Triclosan (TCS) and triclocarban (TCC) are widely used synthetic broad-spectrum antibacterial agents that can enter the human body through the skin, gastrointestinal tract, and other pathways. More and more studies have found that exposure to TCS and TCC can affect human health, but currently, review reports on the health effects of human exposure to TCS and TCC are limited. Therefore, this study reviewed population studies on the relationship between TCS and TCC exposure and health effects by searching the PubMed database, summarized the associated health outcomes, and elucidated the biological mechanisms. A total of 56 studies were retrieved, among which cross-sectional studies (25 studies, 44.64%) and cohort studies (25 studies, 44.64%) accounted for a relatively large proportion, while case-control studies (6 studies, 10.72%) were relatively few. Studies on TCS exposure (48 studies, 85.71%) were far more prevalent than those on TCC exposure (2 studies, 3.57%). The remaining 6 studies involved both TCS and TCC exposure. The research results revealed that TCS exposure was associated with male and female abnormal reproductive functions, fetal growth restriction, abnormal behavior development in children, obesity, gestational diabetes mellitus (GDM), and immune-related diseases. Although the results of different studies show significant differences, they have indicated that exposure to TCS is a potential risk factor for these health problems. Due to the limited number of studies, the evidence for the relationship between TCC exposure and most of the aforementioned health effects is insufficient. Population studies and in vitro and in vivo studies have shown that exposure to TCS and TCC can interfere with the microbial homeostasis, the endocrine system, oxidative stress and immune function of the body, which are potential mechanisms causing adverse health effects. In the future, large-scale prospective cohort studies, as well as in vivo and in vitro studies, are still needed to further clarify the associations between TCS and TCC exposure and health effects, and to deeply explore its mechanism of action. These efforts will provide references for clarifying the human health hazards of TCS and TCC exposure and formulating targeted prevention and control strategies.

Objective:To evaluate the diagnostic performance of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination.Methods:Cervical cytology slide data were retrospectively collected from four hospitals for the external validation of the developed artificial intelligence-assisted diagnostic system. Subsequently, prospective data collection was conducted for human-machine assisted studies.Results:In the retrospective study, a total of 3 162 valid samples were collected as external validation data. The system showed an area under the curve (AUC) of 0.890 (95% CI: 0.878-0.902), accuracy of 0.885 (95% CI: 0.873-0.896), sensitivity of 0.928 (95% CI: 0.914-0.941), and specificity of 0.852 (95% CI: 0.834-0.867). In the prospective study, 212 valid samples were collected, and five junior cytologists participated in the human-machine assisted study. Without artificial intelligence assistance, the average AUC for the five cytologists was 0.686 (95% CI: 0.650-0.722), the accuracy was 0.699 (95% CI: 0.671-0.727), the sensitivity was 0.653 (95% CI: 0.599-0.703), the specificity was 0.719 (95% CI: 0.685-0.750), the Fleiss κ value was 0.510, and the reading time was 223 seconds. With artificial intelligence assistance, the AUC, accuracy, sensitivity, and specificity increased by 0.166, 0.143, 0.225, and 0.107, respectively. Additionally, Fleiss κ was 0.730 and the reading time decreased by 188 seconds. All differences were statistically significant (all P<0.001). Conclusions:Artificial intelligence-assisted diagnosis system shows excellent performance and good generalizability, significantly improving the diagnostic accuracy, consistency, and efficiency of junior cytologists. It can be an effective auxiliary tool for junior cytologists in clinical practice.

Clinical prediction models, which utilize clinical data and statistical methods, aim to enhance the accuracy and efficiency of medical decision-making and improve patient health outcomes. These models play a crucial role in optimizing healthcare decisions and tailoring treatments to individual needs. However, many studies currently face systemic challenges during the development process, including unclear model design objectives, redundant model construction, lack of clinical relevance in variable selection, and irregular data preprocessing. These issues finally lead to reduced model performance and limited clinical applicability. To address these challenges, this study systematically reviews relevant literature, including articles from the BMJ, and draws on practical research experience to propose a structured preparation process. This process aims to provide a scientific guiding framework for model development, ensuring the efficiency of subsequent model construction and the accuracy of predictions, thus laying a foundation for the application and advancement of clinical prediction models.

Clinical prediction models are statistical tools that incorporate multiple variables to predict the likelihood of specific outcomes, by which the accuracy and efficiency of medical decision-making can be facilitated and patient health outcomes can be improved. However, many current studies face problems, such as model construction and reporting irregularities, as well as questionable reliability, which limit their clinical application of clinical prediction model. Therefore, this study systematically reviews relevant literatures, including publications from journals like BMJ, and outline the steps involved in constructing clinical prediction models based on practical research experience. It also provides an in-depth comparison of commonly used methods during the construction process and proposes a comprehensive guiding framework to help researchers in the field to better understand and master the core concepts and practical skills of clinical prediction models for the purpose of improving their professional capabilities in the development, validation, and application of clinical prediction models.

Objective:To systematically evaluate the application of artificial intelligence (AI) in cervical cytopathology diagnosis.Methods:A systematic search was conducted using the keywords ′′cervical cancer′′ ′′cytology′′ ′′artificial intelligence′′ ′′sensitivity′′ and ′′specificity′′ (in both English and Chinese) across databases including PubMed, Web of Science, Embase, Cochrane Library, IEEE Xplore, CNKI, Wanfang, VIP Chinese Science and Technology Journals, and SinoMed. The search covered literature from inception until January 1, 2024, on the application of AI in cervical cytopathological diagnosis. Data were extracted using a predefined data extraction form to compile the contingency table data, from which sensitivity, specificity and area under the curve (AUC) were calculated.Results:A total of 1 616 articles were initially retrieved, and 27 articles were finally included in this study according to the inclusion and exclusion criteria. Five researches were conducted on the diagnosis of cytopathology slides, with pooled AUC, sensitivity and specificity of 0.92 (95% CI: 0.89-0.94), 0.91 (95% CI: 0.77-0.97) and 0.84 (95% CI: 0.77-0.90), respectively. About 22 researches were conducted on the diagnosis of cytopathology images (individual cells or cell clusters), with pooled AUC, sensitivity and specificity of 1.00 (95% CI: 0.99-1.00), 0.98 (95% CI: 0.97-0.99) and 0.98 (95% CI: 0.97-0.99), respectively. Conclusion:The application of AI in the field of cervical cytopathology shows certain diagnostic performance and potential clinical application value.

Objective:To evaluate the diagnostic performance of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination.Methods:Cervical cytology slide data were retrospectively collected from four hospitals for the external validation of the developed artificial intelligence-assisted diagnostic system. Subsequently, prospective data collection was conducted for human-machine assisted studies.Results:In the retrospective study, a total of 3 162 valid samples were collected as external validation data. The system showed an area under the curve (AUC) of 0.890 (95% CI: 0.878-0.902), accuracy of 0.885 (95% CI: 0.873-0.896), sensitivity of 0.928 (95% CI: 0.914-0.941), and specificity of 0.852 (95% CI: 0.834-0.867). In the prospective study, 212 valid samples were collected, and five junior cytologists participated in the human-machine assisted study. Without artificial intelligence assistance, the average AUC for the five cytologists was 0.686 (95% CI: 0.650-0.722), the accuracy was 0.699 (95% CI: 0.671-0.727), the sensitivity was 0.653 (95% CI: 0.599-0.703), the specificity was 0.719 (95% CI: 0.685-0.750), the Fleiss κ value was 0.510, and the reading time was 223 seconds. With artificial intelligence assistance, the AUC, accuracy, sensitivity, and specificity increased by 0.166, 0.143, 0.225, and 0.107, respectively. Additionally, Fleiss κ was 0.730 and the reading time decreased by 188 seconds. All differences were statistically significant (all P<0.001). Conclusions:Artificial intelligence-assisted diagnosis system shows excellent performance and good generalizability, significantly improving the diagnostic accuracy, consistency, and efficiency of junior cytologists. It can be an effective auxiliary tool for junior cytologists in clinical practice.

Clinical prediction models, which utilize clinical data and statistical methods, aim to enhance the accuracy and efficiency of medical decision-making and improve patient health outcomes. These models play a crucial role in optimizing healthcare decisions and tailoring treatments to individual needs. However, many studies currently face systemic challenges during the development process, including unclear model design objectives, redundant model construction, lack of clinical relevance in variable selection, and irregular data preprocessing. These issues finally lead to reduced model performance and limited clinical applicability. To address these challenges, this study systematically reviews relevant literature, including articles from the BMJ, and draws on practical research experience to propose a structured preparation process. This process aims to provide a scientific guiding framework for model development, ensuring the efficiency of subsequent model construction and the accuracy of predictions, thus laying a foundation for the application and advancement of clinical prediction models.

Clinical prediction models are statistical tools that incorporate multiple variables to predict the likelihood of specific outcomes, by which the accuracy and efficiency of medical decision-making can be facilitated and patient health outcomes can be improved. However, many current studies face problems, such as model construction and reporting irregularities, as well as questionable reliability, which limit their clinical application of clinical prediction model. Therefore, this study systematically reviews relevant literatures, including publications from journals like BMJ, and outline the steps involved in constructing clinical prediction models based on practical research experience. It also provides an in-depth comparison of commonly used methods during the construction process and proposes a comprehensive guiding framework to help researchers in the field to better understand and master the core concepts and practical skills of clinical prediction models for the purpose of improving their professional capabilities in the development, validation, and application of clinical prediction models.

Objective:To systematically evaluate the application of artificial intelligence (AI) in cervical cytopathology diagnosis.Methods:A systematic search was conducted using the keywords ′′cervical cancer′′ ′′cytology′′ ′′artificial intelligence′′ ′′sensitivity′′ and ′′specificity′′ (in both English and Chinese) across databases including PubMed, Web of Science, Embase, Cochrane Library, IEEE Xplore, CNKI, Wanfang, VIP Chinese Science and Technology Journals, and SinoMed. The search covered literature from inception until January 1, 2024, on the application of AI in cervical cytopathological diagnosis. Data were extracted using a predefined data extraction form to compile the contingency table data, from which sensitivity, specificity and area under the curve (AUC) were calculated.Results:A total of 1 616 articles were initially retrieved, and 27 articles were finally included in this study according to the inclusion and exclusion criteria. Five researches were conducted on the diagnosis of cytopathology slides, with pooled AUC, sensitivity and specificity of 0.92 (95% CI: 0.89-0.94), 0.91 (95% CI: 0.77-0.97) and 0.84 (95% CI: 0.77-0.90), respectively. About 22 researches were conducted on the diagnosis of cytopathology images (individual cells or cell clusters), with pooled AUC, sensitivity and specificity of 1.00 (95% CI: 0.99-1.00), 0.98 (95% CI: 0.97-0.99) and 0.98 (95% CI: 0.97-0.99), respectively. Conclusion:The application of AI in the field of cervical cytopathology shows certain diagnostic performance and potential clinical application value.