Development of a Suicide Prediction Model for the Elderly Using Health Screening Data

Suicide poses a serious problem globally, especially among the elderly population. To tackle the issue, this study aimed to develop a model for predicting suicide by using machine learning based on the elderly population. To obtain a large sample, the study used the big data health screening cohort provided by the National Health Insurance Sharing Service. By applying a machine learning technique, a predictive model that comprehensively utilized various factors was developed to select the elderly aged > 65 years at risk of suicide. A total of 48,047 subjects were included in the analysis. Individuals who died by suicide were older, and the number of men was significantly greater. The suicide group had a more prominent history of depression, with the use of medicaments significantly higher. Specifically, the prescription of benzodiazepines alone was associated with a high suicide risk. Furthermore, body mass index, waist circumference, total cholesterol, and low-density lipoprotein level were lower in the suicide group. We developed a model for predicting suicide by using machine learning based on the elderly population. This suicide prediction model can satisfy the performance to some extent by employing only the medical service usage behavior without subjective reports.

Download Full-text

Is Machine Learning-derived Low-Density Lipoprotein Estimation more reliable than standard closed form equations? Insights from a laboratory database by comparison with a direct homogeneous assay

Clinica Chimica Acta ◽

10.1016/j.cca.2021.05.008 ◽

2021 ◽

Author(s):

Vanda Barakett-Hamade ◽

Jean Pierre Ghayad ◽

Gilbert Mchantaf ◽

Ghassan Sleilaty

Keyword(s):

Machine Learning ◽

Closed Form ◽

Low Density Lipoprotein ◽

Density Lipoprotein ◽

Low Density ◽

Homogeneous Assay

Download Full-text

Baseline Characteristics and Effects of Growth Hormone Therapy over Two Years in Younger and Elderly Adults with Adult Onset GH Deficiency

The Journal of Clinical Endocrinology & Metabolism ◽

10.1210/jc.2006-0887 ◽

2006 ◽

Vol 91 (11) ◽

pp. 4408-4414 ◽

Cited By ~ 21

Author(s):

Celina Franco ◽

Gudmundur Johannsson ◽

Bengt-Åke Bengtsson ◽

Johan Svensson

Keyword(s):

Elderly Patients ◽

Low Density Lipoprotein ◽

Density Lipoprotein ◽

The Elderly ◽

Adult Onset ◽

Mineral Density ◽

Open Label ◽

Gh Replacement ◽

Waist Hip Ratio ◽

Baseline Characteristics

Abstract Context: The effects of GH replacement in elderly GH-deficient (GHD) adults are not well known. Objective/Design/Patients: In this prospective, single-center, open-label study, baseline characteristics and the effects of 2-yr GH replacement were determined in 24 GHD adults above 65 yr of age and in 24 younger GHD patients (mean age, 37 yr; range, 27–46 yr). All patients had adult onset disease, and both groups were comparable in terms of the number of pituitary hormonal deficiencies, gender, body mass index, and waist/hip ratio. Duration of hypopituitarism was, however, longer in the elderly patients. Results: The mean maintenance dose of GH was 0.31 (sem, 0.03) mg/d in the elderly GHD patients and 0.44 (0.04) mg/d in the younger patients. The less marked response in IGF-I sd score, total body fat, and extracellular water in the elderly patients lost significance when the dose of GH was accounted for in the statistical analyses. Despite the lower dose in the elderly GHD group, these patients had a more marked reduction in waist/hip ratio and serum low-density lipoprotein-cholesterol level, and these differences remained also after correction for duration of hypopituitarism. There was no difference at baseline or in responsiveness in lean mass, bone mineral density, and glucose homeostasis. Conclusions: This study identifies elderly GHD adults as a GH-sensitive group in whom a low dose of GH can improve body composition and serum lipid profile without any significant impairment of glucose metabolism. GH replacement should therefore be considered in elderly GHD adults.

Download Full-text