Scribd
Upload
2 views1 page

Poisson Regression for ER Visit Prediction

The hospital uses a Poisson regression model to predict weekly emergency room visits based on patient age and chronic condition. The coefficient for Age indicates that each additional year decreases the expected visits by 0.03, while having a chronic condition increases expected visits by 0.5. For a 60-year-old patient with a chronic condition, the expected number of visits per week is approximately 15.14.

Uploaded by

slakshmi.epcet
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
2 views1 page

Poisson Regression for ER Visit Prediction

The hospital uses a Poisson regression model to predict weekly emergency room visits based on patient age and chronic condition. The coefficient for Age indicates that each additional year decreases the expected visits by 0.03, while having a chronic condition increases expected visits by 0.5. For a 60-year-old patient with a chronic condition, the expected number of visits per week is approximately 15.14.

Uploaded by

slakshmi.epcet
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd

A hospital is using a Poisson regression model (a type of GLM) to predict the

number of emergency room visits per week based on patient age and medical history.
The model is given by: Log(λ) =2.5-0.03*Age+0.5*condition
where λ is the expected number of visits per week, Age is the patient's age, and
condition is a binary variable (1 if the patient has a chronic condition, 0
otherwise).
Interpret the coefficients of Age and condition.
What is the expected number of visits per week for a 60-year-old patient with a
chronic condition?

import numpy as np
# Given Poisson regression coefficients
intercept = 2.5
coef_age = -0.03
coef_condition = 0.5

# Patient information
age = 60
condition = 1 # 1 if patient has chronic condition, 0 otherwise

# Calculate log(lambda)
log_lambda = intercept + coef_age * age + coef_condition * condition

# Convert to expected number of visits


expected_visits = [Link](log_lambda)
print(f"Expected number of visits (with chronic condition): {expected_visits:.2f}")

# If patient does NOT have chronic condition


condition = 0
log_lambda_no_condition = intercept + coef_age * age + coef_condition * condition
expected_visits_no_condition = [Link](log_lambda_no_condition)
print(f"Expected number of visits (without chronic condition):
{expected_visits_no_condition:.2f}")

You might also like