ObjectiveThe value of the transformation zone (TZ) is often overlooked in clinical settings. This study aims to assess TZ distribution, associated factors, and its impact on colposcopic diagnosis.Methods chi 2 tests were used to analyze demographics, clinical history, and tissue samples to examine the differences in TZ distribution. Factors affecting the TZ were explored using logistic regression, and diagnostic indicators were calculated.ResultsA total of 5,302 individual datasets were finally included. TZ1, TZ2, and TZ3 accounted for 31.6%, 38.5%, and 30.0%, respectively. Age is the most important factor that influences the location of the TZ. The proportion of TZ3 steadily increased with age, comprising over 55% in women over 50. The colposcopic diagnostic performance shows that high-grade squamous intraepithelial lesion or worse (HSIL+) sensitivity of TZ3 (58.1%, 95% confidence interval [CI] = 52.9-63.4) is significantly lower than that of TZ1 (69.8%, 95% CI = 65.5-74.1) and TZ2 (73.2%, 95% CI = 69.7-76.8). The HSIL+ specificity of TZ3 (96.3, 95% CI = 95.3-97.4) was higher than that of TZ1 (96.3, 95% CI = 95.2-97.3) and TZ2 (92.5, 95% CI = 91.1-93.9). The HSIL+ positive predictive value (81.3%, 95% CI = 76.4-86.2) and negative predictive value (89.3%, 95% CI = 87.6-90.9) for TZ3 are high, with no significant differences when compared with TZ1 and TZ2.ConclusionsAge predominantly influences TZ location, with TZ3 being most frequently found in women over 50. While TZ3 poses a higher risk of missed diagnosis during colposcopy, it remains clinically valuable in identifying diseased and nondiseased status. Increasing colposcopists' awareness of TZ importance is needed in clinical practice.

Objective The objective of this study was to assess the attitudes toward the Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) of colposcopists working in mainland China. Methods A questionnaire was developed to collect participants' sociodemographic information and assess their awareness, attitudes, and acceptance toward the CAIADS. Results There were 284 respondents from 24 provinces across mainland China, with 55% working in primary care institutions. Participant data were divided into two subgroups based on their colposcopy case load per year (i.e. ≥50 cases; <50 cases). The analysis showed that participants with higher loads had more experience working with CAIADS and were more knowledgeable about CAIADS and AI systems. Overall, in both groups, about half of the participants understood the potential applications of big data and AI-assisted diagnostic systems in medicine. Although less than one-third of the participants were knowledgeable about CAIADS and its latest developments, more than 90% of the participants were open with the idea of using CAIADS. Conclusions While a related lack of acknowledgement of CAIADS exists, the participants in general had an open attitude toward CAIADS. Practical experience with colposcopy or CAIADS contributed to participants' awareness and positive attitudes. The promotion of AI tools like CAIADS could help address regional health inequities to improve women's well-being, especially in low- and middle-income countries.

Background Colposcopy plays an essential role in diagnosing cervical lesions and directing biopsy; however, there are few studies of the capabilities of colposcopists in medically underserved communities in China. This study aims to fill this gap by assessing colposcopists’ competencies in medically underserved communities of China. Methods Colposcopists in medically underserved communities across China were considered eligible to participate. Assessments involved presenting participants with 20 cases, each consisting of several images and various indications. Participants were asked to determine transformation zone (TZ) type, colposcopic diagnoses and to decide whether biopsy was necessary. Participants are categorized according to the number of colposcopic examinations, i.e., above or below 50 per annum. Results There were 214 participants in this study. TZ determination accuracy was 0.47 (95% CI 0.45,0.49). Accuracy for colposcopic diagnosis was 0.53 (95% CI 0.51,0.55). Decision to perform biopsies was 0.73 accurate (95% CI 0.71,0.74). Participants had 0.61 (95% CI 0.59,0.64) sensitivity and a 0.80 (95% CI 0.79,0.82) specificity for detecting high-grade lesions. Colposcopists who performed more than 50 cases were more accurate than those performed fewer across all indicators, with a higher sensitivity (0.66 vs. 0.57, p = 0.001) for detecting high-grade lesions. Conclusions In medically underserved communities of China, colposcopists appear to perform poorly at TZ identification, colposcopic diagnosis, and when deciding to biopsy. Colposcopists who undertake more than 50 colposcopies each year performed better than those who perform fewer. Therefore, colposcopic practice does improve through case exposure although there is an urgent need for further pre-professional and clinical training.

BACKGROUND:Human papillomavirus (HPV) vaccination is a promising step toward cervical cancer elimination. This study was conducted to investigate the knowledge, attitude, and HPV vaccine uptake among female adults in mainland China based on a large e-commerce platform. METHODS:We conducted a cross-sectional online survey of female adults between March 4 to April 20, 2022. The survey consisted of sociodemographic information, related knowledge, vaccination uptake, and attitudes toward vaccination. We included women aged 18-45 years in the final analysis. Logistic regressions were conducted to explore influencing factors associated with related knowledge, HPV vaccination uptake, and willingness to be vaccinated. RESULTS:In total, 3,572 female adults (34 years, IQR 30-39) were included in the analysis. The majority of the participants were highly educated (78.7%) with a high monthly family income (79.0%). The median HPV knowledge score was 8.25 out of 11. More than 75% of respondents were unvaccinated, while 95.8% of unvaccinated female adults are willing to be vaccinated. Variables such as age, insurance, vaccination history, and whether one had heard of the HPV vaccine influence HPV vaccination practice (all p-values < 0.05). The main barriers to vaccination were vaccine inaccessibility and the high cost of the vaccine. CONCLUSION:The findings of our study highlight a moderate knowledge level, poor vaccination rate, and strong willingness to be vaccinated among Chinese female adults who were better educated and wealthier. Targeted health education and practical support should be provided in the future, to reduce gaps between vaccine uptake and vaccine acceptance.

The risk associated with single and multiple human papillomavirus (HPV) infections in cervical intraepithelial neoplasia (CIN) remains uncertain. This study aims to explore the distribution and diagnostic significance of the number of high-risk HPV (hr-HPV) infections in detecting CIN, addressing a crucial gap in our understanding. This comprehensive multicenter, retrospective study meticulously analyzed the distribution of single and multiple hr-HPV, the risk of CIN2+, the relationship with CIN, and the impact on the diagnostic performance of colposcopy using demographic information, clinical histories, and tissue samples. The composition of a single infection was predominantly HPV16, 52, 58, 18, and 51, while HPV16 and 33 were identified as the primary causes of CIN2+. The primary instances of dual infection were mainly observed in combinations such as HPV16/18, HPV16/52, and HPV16/58, while HPV16/33 was identified as the primary cause of CIN2+. The incidence of hr-HPV infections shows a dose-response relationship with the risk of CIN (p for trend <0.001). Compared to single hr-HPV, multiple hr-HPV infections were associated with increased risks of CIN1 (1.44, 95% confidence interval [CI]: 1.20-1.72), CIN2 (1.70, 95% CI: 1.38-2.09), and CIN3 (1.08, 95% CI: 0.86-1.37). The colposcopy-based specificity of single hr-HPV (93.4, 95% CI: 92.4-94.4) and multiple hr-HPV (92.9, 95% CI: 90.8-94.6) was significantly lower than negative (97.9, 95% CI: 97.0-98.5) in detecting high-grade squamous intraepithelial lesion or worse (HSIL+). However, the sensitivity of single hr-HPV (73.5, 95% CI: 70.8-76.0) and multiple hr-HPV (71.8, 95% CI: 67.0-76.2) was higher than negative (62.0, 95% CI: 51.0-71.9) in detecting HSIL+. We found that multiple hr-HPV infections increase the risk of developing CIN lesions compared to a single infection. Colposcopy for HSIL+ detection showed high sensitivity and low specificity for hr-HPV infection. Apart from HPV16, this study also found that HPV33 is a major pathogenic genotype.

To investigate age and type-specific prevalences of high-risk human papillomavirus (hrHPV) and cervical intraepithelial neoplasia (CIN) in hrHPV+ women referred to colposcopy. This is a retrospective, multicenter study. Participants were women referred to one of seven colposcopy clinics in China after testing positive for hrHPV. Patient characteristics, hrHPV genotyping, colposcopic impressions, and histological diagnoses were abstracted from electronic records. Main outcomes were age-related type-specific prevalences associated with hrHPV and CIN, and colposcopic accuracy. Among 4419 hrHPV+ women referred to colposcopy, HPV 16, 52, and 58 were the most common genotypes. HPV 16 prevalence was 39.96%, decreasing from 42.57% in the youngest group to 30.81% in the eldest group. CIN3+ prevalence was 15.00% and increased with age. As lesion severity increases, HPV16 prevalence increased while the prevalence of HPV 52 and 58 decreased. No age-based trend was identified with HPV16 prevalence among CIN2+, and HPV16-related CIN2+ was less common in women aged 60 and above (44.26%) compared to those younger than 60 years (59.61%). Colposcopy was 0.73 sensitive at detecting CIN2+ (95% confidence interval[CI]: 0.71, 0.75), with higher sensitivity (0.77) observed in HPV16+ women (95% CI: 0.74, 0.80) compared to HPV16- women (0.68, 95% CI: 0.64, 0.71). Distributions of hrHPV genotypes, CIN, and type-specific CIN in Chinese mainland hrHPV+ women referred to colposcopy were investigated for the first time. Distributions were found to be age-dependent and colposcopic performance appears related to HPV genotypes. These findings could be used to improve the management of women referred to colposcopy.

BACKGROUND:Melanoma is a serious risk to human health and early identification is vital for treatment success. Deep learning (DL) has the potential to detect cancer using imaging technologies and many studies provide evidence that DL algorithms can achieve high accuracy in melanoma diagnostics. OBJECTIVES:To critically assess different DL performances in diagnosing melanoma using dermatoscopic images and discuss the relationship between dermatologists and DL. METHODS:Ovid-Medline, Embase, IEEE Xplore, and the Cochrane Library were systematically searched from inception until 7th December 2021. Studies that reported diagnostic DL model performances in detecting melanoma using dermatoscopic images were included if they had specific outcomes and histopathologic confirmation. Binary diagnostic accuracy data and contingency tables were extracted to analyze outcomes of interest, which included sensitivity (SEN), specificity (SPE), and area under the curve (AUC). Subgroup analyses were performed according to human-machine comparison and cooperation. The study was registered in PROSPERO, CRD42022367824. RESULTS:2309 records were initially retrieved, of which 37 studies met our inclusion criteria, and 27 provided sufficient data for meta-analytical synthesis. The pooled SEN was 82 % (range 77-86), SPE was 87 % (range 84-90), with an AUC of 0.92 (range 0.89-0.94). Human-machine comparison had pooled AUCs of 0.87 (0.84-0.90) and 0.83 (0.79-0.86) for DL and dermatologists, respectively. Pooled AUCs were 0.90 (0.87-0.93), 0.80 (0.76-0.83), and 0.88 (0.85-0.91) for DL, and junior and senior dermatologists, respectively. Analyses of human-machine cooperation were 0.88 (0.85-0.91) for DL, 0.76 (0.72-0.79) for unassisted, and 0.87 (0.84-0.90) for DL-assisted dermatologists. CONCLUSIONS:Evidence suggests that DL algorithms are as accurate as senior dermatologists in melanoma diagnostics. Therefore, DL could be used to support dermatologists in diagnostic decision-making. Although, further high-quality, large-scale multicenter studies are required to address the specific challenges associated with medical AI-based diagnostics.

Clinicians face increasing workloads in medical imaging interpretation, and artificial intelligence (AI) offers potential relief. This meta-analysis evaluates the impact of human-AI collaboration on image interpretation workload. Four databases were searched for studies comparing reading time or quantity for image-based disease detection before and after AI integration. The Quality Assessment of Studies of Diagnostic Accuracy was modified to assess risk of bias. Workload reduction and relative diagnostic performance were pooled using random-effects model. Thirty-six studies were included. AI concurrent assistance reduced reading time by 27.20% (95% confidence interval, 18.22%-36.18%). The reading quantity decreased by 44.47% (40.68%-48.26%) and 61.72% (47.92%-75.52%) when AI served as the second reader and pre-screening, respectively. Overall relative sensitivity and specificity are 1.12 (1.09, 1.14) and 1.00 (1.00, 1.01), respectively. Despite these promising results, caution is warranted due to significant heterogeneity and uneven study quality.

Abstract Background Improving the coverage rate of cervical cancer screening is a challenge mission for cervical cancer elimination. This study attempted to assess the knowledge, willingness, and uptake of cervical cancer screening services among Chinese females and determined associated factors. Methods This is a cross-sectional online survey conducted in China from March to April 2022. Information on demographic characteristics, knowledge, willingness, and uptake of cervical cancer screening was collected through a large e-commerce platform. Women aged 18–65 were included in the analysis. Logistic regression analysis was employed to detect the possible factors associated with knowledge, willingness, and screening participation. Results A total of 4518 women (37.83 ± 9.14 years) were included in the final analysis, of whom 87.16% (n = 3938) lived in urban areas. About 93.40% (n = 4220) of the respondents reported hearing of cervical cancer screening. The median score of knowledge about cervical cancer was 16 out of 26. Over 84% (n = 3799) of the respondents were willing to receive regular cervical cancer screening. Nearly 40% (n = 1785) had never received cervical cancer screening. Among the screened women, 21.26% (n = 581), 35.24% (n = 1151), and 42.37% (n = 1158) were screened through a national cervical cancer screening program, employee physical examination, and self-paid physical examination, respectively. Knowledge was positively associated with willingness and screening participation. Age, marital status, occupation, monthly household income, and HPV vaccination history could influence screening participation (all p < 0.05). Conclusions Though women had high-level awareness and strong participation willingness in cervical cancer screening, the overall screening coverage among Chinese women was still low. Besides, the knowledge about cervical cancer was still limited. Comprehensive health education should be enhanced by utilizing social media platforms and medical workers. It is also important to promote national free cervical cancer screening with high-performance screening methods.

BACKGROUND:Colposcopy is a cornerstone of cervical cancer prevention; however, there is a global shortage of colposcopists. It is challenging to train a sufficient number of colposcopists through in-person methods, which hinders our ability to adequately diagnose and manage positive cases. A digital platform is needed to make colposcopy training more efficient, scalable, and sustainable; however, current online training programs are generally based on didactic curricula that do not incorporate image analysis training. In addition, long-term assessments of online training are not readily available. Therefore, innovative digital training and an assessment of its effectiveness are needed.OBJECTIVE:This study aimed to evaluate the short- and long-term effects of DECO (an online Digital Education Tool for Colposcopy) on trainees' colposcopy competencies and confidence.STUDY DESIGN:DECO can be used both on laptops and smartphones and comprises 4 training modules (image interpretation; terminology learning; video teaching; and collection of guidelines and typical cases) and 2 test modules. DECO was tested through a pre-post study between September and November 2022. Participants were recruited in China, and DECO training lasted 12 days. Trainees initially learned basic theory before completing training using 200 image-based cases. Pretest, posttest, and follow-up testing included 20 distinct image-based questions, and was conducted on Days 0, 13, and 60. Primary outcomes were competence and confidence scores. Secondary measures were response distributions for colposcopic diagnoses, biopsies, and DECO training satisfaction. Multilevel modeling was used to determine improvement from baseline to posttraining and follow-up for the outcomes of interest.RESULTS:Among 402 participants recruited, 96.8% (n=389) completed pretesting, 84.1% (n=338) posttesting, and 75.1% (n=302) follow-up testing. Colposcopic competence and confidence increased across this study. Diagnostic scores improved on average from 55.3 (53.7-56.9) to 70.4 (68.9-71.9). The diagnostic accuracy for normal/benign lesions, low-grade squamous intraepithelial lesions, and high-grade squamous intraepithelial lesions or worse increased by 16.9%, 13.1%, and 16.9%, respectively. Mean confidence scores increased from 48.1 (45.6-50.6) to 56.2 (54.5-57.9). These improvements remained evident 2 months after training. Trainees were also satisfied with DECO overall. Most found DECO to be scientific (82.5%), easy to use (75.2%), and clinically useful (98.4%), and would recommend it to colleagues (93.2%).CONCLUSION:DECO is a useful, acceptable digital education tool that improves colposcopy competencies and confidence. DECO could make colposcopy training more efficient, scalable, and sustainable because there are no geographic or time limitations. Therefore, DECO could be used to alleviate the shortage of trained colposcopists around the world.

BACKGROUND:A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. OBJECTIVE:We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. METHODS:PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality. RESULTS:In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups. CONCLUSIONS:The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required. TRIAL REGISTRATION:PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372.

Background: Colposcopy plays an essential role in cervical cancer control, but its performance remains unsatisfactory. This study evaluates the feasibility of machine learning (ML) models for predicting high-grade squamous intraepithelial lesions or worse (HSIL+) in patients referred for colposcopy by combining colposcopic findings with demographic and screening results. Methods: In total, 7485 patients who underwent colposcopy examination in seven hospitals in mainland China were used to train, internally validate, and externally validate six commonly used ML models, including logistic regression, decision tree, naïve bayes, support vector machine, random forest, and extreme gradient boosting. Nine variables, including age, gravidity, parity, menopause status, cytological results, high-risk human papillomavirus (HR-HPV) infection type, HR-HPV multi-infection, transformation zone (TZ) type, and colposcopic impression, were used for model construction. Results: Colposcopic impression, HR-HPV results, and cytology results were the top three variables that determined model performance among all included variables. In the internal validation set, six ML models that integrated demographics, screening results, and colposcopic impression showed significant improvements in the area under the curve (AUC) (0.067 to 0.099) and sensitivity (11.55% to 14.88%) compared with colposcopists. Greater increases in AUC (0.087 to 0.119) and sensitivity (17.17% to 22.08%) were observed in the six models with the external validation set. Conclusions: By incorporating demographics, screening results, and colposcopic impressions, ML improved the AUC and sensitivity for detecting HSIL+ in patients referred for colposcopy. Such models could transform the subjective experience into objective judgments to help clinicians make decisions at the time of colposcopy examinations.

Background Artificial intelligence (AI) needs to be accepted and understood by physicians and medical students, but few have systematically assessed their attitudes. We investigated clinical AI acceptance among physicians and medical students around the world to provide implementation guidance. Materials and methods We conducted a two-stage study, involving a foundational systematic review of physician and medical student acceptance of clinical AI. This enabled us to design a suitable web-based questionnaire which was then distributed among practitioners and trainees around the world. Results Sixty studies were included in this systematic review, and 758 respondents from 39 countries completed the online questionnaire. Five (62.50%) of eight studies reported 65% or higher awareness regarding the application of clinical AI. Although, only 10–30% had actually used AI and 26 (74.28%) of 35 studies suggested there was a lack of AI knowledge. Our questionnaire uncovered 38% awareness rate and 20% utility rate of clinical AI, although 53% lacked basic knowledge of clinical AI. Forty-five studies mentioned attitudes toward clinical AI, and over 60% from 38 (84.44%) studies were positive about AI, although they were also concerned about the potential for unpredictable, incorrect results. Seventy-seven percent were optimistic about the prospect of clinical AI. The support rate for the statement that AI could replace physicians ranged from 6 to 78% across 40 studies which mentioned this topic. Five studies recommended that efforts should be made to increase collaboration. Our questionnaire showed 68% disagreed that AI would become a surrogate physician, but believed it should assist in clinical decision-making. Participants with different identities, experience and from different countries hold similar but subtly different attitudes. Conclusion Most physicians and medical students appear aware of the increasing application of clinical AI, but lack practical experience and related knowledge. Overall, participants have positive but reserved attitudes about AI. In spite of the mixed opinions around clinical AI becoming a surrogate physician, there was a consensus that collaborations between the two should be strengthened. Further education should be conducted to alleviate anxieties associated with change and adopting new technologies.