Tuberculous pleural effusion-induced Arg-1+ macrophage polarization contributes to lung cancer progression via autophagy signaling.

BACKGROUND: The association between tuberculous fibrosis and lung cancer development has been reported by some epidemiological and experimental studies; however, its underlying mechanisms remain unclear, and the role of macrophage (MФ) polarization in cancer progression is unknown. The aim of the present study was to investigate the role of M2 Arg-1+ MФ in tuberculous pleurisy-assisted tumorigenicity in vitro and in vivo. METHODS: The interactions between tuberculous pleural effusion (TPE)-induced M2 Arg-1+ MФ and A549 lung cancer cells were evaluated. A murine model injected with cancer cells 2 weeks after Mycobacterium bovis bacillus Calmette-Guérin pleural infection was used to validate the involvement of tuberculous fibrosis to tumor invasion. RESULTS: Increased CXCL9 and CXCL10 levels of TPE induced M2 Arg-1+ MФ polarization of murine bone marrow-derived MФ. TPE-induced M2 Arg-1+ MФ polarization facilitated lung cancer proliferation via autophagy signaling and E-cadherin signaling in vitro. An inhibitor of arginase-1 targeting M2 Arg-1+ MФ both in vitro and in vivo significantly reduced tuberculous fibrosis-induced metastatic potential of lung cancer and decreased autophagy signaling and E-cadherin expression. CONCLUSION: Tuberculous pleural fibrosis induces M2 Arg-1+ polarization, and M2 Arg-1+ MФ contribute to lung cancer metastasis via autophagy and E-cadherin signaling. Therefore, M2 Arg-1+ tumor associated MФ may be a novel therapeutic target for tuberculous fibrosis-induced lung cancer progression.

Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: development and validation study.

BACKGROUND : Deep learning models have previously been established to predict the histopathology and invasion depth of gastric lesions using endoscopic images. This study aimed to establish and validate a deep learning-based clinical decision support system (CDSS) for the automated detection and classification (diagnosis and invasion depth prediction) of gastric neoplasms in real-time endoscopy. METHODS : The same 5017 endoscopic images that were employed to establish previous models were used for the training data. The primary outcomes were: (i) the lesion detection rate for the detection model, and (ii) the lesion classification accuracy for the classification model. For performance validation of the lesion detection model, 2524 real-time procedures were tested in a randomized pilot study. Consecutive patients were allocated either to CDSS-assisted or conventional screening endoscopy. The lesion detection rate was compared between the groups. For performance validation of the lesion classification model, a prospective multicenter external test was conducted using 3976 novel images from five institutions. RESULTS : The lesion detection rate was 95.6 % (internal test). On performance validation, CDSS-assisted endoscopy showed a higher lesion detection rate than conventional screening endoscopy, although statistically not significant (2.0 % vs. 1.3 %; P = 0.21) (randomized study). The lesion classification rate was 89.7 % in the four-class classification (advanced gastric cancer, early gastric cancer, dysplasia, and non-neoplastic) and 89.2 % in the invasion depth prediction (mucosa confined or submucosa invaded; internal test). On performance validation, the CDSS reached 81.5 % accuracy in the four-class classification and 86.4 % accuracy in the binary classification (prospective multicenter external test). CONCLUSIONS : The CDSS demonstrated its potential for real-life clinical application and high performance in terms of lesion detection and classification of detected lesions in the stomach.

The association between depression and non-compliance with COVID-19 preventive behaviors in South Korean older adults stratified by sex.

OBJECTIVES: This study evaluated the association between depression and non-compliance with COVID-19 preventive behaviors among community-dwelling South Korean older adults. METHODS: We utilized the 2020 Korean Community Health Survey-a community-based nationwide survey. A score of 10 points or higher on the Patient Health Questionnaire-9 was defined as depression. Non-compliance with COVID-19 preventive behaviors was assessed on the following three behaviors: washing hands, wearing masks, and watching distance. We also included socio-demographic characteristics, health behaviors, and COVID-19-related characteristics as covariates. Multiple logistic regression analyses were performed, and all statistical analyses were stratified by sex. RESULTS: The 70,693 participants included 29,736 men and 40,957 women. Notably, 2.3% of men and 4.2% of women had depression. Non-compliance with washing hands was significantly higher in men than women (1.3% vs. 0.9%), whereas no significant differences were observed in wearing masks and watching distance. The adjusted logistic regression analysis showed that depression was positively associated with non-compliance with washing hands and watching distance in both sexes. The association between depression and non-compliance with wearing masks was significant only in women. CONCLUSIONS: There was an association between depression and non-compliance with COVID-19 preventive behaviors in South Korean older adults. This signifies that health providers need to reduce depression to improve compliance with preventive behaviors in older adults.

Two-year longitudinal associations between nutritional status and frailty in community-dwelling older adults: Korean Frailty and Aging Cohort Study.

BACKGROUND: Korea is expected to become a super-aged society in 2026, and improving nutritional status, which is directly related to health problems, is therefore important for increasing healthy life expectancy. Frailty is the most complex phenotype of aging, and leads to adverse health outcomes, disability, poor quality of life, hospitalization, and mortality. Malnutrition is a major risk factor for frailty syndrome. This study aimed to investigate the incidence of pre-frailty or frailty in the second wave (T2, 2018-2019) according to general characteristics and nutritional status in the first wave (T1, 2016-2017); and examine the longitudinal association of nutritional status in T1 and the incidence of pre-frailty or frailty in T2 among older adults living in a community. METHODS: A secondary data analysis was performed using the Korean Frailty and Aging Cohort Study (KFACS). Participants comprised 1125 community-dwelling older Korean adults aged 70-84 years (mean age: 75.03 ± 3.56 years; 53.8% males). Frailty was assessed using the Fried frailty index, and nutritional status was assessed using the Korean version of the Mini Nutritional Assessment Short-Form and blood nutritional biomarkers. Binary logistic regression was used to identify longitudinal associations between the nutritional status at T1 and pre-frailty or frailty at T2. RESULTS: Over the two-year follow-up period, 32.9% and 1.7% of the participants became pre-frail and frail, respectively. After the potential confounders were adjusted (sociodemographic, health behaviors, and health status characteristics), pre-frailty or frailty had a significant longitudinal association with severe anorexia (adjusted odds ratio [AOR], 4.17; 95% confidence interval [CI], 1.05-16.54), moderate anorexia (AOR, 2.31; 95% CI, 1.46-3.64), psychological stress or acute disease (AOR, 2.61; 95% CI, 1.26-5.39), and body mass index (BMI) less than 19 (AOR, 4.11; 95% CI, 1.20-14.04). CONCLUSIONS: Anorexia, psychological stress, acute disease, and low BMI are the most significant longitudinal risk factors for pre-frailty or frailty in older adults. As nutritional risk factors may be preventable or modifiable, it is important to develop interventions targeting the same. Community-based health professionals in health-related fields should recognize and manage these indicators appropriately to prevent frailty among older adults living in the community.

Post-operative recurrence of focal segmental glomerulosclerosis according to pre-transplant treatment after kidney transplantation.

BACKGROUND: Recurrent focal segmental glomerulosclerosis (FSGS) after kidney transplantation (KT) is a serious complication and a significant risk factor for graft failure. However, there is no clear evidence of the effectiveness of pre-transplant treatment using plasmapheresis (PP) or rituximab in preventing post-operative FSGS recurrence after KT. METHODS: This single-center retrospective study included 99 adult patients with biopsy-proven primary FSGS who underwent KT between 2007 and 2018. The patients were divided into the pre-treatment group (N = 53, 53.5%) and no pre-treatment group (N = 46, 46.5%). In the pre-transplant group, prophylactic PP was administered before KT in patients undergoing living donor transplantation and the day after KT in those undergoing deceased donor transplantation. RESULTS: The rate of immediate post-operative recurrence was significantly higher in the no pre-treatment group (16 [34.8%]) than in the pre-treatment group (5 [9.4%]; P = 0.002). There were three cases of graft failure due to recurrent FSGS, all of which were in the no pre-treatment group. After adjusting for possible confounding factors, age (per 10-year increase; OR = 0.61, CI, 0.42-0.90; P = 0.012) and pre-transplant treatment (vs. no pre-transplant treatment; OR = 0.17, CI, 0.05-0.54; P = 0.003) were identified as significant factors associated with FSGS recurrence. The rate of death-censored graft survival was significantly superior in the pretransplant treatment group (P = 0.042). CONCLUSION: Pre-transplant treatment with PP was associated with beneficial effects on preventing FSGS recurrence after KT.

Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time Endoscopy: Model Establishment and Validation Study.

BACKGROUND: Our research group previously established a deep-learning-based clinical decision support system (CDSS) for real-time endoscopy-based detection and classification of gastric neoplasms. However, preneoplastic conditions, such as atrophy and intestinal metaplasia (IM) were not taken into account, and there is no established model that classifies all stages of gastric carcinogenesis. OBJECTIVE: This study aims to build and validate a CDSS for real-time endoscopy for all stages of gastric carcinogenesis, including atrophy and IM. METHODS: A total of 11,868 endoscopic images were used for training and internal testing. The primary outcomes were lesion classification accuracy (6 classes: advanced gastric cancer, early gastric cancer, dysplasia, atrophy, IM, and normal) and atrophy and IM lesion segmentation rates for the segmentation model. The following tests were carried out to validate the performance of lesion classification accuracy: (1) external testing using 1282 images from another institution and (2) evaluation of the classification accuracy of atrophy and IM in real-world procedures in a prospective manner. To estimate the clinical utility, 2 experienced endoscopists were invited to perform a blind test with the same data set. A CDSS was constructed by combining the established 6-class lesion classification model and the preneoplastic lesion segmentation model with the previously established lesion detection model. RESULTS: The overall lesion classification accuracy (95% CI) was 90.3% (89%-91.6%) in the internal test. For the performance validation, the CDSS achieved 85.3% (83.4%-97.2%) overall accuracy. The per-class external test accuracies for atrophy and IM were 95.3% (92.6%-98%) and 89.3% (85.4%-93.2%), respectively. CDSS-assisted endoscopy showed an accuracy of 92.1% (88.8%-95.4%) for atrophy and 95.5% (92%-99%) for IM in the real-world application of 522 consecutive screening endoscopies. There was no significant difference in the overall accuracy between the invited endoscopists and established CDSS in the prospective real-clinic evaluation (P=.23). The CDSS demonstrated a segmentation rate of 93.4% (95% CI 92.4%-94.4%) for atrophy or IM lesion segmentation in the internal testing. CONCLUSIONS: The CDSS achieved high performance in terms of computer-aided diagnosis of all stages of gastric carcinogenesis and demonstrated real-world application potential.

A colorimetric/ratiometric chemosensor based on an aggregation-induced emission strategy for tracing hypochlorite in vitro and in vivo.

Excessive levels of hypochlorite (ClO-) negatively affect environmental and biological systems. Thus, it is essential to develop sensors that can identify ClO- in various systems such as the environment and living organisms. In this study, we report the development and evaluation of a novel aggregation-induced emission (AIE) strategy-based colorimetric and ratiometric fluorescent chemosensor 2,2'-(((1E,1'E)-[2,2'-bithiophene]- 5,5'-diylbis(methanylylidene))bis(hydrazin-1-yl-2-ylidene))bis(N,N,N-trimethyl-2-oxoethan-1-aminium) chloride (BMH-2∙Cl) for detecting ClO-. BMH-2∙Cl enabled highly selective ClO- detection through a color change from yellow to colorless and a fluorescence color change from turquoise to blue in a perfect aqueous solution. BMH-2∙Cl exhibited low limits of detection (2.4 ×10-6 M for colorimetry and 2.9 ×10-7 M for ratiometric fluorescence) for detecting ClO- with a rapid response within 5 s. The detection mechanism for ClO- and an AIE property change of BMH-2∙Cl were demonstrated by 1H NMR titration, ESI-MS, variation of water fraction (fw) and theoretical calculations. In particular, we confirmed not only the practicality of BMH-2∙Cl by using test strips, but also demonstrated the potential for efficient ClO- detection in biological and environmental systems such as real water samples, living zebrafish and bean sprouts.

Waste-Wood-Isolated Cellulose-Based Activated Carbon Paper Electrodes with Graphene Nanoplatelets for Flexible Supercapacitors.

Waste wood, which has a large amount of cellulose fibers, should be transformed into useful materials for addressing environmental and resource problems. Thus, this study analyzed the application of waste wood as supercapacitor electrode material. First, cellulose fibers were extracted from waste wood and mixed with different contents of graphene nanoplatelets (GnPs) in water. Using a facile filtration method, cellulose papers with GnPs were prepared and converted into carbon papers through carbonization and then to porous activated carbon papers containing GnPs (ACP-GnP) through chemical activation processes. For the morphology of ACP-GnP, activated carbon fibers with abundant pores were formed. The increase in the amount of GnPs attached to the fiber surfaces decreased the number of pores. The Brunauer-Emmett-Teller surface areas and specific capacitance of the ACP-GnP electrodes decreased with an increase in the GnP content. However, the galvanostatic charge-discharge curves of ACPs with higher GnP contents gradually changed into triangular and linear shapes, which are associated with the capacitive performance. For example, ACP with 15 wt% GnP had a low mass transfer resistance and high charge delivery of ions, resulting in the specific capacitance value of 267 Fg-1 owing to micropore and mesopore formation during the activation of carbon paper.

The Role of ROR1 in Chemoresistance and EMT in Endometrial Cancer Cells.

Background and Objectives: Receptor tyrosine kinase-like orphan receptor type 1 (ROR1) plays a critical role in embryogenesis and is overexpressed in many malignant cells. These characteristics allow ROR1 to be a potential new target for cancer treatment. The aim of this study was to investigate the role of ROR1 through in vitro experiments in endometrial cancer cell lines. Materials and Methods: ROR1 expression was identified in endometrial cancer cell lines using Western blot and RT-qPCR. The effects of ROR1 on cell proliferation, invasion, migration, and epithelial-mesenchymal transition (EMT) markers were analyzed in two endometrial cancer cell lines (HEC-1 and SNU-539) using either ROR1 silencing or overexpression. Additionally, chemoresistance was examined by identifying MDR1 expression and IC50 level of paclitaxel. Results: The ROR1 protein and mRNA were highly expressed in SNU-539 and HEC-1 cells. High ROR1 expression resulted in a significant increase in cell proliferation, migration, and invasion. It also resulted in a change of EMT markers expression, a decrease in E-cadherin expression, and an increase in Snail expression. Moreover, cells with ROR1 overexpression had a higher IC50 of paclitaxel and significantly increased MDR1 expression. Conclusions: These in vitro experiments showed that ROR1 is responsible for EMT and chemoresistance in endometrial cancer cell lines. Targeting ROR1 can inhibit cancer metastasis and may be a potential treatment method for patients with endometrial cancer who exhibit chemoresistance.

Highly stable semitransparent multilayer graphene/LaVO3vertical-heterostructure photodetectors.

A heterostructure composed of a combination of semi-metallic graphene (Gr) and high-absorption LaVO3is ideal for high-performance translucent photodetector (PD) applications. Here, we present multilayer Gr/LaVO3vertical-heterostructure semitransparent PDs with various layer numbers (Ln). AtLn= 2, the PD shows the best performance with a responsivity (R) of 0.094 A W-1and a specific detectivity (D*) of 7.385 × 107cm Hz1/2W-1at 532 nm. Additionally, the average visible transmittance of the PD is 63%, i.e. it is semitransparent. We increased photocurrent (PC) by approximately 13%, from 0.564 to 0.635µA cm-2by using an Al reflector on the semitransparent PD. The PC of an unencapsulated PD maintains about 86% (from 0.571 to 0.493µA cm-2) of its initial PC value after 2000 h at 25 °C temperature/30% relative humidity, showing good stability. This behavior is superior to that of previously reported graphene-based PDs. These results show that these PDs have great potential for semitransparent optoelectronic applications.

Correction: Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis.

[This corrects the article DOI: 10.2196/33267.].

MicroRNA 148a Suppresses Tuberculous Fibrosis by Targeting NOX4 and POLDIP2.

Extracellular matrix production by pleural mesothelial cells in response to Mycobacterium tuberculosis contributes to tuberculous fibrosis. NOX4 is involved in the pathogenesis of tuberculous fibrosis. In this study, we evaluated whether NOX4 gene-targeting microRNAs showed protective effects in tuberculosis fibrosis. TargetScan prediction software was used to identify candidate microRNAs that bind the 3' UTRs of NOX4, and microRNA-148a (miR-148a) was selected as the best miRNA candidate. A repressed and forced expression assay in Met5A cells was performed to investigate the causal relationship between miR-148a and NOX4. The role of miR-148a in tuberculous pleural fibrosis was studied using a murine model of Mycobacterium bovis bacillus Calmette-Guérin (BCG) pleural infection. Heat-killed M. tuberculosis (HKMT) induces NOX4 and POLDIP2 expression. We demonstrated the inhibitory effect of miR-148a on NOX4 and POLDIP2 expression. The increased expression of miR-148a suppressed HKMT-induced collagen-1A synthesis in PMC cells. In the BCG pleurisy model, miR-148a significantly reduced fibrogenesis and epithelial mesenchymal transition. High levels of miR-148a in tuberculous pleural effusion can be interpreted as a self-limiting homeostatic response. Our data indicate that miR-148a may protect against tuberculous pleural fibrosis by regulating NOX4 and POLDIP2.

The Relationship between Perioperative Blood Transfusion and Postoperative Delirium in Patients Undergoing Spinal Fusion Surgery: Clinical Data Warehouse Analysis.

Background and Objectives: For preventing postoperative delirium (POD), identifying the risk factors is important. However, the relationship between blood transfusion and POD is still controversial. The aim of this study was to identify the risk factors of POD, to evaluate the impact of blood transfusion in developing POD among people undergoing spinal fusion surgery, and to show the effectiveness of big data analytics using a clinical data warehouse (CDW). Materials and Methods: The medical data of patients who underwent spinal fusion surgery were obtained from the CDW of the five hospitals of Hallym University Medical Center. Clinical features, laboratory findings, perioperative variables, and medication history were compared between patients without POD and with POD. Results: 234 of 3967 patients (5.9%) developed POD. In multivariate logistic regression analysis, the risk factors of POD were as follows: Parkinson's disease (OR 5.54, 95% CI 2.15-14.27; p < 0.001), intensive care unit (OR 3.45 95% CI 2.42-4.91; p < 0.001), anti-psychotics drug (OR 3.35 95% CI 1.91-5.89; p < 0.001), old age (≥70 years) (OR 3.08, 95% CI 2.14-4.43; p < 0.001), depression (OR 2.8 95% CI 1.27-6.2; p < 0.001). The intraoperative transfusion (OR 1.1, 95% CI 0.91-1.34; p = 0.582), and the postoperative transfusion (OR 0.91, 95% CI 0.74-1.12; p = 0.379) had no statistically significant effect on the incidence of POD. Conclusions: There was no relationship between perioperative blood transfusion and the incidence of POD in spinal fusion surgery. Big data analytics using a CDW could be helpful for the comprehensive understanding of the risk factors of POD, and for preventing POD in spinal fusion surgery.

Meta-Analysis of Survival Effects of Receptor Tyrosine Kinase-like Orphan Receptor 1 (ROR1).

Background and Objectives: Identification and targeting of membrane proteins in tumor cells is one of the key steps in the development of cancer drugs. The receptor tyrosine kinase-like orphan receptor (ROR) type 1 is a type-I transmembrane protein expressed in various cancer tissues, which is in contrast to its limited expression in normal tissues. These characteristics make ROR1 a candidate target for cancer treatment. This study aimed to identify the prognostic value of ROR1 expression in cancers. Materials and Methods: We conducted a comprehensive systematic search of electronic databases (PubMed) from their inception to September 2021. The included studies assessed the effect of ROR1 on overall survival (OS) and progression-free survival (PFS). Hazard ratios (HR) from collected data were pooled in a meta-analysis using Revman version 5.4 with generic inverse-variance and random effects modeling. Results: A total of fourteen studies were included in the final analysis. ROR1 was associated with worse OS (HR 1.95, 95% confidence interval (CI) 1.50−2.54; p < 0.001) with heterogeneity. The association between poor OS and ROR1 expression was high in endometrial cancer, followed by ovarian cancer, and diffuse large B cell lymphoma. In addition, ROR1 was associated with poor PFS (HR 1.84, 95% CI 1.60−2.10; p < 0.001), but heterogeneity was not statistically significant. In subgroup analysis, high ROR1 expression showed a significantly higher rate of advanced stage or lymph node metastasis. Conclusions: This meta-analysis provides evidence that ROR1 expression is associated with adverse outcome in cancer survival. This result highlights ROR1 as a target for developmental therapeutics in cancers.

Analysis of the tumor characteristics in young age breast cancer patients using collaborative stage data of the Korea Central Cancer Registry.

PURPOSE: This study aimed to evaluate tumor characteristics in young age (20-39 years old) breast cancer (YABC) patients in Korea. MATERIALS AND METHODS: We identified 10,897 breast cancer patients from 2010 to 2015. The data were collected through 10% systematic sampling of the Korea National Cancer Incidence Database (KNCI DB). Tumor size, lymph node status, estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status were collected according to the Collaborative Stage version 2 (CSv2) Data Collection System. RESULTS: Of the 10,897 patients, 1245 (11.4%) were YABC patients. They were found to have larger tumors (T2: 41.6% in 20-39 age group vs 36.4% in 40-49 age group vs 36.5% in 50-59 age group vs 38.4% in ≥ 60 age group; T3: 10.1% vs 7.3% vs 6.5% vs 6.2%, P < .0001), greater rates of lymph node involvement (41.2% vs 32.7% vs 35.7% vs 32.5%, P < .0001), higher tumor grade (High grade: 26.8% vs 19.4% vs 23.5% vs 22.1%, P < .0001), and a larger proportion of triple-negative subtype (18.2% vs 11.0% vs 12.2% vs 13.5%, P < .0001). Compared to the 40-49 age group, breast cancer-related survival (BCRS) rates were worse (91.74% vs 95.04%, P < .0001), and the characteristics of YABC patients were associated with higher risk of death from breast cancer. CONCLUSION: YABC patients have more aggressive tumor characteristics and worse survival rates. Therefore, we need to identify high-risk groups among YABC patients and support active surveillance in them. These findings from a national cohort provide important information for establishing a national cancer care strategy to manage YABC patients.

Whole blood RNA sequencing reveals a differential transcriptomic profile associated with cervical insufficiency: a pilot study.

BACKGROUND: The uterine cervix is a mechanical and immunological barrier against ascending infection during pregnancy. Cervical insufficiency (CI), a painless cervical dilation that occurs in the mid-trimester, is an important cause of extremely preterm birth. We hypothesized that women with CI have a differential transcriptomic profile. Therefore, we compared the transcriptomic profile of peripheral blood in women with CI and that of controls. METHODS: RNA sequencing was used to generate the global gene expression profiles of 11 women with CI and 4 controls, and differential expression analysis was performed to identify genes showing significant expression changes between the CI (n = 11) and control (n = 4) groups as well as between the CI-preterm (n = 7) and CI-term (n = 4) groups. Gene set enrichment was assessed in terms of Gene Ontology processes, and a subset of differentially expressed genes in CI was validated in a different sample-set by qRT-PCR and ELISA. RESULTS: Thirty genes were differentially expressed between the CI and control groups. Differentially upregulated genes in the CI group included neutrophil-mediated immunity-associated (DEFA3 and ELANE) and bicarbonate transport-related genes. The serum concentration of alpha defensin 3 was significantly higher in women with CI than in controls (P = 0.014). Analysis of differential gene expression according to pregnancy outcomes revealed 338 differentially expressed genes between the CI-term and CI-preterm groups. Immune and defense response to organism-associated genes and influenza A and NOD-like receptor signaling pathways were upregulated in the CI-term group. CONCLUSIONS: Our results revealed significant differences in the whole blood transcriptomic profiles of women with CI compared to those of controls. Different immune responses in women with CI may affect pregnancy outcomes.

Computer-aided diagnosis of esophageal cancer and neoplasms in endoscopic images: a systematic review and meta-analysis of diagnostic test accuracy.

BACKGROUND AND AIMS: Diagnosis of esophageal cancer or precursor lesions by endoscopic imaging depends on endoscopist expertise and is inevitably subject to interobserver variability. Studies on computer-aided diagnosis (CAD) using deep learning or machine learning are on the increase. However, studies with small sample sizes are limited by inadequate statistical strength. Here, we used a meta-analysis to evaluate the diagnostic test accuracy (DTA) of CAD algorithms of esophageal cancers or neoplasms using endoscopic images. METHODS: Core databases were searched for studies based on endoscopic imaging using CAD algorithms for the diagnosis of esophageal cancer or neoplasms and presenting data on diagnostic performance, and a systematic review and DTA meta-analysis were performed. RESULTS: Overall, 21 and 19 studies were included in the systematic review and DTA meta-analysis, respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD algorithms for the diagnosis of esophageal cancer or neoplasms in the image-based analysis were 0.97 (95% confidence interval [CI], 0.95-0.99), 0.94 (95% CI, 0.89-0.96), 0.88 (95% CI, 0.76-0.94), and 108 (95% CI, 43-273), respectively. Meta-regression showed no heterogeneity, and no publication bias was detected. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD algorithms for the diagnosis of esophageal cancer invasion depth were 0.96 (95% CI, 0.86-0.99), 0.90 (95% CI, 0.88-0.92), 0.88 (95% CI, 0.83-0.91), and 138 (95% CI, 12-1569), respectively. CONCLUSIONS: CAD algorithms showed high accuracy for the automatic endoscopic diagnosis of esophageal cancer and neoplasms. The limitation of a lack in performance in external validation and clinical applications should be overcome.

Development and validation of a difficult laryngoscopy prediction model using machine learning of neck circumference and thyromental height.

BACKGROUND: Predicting difficult airway is challengeable in patients with limited airway evaluation. The aim of this study is to develop and validate a model that predicts difficult laryngoscopy by machine learning of neck circumference and thyromental height as predictors that can be used even for patients with limited airway evaluation. METHODS: Variables for prediction of difficulty laryngoscopy included age, sex, height, weight, body mass index, neck circumference, and thyromental distance. Difficult laryngoscopy was defined as Grade 3 and 4 by the Cormack-Lehane classification. The preanesthesia and anesthesia data of 1677 patients who had undergone general anesthesia at a single center were collected. The data set was randomly stratified into a training set (80%) and a test set (20%), with equal distribution of difficulty laryngoscopy. The training data sets were trained with five algorithms (logistic regression, multilayer perceptron, random forest, extreme gradient boosting, and light gradient boosting machine). The prediction models were validated through a test set. RESULTS: The model's performance using random forest was best (area under receiver operating characteristic curve = 0.79 [95% confidence interval: 0.72-0.86], area under precision-recall curve = 0.32 [95% confidence interval: 0.27-0.37]). CONCLUSIONS: Machine learning can predict difficult laryngoscopy through a combination of several predictors including neck circumference and thyromental height. The performance of the model can be improved with more data, a new variable and combination of models.

Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis.

BACKGROUND: Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models. OBJECTIVE: To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images. METHODS: We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS: Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected. CONCLUSIONS: CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.

Computer-Aided Diagnosis of Diminutive Colorectal Polyps in Endoscopic Images: Systematic Review and Meta-analysis of Diagnostic Test Accuracy.

BACKGROUND: Most colorectal polyps are diminutive and benign, especially those in the rectosigmoid colon, and the resection of these polyps is not cost-effective. Advancements in image-enhanced endoscopy have improved the optical prediction of colorectal polyp histology. However, subjective interpretability and inter- and intraobserver variability prohibits widespread implementation. The number of studies on computer-aided diagnosis (CAD) is increasing; however, their small sample sizes limit statistical significance. OBJECTIVE: This review aims to evaluate the diagnostic test accuracy of CAD models in predicting the histology of diminutive colorectal polyps by using endoscopic images. METHODS: Core databases were searched for studies that were based on endoscopic imaging, used CAD models for the histologic diagnosis of diminutive colorectal polyps, and presented data on diagnostic performance. A systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS: Overall, 13 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of diminutive colorectal polyps (adenomatous or neoplastic vs nonadenomatous or nonneoplastic) were 0.96 (95% CI 0.93-0.97), 0.93 (95% CI 0.91-0.95), 0.87 (95% CI 0.76-0.93), and 87 (95% CI 38-201), respectively. The meta-regression analysis showed no heterogeneity, and no publication bias was detected. Subgroup analyses showed robust results. The negative predictive value of CAD models for the diagnosis of adenomatous polyps in the rectosigmoid colon was 0.96 (95% CI 0.95-0.97), and this value exceeded the threshold of the diagnosis and leave strategy. CONCLUSIONS: CAD models show potential for the optical histological diagnosis of diminutive colorectal polyps via the use of endoscopic images. TRIAL REGISTRATION: PROSPERO CRD42021232189; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=232189.