
Home Research Community acquired pneumonia Pre-op screening Legionella detection Virtual Sentinel Node Falls Risk Assessment CV Line Cost Benefit Health Systems Analysis Topics Courses People Links

Health Informatics Unit
The University of Adelaide
SA 5005 Australia
Email

Telephone:
+61 8 8274 3713
Facsimile:
+61 8 8271 9158

Patient Risk Modelling in Community Acquired Pneumonia (CAP)

Scott Clark

Health Informatics, University of Adelaide

A number of risk assessment rules have been derived to assist clinicians in the hospital admission decision for CAP [ 1 2 ]. The majority of these rules were derived to predict risk of mortality from risk factors and severity signs and are used for the decision to admit patients with CAP to hospital. While mortality is the most important outcome to consider, there are many complications of pneumonia that add significant components to the personal, social and financial cost of the disease [3] . Furthermore, none of the current prediction rules have been designed to assist other important decisions such as the decision to switch from IV to oral antibiotics, decision for further investigations, decision to discharge and decisions for supportive care such as oxygen. I plan to consider these factors when constructing risk models for CAP treatment decision support systems.

A decision model using influence diagrams considering variable dependencies has already been constructed (see figure 1). This model uses probability values from literature review for risk factors, severity signs, complications, treatment efficacies and outcomes. This will be supplemented by values from a teaching hospital CAP patient database. Cost is the current utility measure, however, the model will be expanded to include quasi-utility functions to represent patient preference [4] .

Figure 1: Decision model for CAP

The stability of the predictions of this model will be assessed by sensitivity analysis [5] . The performance of this model in comparison to that of the current teaching hospital guideline, and other current prediction models such as the Pneumonia Severity Index [2] and the BTS prediction rule [1] will be simulated using teaching hospital data.

References

1. Lim WS, Lewis S, Macfarlane JT. Severity prediction rules in community acquired pneumonia: a validation study. Thorax 2000;55(3):219-23.

2. Fine MJ, Auble TE, Yealy DM, Hanusa BH, Weissfeld LA, Singer DE, et al. A prediction rule to identify low-risk patients with community-acquired pneumonia [see comments]. N Engl J Med 1997;336(4):243-50.

3. Fine MJ, Smith MA, Carson CA, Mutha SS, Sankey SS, Weissfeld LA, et al. Prognosis and outcomes of patients with community-acquired pneumonia. A meta-analysis [see comments]. Jama 1996;275(2):134-41.

4. Glasziou P, Hilden J. Test selection measures. Med Decis Making 1989;9(2):133-41.

5. Clemen RT. Making Hard Decisions . Belmont, CA: Wadsworth, 1996.