Multiple sclerosis is a complex and costly chronic (“3C”) condition that currently has no cure. In a condition like multiple sclerosis, which has an unpredictable course, the use of predictive analytics could help health systems learn better, faster, and to improve more effectively and predict rather than react to emerging health needs for people with MS. This study compared traditional statistical methods to different predictive analytics methods on two separate endpoints, MS relapse and all-cause urgent care. Binary logistic regression was compared with other machine learning models, specifically ridge, least absolute shrinkage and selection operator (LASSO), and random forest. Results indicated when comparing relapse indices across models’ random forest significantly outperformed logistic regression and other machine learning algorithms (ΔperfA =27.1%, ΔperfM =27.5%). However, for ΔperfF,, logistic regression and random forest performed relatively the same. Ridge and LASSO outperformed logistic regression (ΔperfM1 =0.9%, ΔperfM2 =9.4%, ΔperfF2=25.8%) respectively. Results indicated when comparing all-cause urgent care indices across models, logistic regression performed similarly to random forest and LASSO (ΔperfA = -1.1%, ΔperfM =1.58%, ΔperfA1 = -0.5%). Ridge performed worse overall compared to logistic regression (ΔperfA2 = -17.8%, ΔperfM2 = -3.84%).