In the dynamic hospital setting, decision support can be a valuable tool for improving patient outcomes. Data-driven inference of future outcomes is challenging in this dynamic setting, where long sequences such as laboratory tests and medications are updated frequently. This is due in part to heterogeneity of data types and mixed-sequence types contained in variable length sequences. In this work we design a probabilistic unsupervised model for multiple arbitrary-length sequences contained in hospitalization Electronic Health Record (EHR) data. The model uses a latent variable structure and captures complex relationships between medications, diagnoses, laboratory tests, neurological assessments, and medications. It can be trained on original data, without requiring any lossy transformations or time binning. Inference algorithms are derived that use partial data to infer properties of the complete sequences, including their length and presence of specific values. We train this model on data from subjects receiving medical care in the Kaiser Permanente Northern California integrated healthcare delivery system. The results are evaluated against held-out data for predicting the length of sequences and presence of Intensive Care Unit (ICU) in hospitalization bed sequences. Our method outperforms a baseline approach, showing that in these experiments the trained model captures information in the sequences that is informative of their future values.
SOCIETY OF CRITICAL CARE MEDICINE 34TH CRITICAL CARE CONGRESS PHOENIX, ARIZONA, USA JANUARY 15-19, 2005: Poster Presentation: Clinical Science: Sepsis/Inflammation/Infection/Antimicrobial Agents (Adult) IV
Twenty patients undergoing an upper abdominal procedure were randomly assigned in two groups. One group was treated with both chest physical therapy and incentive spirometry and the other was treated with chest physical therapy alone. Spirometric values, respiratory rate, tidal volume and vital capacity were determined during the postoperative course. We observed that patients treated with incentive spirometry bad a faster return to preoperative pulmonary volumes. This observation confirms the prophylactic role of incentive spirometry in the prevention of pulmonary complications after laparotomy.
In patients with acute brain injury, altered CSF concentrations of protein biomarkers related to cytoskeletal damage, inflammation, apoptosis and oxidative stress may be predictive of worse neurological outcomes.
