Table 3 AUC and 95% CI based on the conditional LASSO for each age if the explanatory variables were varied. The conditional logistic model was used for the analysis when only the number of medications taken was used as an explanatory variable, while the other analyses were conducted using conditional LASSO. All patients, 65–100 years; Early elderly, 65–74 years; Late elderly, 75–100 years; AUC, area under the curve; CI, confidence interval; PPV, Positive Predictive Value; NPV, Negative Predictive Value. Row 1 (total 1 variable), Number of medications; Row 2 (total 17 variables), Number of medications and comorbidities (16 variables); Row 3 (total 61 variables), Number of medications and concomitant medications (60 variables); Row 4 (total 77 variables), Number of medications, comorbidities (16 variables) and concomitant medications (60 variables).

From: Association between number of medications and hip fractures in Japanese elderly using conditional logistic LASSO regression