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.

OBJECTIVES: We explored whether the association between vitamin B2 and colorectal cancer (CRC) risk could be modified by the MTRR rs1801394 and MTR rs1805087 genetic polymorphisms and examined whether the interaction effects are sex-specific. METHODS: We performed a case-control study involving 1,420 CRC patients and 2,840 controls from the Korea National Cancer Center. Dietary vitamin B2 intake was assessed using a semiquantitative food frequency questionnaire, and the association with CRC was evaluated. Genotyping was performed using an Illumina MEGA-Expanded Array. For gene-nutrient interaction analysis, pre-matched (1,081 patients and 2,025 controls) and matched (1,081 patients and 1,081 controls) subsets were included. Unconditional and conditional logistic regression models were used to calculate odds ratios (ORs) and 95% confidence intervals (CIs). RESULTS: A higher intake of vitamin B2 was associated with a significantly lower CRC risk (OR, 0.65; 95% CI, 0.51 to 0.82; p<0.001). Carriers of at least 1 minor allele of MTRR rs1801394 showed a significantly higher CRC risk (OR, 1.43; 95% CI, 1.12 to 1.83). Males homozygous for the major allele (A) of MTRR rs1801394 and who had a higher intake of vitamin B2 had a significantly lower CRC risk (OR, 0.31; 95% CI, 0.18 to 0.54; p-interaction=0.02). In MTR rs1805087, males homozygous for the major allele (A) and who had a higher vitamin B2 intake had a significantly lower CRC risk (OR, 0.38; 95% CI, 0.25 to 0.60; p-interaction<0.001). CONCLUSIONS The MTRR rs1801394 and MTR rs1805087 genetic polymorphisms may modify the association between vitamin B2 and CRC risk, particularly in males. However, further studies are warranted to confirm these interaction results.

Background: The relationship between aspirin usage and the risk of colorectal cancer (CRC) among individuals with both hypertension (HTN) and diabetes mellitus (DM) remains unclear. This study aims to explore the impact of aspirin use on the site-specific CRC risk in patients with metabolic comorbidity. Methods: A case-control study was conducted among 1,331 CRC patients and 2,771 controls recruited from the Nation Cancer Center in Korea. Multinomial logistic regression analyses were used to calculate the odds ratios (ORs) and 95% confidence intervals (CIs) for the association between aspirin use, metabolic disease status, and site-specific CRC risk. Results: Among the 4,102 participants, 1,191 individuals had neither HTN nor DM, 2,044 were diagnosed with HTN, 203 with DM, and 664 presented with HTN and DM comorbidity.An increasing number of HTN and DM was associated with an increased risk of overall CRC (HTN or DM: OR, 1.70; 95% CI, 1.39–2.07; HTN and DM: OR, 8.43; 95% CI, 6.37–11.16), while aspirin use was associated with a decreased risk of overall CRC (OR, 0.31; 95% CI, 0.21–0.46).These results remained consistent across anatomical sites. Among individuals with HTN and DM comorbidity, aspirin use notably associated with lower risk of overall CRC (OR, 0.39; 95% CI, 0.21–0.72), proximal colon (OR, 0.32; 95% CI, 0.13–0.71) and rectal cancer (OR, 0.27;95% CI, 0.08–0.97), but not distal colon cancer (OR, 0.58; 95% CI, 0.27–1.24). Conclusion This study showed that aspirin use is negatively associated with overall and sitespecific CRC, even among individuals with HTN and DM comorbidity.

Background: and Purpose The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS. Methods: We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3–6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3–6. Results: Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3–6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004). Conclusion The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.