1.Dementia Overdiagnosis in Younger, Higher Educated Individuals Based on MMSE Alone: Analysis Using Deep Learning Technology
Hye-Geum KIM ; Dai-Seg BAI ; Bon-Hoon KOO ; Eun-Jin CHEON ; Seokho YUN ; So Hye JO ; Byoungyoung GU
Journal of Korean Medical Science 2025;40(9):e20-
		                        		
		                        			 Background:
		                        			Dementia is a multifaceted disorder that affects cognitive function, necessitating accurate diagnosis for effective management and treatment. Although the Mini-Mental State Examination (MMSE) is widely used to assess cognitive impairment, its standalone efficacy is debated. This study examined the effectiveness of the MMSE alone versus in combination with other cognitive assessments in predicting dementia diagnosis, with the aim of refining the diagnostic accuracy for dementia. 
		                        		
		                        			Methods:
		                        			A total of 2,863 participants with subjective cognitive complaints who underwent comprehensive neuropsychological assessments were included. We developed two random forest models: one using only the MMSE and another incorporating additional cognitive tests.These models were evaluated based on their accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) on a 70:30 training-to-testing split. 
		                        		
		                        			Results:
		                        			The MMSE-alone model predicted dementia with an accuracy of 86% and AUC of 0.872. The expanded model demonstrated increased accuracy (88%) and an AUC of 0.934.Notably, 17.46% of the cases were reclassified from dementia to non-dementia category upon including additional tests. Higher educational level and younger age were associated with these shifts. 
		                        		
		                        			Conclusion
		                        			The findings suggest that although the MMSE is a valuable screening tool, it should not be used in isolation to determine dementia severity. The addition of diverse cognitive assessments can significantly enhance diagnostic precision, particularly in younger and more educated populations. Future diagnostic protocols should integrate multifaceted cognitive evaluations to reflect the complexity of dementia accurately. 
		                        		
		                        		
		                        		
		                        	
2.Who Dies Alone? Demographics, Underlying Diseases, and Healthcare Utilization Patterns of Lonely Death Individuals in Korea
Haibin BAI ; Jae-ryun LEE ; Min Jung KANG ; Young-Ho JUN ; Hye Yeon KOO ; Jieun YUN ; Jee Hoon SOHN ; Jin Yong LEE ; Hyejin LEE
Journal of Preventive Medicine and Public Health 2025;58(2):218-226
		                        		
		                        			 Objectives:
		                        			Lonely death is defined as “a person living in a state of social isolation, disconnected from family, relatives, and others, who dies from suicide, illness, or other causes”. This study investigated the characteristics of individuals who die alone in Korea. 
		                        		
		                        			Methods:
		                        			We constructed a database of lonely death cases by linking data from the Korea Crime Scene Investigation Unit of the Korea National Police Agency with National Health Insurance Service (NHIS) records. A descriptive analysis was performed to evaluate the demographics, underlying diseases, and healthcare utilization patterns among lonely death cases. 
		                        		
		                        			Results:
		                        			Among the 3122 individuals identified as lonely death cases, 2621 (84.0%) were male and 501 (16.0%) were female. The most common age group was 50-59 years (n=930, 29.8%). The NHIS covered 2161 individuals (69.2%), whereas 961 individuals (30.8%) were enrolled in Medical Aid (MA). The highest number of lonely deaths occurred in Seoul areas, with 1468 cases (47.0%). Mood disorders were diagnosed in 1020 individuals (32.7%), and various alcohol-related diseases, including alcoholic liver disease, were also observed. Outpatient visits increased leading up to death but declined in the final 3 months, while hospitalizations decreased and emergency room visits slightly increased. 
		                        		
		                        			Conclusions
		                        			Most lonely death cases involved male in their 50s, with a disproportionately high number of MA beneficiaries compared to the general population. Many of these individuals also experienced mental health issues or alcohol-related disorders. Preventing social isolation and strengthening social safety nets are critical to reducing the occurrence of lonely deaths. 
		                        		
		                        		
		                        		
		                        	
3.Factors Affecting Life-Sustaining Treatment Decisions and Changes in Clinical Practice after Enforcement of the Life-Sustaining Treatment (LST) Decision Act: A Tertiary Hospital Experience in Korea
Yoon Jung JANG ; Yun Jung YANG ; Hoi Jung KOO ; Hye Won YOON ; Seongbeom UHM ; Sun Young KIM ; Jeong Eun KIM ; Jin Won HUH ; Tae Won KIM ; Seyoung SEO
Cancer Research and Treatment 2025;57(1):280-288
		                        		
		                        			 Purpose:
		                        			In Korea, the Act on Hospice and Palliative Care and Decisions on Life-Sustaining Treatment (LST) was implemented on February 4, 2018. We aimed to investigate relevant factors and clinical changes associated with LST decisions after law enforcement. 
		                        		
		                        			Materials and Methods:
		                        			This single-center retrospective study included patients who completed LST documents using legal forms at Asan Medical Center from February 5, 2018, to June 30, 2020. 
		                        		
		                        			Results:
		                        			5,896 patients completed LST documents, of which 2,704 (45.8%) signed the documents in person, while family members of 3,192 (54%) wrote the documents on behalf of the patients. Comparing first year and following year of implementation of the act, the self-documentation rate increased (43.9% to 47.2%, p=0.014). Moreover, the number of LST decisions made during or after intensive care unit admission decreased (37.8% vs. 35.2%, p=0.045), and the completion rate of LST documents during chemotherapy increased (6.6% vs. 8.9%, p=0.001). In multivariate analysis, age < 65 (odds ratio [OR], 1.724; 95% confidence interval [CI], 1.538 to 1.933; p < 0.001), unmarried status (OR, 1.309; 95% CI, 1.097 to 1.561; p=0.003), palliative care consultation (OR, 1.538; 95% CI, 1.340 to 1.765; p < 0.001), malignancy (OR, 1.864; 95% CI, 1.628 to 2.133; p < 0.001), and changes in timing on the first year versus following year (OR, 1.124; 95% CI, 1.003 to 1.260; p=0.045) were related to a higher self-documentation rate. 
		                        		
		                        			Conclusion
		                        			Age < 65 years, unmarried status, malignancy, and referral to a palliative care team were associated with patients making LST decisions themselves. Furthermore, the subject and timing of LST decisions have changed with the LST act. 
		                        		
		                        		
		                        		
		                        	
4.Dementia Overdiagnosis in Younger, Higher Educated Individuals Based on MMSE Alone: Analysis Using Deep Learning Technology
Hye-Geum KIM ; Dai-Seg BAI ; Bon-Hoon KOO ; Eun-Jin CHEON ; Seokho YUN ; So Hye JO ; Byoungyoung GU
Journal of Korean Medical Science 2025;40(9):e20-
		                        		
		                        			 Background:
		                        			Dementia is a multifaceted disorder that affects cognitive function, necessitating accurate diagnosis for effective management and treatment. Although the Mini-Mental State Examination (MMSE) is widely used to assess cognitive impairment, its standalone efficacy is debated. This study examined the effectiveness of the MMSE alone versus in combination with other cognitive assessments in predicting dementia diagnosis, with the aim of refining the diagnostic accuracy for dementia. 
		                        		
		                        			Methods:
		                        			A total of 2,863 participants with subjective cognitive complaints who underwent comprehensive neuropsychological assessments were included. We developed two random forest models: one using only the MMSE and another incorporating additional cognitive tests.These models were evaluated based on their accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) on a 70:30 training-to-testing split. 
		                        		
		                        			Results:
		                        			The MMSE-alone model predicted dementia with an accuracy of 86% and AUC of 0.872. The expanded model demonstrated increased accuracy (88%) and an AUC of 0.934.Notably, 17.46% of the cases were reclassified from dementia to non-dementia category upon including additional tests. Higher educational level and younger age were associated with these shifts. 
		                        		
		                        			Conclusion
		                        			The findings suggest that although the MMSE is a valuable screening tool, it should not be used in isolation to determine dementia severity. The addition of diverse cognitive assessments can significantly enhance diagnostic precision, particularly in younger and more educated populations. Future diagnostic protocols should integrate multifaceted cognitive evaluations to reflect the complexity of dementia accurately. 
		                        		
		                        		
		                        		
		                        	
5.PDK4 expression and tumor aggressiveness in prostate cancer
Eun Hye LEE ; Yun-Sok HA ; Bo Hyun YOON ; Minji JEON ; Dong Jin PARK ; Jiyeon KIM ; Jun-Koo KANG ; Jae-Wook CHUNG ; Bum Soo KIM ; Seock Hwan CHOI ; Hyun Tae KIM ; Tae-Hwan KIM ; Eun Sang YOO ; Tae Gyun KWON
Investigative and Clinical Urology 2025;66(3):227-235
		                        		
		                        			 Purpose:
		                        			Prostate cancer ranks as the second most common cancer in men globally, representing a significant cause of cancer-related mortality. Metastasis, the spread of cancer cells from the primary site to distant organs, remains a major challenge in managing prostate cancer. Pyruvate dehydrogenase kinase 4 (PDK4) is implicated in the regulation of aerobic glycolysis, emerging as a potential player in various cancers. However, its role in prostate cancer remains unclear. This study aims to analyze PDK4 expression in prostate cancer cells and human samples, and to explore the gene's clinical significance. 
		                        		
		                        			Materials and Methods:
		                        			PDK4 expression was detected in cell lines and human tissue samples. Migration ability was analyzed using Matrigel-coated invasion chambers. Human samples were obtained from the Kyungpook National University Chilgok Hospital. 
		                        		
		                        			Results:
		                        			PDK4 expression was elevated in prostate cancer cell lines compared to normal prostate cells, with particularly high levels in DU145 and LnCap cell lines. PDK4 knockdown in these cell lines suppressed their invasion ability, indicating a potential role of PDK4 in prostate cancer metastasis. Furthermore, our results revealed alterations in epithelial-mesenchymal transition markers and downstream signaling molecules following PDK4 suppression, suggesting its involvement in the modulation of invasion-related pathways. Furthermore, PDK4 expression was increased in prostate cancer tissues, especially in castration-resistant prostate cancer, compared to normal prostate tissues, with PSA and PDK4 expression showing a significantly positive correlation. 
		                        		
		                        			Conclusions
		                        			PDK4 expression in prostate cancer is associated with tumor invasion and castration status. Further validation is needed to demonstrate its effectiveness as a therapeutic target. 
		                        		
		                        		
		                        		
		                        	
6.Factors Affecting Life-Sustaining Treatment Decisions and Changes in Clinical Practice after Enforcement of the Life-Sustaining Treatment (LST) Decision Act: A Tertiary Hospital Experience in Korea
Yoon Jung JANG ; Yun Jung YANG ; Hoi Jung KOO ; Hye Won YOON ; Seongbeom UHM ; Sun Young KIM ; Jeong Eun KIM ; Jin Won HUH ; Tae Won KIM ; Seyoung SEO
Cancer Research and Treatment 2025;57(1):280-288
		                        		
		                        			 Purpose:
		                        			In Korea, the Act on Hospice and Palliative Care and Decisions on Life-Sustaining Treatment (LST) was implemented on February 4, 2018. We aimed to investigate relevant factors and clinical changes associated with LST decisions after law enforcement. 
		                        		
		                        			Materials and Methods:
		                        			This single-center retrospective study included patients who completed LST documents using legal forms at Asan Medical Center from February 5, 2018, to June 30, 2020. 
		                        		
		                        			Results:
		                        			5,896 patients completed LST documents, of which 2,704 (45.8%) signed the documents in person, while family members of 3,192 (54%) wrote the documents on behalf of the patients. Comparing first year and following year of implementation of the act, the self-documentation rate increased (43.9% to 47.2%, p=0.014). Moreover, the number of LST decisions made during or after intensive care unit admission decreased (37.8% vs. 35.2%, p=0.045), and the completion rate of LST documents during chemotherapy increased (6.6% vs. 8.9%, p=0.001). In multivariate analysis, age < 65 (odds ratio [OR], 1.724; 95% confidence interval [CI], 1.538 to 1.933; p < 0.001), unmarried status (OR, 1.309; 95% CI, 1.097 to 1.561; p=0.003), palliative care consultation (OR, 1.538; 95% CI, 1.340 to 1.765; p < 0.001), malignancy (OR, 1.864; 95% CI, 1.628 to 2.133; p < 0.001), and changes in timing on the first year versus following year (OR, 1.124; 95% CI, 1.003 to 1.260; p=0.045) were related to a higher self-documentation rate. 
		                        		
		                        			Conclusion
		                        			Age < 65 years, unmarried status, malignancy, and referral to a palliative care team were associated with patients making LST decisions themselves. Furthermore, the subject and timing of LST decisions have changed with the LST act. 
		                        		
		                        		
		                        		
		                        	
7.Dementia Overdiagnosis in Younger, Higher Educated Individuals Based on MMSE Alone: Analysis Using Deep Learning Technology
Hye-Geum KIM ; Dai-Seg BAI ; Bon-Hoon KOO ; Eun-Jin CHEON ; Seokho YUN ; So Hye JO ; Byoungyoung GU
Journal of Korean Medical Science 2025;40(9):e20-
		                        		
		                        			 Background:
		                        			Dementia is a multifaceted disorder that affects cognitive function, necessitating accurate diagnosis for effective management and treatment. Although the Mini-Mental State Examination (MMSE) is widely used to assess cognitive impairment, its standalone efficacy is debated. This study examined the effectiveness of the MMSE alone versus in combination with other cognitive assessments in predicting dementia diagnosis, with the aim of refining the diagnostic accuracy for dementia. 
		                        		
		                        			Methods:
		                        			A total of 2,863 participants with subjective cognitive complaints who underwent comprehensive neuropsychological assessments were included. We developed two random forest models: one using only the MMSE and another incorporating additional cognitive tests.These models were evaluated based on their accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) on a 70:30 training-to-testing split. 
		                        		
		                        			Results:
		                        			The MMSE-alone model predicted dementia with an accuracy of 86% and AUC of 0.872. The expanded model demonstrated increased accuracy (88%) and an AUC of 0.934.Notably, 17.46% of the cases were reclassified from dementia to non-dementia category upon including additional tests. Higher educational level and younger age were associated with these shifts. 
		                        		
		                        			Conclusion
		                        			The findings suggest that although the MMSE is a valuable screening tool, it should not be used in isolation to determine dementia severity. The addition of diverse cognitive assessments can significantly enhance diagnostic precision, particularly in younger and more educated populations. Future diagnostic protocols should integrate multifaceted cognitive evaluations to reflect the complexity of dementia accurately. 
		                        		
		                        		
		                        		
		                        	
8.Who Dies Alone? Demographics, Underlying Diseases, and Healthcare Utilization Patterns of Lonely Death Individuals in Korea
Haibin BAI ; Jae-ryun LEE ; Min Jung KANG ; Young-Ho JUN ; Hye Yeon KOO ; Jieun YUN ; Jee Hoon SOHN ; Jin Yong LEE ; Hyejin LEE
Journal of Preventive Medicine and Public Health 2025;58(2):218-226
		                        		
		                        			 Objectives:
		                        			Lonely death is defined as “a person living in a state of social isolation, disconnected from family, relatives, and others, who dies from suicide, illness, or other causes”. This study investigated the characteristics of individuals who die alone in Korea. 
		                        		
		                        			Methods:
		                        			We constructed a database of lonely death cases by linking data from the Korea Crime Scene Investigation Unit of the Korea National Police Agency with National Health Insurance Service (NHIS) records. A descriptive analysis was performed to evaluate the demographics, underlying diseases, and healthcare utilization patterns among lonely death cases. 
		                        		
		                        			Results:
		                        			Among the 3122 individuals identified as lonely death cases, 2621 (84.0%) were male and 501 (16.0%) were female. The most common age group was 50-59 years (n=930, 29.8%). The NHIS covered 2161 individuals (69.2%), whereas 961 individuals (30.8%) were enrolled in Medical Aid (MA). The highest number of lonely deaths occurred in Seoul areas, with 1468 cases (47.0%). Mood disorders were diagnosed in 1020 individuals (32.7%), and various alcohol-related diseases, including alcoholic liver disease, were also observed. Outpatient visits increased leading up to death but declined in the final 3 months, while hospitalizations decreased and emergency room visits slightly increased. 
		                        		
		                        			Conclusions
		                        			Most lonely death cases involved male in their 50s, with a disproportionately high number of MA beneficiaries compared to the general population. Many of these individuals also experienced mental health issues or alcohol-related disorders. Preventing social isolation and strengthening social safety nets are critical to reducing the occurrence of lonely deaths. 
		                        		
		                        		
		                        		
		                        	
9.Factors Affecting Life-Sustaining Treatment Decisions and Changes in Clinical Practice after Enforcement of the Life-Sustaining Treatment (LST) Decision Act: A Tertiary Hospital Experience in Korea
Yoon Jung JANG ; Yun Jung YANG ; Hoi Jung KOO ; Hye Won YOON ; Seongbeom UHM ; Sun Young KIM ; Jeong Eun KIM ; Jin Won HUH ; Tae Won KIM ; Seyoung SEO
Cancer Research and Treatment 2025;57(1):280-288
		                        		
		                        			 Purpose:
		                        			In Korea, the Act on Hospice and Palliative Care and Decisions on Life-Sustaining Treatment (LST) was implemented on February 4, 2018. We aimed to investigate relevant factors and clinical changes associated with LST decisions after law enforcement. 
		                        		
		                        			Materials and Methods:
		                        			This single-center retrospective study included patients who completed LST documents using legal forms at Asan Medical Center from February 5, 2018, to June 30, 2020. 
		                        		
		                        			Results:
		                        			5,896 patients completed LST documents, of which 2,704 (45.8%) signed the documents in person, while family members of 3,192 (54%) wrote the documents on behalf of the patients. Comparing first year and following year of implementation of the act, the self-documentation rate increased (43.9% to 47.2%, p=0.014). Moreover, the number of LST decisions made during or after intensive care unit admission decreased (37.8% vs. 35.2%, p=0.045), and the completion rate of LST documents during chemotherapy increased (6.6% vs. 8.9%, p=0.001). In multivariate analysis, age < 65 (odds ratio [OR], 1.724; 95% confidence interval [CI], 1.538 to 1.933; p < 0.001), unmarried status (OR, 1.309; 95% CI, 1.097 to 1.561; p=0.003), palliative care consultation (OR, 1.538; 95% CI, 1.340 to 1.765; p < 0.001), malignancy (OR, 1.864; 95% CI, 1.628 to 2.133; p < 0.001), and changes in timing on the first year versus following year (OR, 1.124; 95% CI, 1.003 to 1.260; p=0.045) were related to a higher self-documentation rate. 
		                        		
		                        			Conclusion
		                        			Age < 65 years, unmarried status, malignancy, and referral to a palliative care team were associated with patients making LST decisions themselves. Furthermore, the subject and timing of LST decisions have changed with the LST act. 
		                        		
		                        		
		                        		
		                        	
10.Dementia Overdiagnosis in Younger, Higher Educated Individuals Based on MMSE Alone: Analysis Using Deep Learning Technology
Hye-Geum KIM ; Dai-Seg BAI ; Bon-Hoon KOO ; Eun-Jin CHEON ; Seokho YUN ; So Hye JO ; Byoungyoung GU
Journal of Korean Medical Science 2025;40(9):e20-
		                        		
		                        			 Background:
		                        			Dementia is a multifaceted disorder that affects cognitive function, necessitating accurate diagnosis for effective management and treatment. Although the Mini-Mental State Examination (MMSE) is widely used to assess cognitive impairment, its standalone efficacy is debated. This study examined the effectiveness of the MMSE alone versus in combination with other cognitive assessments in predicting dementia diagnosis, with the aim of refining the diagnostic accuracy for dementia. 
		                        		
		                        			Methods:
		                        			A total of 2,863 participants with subjective cognitive complaints who underwent comprehensive neuropsychological assessments were included. We developed two random forest models: one using only the MMSE and another incorporating additional cognitive tests.These models were evaluated based on their accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) on a 70:30 training-to-testing split. 
		                        		
		                        			Results:
		                        			The MMSE-alone model predicted dementia with an accuracy of 86% and AUC of 0.872. The expanded model demonstrated increased accuracy (88%) and an AUC of 0.934.Notably, 17.46% of the cases were reclassified from dementia to non-dementia category upon including additional tests. Higher educational level and younger age were associated with these shifts. 
		                        		
		                        			Conclusion
		                        			The findings suggest that although the MMSE is a valuable screening tool, it should not be used in isolation to determine dementia severity. The addition of diverse cognitive assessments can significantly enhance diagnostic precision, particularly in younger and more educated populations. Future diagnostic protocols should integrate multifaceted cognitive evaluations to reflect the complexity of dementia accurately. 
		                        		
		                        		
		                        		
		                        	
            
Result Analysis
Print
Save
E-mail