|
Abstract
|
OBJECTIVE: People with diabetes have a higher risk of suicidal behaviors than the general population. However, few studies have focused on understanding this relationship. We investigated risk factors and predicted suicide attempts in people with diabetes using the Least Absolute Shrinkage and Selection Operator (LASSO) regression.
METHOD: Data was retrieved from Cerner Real-World Data™ and included over 3 million diabetes patients in the study. Least absolute shrinkage and selection operator regression was applied to identify associated factors. Gender-, diabetes-type-, and depression-specific LASSO regression models were analyzed.
RESULTS: There were 7764 subjects diagnosed with suicide attempts with an average age of 45. We found risk factors for suicide attempts in diabetes patients, such as being an American Indian or Alaska Native (β = 0.637), atypical agents (β = 0.704), benzodiazepines (β = 0.784), and antihistamines (β = 0.528). Amyotrophy had a negative coefficient for suicide attempts in males with diabetes (β = -2.025); in contrast, it had a positive coefficient in females with diabetes (β = 3.339). Using MAOI had a negative coefficient for suicide attempts in T1DM patients (β = -7.304). Aged less than 20 had a positive coefficient for suicide attempts in depressed (β = 2.093) and non-depressed patients with diabetes (β = 1.497). The LASSO model had 94.4% AUC and 87.4% F1 score.
CONCLUSIONS: To our knowledge, this is the first study using LASSO regression to identify risk factors for suicide attempts and diabetes. The shrinkage technique successfully reduced the number of variables in the model to improve overfitting. Further research is needed to study cause-and-effect relationships. The results may help providers identify high-risk groups of suicide attempters among diabetes patients.
Language: en |