Yoosun Cho

Dr. Yoosun Cho


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2024 in Breast Cancer Research
Verified
Journal Article
Open access
PDF file
MKMi-ri Kwon
Mi-ri Kwon
YCYoosoo Chang
Yoosoo Chang
SHSoo-Youn Ham
Soo-Youn Ham
YCYoosun Cho
Yoosun Cho
EKEun Young Kim
Eun Young Kim
SRSeungho Ryu
Seungho Ryu
Background: Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women. Methods: We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI’s performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A–D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories. Results: Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7–77.3] vs. 67.1% [95% CI, 58.8–74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9–93.2] vs. 77.6% [95% CI, 61.7–77.9]), PPV (1.5% [95% CI, 1.2–1.9] vs. 0.5% [95% CI, 0.4–0.6]), recall rate (7.1% [95% CI, 6.9–7.2] vs. 22.5% [95% CI, 22.2–22.7]), and AUC values (0.8 [95% CI, 0.76–0.84] vs. 0.74 [95% CI, 0.7–0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category. Conclusions: AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

3 November 2022 in Gut and Liver
Verified
Journal Article
Open access
PDF file
SJSeogsong Jeong
Seogsong Jeong
YOYun Hwan Oh
Yun Hwan Oh
SCSeulggie Choi
Seulggie Choi
JCJooyoung Chang
Jooyoung Chang
SKSung Min Kim
Sung Min Kim
SPSang Min Park
Sang Min Park
Seogsong Jeong, Yun Hwan Oh, Seulggie Choi, Jooyoung Chang, Sung Min Kim, Sun Jae Park, Yoosun Cho, Joung Sik Son, Gyeongsil Lee, and Sang Min Park. Gut and Liver -0001;0:. https://doi.org/10.5009/gnl220038

SCSeulggie Choi
Seulggie Choi
KKKyae Hyung Kim
Kyae Hyung Kim
KKKyuwoong Kim
Kyuwoong Kim
JCJooyoung Chang
Jooyoung Chang
SKSung Min Kim
Sung Min Kim
SPSang Min Park
Sang Min Park
Cancer survivors are at an increased risk for cardiovascular disease (CVD). However, the association between particulate matter (PM) and CVD risk among cancer survivors (alive >5 years since diagnosis) is unclear. We investigated the risk of CVD among 40,899 cancer survivors within the Korean National Health Insurance Service database. Exposure to PM was determined by assessing yearly average PM levels obtained from the Air Korea database from 2008 to 2011. PMs with sizes <2.5 (PM2.5), <10 (PM10), or 2.5–10 (PM2.5–10) μm in diameter were compared, with each PM level exposure further divided into quintiles. Patients were followed up from January 2012 to date of CVD event, death, or December 2017, whichever came earliest. Adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) for CVD were calculated using Cox proportional hazards regression by PM exposure levels. Compared with cancer survivors in the lowest quintile of PM2.5 exposure, those within the highest quintile had a greater risk for CVD (aHR 1.31, 95% CI 1.07–1.59). Conversely, increasing PM10 and PM2.5–10 levels were not associated with increased CVD risk (p for trend 0.078 and 0.361, respectively). Cancer survivors who reduce PM2.5 exposure may benefit from lower risk of developing CVD.

Verified
Journal Article
Open access
PDF file
SKSoungmun Kim
Soungmun Kim
SJSeogsong Jeong
Seogsong Jeong
SPSun Jae Park
Sun Jae Park
JCJooyoung Chang
Jooyoung Chang
SCSeulggie Choi
Seulggie Choi
SPSang Min Park
Sang Min Park
(1) Background: The association between proton pump inhibitor (PPI) use and hepatocellular carcinoma (HCC) has been controversial, especially in the general population. We aimed to determine the impact of PPI on HCC risk in participants without liver cirrhosis or chronic hepatitis virus infection. (2) Methods: We assessed 406,057 participants from the Korean National Health Insurance Service database who underwent health screening from 2003 to 2006. We evaluated exposure to PPI before the index date using a standardized daily defined dose (DDD) system. The association of proton pump inhibitor use with the risk of HCC was evaluated using multivariable-adjusted Cox proportional hazards regression. (3) Results: Compared with non-users, PPI use was not associated with the HCC risk in low (<30 DDDs; aHR, 1.07; 95% CI, 0.91–1.27), intermediate (30 ≤ PPI < 60 DDDs; aHR, 0.96; 95% CI, 0.73–1.26), and high (≥60 DDDs; aHR, 0.86; 95% CI, 0.63–1.17) PPI groups in the final adjustment model. In addition, risks of cirrhosis-associated HCC and non-cirrhosis-associated HCC were not significantly associated with PPI use. The results remained consistent after excluding events that occurred within 1, 2, and 3 years to exclude pre-existing conditions that may be associated with the development of HCC. We also found no PPI-associated increase in HCC risk among the selected population, such as those with obesity, older age, and chronic liver diseases. (4) Conclusions: PPI use may not be associated with HCC risk regardless of the amount. We call for future studies conducted in other regions to generalize our findings.

29 April 2025 in BMC Gastroenterology
Verified
Journal Article
Open access
PDF file
WSWoo-Young Shin
Woo-Young Shin
EKEun Seok Kang
Eun Seok Kang
YOYun Hwan Oh
Yun Hwan Oh
MSMeng Sha
Meng Sha
QXQiang Xia
Qiang Xia
YCYoosun Cho
Yoosun Cho
Background: The relationship between the newly proposed steatotic liver disease (SLD) subtypes—metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic alcohol-associated liver disease (MetALD)—and dementia is understudied. We evaluated the dementia risk associated with these subtypes. Methods: This retrospective cohort study included 296,001 participants aged over 60 who underwent health examinations between 2009 and 2010. Participants were categorized into non-SLD (reference), MASLD, and MetALD groups and followed up until dementia onset, death, or December 31, 2019. SLD was defined by a fatty liver index ≥ 30, with (i) MASLD based on cardiometabolic risk factors, and (ii) MetALD as MASLD with moderate alcohol intake. Outcomes included overall dementia, Alzheimer's disease (AD), and vascular dementia (VaD). Subdistribution hazard ratios (SHRs) was calculated using the Fine–Gray model, treating death as a competing risk. Results: Over 7,430,253 person-years of follow-up, 11,345 dementia cases occurred (10,863 AD and 2,159 VaD). Adjusted SHRs for MASLD were 1.10 (1.07–1.13) for AD and 1.20 (1.13–1.27) for VaD. For MetALD, SHRs were 0.90 (0.87–0.94) for AD and 1.53 (1.40–1.66) for VaD. Dementia risk in both MASLD and MetALD increased over longer periods, with MetALD initially linked to increased VaD risk and decreased AD risk, which reversed after three years. Conclusions: MASLD and MetALD were associated with increased risks of AD and VaD; MetALD showing a stronger association with VaD. Understanding the distinct effects of different SLD subtypes on dementia is crucial for improving risk assessment and management strategies.

15 October 2025 in Nutrients
Verified
Journal Article
Open access
PDF file
YCYoosun Cho
Yoosun Cho
YJYoonyoung Jang
Yoonyoung Jang
Jae Ho ParkJae Ho Park
Jae Ho Park
YCYoosoo Chang
Yoosoo Chang
SRSeungho Ryu
Seungho Ryu
Background/Objectives: The risk of sarcopenic obesity across menopausal transition stages remains unclear. This study investigated the association between menopausal stage and the risk of sarcopenic obesity. Methods: This longitudinal study included 4766 Korean women aged 42–52 years (median follow-up duration, 9.1 years). Menopausal transition was classified by STRAW + 10 stages: premenopause, early transition, late transition, and postmenopause. Sarcopenic obesity was defined as ASM index < 5.7 kg/m2 combined with PBF ≥ 35%. ASM and PBF were measured by bioelectrical impedance analysis with an InBody 720 device. Obesity, defined by BMI or waist circumference, was used for the sensitivity analyses. Associations were analyzed using generalized estimating equations. Results: Participants had a mean age and BMI of 42.2 years (SD 3.0) and 22.1 kg/m2 (SD 2.9), respectively; 16.1% had high body fat, and 15.6% had low muscle mass. Increased age was associated with higher odds of sarcopenic obesity (OR 1.07, 95% CI: 1.03–1.10). Compared to pre-menopause, late transition (OR 1.49, 95% CI: 1.17–1.89) and post-menopause (OR 1.67, 95% CI: 1.26–2.23) were significantly associated with sarcopenic obesity, independent of confounders. Similar trends were observed using waist circumference-based definitions. No significant associations were identified using BMI-based definitions (BMI ≥ 23 kg/m2), although positive trends were observed. Conclusions: In middle-aged Korean women undergoing natural menopause, sarcopenic obesity increased across menopausal stages, becoming significant from the late transition. These unfavorable changes were more evident when using body composition measures, suggesting that BMI alone may underestimate such changes during menopausal transition.