Consider the example used in the instructional materials above

Subject:FinancePrice:8.86 Bought3

Share With

Consider the example used in the instructional materials above. You are an administrator whose responsibilities include a cardiac unit. Because congestive heart failure (CHF) is a high volume condition for your unit, you want to have a better understanding of some of the drivers of length of stay (LOS) for these patients. After a brief review of the literature, you find that several of the key factors affecting patient LOS for CHF are: the number of medications the patient is on upon admission, the duration of intravenous diuretics, and the number of comorbid conditions. You are also interested in whether gender affects LOS for your patient population. You ask a colleague whom you know to be familiar with statistics to perform separate, simple regression analyses regarding LOS and each of the factors of interest. Using the framework LOS = intercept + slope*key factor, your colleague presents you with the following results:

LOS as a function of the number of medications upon admission:

• Intercept = 5.2
• Slope = 0.15

LOS as a function of the duration of intravenous diuretics:

• Intercept = 5.1
• Slope = 0.25

LOS as a function of the number of comorbid conditions:

• Intercept = 5.0
• Slope = 0.4

LOS as a function of gender (when the patient is a male):

• Intercept = 5.85
• Slope = 0.05

Prepare an informal cheat sheet for yourself indicating the predicted LOS for each of the following:

1. What would LOS be for a patient admitted taking 0 prescription drugs? A patient taking 3 prescription drugs? A patient taking 6 prescription drugs?
2. What would LOS be for a patient receiving intravenous diuretics for 0 days? A patient receiving intravenous diuretics for 2 days? A patient receiving intravenous diuretics for 4 days?
3. What would LOS be for a patient who has 0 comorbid conditions? A patient who has 3 comorbid conditions? A patient who has 6 comorbid conditions?
4. What would the LOS be for a patient who is male? A patient who is female? Use a “dummy variable” to isolate the impact of gender on LOS. To do this, assign males the value of 1 and females the value of 0 when conducting your analysis.

Assignment 4.3 Regression Analysis and Predictions Name: 1. LOS for Patient Taking x Prescription Drugs 2. LOS for Patient Receiving Intravenous Diuretics for x Days 3. LOS for Patient with x Comorbid Conditions 4. LOS for patient who is… 0 3 6 0 2 4 0 3 6 Male Female Which of the factors has the biggest impact on LOS, and what insights from your analysis have improved your understanding of some drivers of LOS for your CHF patients? NOTE: GENDER IS KNOWN AS A “DUMMY” VARIABLE AND SHOULD BE INTERPRETED AS 1/0 WITH THE REFERENCE GROUP (i.e., MALE) TAKING THE VALUE 1. Regression Application Example SCENARIO: What is the relationship between a patient's length of stay (LOS) in an acute care hospital and the patient's severity of illness (SOI)? I suspect that patients with a higher SOI will have a longer LOS. There is a fairly easy Sol measure known as the Charlson Comorbidity Index that uses the number of comorbidities as a measure of severity of illness. Comorbidity is another way of saying "additional problem." For example, a patient may be in the hospital for heart failure but may also have diabetes. The key clinical condition is heart failure but the diabetes cannot be ignored. It is a complicating condition or comorbidity. The question that began the scenario is the problem statement. The null hypothesis is that SOI does not affect LOS (i.e., Ho: LOS with SOI = LOS without SOI), and our alternative is that SOI does affect LOS (i.e., Ha: LOS with SOI > LOS without SOI). We set out to collect data on LOS and comorbidities of patients admitted for pneumonia at my hospital. As is conventional, I set the range for the Charlson Comorbidity Index to 0-4. After my data collection, I run a simple regression analysis and find the following results: Intercept term 6.3 Slope term 1.6 I formalize my analysis as follows: RELATIONSHIP: LOS is dependent on SOI. I expect that as Sol increases, so will LOS (.e., there is a positive, direct relationship between LOS and SOI). LOS is the DEPENDENT variable and Sol is the INDEPENDENT variable. INTERCEPT TERM: The intercept term tells me that, independent of Sol, patients with pneumonia stay an average of 6.3 days in the hospital. SLOPE TERM: The slope term tells me the marginal impact of SOI on LOS. For every one unit increase in the Charlson Comorbidity Index, there is a 1.6 day increase in length of stay. APPLICATION: Based on the information above, the regression line is given as LOS = 6.3 + 1.6(SOI) Substituting the Charlson Comorbidity Index scores for SOL I get the following predictions: When SOI = 0, LOS = 6.3 (LOS = 6.3 +1.6*0 = 6.3) When SOI = 1. LOS = 7.9 (LOS = 6.3 +1.6*1 = 6.3 + 1.6 = 7.9) When SOI = 2, LOS = 9.5 (LOS = 6.3 +1.6*2 = 6.3 + 3.2 = 9.5) When SOI = 3, LOS = 11.1 (LOS = 6.3 +1.6* 3 = 6.3 + 4.8 = 11.1) 1