This study reviews the recent progress of artificial intelligence for colonoscopy from detection to diagnosis. The source of data was 27 original studies in PubMed. The search terms were “colonoscopy” (title) and “deep learning” (abstract). The eligibility criteria were: (1) the dependent variable of gastrointestinal disease; (2) the interventions of deep learning for classification, detection and/or segmentation for colonoscopy; (3) the outcomes of accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1, intersection of union (IOU), Dice and/or inference frames per second (FPS); (3) the publication year of 2021 or later; (4) the publication language of English. Based on the results of this study, different deep learning methods would be appropriate for different tasks for colonoscopy, e.g., Efficientnet with neural architecture search (AUC 99.8%) in the case of classification, You Only Look Once with the instance tracking head (F1 96.3%) in the case of detection, and Unet with dense-dilation-residual blocks (Dice 97.3%) in the case of segmentation. Their performance measures reported varied within 74.0–95.0% for accuracy, 60.0–93.0% for sensitivity, 60.0–100.0% for specificity, 71.0–99.8% for the AUC, 70.1–93.3% for precision, 81.0–96.3% for F1, 57.2–89.5% for the IOU, 75.1–97.3% for Dice and 66–182 for FPS. In conclusion, artificial intelligence provides an effective, non-invasive decision support system for colonoscopy from detection to diagnosis.

Objective: This study employs machine learning and population-based data to examine major factors of antidepressant medication including nitrogen dioxides (NO2) seasonality. Methods: Retrospective cohort data came from Korea National Health Insurance Service claims data for 43,251 participants with the age of 15–79 years, residence in the same districts of Seoul and no history of antidepressant medication during 2002–2012. The dependent variable was antidepressant-free months during 2013–2015 and the 103 independent variables for 2012 or 2015 were considered, e.g., particulate matter less than 2.5 micrometer in diameter (PM2.5), PM10, NO2, ozone (O3), sulphur dioxide (SO2) and carbon monoxide (CO) in each of 12 months in 2015. Results: It was found that the Cox hazard ratios of NO2 were statistically significant and registered values larger than 10 for every three months: March, June–July, October, and December. Based on random forest variable importance and Cox hazard ratios in brackets, indeed, the top 20 factors of antidepressant medication included age (0.0041 [1.69–2.25]), migraine and sleep disorder (0.0029 [1.82]), liver disease (0.0017 [1.33–1.34]), exercise (0.0014), thyroid disease (0.0013), cardiovascular disease (0.0013 [1.20]), asthma (0.0008 [1.19–1.20]), September NO2 (0.0008 [0.01]), alcohol consumption (0.0008 [1.31–1.32]), gender - woman (0.0007 [1.80–1.81]), July NO2 (0.0007 [14.93]), July PM10 (0.0007), the proportion of the married (0.0005), January PM2.5 (0.0004), September PM2.5 (0.0004), chronic obstructive pulmonary disease (0.0004), economic satisfaction (0.0004), January PM10 (0.0003), residents in welfare facilities per 1,000 (0.0003 [0.97]), and October NO2 (0.0003). Conclusion Antidepressant medication has strong associations with neighborhood conditions including NO2 seasonality and welfare support.

Background: To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. Methods: Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. Results: In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. Conclusion Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.

Background: To analyze the factors associated with women's vasomotor symptoms (VMS) using machine learning. Methods: Data on 3,298 women, aged 40–80 years, who attended their general health check-up from January 2010 to December 2012 were obtained from Korea University Anam Hospital in Seoul, Korea. Five machine learning methods were applied and compared for the prediction of VMS, measured by the Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying the major factors associated with VMS. Results: In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two, and three hidden layers (1.5576, 1.5184, and 1.5833, respectively). Based on the variable importance from the random forest, the most important factors associated with VMS were age, menopause age, thyroid-stimulating hormone, and monocyte, triglyceride, gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19-9, C-reactive protein, and low-density lipoprotein cholesterol levels. Indeed, the following variables were ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in 1 second, height, homeostatic model assessment for insulin resistance, and carcinoembryonic antigen. Conclusion Machine learning provides an invaluable decision support system for the prediction of VMS. For managing VMS, comprehensive consideration is needed regarding thyroid function, lipid profile, liver function, inflammation markers, insulin resistance, monocyte count, cancer antigens, and lung function.

Background: This study used machine learning and population data for testing the associations of preterm birth with gastroesophageal reflux disease (GERD) and periodontitis. Methods: Retrospective cohort data came from Korea National Health Insurance Service claims data for all women who aged 25–40 years and gave births for the first time as singleton pregnancy during 2015–2017 (405,586 women). The dependent variable was preterm birth during 2015–2017 and the independent variables were GERD (coded as no vs. yes) for each of the years 2002–2014, periodontitis (coded as no vs. yes) for each of the years 2002–2014, age (year) in 2014, socioeconomic status in 2014 measured by an insurance fee, and region (city) (coded as no vs. yes) in 2014. Random forest variable importance was adopted for finding main predictors of preterm birth and testing its associations with GERD and periodontitis. Results: Based on random forest variable importance, main predictors of preterm birth during 2015–2017 were socioeconomic status in 2014, age in 2014, GERD for the years 2012, 2014, 2010, 2013, 2007 and 2009, region (city) in 2014 and GERD for the year 2006. The importance rankings of periodontitis were relatively low. Conclusion Preterm birth has a stronger association with GERD than with periodontitis. For the prevention of preterm birth, preventive measures for GERD would be essential together with the improvement of socioeconomic status for pregnant women. Especially, it would be vital to promote active counseling for general GERD symptoms (neglected by pregnant women).

Background: Periodontitis is reported to be associated with preterm birth (spontaneous preterm labor and birth). Gastroesophageal reflux disease (GERD) is common during pregnancy and is expected to be related to periodontitis. However, little research has been done on the association among preterm birth, GERD and periodontitis. This study uses popular machine learning methods for analyzing preterm birth, GERD and periodontitis. Methods: Data came from Anam Hospital in Seoul, Korea, with 731 obstetric patients during January 5, 1995 - August 28, 2018. Six machine learning methods were applied and compared for the prediction of preterm birth. Variable importance, the effect of a variable on model performance, was used for identifying major determinants of preterm birth. Results: In terms of accuracy, the random forest (0.8681) was similar with logistic regression (0.8736). Based on variable importance from the random forest, major determinants of preterm birth are delivery and pregestational body mass indexes (BMI) (0.1426 and 0.1215), age (0.1211), parity (0.0868), predelivery systolic and diastolic blood pressure (0.0809 and 0.0763), twin (0.0476), education (0.0332) as well as infant sex (0.0331), prior preterm birth (0.0290), progesterone medication history (0.0279), upper gastrointestinal tract symptom (0.0274), GERD (0.0242), Helicobacter pylori (0.0151), region (0.0139), calcium-channel-blocker medication history (0.0135) and gestational diabetes mellitus (0.0130). Periodontitis ranked 22nd (0.0084). Conclusion GERD is more important than periodontitis for predicting and preventing preterm birth. For preventing preterm birth, preventive measures for hypertension, GERD and diabetes mellitus would be needed alongside the promotion of effective BMI management and appropriate progesterone and calcium-channel-blocker medications.

PURPOSE: The objective of the present study was to predict the gestational age at preterm birth using artificial neural networks for singleton pregnancy. METHODS: Artificial neural networks (ANNs) were used as a tool for the prediction of gestational age at birth. ANNs trained using obstetrical data of 125 cases, including 56 preterm and 69 non-preterm deliveries. Using a 36-variable obstetrical input set, gestational weeks at delivery were predicted by 89 cases of training sets, 18 cases of validating sets, and 18 cases of testing sets (total: 125 cases). After training, we validated the model by another 12 cases containing data of preterm deliveries. RESULTS: To define the accuracy of the developed model, we confirmed the correlation coefficient (R) and mean square error of the model. For validating sets, the correlation coefficient was 0.839, but R of testing sets was 0.892, and R of total 125 cases was 0.959. The neural networks were well trained, and the model predictions were relatively good. Furthermore, the model was validated with another dataset of 12 cases, and the correlation coefficient was 0.709. The error days were 11.58±13.73. CONCLUSION: In the present study, we trained the ANNs and developed the predictive model for gestational age at delivery. Although the prediction for gestational age at birth in singleton preterm birth was feasible, further studies with larger data, including detailed risk variables of preterm birth and other obstetrical outcomes, are needed.
Dataset ; Gestational Age ; Parturition ; Pregnancy ; Premature Birth

The purpose of this study was to compare the accuracy of the working models fabricated by the subtractive and additive processing methods based on the 3-dimensional reconstruction model. A total of 20 models were fabricated with subtractive processing method from polymethyl methacrylate (PMMA) blocks using the stereolithography (STL) file of master gypsum model and another 20 models were fabricated with additive processing method using 3D printer with 0.025 mm of a layer thickness. The CAD-reference-model (CRM) and CAD-test-model (CTM) were superimposed by a software for accuracy analysis (Geomagic Qualify 13), where the STL files were transformed to point cloud data and the surface data (CRM and CTM) were subjected to initial alignment and followed by re-alignmented according to best-fit superimposition. The distances between surface data and all points, in this process, were converted to the root mean square (RMS) and averaged. In the experimental results, It was shown that the accuracy is higher in work model fabricated by additive processing method compared to one fabricated by subtractive one (p < 0.05). In addition, it is considered that the working model fabricated by subtractive processing method is to be clinically applicable by improving the improper reproducibility of the tooth surface and depressed area.
Calcium Sulfate ; Methods ; Polymethyl Methacrylate ; Printing, Three-Dimensional ; Tooth

BACKGROUND: Penile cancer is a rare malignancy associated with high rates of mortality and morbidity. Currently, the efficacy of adjuvant treatment (AT), including radiotherapy and chemotherapy, for penile cancer remains unclear. Therefore, we investigated the prognostic factors for treatment outcomes and the efficacy of AT in consecutive patients who underwent penectomy for penile cancer at multiple Korean institutions between 1999 and 2013. METHODS: AT was defined as the administration of chemotherapy, radiotherapy, or both within 12 months after initial treatment. All patients were divided into two groups according to the AT status. RESULTS: Forty-three patients (median age 67.0 years) with a median follow-up after penectomy of 26.4 (interquartile range: 12.0–62.8) months were enrolled. Patients with AT had a significantly higher pathologic stage. However, no differences in age, histologic grade, or type of surgery were identified according to the presence of AT. The 3- and 5-year cancer-specific survival (CSS) rates were 79.0% and 33.0%, respectively. In a multivariate analysis, American Joint Committee on Cancer (AJCC) stage ≥ III disease was an independent predictor of CSS and recurrence-free survival (RFS). However, AT was not associated with CSS and RFS. The type of primary surgical treatment and inguinal lymph node dissection at diagnosis were also not significantly associated with overall survival, CSS, or RFS. CONCLUSION: AJCC stage ≥ III disease, which mainly reflects lymph node positivity, is a significant prognosticator in patients with penile cancer. By contrast, AT does not seem to affect CSS and RFS.
Chemotherapy, Adjuvant ; Diagnosis ; Drug Therapy ; Follow-Up Studies ; Humans ; Joints ; Lymph Node Excision ; Lymph Nodes ; Male ; Mortality ; Multivariate Analysis ; Penile Neoplasms* ; Prognosis ; Radiotherapy ; Radiotherapy, Adjuvant

PURPOSE: The aim of study was to provide suggestions for prioritizing research in effort to reduce cancer burden in Korea based on a comprehensive analysis of cancer burden and Delphi consensus among cancer experts. MATERIALS AND METHODS: Twenty research plans covering 10 topics were selected based on an assessment of the literature, and e-mail surveys were analyzed using a two-round modified Delphi method. Thirty-four out of 79 experts were selected from four organizations to participate in round one, and 21 experts among them had completed round two. Each item had two questions; one regarding the agreement of the topic as a priority item to reduce cancer burden, and the other about the importance of the item on a nine-point scale. A consensus was defined to be an average lower coefficient of variation with less than 30% in importance. RESULTS: Seven plans that satisfied the three criteria were selected as priority research plans for reducing cancer burden. These plans are "research into advanced clinical guidelines for thyroid cancer given the current issue with over-diagnosis," "research into smoking management plans through price and non-price cigarette policy initiatives," "research into ways to measure the quality of cancer care," "research on policy development to expand hospice care," "research into the spread and management of Helicobacter pylori," "research on palliative care in a clinical setting," and "research into alternative mammography methods to increase the accuracy of breast cancer screenings." CONCLUSION: The seven plans identified in this study should be prioritized to reduce the burden of cancer in Korea. We suggest that policy makers and administrators study and invest significant effort in these plans.
Administrative Personnel ; Breast Neoplasms ; Consensus ; Delphi Technique ; Early Detection of Cancer ; Electronic Mail ; Health Policy* ; Helicobacter ; Helicobacter pylori ; Hospices ; Humans ; Korea ; Mammography ; Palliative Care ; Policy Making ; Smoke ; Smoking ; Thyroid Neoplasms ; Tobacco Products