Background/Aims: The incidence of steatotic liver disease (SLD) is increasing across all age groups as the incidence of obesity increases worldwide. The existing noninvasive prediction models for SLD require laboratory tests or imaging and perform poorly in the early diagnosis of infrequently screened populations such as young adults and individuals with healthcare disparities. We developed a machine learning-based point-of-care prediction model for SLD that is readily available to the broader population with the aim of facilitating early detection and timely intervention and ultimately reducing the burden of SLD. Methods: We retrospectively analyzed the clinical data of 28,506 adults who had routine health check-ups in South Korea from January to December 2022. A total of 229,162 individuals were included in the external validation study. Data were analyzed and predictions were made using a logistic regression model with machine learning algorithms. Results: A total of 20,094 individuals were categorized into SLD and non-SLD groups on the basis of the presence of fatty liver disease. We developed three prediction models: SLD model 1, which included age and body mass index (BMI); SLD model 2, which included BMI and body fat per muscle mass; and SLD model 3, which included BMI and visceral fat per muscle mass. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) was 0.817 for model 1, 0.821 for model 2, and 0.820 for model 3. In the internal validation cohort, 86.9% of individuals were correctly classified by the SLD models. The external validation study revealed an AUROC above 0.84 for all the models. Conclusions As our three novel SLD prediction models are cost-effective, noninvasive, and accessible, they could serve as validated clinical tools for mass screening of SLD.

Background/Aims: The incidence of steatotic liver disease (SLD) is increasing across all age groups as the incidence of obesity increases worldwide. The existing noninvasive prediction models for SLD require laboratory tests or imaging and perform poorly in the early diagnosis of infrequently screened populations such as young adults and individuals with healthcare disparities. We developed a machine learning-based point-of-care prediction model for SLD that is readily available to the broader population with the aim of facilitating early detection and timely intervention and ultimately reducing the burden of SLD. Methods: We retrospectively analyzed the clinical data of 28,506 adults who had routine health check-ups in South Korea from January to December 2022. A total of 229,162 individuals were included in the external validation study. Data were analyzed and predictions were made using a logistic regression model with machine learning algorithms. Results: A total of 20,094 individuals were categorized into SLD and non-SLD groups on the basis of the presence of fatty liver disease. We developed three prediction models: SLD model 1, which included age and body mass index (BMI); SLD model 2, which included BMI and body fat per muscle mass; and SLD model 3, which included BMI and visceral fat per muscle mass. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) was 0.817 for model 1, 0.821 for model 2, and 0.820 for model 3. In the internal validation cohort, 86.9% of individuals were correctly classified by the SLD models. The external validation study revealed an AUROC above 0.84 for all the models. Conclusions As our three novel SLD prediction models are cost-effective, noninvasive, and accessible, they could serve as validated clinical tools for mass screening of SLD.

Background/Aims: The incidence of steatotic liver disease (SLD) is increasing across all age groups as the incidence of obesity increases worldwide. The existing noninvasive prediction models for SLD require laboratory tests or imaging and perform poorly in the early diagnosis of infrequently screened populations such as young adults and individuals with healthcare disparities. We developed a machine learning-based point-of-care prediction model for SLD that is readily available to the broader population with the aim of facilitating early detection and timely intervention and ultimately reducing the burden of SLD. Methods: We retrospectively analyzed the clinical data of 28,506 adults who had routine health check-ups in South Korea from January to December 2022. A total of 229,162 individuals were included in the external validation study. Data were analyzed and predictions were made using a logistic regression model with machine learning algorithms. Results: A total of 20,094 individuals were categorized into SLD and non-SLD groups on the basis of the presence of fatty liver disease. We developed three prediction models: SLD model 1, which included age and body mass index (BMI); SLD model 2, which included BMI and body fat per muscle mass; and SLD model 3, which included BMI and visceral fat per muscle mass. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) was 0.817 for model 1, 0.821 for model 2, and 0.820 for model 3. In the internal validation cohort, 86.9% of individuals were correctly classified by the SLD models. The external validation study revealed an AUROC above 0.84 for all the models. Conclusions As our three novel SLD prediction models are cost-effective, noninvasive, and accessible, they could serve as validated clinical tools for mass screening of SLD.

Background/Aims: The incidence of steatotic liver disease (SLD) is increasing across all age groups as the incidence of obesity increases worldwide. The existing noninvasive prediction models for SLD require laboratory tests or imaging and perform poorly in the early diagnosis of infrequently screened populations such as young adults and individuals with healthcare disparities. We developed a machine learning-based point-of-care prediction model for SLD that is readily available to the broader population with the aim of facilitating early detection and timely intervention and ultimately reducing the burden of SLD. Methods: We retrospectively analyzed the clinical data of 28,506 adults who had routine health check-ups in South Korea from January to December 2022. A total of 229,162 individuals were included in the external validation study. Data were analyzed and predictions were made using a logistic regression model with machine learning algorithms. Results: A total of 20,094 individuals were categorized into SLD and non-SLD groups on the basis of the presence of fatty liver disease. We developed three prediction models: SLD model 1, which included age and body mass index (BMI); SLD model 2, which included BMI and body fat per muscle mass; and SLD model 3, which included BMI and visceral fat per muscle mass. In the derivation cohort, the area under the receiver operating characteristic curve (AUROC) was 0.817 for model 1, 0.821 for model 2, and 0.820 for model 3. In the internal validation cohort, 86.9% of individuals were correctly classified by the SLD models. The external validation study revealed an AUROC above 0.84 for all the models. Conclusions As our three novel SLD prediction models are cost-effective, noninvasive, and accessible, they could serve as validated clinical tools for mass screening of SLD.

Background/Aims: The pathophysiology of lean nonalcoholic fatty liver disease (NAFLD) is unclear but has been shown to be associated with more diverse pathogenic mechanisms than that of obese NAFLD. We investigated the characteristics of genetic or metabolic lean NAFLD in a health checkup cohort. Methods: This retrospective cross-sectional study analyzed single nucleotide polymorphism data for 6,939 health examinees. Lean individuals were categorized according to a body mass index cutoff of 23 kg/m 2 . Single nucleotide polymorphisms were analyzed using genotyping arrays. Results: The prevalence of lean NAFLD was 21.6% among all participants with NAFLD, and the proportion of lean NAFLD was 18.5% among lean participants. The prevalence of metabolic syndrome and diabetes among lean patients with NAFLD was 12.4% and 10.4%, respectively.Lean NAFLD appeared to be metabolic-associated in approximately 20.1% of patients. The homozygous minor allele (GG) of PNPLA3 (rs738409) and heterozygous minor alleles (CT, TT) of TM6SF2 (rs58542926) were associated with lean NAFLD. However, the prevalence of fatty liver was not associated with the genetic variants MBOAT7 (rs641738), HSD17B13 (rs72613567), MARC1 (rs2642438), or AGXT2 (rs2291702) in lean individuals. Lean NAFLD appeared to be associated with PNPLA3 or TM6SF2 genetic variation in approximately 32.1% of cases. Multivariate risk factor analysis showed that metabolic risk factors, genetic risk variants, and waist circumference were independent risk factors for lean NAFLD. Conclusions In a considerable number of patients, lean NAFLD did not appear to be associated with known genetic or metabolic risk factors. Further studies are required to investigate additional risk factors and gain a more comprehensive understanding of lean NAFLD.

Background/Aims: We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user’s experience and polyp characteristics. Methods: We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed. Results: The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively). Conclusions CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user’s experience, particularly for challenging lesions.

Background/Aims: A relationship between fatty liver and lung function impairment has been identified, and both are independently associated with metabolic dysfunction. However, the temporal relationship between changes in fatty liver status and lung function and their genome-wide association remain unclear. Methods: This longitudinal cohort consisted of subjects who received serial health check-ups, including liver ultrasonography and spirometry, for ≥3 years between 2003 and 2015. Lung func-tion decline rates were classified as “slow” and “accelerated” and compared among four different sonographic changes in steatosis status: “normal,” “improved,” “worsened,” and “persistent.” A genome-wide association study was conducted between the two groups: normal/improved steatosis with a slow decline in lung function versus worsened/persistent steatosis with an accelerated decline in lung function. Results: Among 6,149 individuals, the annual rates of decline in forced vital capacity (FVC) and forced expiratory volume measured in the first second of exhalation (FEV 1 ) were higher in the worsened/persistent steatosis group than in the normal/improved steatosis group. In multivariable analysis, persistent or worsened status of fatty liver was significantly associated with accelerated declines in FVC (persistent status, odds ratio [OR]=1.22, 95% confidence interval [CI]=1.04–1.44; worsened status, OR=1.30, 95% CI=1.12–1.50), while improved status of fatty liver was significantly associated with slow declines in FEV 1 (OR=0.77, 95% CI=0.64–0.92). The PNPLA3 risk gene was most strongly associated with steatosis status change and accelerated declines in FVC (rs12483959, p=2.61×10 -7 ) and FEV 1(rs2294433, p=3.69×10 -8 ). Conclusions Regression of fatty liver is related to lung function decline. Continuing efforts to improve fatty liver may preserve lung function, especially for subjects with a high genetic risk.

Background: Nonalcoholic fatty liver disease (NAFLD) is associated with a wide spectrum of metabolic abnormalities. This study aimed to evaluate whether NAFLD is associated with benign prostatic hyperplasia (BPH) independent of other risk factors. Methods: A total of 3,508 subjects who underwent prostate and hepatic ultrasonography were enrolled. NAFLD was diagnosed and graded by ultrasonographic findings. BPH was defined by total prostate volume. Results: The prevalence of BPH was significantly increased according to NAFLD severity (P < 0.001). The multivariate analysis showed that NAFLD was associated with a 22% increase in the risk of BPH (odds ratio [OR], 1.22; 95% confidence interval [CI], 1.02–1.45). In non-obese subjects, NAFLD was associated with a 41% increase in the risk of BPH (OR, 1.41; 95% CI, 1.14–1.73), and an incremental increase in the risk of BPH according to NAFLD severity was pronounced (adjusted OR [95% CI], 1.32 [1.05–1.68] for mild NAFLD, 1.55 [1.15–2.10] for moderate to severe NAFLD vs. no NAFLD, P for trend = 0.004). However, in the obese population, the association of NAFLD in the risk of BPH was insignificant (P = 0.208). Conclusion NAFLD is associated with an increased risk of BPH regardless of metabolic syndrome, especially in non-obese subjects. An incrementally increased risk of BPH according to NAFLD severity is prominent in non-obese subjects with NAFLD. Thus, physicians caring for non-obese patients with NAFLD may consider assessing the risk of BPH and associated urologic conditions.

BACKGROUND/AIMS: The development of nonalcoholic fatty liver disease (NAFLD) is associated with multiple genetic and environmental factors. METHODS: We performed a genome-wide association study to identify the genetic factors related to NAFLD in a Korean population-based sample of 1,593 subjects with NAFLD and 2,816 controls. We replicated the data in another sample that included 744 NAFLD patients and 1,137 controls. We investigated single-nucleotide polymorphisms (SNPs) that were related to NAFLD. RESULTS: After adjusting for age, sex and body mass index, rs738409, rs12483959 and rs2281135, located in the PNPLA3 gene, were validated in our population (p < 8.56×10⁻⁸) in the same linkage disequilibrium block. Additionally, rs2143571, rs3761472, and rs2073080 in the SAMM50 gene showed significant associations with NAFLD (p < 8.56×10⁻⁸). Furthermore, these six SNPs showed significant associations with the severity of fatty liver (all p < 2.0×10⁻¹⁰ in the discovery set and p < 2.0×10⁻⁶ in the validation set) and NAFLD, with elevated levels of alanine aminotransferase (all p < 2.0×10⁻¹⁰ in the discovery set and p < 2.0×10⁻⁶ in the validation set). CONCLUSIONS: We demonstrated that the PNPLA3 and SAMM50 genes are significantly associated with the presence and severity of NAFLD in a Korean population. These findings confirm the important roles of genetic factors in the pathogenesis of NAFLD.
Alanine Transaminase ; Body Mass Index ; Fatty Liver ; Genome-Wide Association Study ; Humans ; Linkage Disequilibrium ; Non-alcoholic Fatty Liver Disease* ; Polymorphism, Genetic* ; Polymorphism, Single Nucleotide

PURPOSE: Advanced hepatocellular carcinoma (HCC) is associated with various clinical conditions including major vessel invasion, metastasis, and poor performance status. The aim of this study was to establish a prognostic scoring system and to propose a sub-classification of the Barcelona-Clinic Liver Cancer (BCLC) stage C. MATERIALS AND METHODS: This retrospective study included consecutive patients who received sorafenib for BCLC stage C HCC at a single tertiary hospital in Korea. A Cox proportional hazard model was used to develop a scoring system, and internal validationwas performed by a 5-fold cross-validation. The performance of the model in predicting risk was assessed by the area under the curve and the Hosmer-Lemeshow test. RESULTS: A total of 612 BCLC stage C HCC patients were sub- classified into strata depending on their performance status. Five independent prognostic factors (Child-Pugh score, α-fetoprotein, tumor type, extrahepatic metastasis, and portal vein invasion) were identified and used in the prognostic scoring system. This scoring system showed good discrimination (area under the receiver operating characteristic curve, 0.734 to 0.818) and calibration functions (both p < 0.05 by the Hosmer-Lemeshow test at 1 month and 12 months, respectively). The differences in survival among the different risk groups classified by the total score were significant (p < 0.001 by the log-rank test in both the Eastern Cooperative Oncology Group 0 and 1 strata). CONCLUSION: The heterogeneity of patientswith BCLC stage C HCC requires sub-classification of advanced HCC. A prognostic scoring system with five independent factors is useful in predicting the survival of patients with BCLC stage C HCC.
Calibration ; Carcinoma, Hepatocellular* ; Cohort Studies* ; Discrimination (Psychology) ; Humans ; Korea ; Liver Neoplasms ; Neoplasm Metastasis ; Population Characteristics ; Portal Vein ; Prognosis ; Proportional Hazards Models ; Retrospective Studies ; ROC Curve ; Tertiary Care Centers