🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!
susceptibility_bias
Susceptibility bias occurs when the groups being compared in a study have different baseline risks for the outcome of interest. This often happens in observational studies where treatment decisions are influenced by disease severity or patient characteristics. The resulting outcome differences may reflect the pre-existing risk profile rather than the treatment effect.
An observational study finds that patients receiving a new cancer drug have higher mortality than those on the standard treatment. However, the new drug was disproportionately prescribed to patients with more advanced disease, making it appear less effective than it actually is.
A study finds that patients who receive annual full-body MRI scans have higher rates of cancer diagnosis than those who don't, leading a journalist to claim MRI scans cause cancer. In reality, people who seek out expensive preventive scans tend to have stronger family histories of cancer or prior health concerns, making them inherently more likely to have cancer detected.
A health insurer's data shows that members enrolled in a disease management program for diabetes have more hospitalizations than non-enrolled diabetics. The insurer concludes the program is ineffective, ignoring that enrollment was targeted at the highest-risk, most poorly controlled patients who were already on a trajectory toward hospitalization.
Binary (yes/no) questions an LLM must answer to identify this aspect:
Do the treatment and control groups differ in their baseline risk for the outcome?
Type: binaryWas treatment assignment influenced by patient prognosis or disease severity?
Type: binaryCould physicians have selected treatments based on perceived patient vulnerability?
Type: binaryDoes the analysis fail to adjust for baseline risk differences between groups?
Type: binarySusceptibility bias occurs when the groups being compared in a study have different baseline risks for the outcome of interest. This often happens in observational studies where treatment decisions are influenced by disease severity or patient characteristics. The resulting outcome differences may reflect the pre-existing risk profile rather than the treatment effect.
In non-randomized settings, treatment choices are rarely random — they are guided by clinical judgment. Sicker patients often receive more aggressive treatments, creating a systematic confound between treatment assignment and prognosis.
Use randomized controlled trials to ensure balanced baseline risk. In observational studies, adjust for severity and prognostic factors using regression, stratification, or propensity scores. Be skeptical of treatment comparisons where allocation was based on clinical judgment.
Observational studies of statins initially showed conflicting results because patients prescribed statins tended to have higher cardiovascular risk. Without proper adjustment, statins appeared less effective — or even harmful — compared to no treatment.
Failing to account for a third variable that influences both the independent and dependent variables, creating a spurious apparent relationship. The 'lurking variable' problem that undermines causal claims from observational data.
Occupational studies overestimate worker health because severely ill people exit the workforce.
A trend in several groups that disappears or reverses when combined.
A statistical error that occurs when conditioning on a variable that is causally affected by two other variables creates a spurious association between those two variables. In a causal diagram, a collider is a variable where two causal arrows converge, and conditioning on it opens a non-causal path.
Systematic differences in care or treatment between groups beyond the intervention studied.
Use these tools to detect, analyze, or train this aspect.