UNASSIGNED: Thyroid nodules, increasingly prevalent globally, pose a risk of malignant transformation. Early screening is crucial for management, yet current models focus mainly on ultrasound features. This study explores machine learning for screening using demographic and biochemical indicators.
UNASSIGNED: Analyzing data from 6,102 individuals and 61 variables, we identified 17 key variables to construct models using six machine learning classifiers: Logistic Regression, SVM, Multilayer Perceptron, Random Forest, XGBoost, and LightGBM. Performance was evaluated by accuracy, precision, recall, F1 score, specificity, kappa statistic, and AUC, with internal and external validations assessing generalizability. Shapley values determined feature importance, and Decision Curve Analysis evaluated clinical benefits.
UNASSIGNED: Random Forest showed the highest internal validation accuracy (78.3%) and AUC (89.1%). LightGBM demonstrated robust external validation performance. Key factors included age, gender, and urinary iodine levels, with significant clinical benefits at various thresholds. Clinical benefits were observed across various risk thresholds, particularly in ensemble models.
UNASSIGNED: Machine learning, particularly ensemble methods, accurately predicts thyroid nodule presence using demographic and biochemical data. This cost-effective strategy offers valuable insights for thyroid health management, aiding in early detection and potentially improving clinical outcomes. These findings enhance our understanding of the key predictors of thyroid nodules and underscore the potential of machine learning in public health applications for early disease screening and prevention.

Metabolic dysfunction-associated fatty liver disease (MAFLD) is the most prevalent chronic liver condition worldwide. Current liver enzyme-based screening methods have limitations that may missed diagnoses and treatment delays. Regarding Chen et al, the risk of developing MAFLD remains elevated even when alanine aminotransferase levels fall within the normal range. Therefore, there is an urgent need for advanced diagnostic techniques and updated algorithms to enhance the accuracy of MAFLD diagnosis and enable early intervention. This paper proposes two potential screening methods for identifying individuals who may be at risk of developing MAFLD: Lowering these thresholds and promoting the use of noninvasive liver fibrosis scores.

In this editorial, we comment on the article entitled \"Stage at diagnosis of colorectal cancer through diagnostic route: Who should be screened?\" by Agatsuma et al. Colorectal cancer (CRC) is emerging as an important health issue as its incidence continues to rise globally, adversely affecting the quality of life. Although the public has become more aware of CRC prevention, most patients lack screening awareness. Some poor lifestyle practices can lead to CRC and symptoms can appear in the early stages of CRC. However, due to the lack of awareness of the disease, most of the CRC patients are diagnosed already at an advanced stage and have a poor prognosis.

BACKGROUND: Evidence from observational studies indicates that lung cancer screening (LCS) guidelines with high rates of lung cancer (LC) underdiagnosis, and although current screening guidelines have been updated and eligibility criteria for screening have been expanded, there are no studies comparing the efficiency of LCS guidelines in Chinese population.
METHODS: Between 2005 and 2022, 31,394 asymptomatic individuals were screened using low-dose computed tomography (LDCT) at our institution. Demographic data and relevant LC risk factors were collected. The efficiency of the LCS for each guideline criteria was expressed as the efficiency ratio (ER). The inclusion rates, eligibility rates, LC detection rates, and ER based on the different eligibility criteria of the four guidelines were comparatively analyzed. The four guidelines were as follows: China guideline for the screening and early detection of lung cancer (CGSL), the National Comprehensive Cancer Network (NCCN), the United States Preventive Services Task Force (USPSTF), and International Early Lung Cancer Action Program (I-ELCAP).
RESULTS: Of 31,394 participants, 298 (155 women, 143 men) were diagnosed with LC. For CGSL, NCCN, USPSTF, and I-ELCAP guidelines, the eligibility rates for guidelines were 13.92%, 6.97%, 6.81%, and 53.46%; ERe for eligibility criteria were 1.46%, 1.64%, 1.51%, and 1.13%, respectively; and for the inclusion rates, they were 19.0%, 9.5%, 9.3%, and 73.0%, respectively. LCs which met the screening criteria of CGSL, NCCN, USPSTF, and I-ELCAP guidelines were 29.2%, 16.4%, 14.8%, and 86.6%, respectively. The age and smoking criteria for CGSL were stricter, hence resulting in lower rates of LC meeting the screening criteria. The CGSL, NCCN, and USPSTF guidelines showed the highest underdiagnosis in the 45-49 age group (17.4%), while the I-ELCAP guideline displayed the highest missed diagnosis rate (3.0%) in the 35-39 age group. Males and females significantly differed in eligibility based on the criteria of the four guidelines (P < 0.001).
CONCLUSIONS: The I-ELCAP guideline has the highest eligibility rate for both males and females. But its actual efficiency ratio for those deemed eligible by the guideline was the lowest. Whereas the NCCN guideline has the highest ERe value for those deemed eligible by the guideline.

BACKGROUND: In 2016, WHO estimated there were roughly 374 million new infections among adults of the following four curable sexually transmitted infections (STIs): chlamydia (caused by Chlamydia trachomatis (CT)), gonorrhoea (Neisseria gonorrhoeae (NG)), syphilis (Treponema pallidum) and trichomoniasis (Trichomonas vaginalis (TV)). Accurate point-of-care tests (POCTs) for screening of genital and extragenital CT, NG and TV infections are of great value and have been developed during recent decade. Several tests are commercially available and have shown encouraging performance compared with \'gold-standard\' reference tests in laboratory-based studies. However, there is limited data on their clinical performance, including at the POC. Key populations, such as men who have sex with men (MSM), are at higher risk of these STIs at genital and extragenital sites and these STIs are often asymptomatic, especially in extragenital sites and in women. We will conduct a clinical-based evaluation to assess the performance characteristics and acceptability to end-users of molecular-based diagnostic technology for POC/near patient use of the Xpert CT/NG (Cepheid, Sunnyvale, California, USA) test for screening of genital, anorectal and pharyngeal CT and NG infections in MSM and the Xpert CT/NG and Xpert TV (Cepheid, Sunnyvale, California, USA) for screening of genital CT, NG and TV among women at risk for these STIs compared with gold-standard reference nucleic acid amplification tests. This master protocol outlines the overall research approach that will be used in seven countries.
METHODS: Consecutive MSM and women at risk presenting at the clinical sites in high, and low- and middle-income countries will be enrolled. The POCTs to be evaluated are Xpert CT/NG and Xpert TV. All procedures will be carried out by trained healthcare staff and tests performed in strict accordance with the manufacturer\'s instructions. The sensitivity, specificity, positive and negative predictive values for each POCT will be calculated. The study is ongoing with recruitment expected to be completed in all countries by mid-2022 to late-2022.
BACKGROUND: Prior to enrolment, this core protocol was independently peer-reviewed and approved by the research project review panel (RP2) of the WHO Department of Sexual and Reproductive Health and Research and by the WHO Ethics Review Committee (ERC). The core protocol has been slightly adapted accordingly to individual countries and adaptations approved by both RP2 and ERC, as well as all relevant institutional review boards at each participating site. Results will be disseminated through peer-reviewed journals and presented at relevant national/international conferences.

BACKGROUND: The overall benefits of the newly introduced family-based Helicobacter pylori (H. pylori) infection control and management (FBCM) and screen-and-treat strategies in preventing multiple upper gastrointestinal diseases at national level in China have not been explored. We investigate the cost-effectiveness of these strategies in the whole Chinese population.
METHODS: Decision trees and Markov models of H. pylori infection-related non-ulcer dyspepsia (NUD), peptic ulcer disease (PUD), and gastric cancer (GC) were developed to simulate the cost-effectiveness of these strategies in the whole 494 million households in China. The main outcomes include cost-effectiveness, life years (LY), quality-adjusted life year (QALY), and incremental cost-effectiveness ratio (ICER).
RESULTS: When compared with no-screen strategy, both FBCM and screen-and-treat strategies reduced the number of new cases of NUD, PUD, PUD-related deaths, and the prevalence of GC, and cancer-related deaths. The costs saved by these two strategies were $1467 million and $879 million, quality-adjusted life years gained were 227 million and 267 million, and life years gained were 59 million and 69 million, respectively. Cost-effectiveness analysis showed that FBCM strategy costs -$6.46/QALY and -$24.75/LY, and screen-and-treat strategy costs -$3.3/QALY and -$12.71/LY when compared with no-screen strategy. Compared to the FBCM strategy, the screen-and-treat strategy reduced the incidence of H. pylori-related diseases, added 40 million QALYs, and saved 10 million LYs, but at the increased cost of $588 million. Cost-effectiveness analysis showed that screen-and-treat strategy costs $14.88/QALY and $59.5/LY when compared with FBCM strategy. The robustness of the results was also verified.
CONCLUSIONS: Both FBCM and screen-and-treat strategies are highly cost-effective in preventing NUD, PUD, and GC than the no-screen strategy in Chinese families at national level. As FBCM strategy is more practical and efficient, it is expected to play a more important role in preventing familial H. pylori infection and also serves as an excellent reference for other highly infected societies.

BACKGROUND: A rapid screening test for urinary tract infections (UTIs) in children is needed to avoid unnecessary cultures and provide prompt reports to make appropriate clinical decisions. We have evaluated for the first time the performance of the Sysmex UF-5000 flow cytometer as a screening tool for UTIs in children.
METHODS: This study included 4445 pediatric patients, with urinary sediment and urine culture data collected from January 2020 to September 2023. The Sysmex UF-5000 analyzer was utilized to measure urine white blood cell (WBC) and bacteria (BACT), with the findings being compared to the culture results.
RESULTS: At ≥ 104 colony-forming unit (CFU)/mL, 513 samples were culture-positive (400 samples presented 104-105 CFU/mL, and 113 demonstrated ≥ 105 CFU/mL bacterial growth). Optimal indicators for positive cultures were BACT counts of 92.2/μL (AUC: 0.944) and WBC counts of 40.8/μL (AUC:0.863). False negative rate were 0.9% when using a 7.8 bacteria/μL cut-off and avoiding unnecessary cultures in 28.1%. The UF-5000 has a higher consistency rate for Gram-negative (GN) bacteria (90.3%) than Gram-positive (GP) bacteria (86.8%). For samples with 105 CFU/mL, UF-5000\'s Bacteria -Information flags showed superior concordance for samples with 104-105 CFU/mL bacteria.
CONCLUSIONS: Screening pediatric urine cultures with the UF-5000 showed potential application value in identifying negative cultures and significant bacterial growth, although performance may vary depending on the study population. Furthermore, detecting Gram typing aids in guiding early clinical empirical medication, particularly for UTIs caused by GN bacteria.

OBJECTIVE: In this article, we provide a database of nonproliferative diabetes retinopathy, which focuses on early diabetes retinopathy with hard exudation, and further explore its clinical application in disease recognition.
METHODS: We collect the photos of nonproliferative diabetes retinopathy taken by Optos Panoramic 200 laser scanning ophthalmoscope, filter out the pictures with poor quality, and label the hard exudative lesions in the images under the guidance of professional medical personnel. To validate the effectiveness of the datasets, five deep learning models are used to perform learning predictions on the datasets. Furthermore, we evaluate the performance of the model using evaluation metrics.
RESULTS: Nonproliferative diabetes retinopathy is smaller than proliferative retinopathy and more difficult to identify. The existing segmentation models have poor lesion segmentation performance, while the intersection over union (IOU) value for deep lesion segmentation of models targeting small lesions can reach 66.12%, which is higher than ordinary lesion segmentation models, but there is still a lot of room for improvement.
CONCLUSIONS: The segmentation of small hard exudative lesions is more challenging than that of large hard exudative lesions. More targeted datasets are needed for model training. Compared with the previous diabetes retina datasets, the NDRD dataset pays more attention to micro lesions.

BACKGROUND: Obesity is an important risk factor for kidney stones(KS). Chinese Visceral Adiposity Index (CVAI), as a specific indicator for visceral obesity in the Chinese population, can more accurately assess the visceral fat content in Chinese individuals compared to Visceral Adiposity Index (VAI). However, the association between CVAI and risk for KS has not been studied.
METHODS: A total of 97,645 participants from a health screening cohort underwent ultrasound examinations for the diagnosis of kidney stones, along with measurements of their CVAI. Logistic regressions were utilized to determine the relationship between different quartiles of CVAI and the incidence of kidney stones. Simultaneously, subgroup analysis and the computation of dose-response curves were employed to pinpoint susceptible populations.
RESULTS: Among the participants, 2,888 individuals (3.0%) were diagnosed with kidney stones. The mean CVAI values ± standard deviation for the four groups were: Q1 (18.42 ± 19.64), Q2 (65.24 ± 10.39), Q3 (98.20 ± 9.11), and Q4 (140.40 ± 21.73). In the fully adjusted multivariable model, CVAI was positively correlated with urolithiasis (OR = 1.001; 95% CI = 1.000, 1.002). Compared with the first quartile of CVAI, the population in the fourth quartile of CVAI had a higher prevalence of kidney stones (OR = 1.231; 95% CI = 1.066, 1.415). Through subgroup analysis, a positive correlation between CVAI and the risk of kidney stones was found in non-smokers (OR = 1.001, 95%CI:1.000, 1.002), non-drinkers (OR = 1.001, 95%CI:1.000, 1.002), non-hypertensive subgroups (OR = 1.003, 95%CI:1.002, 1.003), and non-diabetes subgroups (OR = 1.001, 95%CI:1.000, 1.002).
CONCLUSIONS: The findings suggest that CVAI could be a reliable and effective biomarker for assessing the potential risk of kidney stone prevalence, with significant implications for the primary prevention of kidney stones and public health.

UNASSIGNED: Several obstacles can hinder breast cancer screening. This study aimed to investigate the knowledge, attitude, and practice (KAP) toward ultrasound screening for breast cancer in women.
UNASSIGNED: This cross-sectional study recruited women who visited the breast specialist clinic of Zhongshan City People\'s Hospital (a tertiary hospital) between August 2022 and April 2023 through convenience sampling. KAP scores ≥70% were considered adequate.
UNASSIGNED: This study enrolled 501 participants. The mean knowledge, attitude, and practice levels were 8.56 ± 1.81/12 (possible range 0-12, 71.33%), 29.80 ± 2.71 (possible range 8-40, 74.50%), and 32.04 ± 3.09 (possible range 8-40, 80.10%). Senior high school education (vs. junior high school and below, coefficient = 1.531, 95%CI: 1.013-2.312, p = 0.044), bachelor\'s education and above (vs. junior high school and below, coefficient = 5.315, 95%CI: 3.546-7.966, p < 0.001), housewife or unemployed (vs. employed, coefficient = 0.671, 95%CI: 0.466-0.966, p = 0.032), and a history of breast ultrasound (vs. no, coefficient = 1.466, 95%CI: 1.121-1.917, p = 0.005) were independently and positively associated with knowledge. Knowledge (coefficient = 1.303, 95%CI: 1.100-1.544, p = 0.002) and monthly income >10,000 (vs. <5,000, coefficient = 4.364, 95%CI: 1.738-10.956, p = 0.002) were independently and positively associated with attitude. Only attitude (coefficient = 1.212, 95%CI: 1.096-1.340, p < 0.001) was independently and positively associated with the practice. A structural equation modeling (SEM) analysis was used to estimate causality among KAP dimensions, showing that knowledge directly influenced attitude (β = -1.090, p = 0.015), knowledge did not directly influence practice (β = -0.117, p = 0.681) but had an indirect influence (β = 0.826, p = 0.028), and attitude directly influenced practice (β = -0.757, p = 0.016).
UNASSIGNED: Women in Zhongshan City had good knowledge, favorable attitudes, and active practice toward breast ultrasound screening for breast cancer. Women\'s characteristics associated with a poorer KAP were identified, allowing for more targeted interventions.