Machine learning-based identification of colorectal advanced adenoma using clinical and laboratory data: a phase I exploratory study in accordance with updated World Endoscopy Organization guidelines for noninvasive colorectal cancer screening tests.

Objective: The recent World Endoscopy Organization (WEO) guidelines now recognize precursor lesions of colorectal cancer (CRC) as legitimate screening targets. However, an optimal screening method for detecting advanced adenoma (AA), a significant precursor lesion, remains elusive. Methods: We employed five machine learning methods, using clinical and laboratory data, to develop and validate a diagnostic model for identifying patients with AA (569 AAs vs. 3228 controls with normal colonoscopy). The best-performing model was selected based on sensitivity and specificity assessments. Its performance in recognizing adenoma-carcinoma sequence was evaluated in line with guidelines, and adjustable thresholds were established. For comparison, the Fecal Occult Blood Test (FOBT) was also selected. Results: The XGBoost model demonstrated superior performance in identifying AA, with a sensitivity of 70.8% and a specificity of 83.4%. It successfully detected 42.7% of non-advanced adenoma (NAA) and 80.1% of CRC. The model-transformed risk assessment scale provided diagnostic performance at different positivity thresholds. Compared to FOBT, the XGBoost model better identified AA and NAA, however, was less effective in CRC. Conclusion: The XGBoost model, compared to FOBT, offers improved accuracy in identifying AA patients. While it may not meet the recommendations of some organizations, it provides value for individuals who are unable to use FOBT for various reasons.

ß2-microglobulin and colorectal cancer among inpatients: a case-control study.

Β2-microglobulin (ß2-M) is associated with various malignancies. However, the relationship between ß2-M and colorectal cancer (CRC) remains unclear. We explored the association between ß2-M and CRC among inpatients who underwent colonoscopy and explored factors that may modify the association. All consecutive inpatients who underwent colonoscopy were enrolled in a tertiary hospital between April 2015 and June 2022. Inpatients with initial CRC or normal colonoscopies were considered eligible as cases or controls, respectively. Baseline characteristics and laboratory indicators of the participants were collected from electronic medical records. Logistic regression analysis, smooth curve fitting, sensitivity analysis, and subgroup analysis were conducted in the present study. After adjusting for baseline clinical characteristics and laboratory parameters, ß2-M was positively associated with CRC (odds ratio [OR] 1.32; 95% confidence interval [CI] 1.11-1.58) among inpatients. When the ß2-M level was assigned as tertiles, participants in the highest tertile presented with a higher risk of CRC (OR 2.33; 95% CI 1.57-3.48). A positive linear association was observed between ß2-M and CRC with smooth curve fitting. In particular, it may be of great importance to monitor ß2-M levels for predicting CRC patients.

A KSA system for competency-based assessment of clinicians' professional development in China and quality gap analysis.

BACKGROUND: We aim to create a holistic competency-based assessment system to measure competency evolution over time - one of the first such systems in China. METHOD: Two rounds of self-reported surveys were fielded among the graduates from the Shantou University Medical College: June through December 2017, and May through August 2018. Responses from three cohorts of graduates specializing in clinical medicine - new graduates, resident physicians, and senior physicians - were analyzed. Gaps between respondents' expected and existing levels of competencies were examined using a modified service quality model, SERVQUAL. RESULTS: A total of 605 questionnaires were collected in 2017 for the construction of competency indicators and a 5-level proficiency rating scale, and 407 in 2018, for confirmatory factor and competency gap analysis. Reliability coefficients of all competency indicators (36) were greater than 0.9. Three competency domains were identified through exploratory factor analysis: knowledge (K), skills (S), and attitude (A). The confirmatory factor analysis confirmed the fit of the scale (CMIN/DF < 4; CFI > 0.9; IFI > 0.9; RMSEA ≤ 0.08). Within the cohorts of resident and senior physicians, the largest competency gap was seen in the domain of knowledge (K): -1.84 and -1.41, respectively. Among new graduates, the largest gap was found in the domain of skills (S) (-1.92), with the gap in knowledge (-1.91) trailing closely behind. CONCLUSIONS: A competency-based assessment system is proposed to evaluate clinician's competency development in three domains: knowledge (K), skills (S), and attitude (A). The system consists of 36 competency indicators, a rating scale of 5 proficiency levels, and a gap analysis to measure competency evolution through 3 key milestones in clinician's professional career: new graduate, resident physician, and senior physician. The competency gaps identified can provide evidence-based guide to clinicians' own continuous development as well as future medical curriculum improvements.

Exosomal lncRNA CHL1-AS1 Derived from Peritoneal Macrophages Promotes the Progression of Endometriosis via the miR-610/MDM2 Axis.

BACKGROUND: Exosomes secreted by peritoneal macrophages (pMφ) are deeply involved in the development of endometriosis (EMs). Exosomes can mediate cell-to-cell communication by transferring biological molecules. This study aimed to explore the effect and mechanism of exosomal long non-coding RNA (lncRNA) CHL1-AS1 derived from pMφ on EMs. MATERIALS AND METHODS: Exosomes (exo) from pMφ were isolated, identified, and co-cultured with ectopic endometrial stromal cells (eESCs) to investigate the biological functions of pMφ-exo. qRT-PCR was used to detect the expression of lncRNA CHL1-AS1 in pMφ-exo from EMs and control patients and verify the transportation of lncRNA CHL1-AS1 from pMφ to eESCs. The effects of exosomal lncRNA CHL1-AS1 on eESC proliferation, migration, invasion, and apoptosis were also detected. The relationships among lncRNA CHL1-AS1, miR-610, and MDM2 (mouse double minute 2) were verified by dual-luciferase reporter assay. The in vivo experiments were conducted to verify the effects of exosomal lncRNA on EMs using a xenograft model of EMs. RESULTS: Exosomes from pMφ were successfully isolated. EMs-pMφ-exo promoted eESC proliferation, migration, and invasion and inhibited their apoptosis. lncRNA CHL1-AS1 was upregulated in EMs-pMφ-exo and transported from pMφ to eESCs via exosomes. lncRNA CHL1-AS1 was found to act as a competing endogenous RNA of miR­610 to promote the expression of MDM2. EMs-pMφ-exo shuttled lncRNA CHL1-AS1 to promote eESC proliferation, migration, and invasion and inhibit apoptosis by downregulating miR-610 and upregulating MDM2. Furthermore, exosomal lncRNA CHL1-AS1 promoted EMs lesions growth by increasing MDM2 in vivo. CONCLUSION: The results demonstrate that exosomal lncRNA CHL1-AS1 promotes the proliferation, migration, and invasion of eESCs and inhibits their apoptosis by downregulating miR-610 and upregulating MDM2, which might be a potential therapeutic target for EMs.