Models for complications are being developed that can be used to analyze clinical data sets. In addition to regression models, Markov chains are used to analyze datasets in which care processes are incompletely mapped and are therefore only partially observable. Models for diabetic nephropathy and diabetic foot syndrome have been developed and are currently used.
Begun A, Icks A, Waldeyer R, Landwehr S, Koch M, Giani G. Identification of a Multistate Continuous Time Non-homogeneous Markov Chain Model for Patients with Decreased Renal Function. Medical Decision Making 2013; 33(2):298-306.
Begun A, Morbach S, Rümenapf G, Icks A. Study of Disease Progression and Relevant Risk Factors in Diabetic Foot Patients Using a Multistate Continuous-Time Markov Chain Model. PLos ONE 2016; 11(1):e0147533.