Prediction of mortality in an intensive care unit using logistic regression and a hidden Markov model

Intensive care medicine is a large share of the health care budget, and in the last decade there has been an increasing focus on making intensive care medicine more cost-effective by the efficient use of resources while still providing the best outcome for critically-ill patients. One important set of tools to perform this are critical illness severity assessment scores such as Simplified Acute Physiology score (SAPS-I) which help clinicians prioritize resources and determine the appropriate diagnostic/therapeutic plan for each patient. These scores are also used for assessing how medications, care guidelines, surgery, and other interventions impact mortality in Intensive Care Unit (ICU) patients. In an attempt to develop an improved patient-specific prediction of in-hospital mortality, we propose an algorithm based on logistic regression and Hidden-Markov model using vital signs (vitals), laboratory values (labs) and fluid measurements that are commonly available in ICUs. The algorithm was trained on 4000 ICU patient records and was validated on two sets of unseen test data of 4000 ICU patients each. These datasets were obtained as a part of PhysionNet/CinC Challenge 2012 (prediction of the mortality in ICU). Two different metrics, namely, (Event1) the minimum of sensitivity and positive predictive value and (Event2) a goodness of fit measure (range-normalized Hosmer-Lemeshow (H) statistic) was used to assess the algorithm's performance. The proposed algorithm achieved an Event 1 score of 0.50, 0.50 and an Event 2 score of 15.18, 78.9 compared to SAPS-I (Event 1: 0.3170, 0.312 and Event 2: 66.03, 68.58) in the two different validation dataset respectively. Furthermore, since the proposed algorithm uses instantaneous values of vitals and labs, it could be used as a continuous, realtime patient specific indicator of mortality risk.