Artificial intelligence in colonoscopy: from detection to diagnosis.

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.

Explainable Model Using Shapley Additive Explanations Approach on Wound Infection after Wide Soft Tissue Sarcoma Resection: "Big Data" Analysis Based on Health Insurance Review and Assessment Service Hub.

Background and Objectives: Soft tissue sarcomas represent a heterogeneous group of malignant mesenchymal tissues. Despite their low prevalence, soft tissue sarcomas present clinical challenges for orthopedic surgeons owing to their aggressive nature, and perioperative wound infections. However, the low prevalence of soft tissue sarcomas has hindered the availability of large-scale studies. This study aimed to analyze wound infections after wide resection in patients with soft tissue sarcomas by employing big data analytics from the Hub of the Health Insurance Review and Assessment Service (HIRA). Materials and Methods: Patients who underwent wide excision of soft tissue sarcomas between 2010 and 2021 were included. Data were collected from the HIRA database of approximately 50 million individuals' information in the Republic of Korea. The data collected included demographic information, diagnoses, prescribed medications, and surgical procedures. Random forest has been used to analyze the major associated determinants. A total of 10,906 observations with complete data were divided into training and validation sets in an 80:20 ratio (8773 vs. 2193 cases). Random forest permutation importance was employed to identify the major predictors of infection and Shapley Additive Explanations (SHAP) values were derived to analyze the directions of associations with predictors. Results: A total of 10,969 patients who underwent wide excision of soft tissue sarcomas were included. Among the study population, 886 (8.08%) patients had post-operative infections requiring surgery. The overall transfusion rate for wide excision was 20.67% (2267 patients). Risk factors among the comorbidities of each patient with wound infection were analyzed and dependence plots of individual features were visualized. The transfusion dependence plot reveals a distinctive pattern, with SHAP values displaying a negative trend for individuals without blood transfusions and a positive trend for those who received blood transfusions, emphasizing the substantial impact of blood transfusions on the likelihood of wound infection. Conclusions: Using the machine learning random forest model and the SHAP values, the perioperative transfusion, male sex, old age, and low SES were important features of wound infection in soft-tissue sarcoma patients.

Explainable artificial intelligence for predicting red blood cell transfusion in geriatric patients undergoing hip arthroplasty: Machine learning analysis using national health insurance data.

This study uses machine learning and population data to analyze major determinants of blood transfusion among patients with hip arthroplasty. Retrospective cohort data came from Korea National Health Insurance Service claims data for 19,110 patients aged 65 years or more with hip arthroplasty in 2019. The dependent variable was blood transfusion (yes vs no) in 2019 and its 31 predictors were included. Random forest variable importance and Shapley Additive Explanations were used for identifying major predictors and the directions of their associations with blood transfusion. The random forest registered the area under the curve of 73.6%. Based on random forest variable importance, the top-10 predictors were anemia (0.25), tranexamic acid (0.17), age (0.16), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.04), dementia (0.03), iron (0.02), and congestive heart failure (0.02). These predictors were followed by their top-20 counterparts including cardiovascular disease, statin, chronic obstructive pulmonary disease, diabetes mellitus, chronic kidney disease, peripheral vascular disease, liver disease, solid tumor, myocardial infarction and hypertension. In terms of max Shapley Additive Explanations values, these associations were positive, e.g., anemia (0.09), tranexamic acid (0.07), age (0.09), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.02), dementia (0.03), iron (0.04), and congestive heart failure (0.03). For example, the inclusion of anemia, age, tranexamic acid or spinal anesthesia into the random forest will increase the probability of blood transfusion among patients with hip arthroplasty by 9%, 7%, 9% or 5%. Machine learning is an effective prediction model for blood transfusion among patients with hip arthroplasty. The high-risk group with anemia, age and comorbid conditions need to be treated with tranexamic acid, iron and/or other appropriate interventions.

Explainable artificial intelligence on life satisfaction, diabetes mellitus and its comorbid condition.

This study uses artificial intelligence for testing (1) whether the comorbidity of diabetes and its comorbid condition is very strong in the middle-aged or old (hypothesis 1) and (2) whether major determinants of the comorbidity are similar for different pairs of diabetes and its comorbid condition (hypothesis 2). Three pairs are considered, diabetes-cancer, diabetes-heart disease and diabetes-mental disease. Data came from the Korean Longitudinal Study of Ageing (2016-2018), with 5527 participants aged 56 or more. The evaluation of the hypotheses were based on (1) whether diabetes and its comorbid condition in 2016 were top-5 determinants of the comorbidity in 2018 (hypothesis 1) and (2) whether top-10 determinants of the comorbidity in 2018 were similar for different pairs of diabetes and its comorbid condition (hypothesis 2). Based on random forest variable importance, diabetes and its comorbid condition in 2016 were top-2 determinants of the comorbidity in 2018. Top-10 determinants of the comorbidity in 2018 were the same for different pairs of diabetes and its comorbid condition: body mass index, income, age, life satisfaction-health, life satisfaction-economic, life satisfaction-overall, subjective health and children alive in 2016. In terms of SHAP values, the probability of the comorbidity is expected to decrease by 0.02-0.03 in case life satisfaction overall is included to the model. This study supports the two hypotheses, highlighting the importance of preventive measures for body mass index, socioeconomic status, life satisfaction and family support to manage diabetes and its comorbid condition.

Associations of Preterm Birth with Dental and Gastrointestinal Diseases: Machine Learning Analysis Using National Health Insurance Data.

BACKGROUND: This study uses machine learning with large-scale population data to assess the associations of preterm birth (PTB) with dental and gastrointestinal diseases. METHODS: Population-based retrospective cohort data came from Korea National Health Insurance claims for 124,606 primiparous women aged 25-40 and delivered in 2017. The 186 independent variables included demographic/socioeconomic determinants, disease information, and medication history. Machine learning analysis was used to establish the prediction model of PTB. Random forest variable importance was used for identifying major determinants of PTB and testing its associations with dental and gastrointestinal diseases, medication history, and socioeconomic status. RESULTS: The random forest with oversampling data registered an accuracy of 84.03, and the areas under the receiver-operating-characteristic curves with the range of 84.03-84.04. Based on random forest variable importance with oversampling data, PTB has strong associations with socioeconomic status (0.284), age (0.214), year 2014 gastroesophageal reflux disease (GERD) (0.026), year 2015 GERD (0.026), year 2013 GERD (0.024), progesterone (0.024), year 2012 GERD (0.023), year 2011 GERD (0.021), tricyclic antidepressant (0.020) and year 2016 infertility (0.019). For example, the accuracy of the model will decrease by 28.4%, 2.6%, or 1.9% if the values of socioeconomic status, year 2014 GERD, or year 2016 infertility are randomly permutated (or shuffled). CONCLUSION: By using machine learning, we established a valid prediction model for PTB. PTB has strong associations with GERD and infertility. Pregnant women need close surveillance for gastrointestinal and obstetric risks at the same time.

Artificial intelligence for predicting survival following deceased donor liver transplantation: Retrospective multi-center study.

BACKGROUND: Previous studies have indicated that the model for end-stage liver disease (MELD) score may fail to predict post-transplantation patient survival. Similarly, other scores (donor MELD score, balance of risk score) that have been developed to predict transplant outcomes have not gained widespread use. These scores are typically derived using linear statistical models. This study aimed to compare the performance of traditional statistical models with machine learning approaches for predicting survival following liver transplantation. MATERIALS AND METHODS: Data were obtained from 785 deceased donor liver transplant recipients enrolled in the Korean Organ Transplant Registry (2014-2019). Five machine learning methods (random forest, artificial neural networks, decision tree, naïve Bayes, and support vector machine) and four traditional statistical models (Cox regression, MELD score, donor MELD score and balance of risk score) were compared to predict survival. RESULTS: Among the machine learning methods, the random forest yielded the highest area under the receiver operating characteristic curve (AUC-ROC) values (1-month = 0.80; 3-month = 0.85; and 12-month = 0.81) for predicting survival. The AUC-ROC values of the Cox regression analysis were 0.75, 0.86, and 0.77 for 1-month, 3-month, and 12-month post-transplant survival, respectively. However, the AUC-ROC values of the MELD, donor MELD, and balance of risk scores were all below 0.70. Based on the variable importance of the random forest analysis in this study, the major predictors associated with survival were cold ischemia time, donor ICU stay, recipient weight, recipient BMI, recipient age, recipient INR, and recipient albumin level. As with the Cox regression analysis, donor ICU stay, donor bilirubin level, BAR score, and recipient albumin levels were also important factors associated with post-transplant survival in the RF model. The coefficients of these variables were also statistically significant in the Cox model (p < 0.05). The SHAP ranges for selected predictors for the 12-month survival were (-0.02,0.10) for recipient albumin, (-0.05,0.07) for donor bilirubin and (-0.02,0.25) for recipient height. Surprisingly, although not statistically significant in the Cox model, recipient weight, recipient BMI, recipient age, or recipient INR were important factors in our random forest model for predicting post-transplantation survival. CONCLUSION: Machine learning algorithms such as the random forest were superior to conventional Cox regression and previously reported survival scores for predicting 1-month, 3-month, and 12-month survival following liver transplantation. Therefore, artificial intelligence may have significant potential in aiding clinical decision-making during liver transplantation, including matching donors and recipients.

Association of Preterm Birth with Inflammatory Bowel Disease and Salivary Gland Disease: Machine Learning Analysis Using National Health Insurance Data.

This study employs machine learning and population data for testing the associations of preterm birth with inflammatory bowel disease (IBD), salivary gland disease, socioeconomic status and medication history, including proton pump inhibitors. The source of population-based retrospective cohort data was the Korea National Health Insurance Service claims data for all women aged 25-40 years and who experience their first childbirths as singleton pregnancy during 2015 to 2017 (402,092 women). These participants were divided into the Ulcerative Colitis (UC) Group (1782 women), the Crohn Group (1954 women) and the Non-IBD Group (398,219 women). For each group, the dependent variable was preterm birth during 2015-2017, and 51 independent variables were included. Random forest variable importance was employed for investigating the main factors of preterm birth and testing its associations with salivary gland disease, socioeconomic status and medication history for each group. The proportion of preterm birth was higher for the UC Group and the Non-IBD Group than for the Crohn Group: 7.86%, 7.17% vs. 6.76%. Based on random forest variable importance, salivary gland disease was a top 10 determinant for the prediction of preterm birth for the UC Group, but this was not the case for the Crohn Group or the Non-IBD Group. The top 5 variables of preterm birth for the UC Group during 2015-2017 were socioeconomic status (8.58), age (8.00), proton pump inhibitors (2.35), progesterone (2.13) and salivary gland disease in 2014 (1.72). In conclusion, preterm birth has strong associations with ulcerative colitis, salivary gland disease, socioeconomic status and medication history including proton pump inhibitors.

Machine learning on thyroid disease: a review.

This study reviews the recent progress of machine learning for the early diagnosis of thyroid disease. Based on the results of this review, different machine learning methods would be appropriate for different types of data for the early diagnosis of thyroid disease: (1) the random forest and gradient boosting in the case of numeric data; (2) the random forest in the case of genomic data; (3) the random forest and the ensemble in the case of radiomic data; and (4) the random forest in the case of ultrasound data. Their performance measures varied within 64.3-99.5 for accuracy, 66.8-90.1 for sensitivity, 61.8-85.5 for specificity, and 64.0-96.9 for the area under the receiver operating characteristic curve. According to the findings of this review, indeed, the following attributes would be important variables for the early diagnosis of thyroid disease: clinical stage, marital status, histological type, age, nerve injury symptom, economic income, surgery type [the quality of life 3 months after thyroid cancer surgery]; tumor diameter, symptoms, extrathyroidal extension [the local recurrence of differentiated thyroid carcinoma]; RNA feasures including ADD3-AS1 (downregulation), MIR100HG (downregulation), FAM95C (downregulation), MORC2-AS1 (downregulation), LINC00506 (downregulation), ST7-AS1 (downregulation), LOC339059 (downregulation), MIR181A2HG (upregulation), FAM181A-AS1 (downregulation), LBX2-AS1 (upregulation), BLACAT1 (upregulation), hsa-miR-9-5p (downregulation), hsa-miR-146b-3p (upregulation), hsa-miR-199b-5p (downregulation), hsa-miR-4709-3p (upregulation), hsa-miR-34a-5p (upregulation), hsa-miR-214-3p (downregulation) [papillary thyroid carcinoma]; gut microbiota RNA features such as veillonella, paraprevotella, neisseria, rheinheimera [hypothyroidism]; and ultrasound features, i.e., wreath-shaped feature, micro-calcification, strain ratio [the malignancy of thyroid nodules].

Artificial intelligence approaches to the determinants of women's vaginal dryness using general hospital data.

The aim of this study is to analyse the determinants of women's vaginal dryness using machine learning. Data came from Korea University Anam Hospital in Seoul, Republic of Korea, with 3298 women, aged 40-80 years, who attended their general health check from January 2010 to December 2012. Five machine learning methods were applied and compared for the prediction of vaginal dryness, measured by a Menopause Rating Scale. Random forest variable importance, a performance gap between a complete model and a model excluding a certain variable, was adopted for identifying major determinants of vaginal dryness. In terms of the mean squared error, the random forest (1.0597) was much better than linear regression (17.9043) and artificial neural networks with one, two and three hidden layers (1.7452, 1.7148 and 1.7736, respectively). Based on random forest variable importance, the top-10 determinants of vaginal dryness were menopause age, age, menopause, height, thyroid stimulating hormone, neutrophils, years since menopause, lymphocytes, alkaline phosphatase and blood urea nitrogen. In addition, its top-20 determinants were peak expiratory flow rate, low-density lipoprotein cholesterol, white blood cells, monocytes, cancer antigen 19-9, creatinine, eosinophils, total cholesterol, triglyceride and amylase. Machine learning presents a great decision support system for the prediction of vaginal dryness. For preventing vaginal dryness, preventive measures would be needed regarding early menopause, the thyroid function and systematic inflammation.Impact StatementWhat is already known on this subject? Only a few studies have investigated the risk factors of vaginal dryness in middle-aged women. More research is to be done for finding its various risk factors, identifying its major risk groups and drawing its effective clinical implications.What do the results of this study add? This study is the first machine-learning study to predict women's vaginal dryness and analyse their determinants. The random forest could discuss which factors are more important for the prediction of vaginal dryness. Based on random forest variable importance, menopause age was the most important determinant of vaginal dryness and their association was discovered to be negative in this study. Vaginal dryness was closely associated with the height, rather than the body weight or body mass index. The importance rankings of blood conditions related to systematic inflammation were within the top-20 in this study: neutrophils, lymphocytes, white blood cells, monocytes and eosinophils.What are the implications of these findings for clinical practice and/or further research? Machine learning presents a great decision support system for the prediction of vaginal dryness. For preventing vaginal dryness, preventive measures would be needed regarding early menopause and systematic inflammation.

Association of preterm birth with medications: machine learning analysis using national health insurance data.

PURPOSE: To use machine learning and population data for testing the associations of preterm birth with socioeconomic status, gastroesophageal reflux disease (GERD) and medication history including proton pump inhibitors, sleeping pills and antidepressants. METHODS: Population-based 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 65 independent variables were included (demographic/socioeconomic determinants, disease information, medication history, obstetric information). Random forest variable importance (outcome measure) was used for identifying major determinants of preterm birth and testing its associations with socioeconomic status, GERD and medication history including proton pump inhibitors, sleeping pills and antidepressants. RESULTS: Based on random forest variable importance, major determinants of preterm birth during 2015-2017 were socioeconomic status (645.34), age (556.86), proton pump inhibitors (107.61), GERD for the years 2014, 2012 and 2013 (106.78, 105.87 and 104.96), sleeping pills (97.23), GERD for the years 2010, 2011 and 2009 (95.56, 94.84 and 93.81), and antidepressants (90.13). CONCLUSION: Preterm birth has strong associations with low socioeconomic status, GERD and medication history such as proton pump inhibitors, sleeping pills and antidepressants. For preventing preterm birth, appropriate medication would be needed alongside preventive measures for GERD and the promotion of socioeconomic status for pregnant women.

ORIGINAL ARTICLE: Associations of antidepressant medication with its various predictors including particulate matter: Machine learning analysis using national health insurance data.

This study uses machine learning and population-based data to analyze major determinants of antidepressant medication including the concentration of particulate matter under 2.5 µm (PM2.5). Retrospective cohort data came from Korea National Health Insurance Service claims data for 43,251 participants, who were aged 15-79 years, lived in the same districts of Seoul and had no history of antidepressant medication during 2002-2012. The dependent variable was antidepressant-free months during 2013-2015 and the 30 independent variables for 2012 were included (demographic/socioeconomic information, health information, district-level information including PM2.5). Random forest variable importance, the contribution of a variable for the performance of the model, was used for identifying major predictors of antidepressant-free months. Based on random forest variable importance, the top 15 determinants of antidepressant medication during 2013-2015 included cardiovascular disease (0.0054), age (0.0047), household income (0.0037), gender (0.0027), the district-level proportion of recipients of national basic living security program benefits (0.0019), district-level social satisfaction (0.0013), diabetes mellitus (0.0012), January 2012 PM2.5 (0.0011), district-level street ratio (0.0010), drinker (0.0009), chronic obstructive pulmonary disease (0.0008), district-level economic satisfaction (0.0006), exercise (0.0005), March 2012 PM2.5 (0.0005) and November 2012 PM2.5 (0.0004). Besides these predictors, smoker and district-level deprivation index are found to be influential most widely, given that they ranked within the top 10 most often in sub-group analysis. In conclusion, antidepressant medication has strong associations with neighborhood conditions including socioeconomic satisfaction and the seasonality of particulate matter. Strong interventions for these factors are really needed for the effective management of major depressive disorder.

Radiomic machine learning for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumor heterogeneity and angiogenesis properties on MRI.

OBJECTIVES: To investigate machine learning approaches for radiomics-based prediction of prognostic biomarkers and molecular subtypes of breast cancer using quantification of tumor heterogeneity and angiogenesis properties on magnetic resonance imaging (MRI). METHODS: This prospective study examined 291 invasive cancers in 288 patients who underwent breast MRI at 3 T before treatment between May 2017 and July 2019. Texture and perfusion analyses were performed and a total of 160 parameters for each cancer were extracted. Relationships between MRI parameters and prognostic biomarkers were analyzed using five machine learning algorithms. Each model was built using only texture features, only perfusion features, or both. Model performance was compared using the area under the receiver-operating characteristic curve (AUC) and the DeLong method, and the importance of MRI parameters in prediction was derived. RESULTS: Texture parameters were associated with the status of hormone receptors, human epidermal growth factor receptor 2, and Ki67, tumor size, grade, and molecular subtypes (p < 0.002). Perfusion parameters were associated with the status of hormone receptors and Ki67, grade, and molecular subtypes (p < 0.003). The random forest model integrating texture and perfusion parameters showed the highest performance (AUC = 0.75). The performance of the random forest model was the best with a special scale filter of 0 (AUC = 0.80). The important parameters for prediction were texture irregularity (entropy) and relative extracellular extravascular space (Ve). CONCLUSIONS: Radiomic machine learning that integrates tumor heterogeneity and angiogenesis properties on MRI has the potential to noninvasively predict prognostic factors of breast cancer. KEY POINTS: • Machine learning, integrating tumor heterogeneity and angiogenesis properties on MRI, can be applied to predict prognostic biomarkers and molecular subtypes in breast cancer. • The random forest model showed the best predictive performance among the five machine learning models (logistic regression, decision tree, naïve Bayes, random forest, and artificial neural network). • The most important MRI parameters for predicting prognostic factors in breast cancer were texture irregularity (entropy) among texture parameters and relative extracellular extravascular space (Ve) among perfusion parameters.

Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients.

This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01-1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.

Risk factor assessments of temporomandibular disorders via machine learning.

This study aimed to use artificial intelligence to determine whether biological and psychosocial factors, such as stress, socioeconomic status, and working conditions, were major risk factors for temporomandibular disorders (TMDs). Data were retrieved from the fourth Korea National Health and Nutritional Examination Survey (2009), with information concerning 4744 participants' TMDs, demographic factors, socioeconomic status, working conditions, and health-related determinants. Based on variable importance observed from the random forest, the top 20 determinants of self-reported TMDs were body mass index (BMI), household income (monthly), sleep (daily), obesity (subjective), health (subjective), working conditions (control, hygiene, respect, risks, and workload), occupation, education, region (metropolitan), residence type (apartment), stress, smoking status, marital status, and sex. The top 20 determinants of temporomandibular disorders determined via a doctor's diagnosis were BMI, age, household income (monthly), sleep (daily), obesity (subjective), working conditions (control, hygiene, risks, and workload), household income (subjective), subjective health, education, smoking status, residence type (apartment), region (metropolitan), sex, marital status, and allergic rhinitis. This study supports the hypothesis, highlighting the importance of obesity, general health, stress, socioeconomic status, and working conditions in the management of TMDs.

Usefulness of artificial intelligence for predicting recurrence following surgery for pancreatic cancer: Retrospective cohort study.

BACKGROUND: or Purpose: Pancreatic ductal adenocarcinoma (PDAC) is a leading cause of mortality in the world with the overall 5-year survival rate of 6%. The survival of patients with PDAC is closely related to recurrence and therefore it is necessary to identify the risk factors for recurrence. This study uses artificial intelligence approaches and multi-center registry data to analyze the recurrence of pancreatic cancer after surgery and its major determinants. METHODS: Data came from 4846 patients enrolled in a multi-center registry system, the Korea Tumor Registry System (KOTUS). The random forest and the Cox proportional-hazards model (the Cox model) were applied and compared for the prediction of disease-free survival. Variable importance, the contribution of a variable for the performance of the model, was used for identifying major predictors of disease-free survival after surgery. The C-Index was introduced as a criterion for validating the models trained. RESULTS: Based on variable importance from the random forest, major predictors of disease-free survival after surgery were tumor size (0.00310), tumor grade (0.00211), TNM stage (0.00211), T stage (0.00146) and lymphovascular invasion (0.00125). The coefficients of these variables were statistically significant in the Cox model (p < 0.05). The C-Index averages of the random forest and the Cox model were 0.6805 and 0.7738, respectively. CONCLUSIONS: This is the first artificial-intelligence study with multi-center registry data to predict disease-free survival after the surgery of pancreatic cancer. The findings of this methodological study demonstrate that artificial intelligence can provide a valuable decision-support system for treating patients undergoing surgery for pancreatic cancer. However, at present, further studies are needed to demonstrate the actual benefit of applying machine learning algorithms in clinical practice.

Machine Learning Approaches to Identify Factors Associated with Women's Vasomotor Symptoms Using General Hospital Data.

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.

Association of Preterm Birth with Depression and Particulate Matter: Machine Learning Analysis Using National Health Insurance Data.

This study uses machine learning and population data to analyze major determinants of preterm birth including depression and particulate matter. Retrospective cohort data came from Korea National Health Insurance Service claims data for 405,586 women who were aged 25-40 years and gave births for the first time after a singleton pregnancy during 2015-2017. The dependent variable was preterm birth during 2015-2017 and 90 independent variables were included (demographic/socioeconomic information, particulate matter, disease information, medication history, obstetric information). Random forest variable importance was used to identify major determinants of preterm birth including depression and particulate matter. Based on random forest variable importance, the top 40 determinants of preterm birth during 2015-2017 included socioeconomic status, age, proton pump inhibitor, benzodiazepine, tricyclic antidepressant, sleeping pills, progesterone, gastroesophageal reflux disease (GERD) for the years 2002-2014, particulate matter for the months January-December 2014, region, myoma uteri, diabetes for the years 2013-2014 and depression for the years 2011-2014. In conclusion, preterm birth has strong associations with depression and particulate matter. What is really needed for effective prenatal care is strong intervention for particulate matters together with active counseling and medication for common depressive symptoms (neglected by pregnant women).

Automated detection of colorectal tumors based on artificial intelligence.

BACKGROUND: This study developed a diagnostic tool to automatically detect normal, unclear and tumor images from colonoscopy videos using artificial intelligence. METHODS: For the creation of training and validation sets, 47,555 images in the jpg format were extracted from colonoscopy videos for 24 patients in Korea University Anam Hospital. A gastroenterologist with the clinical experience of 15 years divided the 47,555 images into three classes of Normal (25,895), Unclear (2038) and Tumor (19,622). A single shot detector, a deep learning framework designed for object detection, was trained using the 47,255 images and validated with two sets of 300 images-each validation set included 150 images (50 normal, 50 unclear and 50 tumor cases). Half of the 47,255 images were used for building the model and the other half were used for testing the model. The learning rate of the model was 0.0001 during 250 epochs (training cycles). RESULTS: The average accuracy, precision, recall, and F1 score over the category were 0.9067, 0.9744, 0.9067 and 0.9393, respectively. These performance measures had no change with respect to the intersection-over-union threshold (0.45, 0.50, and 0.55). This finding suggests the stability of the model. CONCLUSION: Automated detection of normal, unclear and tumor images from colonoscopy videos is possible by using a deep learning framework. This is expected to provide an invaluable decision supporting system for clinical experts.

Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth.

This study reviews the current status and future prospective of knowledge on the use of artificial intelligence for the prediction of spontaneous preterm labor and birth ("preterm birth" hereafter). The summary of review suggests that different machine learning approaches would be optimal for different types of data regarding the prediction of preterm birth: the artificial neural network, logistic regression and/or the random forest for numeric data; the support vector machine for electrohysterogram data; the recurrent neural network for text data; and the convolutional neural network for image data. The ranges of performance measures were 0.79-0.94 for accuracy, 0.22-0.97 for sensitivity, 0.86-1.00 for specificity, and 0.54-0.83 for the area under the receiver operating characteristic curve. The following maternal variables were reported to be major determinants of preterm birth: delivery and pregestational body mass index, age, parity, predelivery systolic and diastolic blood pressure, twins, below high school graduation, infant sex, prior preterm birth, progesterone medication history, upper gastrointestinal tract symptom, gastroesophageal reflux disease, Helicobacter pylori, urban region, calcium channel blocker medication history, gestational diabetes mellitus, prior cone biopsy, cervical length, myomas and adenomyosis, insurance, marriage, religion, systemic lupus erythematosus, hydroxychloroquine sulfate, and increased cerebrospinal fluid and reduced cortical folding due to impaired brain growth.

Machine Learning Approaches to Radiogenomics of Breast Cancer using Low-Dose Perfusion Computed Tomography: Predicting Prognostic Biomarkers and Molecular Subtypes.

Radiogenomics investigates the relationship between imaging phenotypes and genetic expression. Breast cancer is a heterogeneous disease that manifests complex genetic changes and various prognosis and treatment response. We investigate the value of machine learning approaches to radiogenomics using low-dose perfusion computed tomography (CT) to predict prognostic biomarkers and molecular subtypes of invasive breast cancer. This prospective study enrolled a total of 723 cases involving 241 patients with invasive breast cancer. The 18 CT parameters of cancers were analyzed using 5 machine learning models to predict lymph node status, tumor grade, tumor size, hormone receptors, HER2, Ki67, and the molecular subtypes. The random forest model was the best model in terms of accuracy and the area under the receiver-operating characteristic curve (AUC). On average, the random forest model had 13% higher accuracy and 0.17 higher AUC than the logistic regression. The most important CT parameters in the random forest model for prediction were peak enhancement intensity (Hounsfield units), time to peak (seconds), blood volume permeability (mL/100 g), and perfusion of tumor (mL/min per 100 mL). Machine learning approaches to radiogenomics using low-dose perfusion breast CT is a useful noninvasive tool for predicting prognostic biomarkers and molecular subtypes of invasive breast cancer.