A Priori Determination of the Pretest Probability
This work addresses a specific problem in medical diagnostics for clinicians by providing an incremental improvement to existing methods for disease prevalence estimation.
The paper tackles the problem of estimating the pretest probability of disease a priori, which is crucial for interpreting screening tests, by introducing a novel method based on modifying McGee's heuristic using the Logit function from logistic regression, resulting in a formula to approximate the minimal bound of this probability from patient signs or symptoms.
In this manuscript, we present various proposed methods estimate the prevalence of disease, a critical prerequisite for the adequate interpretation of screening tests. To address the limitations of these approaches, which revolve primarily around their a posteriori nature, we introduce a novel method to estimate the pretest probability of disease, a priori, utilizing the Logit function from the logistic regression model. This approach is a modification of McGee's heuristic, originally designed for estimating the posttest probability of disease. In a patient presenting with $n_θ$ signs or symptoms, the minimal bound of the pretest probability, $φ$, can be approximated by: $φ\approx \frac{1}{5}{ln\left[\displaystyle\prod_{θ=1}^{i}κ_θ\right]}$ where $ln$ is the natural logarithm, and $κ_θ$ is the likelihood ratio associated with the sign or symptom in question.