Dr. Jun Young graduated from the Department of Biostatistics at the School of Public Health, Seoul National University, Korea. His major field of study is biostatistics, with a specific focus on the application of machine learning and statistical analysis to medical imaging and genetic data. During his doctoral studies, he concentrated on two primary research areas. Firstly, he dedicated himself to the development of deep learning models for medical images, primarily centered on T1-MRI and cognitive function test images related to Alzheimer's Disease. Secondly, he engaged in extensive genome-wide association analyses of medical images associated with Alzheimer's Disease, using statistical algorithms to uncover novel insights into the genetic factors contributing to this complex condition. Currently, as a postdoctoral fellow at the Greicius Lab at Stanford, he aims to develop statistical methods to discover novel structural variants and model polygenetic risk scores using long-read sequencing data.

Stanford Advisors

All Publications

  • Predicting mild cognitive impairments from cognitively normal brains using a novel brain age estimation model based on structural magnetic resonance imaging CEREBRAL CORTEX Choi, U., Park, J., Lee, J., Choi, K., Won, S., Lee, K. 2023; 33 (21): 10858-10866


    Brain age prediction is a practical method used to quantify brain aging and detect neurodegenerative diseases such as Alzheimer's disease (AD). However, very few studies have considered brain age prediction as a biomarker for the conversion of cognitively normal (CN) to mild cognitive impairment (MCI). In this study, we developed a novel brain age prediction model using brain volume and cortical thickness features. We calculated an acceleration of brain age (ABA) derived from the suggested model to estimate different diagnostic groups (CN, MCI, and AD) and to classify CN to MCI and MCI to AD conversion groups. We observed a strong association between ABA and the 3 diagnostic groups. Additionally, the classification models for CN to MCI conversion and MCI to AD conversion exhibited acceptable and robust performances, with area under the curve values of 0.66 and 0.76, respectively. We believe that our proposed model provides a reliable estimate of brain age for elderly individuals and can identify those at risk of progressing from CN to MCI. This model has great potential to reveal a diagnosis associated with a change in cognitive decline.

    View details for DOI 10.1093/cercor/bhad331

    View details for Web of Science ID 001067030600001

    View details for PubMedID 37718166

  • Machine learning-based quantification for disease uncertainty increases the statistical power of genetic association studies BIOINFORMATICS Park, J., Lee, J., Lee, Y., Lee, D., Gim, J., Farrer, L., Lee, K., Won, S. 2023; 39 (9)


    Allowance for increasingly large samples is a key to identify the association of genetic variants with Alzheimer's disease (AD) in genome-wide association studies (GWAS). Accordingly, we aimed to develop a method that incorporates patients with mild cognitive impairment and unknown cognitive status in GWAS using a machine learning-based AD prediction model.Simulation analyses showed that weighting imputed phenotypes method increased the statistical power compared to ordinary logistic regression using only AD cases and controls. Applied to real-world data, the penalized logistic method had the highest AUC (0.96) for AD prediction and weighting imputed phenotypes method performed well in terms of power. We identified an association (P<5.0×10-8) of AD with several variants in the APOE region and rs143625563 in LMX1A. Our method, which allows the inclusion of individuals with mild cognitive impairment, improves the statistical power of GWAS for AD. We discovered a novel association with LMX1A.Simulation codes can be accessed at

    View details for DOI 10.1093/bioinformatics/btad534

    View details for Web of Science ID 001077825100002

    View details for PubMedID 37665736

    View details for PubMedCentralID PMC10539075

  • Automating Rey Complex Figure Test scoring using a deep learning-based approach: a potential large-scale screening tool for cognitive decline. Alzheimer's research & therapy Park, J. Y., Seo, E. H., Yoon, H. J., Won, S., Lee, K. H. 2023; 15 (1): 145


    The Rey Complex Figure Test (RCFT) has been widely used to evaluate the neurocognitive functions in various clinical groups with a broad range of ages. However, despite its usefulness, the scoring method is as complex as the figure. Such a complicated scoring system can lead to the risk of reducing the extent of agreement among raters. Although several attempts have been made to use RCFT in clinical settings in a digitalized format, little attention has been given to develop direct automatic scoring that is comparable to experienced psychologists. Therefore, we aimed to develop an artificial intelligence (AI) scoring system for RCFT using a deep learning (DL) algorithm and confirmed its validity.A total of 6680 subjects were enrolled in the Gwangju Alzheimer's and Related Dementia cohort registry, Korea, from January 2015 to June 2021. We obtained 20,040 scanned images using three images per subject (copy, immediate recall, and delayed recall) and scores rated by 32 experienced psychologists. We trained the automated scoring system using the DenseNet architecture. To increase the model performance, we improved the quality of training data by re-examining some images with poor results (mean absolute error (MAE) [Formula: see text] 5 [points]) and re-trained our model. Finally, we conducted an external validation with 150 images scored by five experienced psychologists.For fivefold cross-validation, our first model obtained MAE = 1.24 [points] and R-squared ([Formula: see text]) = 0.977. However, after evaluating and updating the model, the performance of the final model was improved (MAE = 0.95 [points], [Formula: see text] = 0.986). Predicted scores among cognitively normal, mild cognitive impairment, and dementia were significantly different. For the 150 independent test sets, the MAE and [Formula: see text] between AI and average scores by five human experts were 0.64 [points] and 0.994, respectively.We concluded that there was no fundamental difference between the rating scores of experienced psychologists and those of our AI scoring system. We expect that our AI psychologist will be able to contribute to screen the early stages of Alzheimer's disease pathology in medical checkup centers or large-scale community-based research institutes in a faster and cost-effective way.

    View details for DOI 10.1186/s13195-023-01283-w

    View details for PubMedID 37649070

    View details for PubMedCentralID PMC10466875

  • Heritability of cognitive abilities and regional brain structures in middle-aged to elderly East Asians. Cerebral cortex (New York, N.Y. : 1991) Lee, Y., Park, J. Y., Lee, J. J., Gim, J., Do, A. R., Jo, J., Park, J., Kim, K., Park, K., Jin, H., Choi, K. Y., Kang, S., Kim, H., Kim, S., Moon, S. H., Farrer, L. A., Lee, K. H., Won, S. 2023; 33 (10): 6051-6062


    This study examined the single-nucleotide polymorphism heritability and genetic correlations of cognitive abilities and brain structural measures (regional subcortical volume and cortical thickness) in middle-aged and elderly East Asians (Korean) from the Gwangju Alzheimer's and Related Dementias cohort study. Significant heritability was found in memory function, caudate volume, thickness of the entorhinal cortices, pars opercularis, superior frontal gyri, and transverse temporal gyri. There were 3 significant genetic correlations between (i) the caudate volume and the thickness of the entorhinal cortices, (ii) the thickness of the superior frontal gyri and pars opercularis, and (iii) the thickness of the superior frontal and transverse temporal gyri. This is the first study to describe the heritability and genetic correlations of cognitive and neuroanatomical traits in middle-aged to elderly East Asians. Our results support the previous findings showing that genetic factors play a substantial role in the cognitive and neuroanatomical traits in middle to advanced age. Moreover, by demonstrating shared genetic effects on different brain regions, it gives us a genetic insight into understanding cognitive and brain changes with age, such as aging-related cognitive decline, cortical atrophy, and neural compensation.

    View details for DOI 10.1093/cercor/bhac483

    View details for PubMedID 36642501

    View details for PubMedCentralID PMC10183741

  • A missense variant in SHARPIN mediates Alzheimer's disease-specific brain damages. Translational psychiatry Park, J. Y., Lee, D., Lee, J. J., Gim, J., Gunasekaran, T. I., Choi, K. Y., Kang, S., Do, A. R., Jo, J., Park, J., Park, K., Li, D., Lee, S., Kim, H., Dhanasingh, I., Ghosh, S., Keum, S., Choi, J. H., Song, G. J., Sael, L., Rhee, S., Lovestone, S., Kim, E., Moon, S. H., Kim, B. C., Kim, S., Saykin, A. J., Nho, K., Lee, S. H., Farrer, L. A., Jun, G. R., Won, S., Lee, K. H. 2021; 11 (1): 590


    Established genetic risk factors for Alzheimer's disease (AD) account for only a portion of AD heritability. The aim of this study was to identify novel associations between genetic variants and AD-specific brain atrophy. We conducted genome-wide association studies for brain magnetic resonance imaging measures of hippocampal volume and entorhinal cortical thickness in 2643 Koreans meeting the clinical criteria for AD (n = 209), mild cognitive impairment (n = 1449) or normal cognition (n = 985). A missense variant, rs77359862 (R274W), in the SHANK-associated RH Domain Interactor (SHARPIN) gene was associated with entorhinal cortical thickness (p = 5.0 × 10-9) and hippocampal volume (p = 5.1 × 10-12). It revealed an increased risk of developing AD in the mediation analyses. This variant was also associated with amyloid-β accumulation (p = 0.03) and measures of memory (p = 1.0 × 10-4) and executive function (p = 0.04). We also found significant association of other SHARPIN variants with hippocampal volume in the Alzheimer's Disease Neuroimaging Initiative (rs3417062, p = 4.1 × 10-6) and AddNeuroMed (rs138412600, p = 5.9 × 10-5) cohorts. Further, molecular dynamics simulations and co-immunoprecipitation indicated that the variant significantly reduced the binding of linear ubiquitination assembly complex proteins, SHPARIN and HOIL-1 Interacting Protein (HOIP), altering the downstream NF-κB signaling pathway. These findings suggest that SHARPIN plays an important role in the pathogenesis of AD.

    View details for DOI 10.1038/s41398-021-01680-5

    View details for PubMedID 34785643

    View details for PubMedCentralID PMC8595886

  • Visuospatial memory impairment as a potential neurocognitive marker to predict tau pathology in Alzheimer's continuum. Alzheimer's research & therapy Seo, E. H., Lim, H. J., Yoon, H. J., Choi, K. Y., Lee, J. J., Park, J. Y., Choi, S. H., Kim, H., Kim, B. C., Lee, K. H. 2021; 13 (1): 167


    Given that tau accumulation, not amyloid-β (Aβ) burden, is more closely connected with cognitive impairment in Alzheimer's disease (AD), a detailed understanding of the tau-related characteristics of cognitive function is critical in both clinical and research settings. We investigated the association between phosphorylated tau (p-Tau) level and cognitive impairment across the AD continuum and the mediating role of medial temporal lobe (MTL) atrophy. We also developed a prediction model for abnormal tau accumulation.We included participants from the Gwangju Alzheimer's Disease and Related Dementia Cohort in Korea, who completed cerebrospinal fluid analysis and clinical evaluation, and corresponded to one of three groups according to the biomarkers of A and T profiles based on the National Institute on Aging and Alzheimer's Association research framework. Multiple linear and logistic regression analyses were performed to examine the association between p-Tau and cognition and to develop prediction models. Receiver operating characteristic curve analysis was performed to examine the discrimination ability of the models.Among 185 participants, 93 were classified as A-T-, 23 as A+T-, and 69 as A+T+. There was an association between decreased visuospatial delayed memory performance and p-Tau level (B = - 0.754, β = - 0.363, p < 0.001), independent of other relevant variables (e.g., Aβ). MTL neurodegeneration was found to mediate the association between the two. Prediction models with visuospatial delayed memory alone (area under the curve [AUC] = 0.872) and visuospatial delayed memory and entorhinal thickness (AUC = 0.921) for abnormal tau accumulation were suggested and they were validated in an independent sample (AUC = 0.879 and 0.891, respectively).It is crucial to identify sensitive cognitive measures that capture subtle cognitive impairment associated with underlying pathological changes. Preliminary findings from the current study might suggest that abnormal tau accumulation underlies episodic memory impairment, particularly visuospatial modality, in the AD continuum. Suggested models are potentially useful in predicting tau pathology, and might be utilized practically in the field.

    View details for DOI 10.1186/s13195-021-00909-1

    View details for PubMedID 34627371

    View details for PubMedCentralID PMC8502282