Long-Term Survival Prediction Model for Elderly Community Members Using a Deep Learning Method.

In an aging society, maintaining healthy aging, preventing death, and enabling a continuation of economic activities are crucial. This study sought to develop a model for predicting survival times among community-dwelling older individuals using a deep learning method, and to identify the level of influence of various risk factors on the survival period, so that older individuals can manage their own health. This study used the Korean National Health Insurance Service claims data. We observed community-dwelling older people, aged 66 years, for 11 years and developed a survival time prediction model. Of the 189,697 individuals enrolled at baseline, 180,235 (95.0%) survived from 2009 to 2019, while 9462 (5.0%) died. Using deep-learning-based models (C statistics = 0.7011), we identified various factors impacting survival: Charlson's comorbidity index; the frailty index; long-term care benefit grade; disability grade; income level; a combination of diabetes mellitus, hypertension, and dyslipidemia; sex; smoking status; and alcohol consumption habits. In particular, Charlson's comorbidity index (SHAP value: 0.0445) and frailty index (SHAP value: 0.0443) were strong predictors of survival time. Prediction models may help researchers to identify potentially modifiable risk factors that may affect survival.

The growth of a low defect InAs HEMT structure on Si by using an AlGaSb buffer layer containing InSb quantum dots for dislocation termination.

It is found that the surface migration and nucleation behaviors of InSb quantum dots on AlSb/Si substrates, formed by molecular beam epitaxy in Stranski-Krastanov (SK) growth mode, are dependent on the substrate temperature. At relatively high temperatures above 430 degrees C, quantum dots are migrated and preferentially assembled onto the surface steps of high defect AlSb layers grown on Si substrates, while they are uniformly distributed on the surface at lower temperatures below 400 degrees C. It is also found that quantum dots located on the defect sites lead to effective termination of the propagation of micro-twin-induced structural defects into overlying layers, resulting in the low defect material grown on a largely mismatched substrate. The resulting 1.0 microm thick Al(x)Ga(1-x)Sb (x = 0.8) layer grown on the silicon substrate shows atomically flat (0.2 nm AFM mean roughness) surface and high crystal quality, represented by a narrow full width at half-maximum of 300 arc s in the x-ray rocking curve. The room-temperature electron mobility of higher than 16 000 cm(2) V(-1) s(-1) in InAs/AlGaSb FETs on the Si substrate is obtained with a relatively thin buffer layer, when a low defect density ( approximately 10(6) cm(-2)) AlGaSb buffer layer is obtained by the proposed method.