Biomedical subjects

J V Tu

Publications and source records attributed to J V Tu.

57 records · Page 4Linked to original sources

PubMed1992

Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery.

A patient's intensive care unit (ICU) length of stay following cardiac surgery is an important issue in Canada, where cardiovascular intensive care resources are limited and waiting lists for cardiac surgery exist. A predictive instrument for ICU length of stay could lead to improved utilization of existing ICU and operating room resources through better scheduling of patients and staff. We trained a neural network with a database of 713 patients and 15 input variables to predict patients who would have a prolonged ICU length of stay, which we defined as a stay greater than 2 days. In an independent test set of 696 patients, the network was able to stratify patients into three risk groups for prolonged stay (low, intermediate, and high), corresponding to frequencies of prolonged stay of 16.3%, 35.3%, and 60.8% respectively. The performance of the network was also evaluated by calculating the area under the Receiver Operating Characteristic (ROC) curve in the training set, 0.7094 (SE 0.0224), and in the test set, 0.6960 (SE 0.0227). We believe the trained network would be a useful predictive instrument for optimizing the scheduling of cardiac surgery patients in times of limited ICU resources. Neural networks are a new alternative method for developing predictive instruments that offer both advantages and disadvantages when compared to other more widely used statistical techniques.

Cardiac Surgical Procedures↗

PubMedDate not supplied

Outpatient antibiotic therapy and short term mortality in elderly patients with chronic obstructive pulmonary disease.

OBJECTIVE: To determine the association between outpatient use of oral antibiotics and 30-day all-cause mortality following hospitalization in a group of elderly chronic obstructive pulmonary disease (COPD) patients. DESIGN: A population-based retrospective cohort study. SETTING: Ontario, Canada. POPULATION STUDIED: All 26,301 patients, 65 years of age or older, who were hospitalized for COPD between 1992 and 1996 in Ontario. METHODS: All elderly patients admitted at least once with a most responsible diagnosis of COPD using the Canadian Institute for Health Information database were identified. They were then linked to the Ontario Drug Benefit database to determine the use of antibiotics within 30 days of the index hospitalization and to the Ontario registered persons database to determine the 30-day mortality following their index hospitalization. RESULTS: Outpatient use of antibiotics within 30 days before the index hospitalization was associated with a significant reduction in the 30-day mortality following hospitalization (odds ratio [OR] 0.83, 95% CI 0.75 to 0.92). Use of macrolides had the lowest relative odds for mortality (OR 0.58, 95% CI 0.47 to 0.73), while use of fluoroquinolones had the highest relative odds (OR 0.98, 95% CI 0.84 to 1.15). CONCLUSIONS: Use of antibiotics before hospitalization was associated with a significant reduction in the risk of short term mortality among a group of elderly COPD patients who eventually required hospitalization for their disease. These findings support the early use of antibiotics in COPD patients who experience an acute exacerbation.

Aged↗

PubMedDate not supplied

Predicting mortality after coronary artery bypass surgery: what do artificial neural networks learn? The Steering Committee of the Cardiac Care Network of Ontario.

OBJECTIVE: To compare the abilities of artificial neural network and logistic regression models to predict the risk of in-hospital mortality after coronary artery bypass graft (CABG) surgery. METHODS: Neural network and logistic regression models were developed using a training set of 4,782 patients undergoing CABG surgery in Ontario, Canada, in 1991, and they were validated in two test sets of 5,309 and 5,517 patients having CABG surgery in 1992 and 1993, respectively. RESULTS: The probabilities predicted from a fully trained neural network were similar to those of a "saturated" regression model, with both models detecting all possible interactions in the training set and validating poorly in the two test sets. A second neural network was developed by cross-validating a network against a new set of data and terminating network training early to create a more generalizable model. A simple "main effects" regression model without any interaction terms was also developed. Both of these models validated well, with areas under the receiver operating characteristic curves of 0.78 and 0.77 (p > 0.10) in the 1993 test set. The predictions from the two models were very highly correlated (r=0.95). CONCLUSIONS: Artificial neural networks and logistic regression models learn similar relationships between patient characteristics and mortality after CABG surgery.

Aged↗