Clinical Characteristics and Follow-up Assessment in Patients Diagnosed With Alzheimer's Dementia Through Regional Dementia Centers and Conventional Hospital System.

BACKGROUND: The rapidly increasing socioeconomic strain caused by dementia represents a significant public health concern. Regional dementia centers (RDCs) have been established nationwide, and they aim to provide timely screening and diagnosis of dementia. This study investigated the clinical characteristics and progression of patients diagnosed with Alzheimer's dementia (AD), who underwent treatment in RDCs or conventional community-based hospital systems. METHODS: This retrospective single-center cohort study included patients who were diagnosed with AD between January 2019 and March 2022. This study compared two groups of patients: the hospital group, consisting of patients who presented directly to the hospital, and the RDC group, those who were referred to the hospital from the RDCs in Pohang city. The clinical courses of the patients were monitored for a year after AD diagnosis. RESULTS: A total of 1,209 participants were assigned to the hospital (n = 579) or RDC group (n = 630). The RDC group had a mean age of 80.1 years ± 6.6 years, which was significantly higher than that of the hospital group (P < 0.001). The RDC group had a higher proportion of females (38.3% vs. 31.9%; P = 0.022), higher risk for alcohol consumption (12.4% vs. 3.3%; P < 0.001), and greater number of patients who discontinued treatment 1 year after diagnosis (48.3% vs. 39.0%; P = 0.001). In the linear regression model, the RDC group was independently associated with the clinical dementia rating sum of boxes increment (ß = 22.360, R²\n = 0.048, and P < 0.001). CONCLUSION: Patients in the RDC group were older, had more advanced stages of conditions, and exhibited a more rapid rate of cognitive decline than patients diagnosed through the conventional hospital system. Our results suggested that RDC contributed to the screening of AD in a local region, and further nationwide study with the RDC database of various areas of Korea is needed.

Effects of Socioeconomic Status and Residence Areas on Long-Term Survival in Patients With Early-Onset Dementia: The Korean National Health Insurance Service Database Study.

BACKGROUND: Early-onset dementia (EOD) is still insufficiently considered for healthcare policies. We investigated the effect of socio-environmental factors on the long-term survival of patients with EOD. METHODS: This retrospective cohort study utilized the Korean National Health Insurance Database from 2007 to 2018. We enrolled 3,825 patients aged 40 to 65 years old with all types of dementia newly diagnosed in 2009 as EOD cases. We defined socioeconomic status using the national health insurance premium (NHIP) levels. Residential areas were classified into capital, metropolitan, city, and county levels. All-cause mortality was the primary outcome. Kaplan-Meier curves and log-rank tests were employed. Further, Cox-proportional hazards models were established. RESULTS: The mean survival of the fourth NHIP level group was 96.31 ± 1.20 months, whereas that of the medical-aid group was 85.53 ± 1.30 months (P < 0.001). The patients living in the capital had a mean survival of 95.73 ± 1.34 months, whereas those living in the county had 89.66 ± 1.75 months (P = 0.035). In the Cox-proportional hazards model, the medical-aid (adjusted hazard ratio [aHR], 1.67; P < 0.001), first NHIP level (aHR, 1.26; P = 0.012), and second NHIP level (aHR, 1.26; P = 0.008) groups were significantly associated with a higher long-term mortality risk. The capital residents exhibited a significantly lower long-term mortality risk than did the county residents (aHR, 0.82; P = 0.041). CONCLUSION: Socioeconomic status and residential area are associated with long-term survival in patients with EOD. This study provides a rational basis for establishing a healthcare policy for patients with EOD.

Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea.

BACKGROUND: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. METHODS: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. RESULTS: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. CONCLUSIONS: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful.