ABSTRACT
Childhood trauma and interpersonal sensitivity impact the development of mood disorders. In this study, we investigate the association between childhood trauma and interpersonal sensitivity in patients with mood disorders. A total 775 patients (major depressive disorder [MDD, n = 241], bipolar I disorder [BD I, n = 119], and bipolar II disorder [BD II, n = 415]) and 734 controls. For evaluation, we used the Childhood Trauma Questionnaire-Short Form (CTQ) and Interpersonal Sensitivity Measure (IPSM). We examined between-group differences for each subscale in the CTQ and IPSM. Patients with BD II had significantly higher IPSM total scores than patients with MDD, BD I, or controls. The CTQ total score was related to the IPSM total score in all participants and subgroups. Among the CTQ subscales, emotional abuse showed the highest correlation with the IPSM total score, while separation anxiety and fragile inner self showed higher positive correlations with CTQ than the other subscales of IPSM in all patient groups and the control group, respectively. The findings reveal that childhood trauma and interpersonal sensitivity are positively correlated among patients with MDD, BD I, and BD II, and that interpersonal sensitivity is higher in patients with BD II than those with BD I or MDD. Childhood trauma is associated with interpersonal sensitivity, and each trauma type has a different impact on mood disorders. We expect that this study will encourage future research on interpersonal sensitivity and childhood trauma in mood disorders to improve treatment approaches.
Subject(s)
Adverse Childhood Experiences , Bipolar Disorder , Depressive Disorder, Major , Psychological Tests , Self Report , Humans , Depressive Disorder, Major/complications , Bipolar Disorder/psychology , Surveys and QuestionnairesABSTRACT
BACKGROUND: The International Classification of Diseases (ICD) codes represent the global standard for reporting disease conditions. The current ICD codes connote direct human-defined relationships among diseases in a hierarchical tree structure. Representing the ICD codes as mathematical vectors helps to capture nonlinear relationships in medical ontologies across diseases. METHODS: We propose a universally applicable framework called "ICD2Vec" designed to provide mathematical representations of diseases by encoding corresponding information. First, we present the arithmetical and semantic relationships between diseases by mapping composite vectors for symptoms or diseases to the most similar ICD codes. Second, we investigated the validity of ICD2Vec by comparing the biological relationships and cosine similarities among the vectorized ICD codes. Third, we propose a new risk score called IRIS, derived from ICD2Vec, and demonstrate its clinical utility with large cohorts from the UK and South Korea. RESULTS: Semantic compositionality was qualitatively confirmed between descriptions of symptoms and ICD2Vec. For example, the diseases most similar to COVID-19 were found to be the common cold (ICD-10: J00), unspecified viral hemorrhagic fever (ICD-10: A99), and smallpox (ICD-10: B03). We show the significant associations between the cosine similarities derived from ICD2Vec and the biological relationships using disease-to-disease pairs. Furthermore, we observed significant adjusted hazard ratios (HR) and area under the receiver operating characteristics (AUROC) between IRIS and risks for eight diseases. For instance, the higher IRIS for coronary artery disease (CAD) can be the higher probability for the incidence of CAD (HR: 2.15 [95% CI 2.02-2.28] and AUROC: 0.587 [95% CI 0.583-0.591]). We identified individuals at substantially increased risk of CAD using IRIS and 10-year atherosclerotic cardiovascular disease risk (adjusted HR: 4.26 [95% CI 3.59-5.05]). CONCLUSIONS: ICD2Vec, a proposed universal framework for converting qualitatively measured ICD codes into quantitative vectors containing semantic relationships between diseases, exhibited a significant correlation with actual biological significance. In addition, the IRIS was a significant predictor of major diseases in a prospective study using two large-scale datasets. Based on this clinical validity and utility evidence, we suggest that publicly available ICD2Vec can be used in diverse research and clinical practices and has important clinical implications.
Subject(s)
COVID-19 , Coronary Artery Disease , Humans , Prospective Studies , Risk Factors , ROC Curve , International Classification of DiseasesABSTRACT
The major suppressive immune cells in tumor sites are myeloid derived suppressor cells (MDSCs), tumor-associated macrophages (TAMs), and Treg cells, and the major roles of these suppressive immune cells include hindering T-cell activities and supporting tumor progression and survival. In this study, we analyzed the pattern of circulating MDSC subtypes in patients with non-small cell lung cancer (NSCLC) whether those suppressive immune cells hinder T-cell activities leading to poor clinical outcomes. First, we verified PMN-MDSCs, monocytic-MDSCs (M-MDSCs), and Treg cells increased according to the stages of NSCLC, and MDSCs effectively suppressed T-cell activities and induced T-cell exhaustion. The analysis of NSCLC patients treated with anti-PD-1 immunotherapy demonstrated that low PMN-MDSCs, M-MDSCs, and CD39+ CD8+ T cells as an individual and all together were associated with longer progression free survival and overall survival, suggesting PMN-MDSCs, M-MDSCs, and CD39+ CD8+ T cells frequencies in peripheral blood might be useful as potential predictive and prognostic biomarkers.
Subject(s)
Antigens, CD/immunology , Apyrase/immunology , CD8-Positive T-Lymphocytes/immunology , Carcinoma, Non-Small-Cell Lung/immunology , Lung Neoplasms/immunology , Myeloid-Derived Suppressor Cells/immunology , Programmed Cell Death 1 Receptor/immunology , Adult , Aged , Aged, 80 and over , Female , Humans , Immunotherapy/methods , Lymphocyte Activation/immunology , Male , Middle AgedABSTRACT
BACKGROUND AND AIM: Proton pump inhibitor (PPI)-induced hypochondria can change the composition of the gut microbiota, inducing overgrowth of small bowel bacteria, which has been suggested to promote the development of fatty liver disease through the gut-liver axis. In this study, we aimed to investigate the association between PPI use and the risk of fatty liver disease. METHODS: A retrospective cohort study was conducted using the Korean National Health Insurance Service-National Sample Cohort, a nationwide population-based representative sample, from January 1, 2002, to December 31, 2015. PPI use was identified from treatment claims and considered as a time-varying variable. RESULTS: During 1 463 556 person-years of follow-up, 75 727 patients had at least one PPI prescription, and 3735 patients developed fatty liver disease. The hazard ratio for fatty liver disease comparing PPI users with non-PPI users was 1.68 (95% confidence interval, 1.61-1.75). When adjusted for multiple confounders, including age, sex, body mass index, smoking, alcohol intake, exercise, income level, and comorbidities, the association was still significant (hazard ratio, 1.50; 95% confidence interval, 1.44-1.57). After considering the amounts of PPIs stratified by cumulative defined daily dose, the dose-response effect was observed until 180 days. Subgroup analysis also revealed that PPI use was correlated to an increased risk of fatty liver disease. CONCLUSIONS: This current national wide cohort study suggests that PPI use was associated with an increased risk of fatty liver disease compared with non-use of PPIs. Clinicians should consider fatty liver as a potential risk when prescribing PPI.
Subject(s)
Fatty Liver/etiology , Gastrointestinal Microbiome/drug effects , Intestine, Small/microbiology , Proton Pump Inhibitors/adverse effects , Adult , Aged , Aged, 80 and over , Biosimilar Pharmaceuticals , Dose-Response Relationship, Drug , Female , Humans , Korea/epidemiology , Male , Middle Aged , Proton Pump Inhibitors/administration & dosage , Retrospective Studies , Risk , Young AdultABSTRACT
The study aimed to investigate the relationship between the use of COX inhibitors and the risk of hepatocellular carcinoma (HCC) development in patients with chronic hepatitis B (CHB) using a nationwide population-based data. A nested case-control study was conducted using the National Health Insurance Service-National Sample Cohort (NHIS-NSC) from 2002 to 2013 in Korea. We compared the use of COX inhibitors between HCC cases and matched controls by categorizing 5 groups according to the cumulative defined daily dose (cDDD, <28, 28-90, 91-180, 181-360, and >360) adjusting the use of antiviral agents. A total of 4980 patients with CHB were analysed as 996 HCC cases and 3984 matched controls. The number of COX inhibitor users (≥28 cDDD) was 358 patients (36%) and 1814 patients (45%) in the HCC group and control group, respectively. The use of COX inhibitors was significantly associated with a decreased risk of HCC development compared with nonusers (adjusted odds ratio [OR] 0.62, 95% confidence interval [CI] 0.52-0.73, P < .001). There was a dose-dependent inverse relationship between the use of COX inhibitors and the risk of HCC. The adjusted ORs were 0.75 (95% CI: 0.63-0.90), 0.41 (95% CI: 0.31-0.56), 0.38 (95% CI: 0.25-0.57) and 0.49 (95% CI: 0.31-0.79) for the 28-90, 91-180, 181-360 and >360 cDDDs, respectively (P < .01). In conclusion, the use of COX inhibitors was associated with a reduced risk of HCC in CHB. COX inhibitor may have a chemopreventive role in HCC development in patients with chronic liver disease.
Subject(s)
Antiviral Agents/therapeutic use , Carcinoma, Hepatocellular/virology , Cyclooxygenase Inhibitors/therapeutic use , Hepatitis B, Chronic/drug therapy , Liver Neoplasms/virology , Adult , Aged , Aged, 80 and over , Case-Control Studies , Cohort Studies , Female , Humans , Male , Mass Screening , Middle Aged , Odds Ratio , Republic of Korea , Risk Factors , Young AdultABSTRACT
Background/Aims: : The effect of proton pump inhibitors (PPIs) on the lower gastrointestinal (GI) tract is uncertain, with potential to worsen damage. This study aimed to find the best method for protecting the entire GI tract from mucosal damage. Methods: : A retrospective cohort study at Samsung Medical Center (2002-2019) included 195,817 patients prescribed GI mucosa-damaging agents. The primary goal was to assess the effectiveness of GI protective agents in preventing significant hemoglobin drops (>2 g/dL), indicating overall GI mucosal damage. Self-controlled case series and landmark analysis were used to address biases in real-world data. Results: : The incidence rate ratios for rebamipide, PPI, and histamine-2 receptor antagonist (H2RA) were 0.34, 0.33, and 0.52, respectively. Rebamipide showed a significantly lower incidence rate than H2RA and was comparable to PPIs. Landmark analysis revealed significant reductions in hemoglobin drop risk with rebamipide and H2RA, but not with PPI. Conclusions: : Rebamipide, like PPIs, was highly effective in preventing blood hemoglobin level decreases, as shown in real-world data. Rebamipide could be a comprehensive strategy for protecting the entire GI tract, especially when considering PPIs' potential side effects on the lower GI tract.
ABSTRACT
BACKGROUND: The incidence of colorectal cancer (CRC) and preinvasive CRC (e.g., early colon cancer and advanced adenoma) is gradually increasing in several countries. AIM: To evaluate the trend in incidence of CRC and preinvasive CRC according to the increase in the number of colonoscopies performed in Korea. METHODS: This retrospective cohort study enrolled Korean patients from 2002 to 2020 to evaluate the incidence of CRC and preinvasive CRC, and assess the numbers of diagnostic colonoscopies and colonoscopic polypectomies. Colonoscopy-related complications by age group were also determined. RESULTS: The incidence of CRC showed a rapid increase, then decreased after 2012 in the 50-75 year-age group. During the study period, the rate of incidence of preinvasive CRC increased at a similar level in patients under 50 and 50-75 years of age. Since 2009, the increase has been rapid, showing a pattern similar to the increase in colonoscopies. The rate of colonoscopic polypectomy in patients aged under 50 was similar to the rate in patients over 75 years of age after 2007. The rate of complications after colonoscopy and related deaths within 3 mo was high for those over 75 years of age. CONCLUSION: The diagnosis of preinvasive CRC increased with the increase in the number of colonoscopies performed. As the risk of colonoscopy-related hospitalization and death is high in the elderly, if early lesions at risk of developing CRC are diagnosed and treated under or at the age of 75, colonoscopy-related complications can be reduced for those aged 76 years or over.
ABSTRACT
Hyperuricemia is an essential causal risk factor for gout and is associated with cardiometabolic diseases. Given the limited contribution of East Asian ancestry to genome-wide association studies of serum urate, the genetic architecture of serum urate requires exploration. A large-scale cross-ancestry genome-wide association meta-analysis of 1,029,323 individuals and ancestry-specific meta-analysis identifies a total of 351 loci, including 17 previously unreported loci. The genetic architecture of serum urate control is similar between European and East Asian populations. A transcriptome-wide association study, enrichment analysis, and colocalization analysis in relevant tissues identify candidate serum urate-associated genes, including CTBP1, SKIV2L, and WWP2. A phenome-wide association study using polygenic risk scores identifies serum urate-correlated diseases including heart failure and hypertension. Mendelian randomization and mediation analyses show that serum urate-associated genes might have a causal relationship with serum urate-correlated diseases via mediation effects. This study elucidates our understanding of the genetic architecture of serum urate control.
Subject(s)
Genome-Wide Association Study , Hyperuricemia , Uric Acid , Humans , DNA-Binding Proteins/genetics , Genetic Predisposition to Disease , Gout/genetics , Gout/blood , Heart Failure/genetics , Heart Failure/blood , Hypertension/genetics , Hypertension/blood , Hyperuricemia/genetics , Hyperuricemia/blood , Mendelian Randomization Analysis , Multifactorial Inheritance , Polymorphism, Single Nucleotide , Transcriptome , Uric Acid/bloodABSTRACT
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.
Subject(s)
Artificial Intelligence , Glaucoma , Humans , Glaucoma/diagnostic imaging , Fundus Oculi , Diagnostic Techniques, Ophthalmological , AlgorithmsABSTRACT
Cardiovascular disease (CVD), the leading cause of death globally, is associated with complicated underlying risk factors. We develop an artificial intelligence model to identify CVD using multimodal data, including clinical risk factors and fundus photographs from the Samsung Medical Center (SMC) for development and internal validation and from the UK Biobank for external validation. The multimodal model achieves an area under the receiver operating characteristic curve (AUROC) of 0.781 (95% confidence interval [CI] 0.766-0.798) in the SMC and 0.872 (95% CI 0.857-0.886) in the UK Biobank. We further observe a significant association between the incidence of CVD and the predicted risk from at-risk patients in the UK Biobank (hazard ratio [HR] 6.28, 95% CI 4.72-8.34). We visualize the importance of individual features in photography and traditional risk factors. The results highlight that non-invasive fundus photography can be a possible predictive marker for CVD.
ABSTRACT
Inflammatory bowel disease (IBD) is an idiopathic inflammatory disorder characterized by chronic and relapsing manifestations. Several environmental factors are known as triggers for exacerbation of IBD. However, an association between exacerbation of IBD and ambient temperature is uncertain. This study aimed to estimate the risk of acute exacerbation of IBD due to ambient temperature. We performed a bidirectional case-crossover study using a nationwide claim data from South Korea. The external validation was conducted with a large prospective cohort in the United Kingdom. We confirmed significant associations between acute exacerbation of IBD and the short-term ambient temperature changes toward severe temperatures, in the cold weather (-19.4°C-4.3°C) (odd ratio [OR] = 1.13, 95% confidence interval [CI]: 1.13-1.14) and in the hot weather (21.3°C-33.5°C) (OR = 1.16, 95% CI: 1.15-1.17). However, the association was not significant in the moderate weather (4.3°C-21.3°C). The external validation suggested consistent results with additional elevation of acute exacerbation risk in the colder weather (-13.4°C to 2.6°C) (OR = 1.90, 95% CI: 1.62-2.22) and in the hotter weather (15.7°C-28.4°C) (OR = 1.41, 95% CI: 1.32-1.51). We observed and validated that the short-term ambient temperature changes were associated with acute exacerbation of IBD in the cold and hot weathers. Our findings provide evidence that temperature changes are associated with the acute exacerbation of IBD.
Subject(s)
Inflammatory Bowel Diseases , Weather , Humans , Temperature , Cross-Over Studies , Prospective Studies , Cold Temperature , Hot TemperatureABSTRACT
The aim of this study was to address the issue of differentiating between Mayo endoscopic subscore (MES) 0 and MES 1 using a deep learning model. A dataset of 492 ulcerative colitis (UC) patients who demonstrated MES improvement between January 2018 and December 2019 at Samsung Medical Center was utilized. Specifically, two representative images of the colon and rectum were selected from each patient, resulting in a total of 984 images for analysis. The deep learning model utilized in this study consisted of a convolutional neural network (CNN)-based encoder, with two auxiliary classifiers for the colon and rectum, as well as a final MES classifier that combined image features from both inputs. In the internal test, the model achieved an F1-score of 0.92, surpassing the performance of seven novice classifiers by an average margin of 0.11, and outperforming their consensus by 0.02. The area under the receiver operating characteristic curve (AUROC) was calculated to be 0.97 when considering MES 1 as positive, with an area under the precision-recall curve (AUPRC) of 0.98. In the external test using the Hyperkvasir dataset, the model achieved an F1-score of 0.89, AUROC of 0.86, and AUPRC of 0.97. The results demonstrate that the proposed CNN-based model, which integrates image features from both the colon and rectum, exhibits superior performance in accurately discriminating between MES 0 and MES 1 in patients with UC.
Subject(s)
Colitis, Ulcerative , Deep Learning , Humans , Colitis, Ulcerative/diagnostic imaging , Colonoscopy/methods , Severity of Illness Index , Intestinal MucosaABSTRACT
Even though the conventional treatment for T1 esophageal cancer is surgery, ESD is becoming the primary treatment. Currently, it is unknown whether secondary esophagectomy after endoscopic submucosal dissection (ESD) is comparable to primary esophagectomy when considering outcomes in patients with T1 esophageal cancer. We compared short- and long-term clinical outcomes between the two groups. Primary surgery (esophagectomy) was performed in 191 patients between 2003 and 2014, and 62 patients underwent secondary surgery (esophagectomy) after ESD for T1 esophageal cancer between 2007 and 2019. Propensity matching was performed for age, sex, Charlson Comorbidity Index (CCI), location, pathology, degree of differentiation, tumor size, and invasion depth. Lymph node metastasis (LNM), overall survival (OS), disease-specific survival (DSS), recurrence-free survival (RFS), and post-operative complications were compared between groups. Sixty-eight patients were included after propensity score matching; LNM, OS, DSS, and RFS were comparable between the two groups. Comparing primary and secondary surgery, the respective LNM rates were 23.5% and 26.5%, 6-year OS 78.0% and 89.7%, p = 0.15; DSS were 80.4% and 96.8%, p = 0.057; and RFS were 80.8% and 89.7%, p = 0.069. Comparing the adverse events between the two groups, there was no significant difference in the overall adverse events. However, more early complications were observed in the primary surgery group than in the secondary surgery group (50% vs. 20.6%, p = 0.021). Secondary surgery did not increase the risk of LNM. The long-term outcomes were comparable. Therefore, attempts to perform upfront ESD for superficial esophageal squamous cell cancers are justified.
ABSTRACT
BACKGROUND: Childhood trauma has lasting negative impacts on individuals' psychological functioning. However, there is limited empirical evidence on the association between childhood trauma and resilience and none examining such relationship among diverse clinical populations. This study aimed to investigate the relationship in patients with major depressive disorder, bipolar I disorder, bipolar II disorder, and a comparison group. METHODS: In total, 787 psychiatric patients and 734 people from the general population participated in the study. The Childhood Trauma Questionnaire-Short Form and Connor-Davidson Resilience Scale were used to assess childhood trauma and resilience, respectively. RESULTS: Individuals with childhood trauma showed lower levels of resilience in all subjects; among them, those who experienced emotional abuse and emotional neglect exhibited even stronger associations than other types of childhood trauma. There was a significant difference in the negative relationship between childhood trauma and resilience by group, where the association was more prominent in the comparison group than in MDD and BD II patient groups. LIMITATIONS: The generalizability of our results may be limited due to unproportionate patient sample size. Also, we could not examine the causal relationship between childhood trauma and resilience. CONCLUSION: Childhood trauma and resilience had a significantly negative association. Our results suggest that people who have experienced emotional abuse and emotional neglect should be closely assisted to develop resilience. Interventions that promote resilience should be provided to individuals predisposed to psychological risks as a result of childhood trauma.
Subject(s)
Adverse Childhood Experiences , Bipolar Disorder , Child Abuse , Depressive Disorder, Major , Resilience, Psychological , Humans , Child , Mood Disorders/epidemiology , Mood Disorders/complications , Depressive Disorder, Major/psychology , Bipolar Disorder/psychology , Child Abuse/psychology , Surveys and QuestionnairesABSTRACT
BACKGROUND: Exacerbation of inflammatory bowel disease (IBD) is common. Identification of the exacerbating factors could facilitate interventions for forecastable environmental factors through adjustment of the patient's daily routine. We assessed the effect of natural environmental factors on the exacerbation of IBD. METHODS: In this systematic review and meta-analysis, studies published from January 1, 1992 to November 3th, 2022 were searched in the MEDLINE, Embase, CINAHL Complete and Cochrane Library databases. We extracted data related to the impact of environmental variations on IBD exacerbation, and performed a meta-analysis of the individual studies' correlation coefficient χ2 converted into Cramér's V (φc) with 95% confidence intervals (CI). RESULTS: A total of 7,346 publications were searched, and 20 studies (sample size 248-84,000 cases) were selected. A meta-analysis with seven studies was performed, and the pooled estimate of the correlation (φc) between the seasonal variations and IBD exacerbations among 4806 cases of IBD exacerbation was 0.11 (95% CI 0.07-0.14; I2 = 39%; p = 0.13). When divided into subtypes of IBD, the pooled estimate of φc in ulcerative colitis (six studies, n = 2649) was 0.07 (95% CI 0.03-0.11; I2 = 3%; p = 0.40) and in Crohn's disease (three studies, n = 1597) was 0.12 (95% CI 0.07-0.18; I2 = 18%; p = 0.30). CONCLUSION: There was a significant correlation between IBD exacerbation and seasonal variations, however, it was difficult to synthesize pooled results of other environmental indicators due to the small number of studies and the various types of reported outcome measures. For clinical implications, additional evidence through well-designed follow-up studies is needed. PROTOCOL REGISTRATION NUMBER (PROSPERO): CRD42022304916.
Subject(s)
Colitis, Ulcerative , Crohn Disease , Inflammatory Bowel Diseases , Humans , Seasons , Temperature , Inflammatory Bowel Diseases/epidemiology , Crohn Disease/epidemiologyABSTRACT
BACKGROUND AND AIMS: Although recent studies have reported that inflammatory bowel disease [IBD] is associated with the development of neurodegenerative diseases via chronic intestinal inflammation and the gut-brain axis, there is insufficient evidence supporting this notion. The aim of this study was to determine the risk of neurodegenerative diseases including Parkinson's disease [PD] and Alzheimer's disease [AD] in patients with IBD. METHODS: Using the National Health Insurance Service data for the entire Korean population, we identified patients with IBD and controls from 2009 to 2011 and followed them up until 2017. We selected the controls in a 1:4 ratio based on age and sex for comparison with cases. RESULTS: Of 24 830 IBD patients and 99 320 non-IBD controls, 98 IBD patients and 256 controls developed PD, and 644 IBD patients and 2303 controls developed AD. The overall neurodegenerative disease risk was higher in IBD patients (PD: adjusted hazard ratio [HR], 1.56; 95% confidence interval [CI], 1.24-1.97; AD: adjusted HR, 1.14; 95% CI, 1.05-1.25). Younger IBD patients aged 40-65 years had a higher risk of PD compared with controls [adjusted HR, 2.34; 1.63-3.35]. In contrast, patients aged ≥65 years had an increased risk of AD compared with controls [adjusted HR, 1.14; 1.04-1.25]. In a nested case-control study of the IBD cohort, patients aged ≥65 years and the female sex were risk factors for AD, whereas living in an urban area was protective against AD. CONCLUSIONS: The risk of neurodegenerative diseases was higher in IBD patients than in the non-IBD population.
Subject(s)
Inflammatory Bowel Diseases , Neurodegenerative Diseases , Adult , Aged , Case-Control Studies , Cohort Studies , Female , Humans , Incidence , Inflammatory Bowel Diseases/complications , Inflammatory Bowel Diseases/epidemiology , Middle Aged , Neurodegenerative Diseases/complications , Neurodegenerative Diseases/etiology , Risk FactorsABSTRACT
Background: Several studies have suggested an association between inflammatory bowel disease (IBD) and the risk of prostate cancer development. However, these findings are inconsistent, and studies based on Asian populations are limited. Objectives: We compared the risk of prostate cancer according to IBD status using the Korean National Health Insurance Service database. Design: A population-based retrospective cohort of age-matched 59,044 non-IBD patients and 14,761 IBD patients between January 2009 and December 2011 was analyzed up to December 2017. Methods: The risk of prostate cancer was compared between patients with IBD and controls using the Cox proportional hazards regression model and Kaplan-Meier survival analysis. Results: During a median follow-up of 6 years, the incidence rate of prostate cancer was 264 per 100,000 person-years in non-IBD patients and 242 per 100,000 person-years in patients with IBD. IBD status was not associated with the risk of prostate cancer compared to non-IBD [adjusted hazard ratio (aHR) 0.93, 95% confidence interval (CI): 0.80-1.08, p = 0.32). The cumulative incidence of prostate cancer did not differ by IBD status (non-IBD patients versus IBD patients: log-rank p = 0.27; non-IBD patients versus ulcerative colitis versus Crohn's disease: log-rank p = 0.42). In multivariate analysis, age was an independent risk factor for the development of prostate cancer (HR 1.03, 95% CI: 1.02-1.03, p < 0.001). Conclusion: In our population-based study, IBD status was not associated with the risk of prostate cancer.
ABSTRACT
BACKGROUND: Bleeding is one of the major complications after endoscopic submucosal dissection (ESD) in early gastric cancer (EGC) patients. There are limited studies on estimating the bleeding risk after ESD using an artificial intelligence system. AIM: To derivate and verify the performance of the deep learning model and the clinical model for predicting bleeding risk after ESD in EGC patients. METHODS: Patients with EGC who underwent ESD between January 2010 and June 2020 at the Samsung Medical Center were enrolled, and post-ESD bleeding (PEB) was investigated retrospectively. We split the entire cohort into a development set (80%) and a validation set (20%). The deep learning and clinical model were built on the development set and tested in the validation set. The performance of the deep learning model and the clinical model were compared using the area under the curve and the stratification of bleeding risk after ESD. RESULTS: A total of 5629 patients were included, and PEB occurred in 325 patients. The area under the curve for predicting PEB was 0.71 (95% confidence interval: 0.63-0.78) in the deep learning model and 0.70 (95% confidence interval: 0.62-0.77) in the clinical model, without significant difference (P = 0.730). The patients expected to the low- (< 5%), intermediate- (≥ 5%, < 9%), and high-risk (≥ 9%) categories were observed with actual bleeding rate of 2.2%, 3.9%, and 11.6%, respectively, in the deep learning model; 4.0%, 8.8%, and 18.2%, respectively, in the clinical model. CONCLUSION: A deep learning model can predict and stratify the bleeding risk after ESD in patients with EGC.
Subject(s)
Deep Learning , Endoscopic Mucosal Resection , Stomach Neoplasms , Artificial Intelligence , Endoscopic Mucosal Resection/adverse effects , Gastric Mucosa/surgery , Humans , Postoperative Hemorrhage/epidemiology , Postoperative Hemorrhage/etiology , Retrospective Studies , Stomach Neoplasms/complicationsABSTRACT
OBJECTIVES: The outlook of artificial intelligence for healthcare (AI4H) is promising. However, no studies have yet discussed the issues from the perspective of stakeholders in Korea. This research aimed to identify stakeholders' requirements for AI4H to accelerate the business and research of AI4H. METHODS: We identified research funding trends from the Korean National Science and Technology Knowledge Information Service (NTIS) from 2015 and 2019 using "healthcare AI" and related keywords. Furthermore, we conducted an online survey with members of the Korean Society of Artificial Intelligence in Medicine to identify experts' opinions regarding the development of AI4H. Finally, expert interviews were conducted with 13 experts in three areas (hospitals, industry, and academia). RESULTS: We found 160 related projects from the NTIS. The major data type was radiology images (59.4%). Dermatology-related diseases received the most funding, followed by pulmonary diseases. Based on the survey responses, radiology images (23.9%) were the most demanding data type. Over half of the solutions were related to diagnosis (33.3%) or prognosis prediction (31%). In the expert interviews, all experts mentioned healthcare data for AI solutions as a major issue. Experts in the industrial field mainly mentioned regulations, practical efficacy evaluation, and data accessibility. CONCLUSIONS: We identified technology, regulatory, and data issues for practical AI4H applications from the perspectives of stakeholders in hospitals, industry, and academia in Korea. We found issues and requirements, including regulations, data utilization, reimbursement, and human resource development, that should be addressed to promote further research in AI4H.
ABSTRACT
Stratification of the risk of lymph node metastasis (LNM) in patients with non-curative resection after endoscopic resection (ER) for early gastric cancer (EGC) is crucial in determining additional treatment strategies and preventing unnecessary surgery. Hence, we developed a machine learning (ML) model and validated its performance for the stratification of LNM risk in patients with EGC. We enrolled patients who underwent primary surgery or additional surgery after ER for EGC between May 2005 and March 2021. Additionally, patients who underwent ER alone for EGC between May 2005 and March 2016 and were followed up for at least 5 years were included. The ML model was built based on a development set (70%) using logistic regression, random forest (RF), and support vector machine (SVM) analyses and assessed in a validation set (30%). In the validation set, LNM was found in 337 of 4428 patients (7.6%). Among the total patients, the area under the receiver operating characteristic (AUROC) for predicting LNM risk was 0.86 in the logistic regression, 0.85 in RF, and 0.86 in SVM analyses; in patients with initial ER, AUROC for predicting LNM risk was 0.90 in the logistic regression, 0.88 in RF, and 0.89 in SVM analyses. The ML model could stratify the LNM risk into very low (<1%), low (<3%), intermediate (<7%), and high (≥7%) risk categories, which was comparable with actual LNM rates. We demonstrate that the ML model can be used to identify LNM risk. However, this tool requires further validation in EGC patients with non-curative resection after ER for actual application.