The dynamics of disease progression in sepsis: Markov modeling describing the natural history and the likely impact of effective antisepsis agents

Abstract

We conducted a 9-month prospective cohort study of 2,527 patients with systemic inflammatory response syndrome in three intensive care units and three general wards in a tertiary health care institution. Markov models were developed to predict the probability of movement to and from more severe stages--sepsis, severe sepsis, or septic shock--at 1, 3, and 7 days. For patients with sepsis, severe sepsis, and septic shock, the probabilities of remaining in the same category after 1 day were .65, .68, and .61, respectively. The probability for progression after 1 day was .09 for sepsis to severe sepsis and .026 for severe sepsis to shock. The probability of patients with sepsis, severe sepsis, and septic shock dying after 1 day was .005, .009, and .079, respectively. The model can be used to predict the reduction in end organ dysfunction and mortality with use of increasingly effective antisepsis agents.