead to other errors, such as unclear recognition of lymph node structure by computer. Therefore, we believe that the process of artificial intelligence pathological diagnosis should be optimized, and the quality control of the pathological sections included in the artificial intelligence reading should be carried out first to exclude the influence of poor section quality on the computer model. For cases of micrometastasis, we suggest that by differentiating slices into high- and low-confidence groups, low-confidence micrometastatic slices can be separated for manual identification. The normal lymph node structure can be improved by adding samples and training the model in a targeted manner.

Delay in seeking health care from community residents during a time with low prevalence of COVID-19: A cross-sectional national survey in China.

Background: The pandemic of COVID-19 has significant implications on health resources allocation and health care delivery. Patients with non-COVID illness may have to change their care seeking behaviors to mitigate the risk of infections. The research aimed to investigate potential delay of community residents in seeking health care at a time with an overall low prevalence of COVID-19 in China. Methods: An online survey was conducted in March 2021 on a random sample drawn from the registered survey participants of the survey platform Wenjuanxing. The respondents who reported a need for health care over the past month (n = 1,317) were asked to report their health care experiences and concerns. Logistic regression models were established to identify predictors of the delay in seeking health care. The selection of independent variables was guided by the Andersen's service utilization model. All data analyses were performed using SPSS 23.0. A two-sided p value of <0.05 was considered as statistically significant. Key results: About 31.4% of respondents reported delay in seeking health care, with fear of infection (53.5%) as a top reason. Middle (31-59 years) age (AOR = 1.535; 95% CI, 1.132 to 2.246), lower levels of perceived controllability of COVID-19 (AOR = 1.591; 95% CI 1.187 to 2.131), living with chronic conditions (AOR = 2.008; 95% CI 1.544 to 2.611), pregnancy or co-habiting with a pregnant woman (AOR = 2.115; 95% CI 1.154 to 3.874), access to Internet-based medical care (AOR = 2.529; 95% CI 1.960 to 3.265), and higher risk level of the region (AOR = 1.736; 95% CI 1.307 to 2.334) were significant predictors of the delay in seeking health care after adjustment for variations of other variables. Medical consultations (38.7%), emergency treatment (18.2%), and obtainment of medicines (16.5%) were the top three types of delayed care, while eye, nose, and throat diseases (23.2%) and cardiovascular and cerebrovascular diseases (20.8%) were the top two conditions relating to the delayed care. Self-treatment at home was the most likely coping strategy (34.9%), followed by Internet-based medical care (29.2%) and family/friend help (24.0%). Conclusions: Delay in seeking health care remained at a relatively high level when the number of new COVID-19 cases was low, which may present a serious health risk to the patients, in particular those living with chronic conditions who need continuous medical care. Fear of infection is the top reason for the delay. The delay is also associated with access to Internet-based medical care, living in a high risk region, and perceived low controllability of COVID-19.

Who is more likely to hesitate to accept COVID-19 vaccine: a cross-sectional survey in China.

BACKGROUND: The aim of our study was to identify factors associated with coronavirus disease 2019 (COVID-19)vaccine willingness in China to aid future public health actions to improve vaccination. RESEARCH DESIGN AND METHODS: This study was conducted in August 2020 using a mixed-method approach, including a cross-sectional self-administered anonymous questionnaire survey and in-depth interviews with community residents in China. RESULTS: Of the participants, 30.9% showedCOVID-19 vaccine hesitancy. Being female(OR = 1.297), having poor health(OR = 1.312), having non-health or medical-related occupations (OR = 1.129), no COVID-19 infection experience(OR = 1.523), living with vulnerable family members(OR = 1.294), less knowledge(OR = 1.371), less attention to COVID-19 information(OR = 1.430), less trust in official media(OR = 1.336), less perceived susceptibility to COVID-19(OR = 1.367), and less protective behavior(OR = 1.195) were more likely to hesitate. Qualitative research has shown that they doubt the importance and necessity, as well as the effectiveness and safety of the vaccination. The economic and service accessibility of the vaccination was an impediment to their vaccine acceptance. CONCLUSION: Nearly one-thirdof people showed hesitancy to accept COVID-19 vaccination in China. Our findings highlight that health communication and publicity should be performed for the targeted population, and immunization programs should be designed to remove underlying barriers to vaccine uptake.

Risk Culture and COVID-19 Protective Behaviors: A Cross-Sectional Survey of Residents in China.

The COVID-19 outbreak caused by the Severe Acute Respiratory Syndrome CoronaVirus type 2 (SARS-CoV-2) has spread across the world. However, our understanding of the public responses, in particular in adopting protective behaviors, has been limited. The current study aimed to determine the level of protective behaviors adopted by the residents in China and its association with their cultural attributes. A national cross-sectional online survey was conducted in mainland China from 4th to 13th August 2020. Protective behaviors were assessed as a summed score (ranging from 0 to 40) measured by ten items. The self-report tendency of study participants toward the four cultural attributes (individualism, egalitarianism, fatalism, hierarchy) was rated on a seven-point Likert scale. A total of 17651 respondents returned a valid questionnaire, representing 47.9% of those who accessed the online survey. Most (89.8%) respondents aged between 18 and 45 years in the age range of and 47.7% were male. High levels of protective behaviors (34.04 ± 5.78) were reported. The respondents had high scores in the cultural attributes of hierarchy (Median = 5) and egalitarianism (Median = 5), compared with low scores in individualism (Median = 1) and fatalism (Median = 1). High levels of protective behaviors were associated a higher tendency toward egalitarianism (AOR = 2.90, 95% CI 2.67-3.15) and hierarchy (AOR = 1.66, 95% CI 1.53-1.81) and a low tendency toward fatalism (AOR = 1.79, 95% CI 1.63-1.97) and individualism (AOR = 2.62, 95% CI 2.41-2.85). The cultural attributes explained 17.3% of the variations in the protective behavioral scores. In conclusion, the adoption of protective behaviors is associated a risk culture characterized by high levels of hierarchy and egalitarianism and low levels of individualism and fatalism. Government actions and communication strategies need to adapt to the cultural characteristics of their target audience.