Compute post-test probabilities from pre-test probability and likelihood ratios using the classic Fagan nomogram (Fagan, 1975). Enter sensitivity and specificity, direct LR+ and LR-, or a 2x2 contingency table. Visualize with an interactive D3.js three-scale nomogram, export R code, and copy an auto-generated methods paragraph.
Load sample data to see how the tool works, or clear all fields to start fresh.
Drag & drop a file or
CSV, TSV, Excel (.xlsx/.xls) - max 500 rows
Use the slider or type a value to set the pre-test probability as a percentage. This represents the estimated probability of disease before testing, based on prevalence, clinical prediction rules, or clinical judgment. The slider covers the full range from 0.1% to 99.9%.
Select your preferred input format: sensitivity and specificity (most common in diagnostic accuracy studies), direct likelihood ratios (LR+ and LR-), or a 2x2 contingency table with true positives, false positives, false negatives, and true negatives. The tool computes all derived values automatically.
Provide the diagnostic test accuracy values for your chosen mode. When using sensitivity/specificity, enter values as percentages. For 2x2 tables, enter the raw cell counts. The tool derives likelihood ratios and post-test probabilities from any input format.
The D3.js nomogram renders three vertical scales with connecting lines. The solid red line traces the path for a positive test result (through LR+), and the dashed blue line traces the path for a negative test result (through LR-). Read the post-test probabilities where the lines intersect the right scale.
Examine the result cards below the nomogram. They display the pre-test probability, pre-test odds, positive and negative likelihood ratios, and the post-test probabilities for both positive and negative test outcomes, along with interpretation guidelines for likelihood ratio magnitudes.
Download the nomogram as a high-resolution PNG or PDF for journal submission. Copy the auto-generated methods paragraph, the R code for reproducing the analysis, or the numerical results as CSV. All exports include the complete set of input parameters and computed values.
Need this done professionally? Get a complete systematic review or meta-analysis handled end-to-end.
Get a Free QuoteThe same test with the same likelihood ratio produces very different post-test probabilities depending on the pre-test probability. A moderately useful test (LR+ of 5) applied in a high-prevalence setting (50%) raises the post-test probability to 83%, but in a low-prevalence screening setting (2%) it only raises it to 9%. Always consider the clinical context when interpreting likelihood ratios.
Likelihood ratios provide the most useful clinical information at extreme values. An LR+ above 10 produces large, clinically meaningful increases in post-test probability across most pre-test probability levels. An LR- below 0.1 produces similarly large decreases. Tests with likelihood ratios between 0.5 and 2.0 contribute very little to diagnostic certainty regardless of the pre-test probability.
The Fagan nomogram is a graphical implementation of Bayes theorem applied to diagnostic testing. The mathematical relationship is: post-test odds = pre-test odds multiplied by likelihood ratio. The log-scaled axes of the nomogram convert this multiplication into a straight-line relationship, making the Bayesian update visually intuitive and transparent.
While sensitivity and specificity describe the intrinsic accuracy of a test, they do not directly tell clinicians how to update their probability estimate after receiving a test result. Likelihood ratios, which combine sensitivity and specificity into a single metric for each test outcome, are the bridge between test accuracy and clinical decision-making.
A test that is excellent at ruling in disease (high LR+) may not be good at ruling it out (LR- close to 1), and vice versa. The Fagan nomogram displays both scenarios simultaneously, allowing clinicians to assess the full diagnostic utility of a test. The clinical question determines which direction matters most: ruling in versus ruling out.
When multiple independent tests are available, the post-test probability from the first test becomes the pre-test probability for the second test. Each sequential test result further updates the probability estimate. The Fagan nomogram can be applied iteratively in this manner, though the assumption of conditional independence between tests must hold for the sequential application to be valid.
The Fagan nomogram was introduced by Fagan (1975) as a simple graphical device for converting pre-test probability to post-test probability using likelihood ratios. It remains one of the most widely used tools in evidence-based medicine for translating the results of diagnostic accuracy studies into clinically actionable information. The underlying mathematics is Bayes theorem applied to diagnostic testing: post-test odds equal pre-test odds multiplied by the likelihood ratio. The nomogram converts this calculation into a visual straight-line operation using logarithmic scales.
In the context of diagnostic test accuracy meta-analysis, the Fagan nomogram serves as the final translational step. After pooling sensitivity and specificity across studies using bivariate or hierarchical models (Reitsma et al., 2005; Rutter and Gatsonis, 2001), researchers compute summary likelihood ratios from the pooled estimates. These summary likelihood ratios are then applied to clinically relevant pre-test probabilities using the nomogram to assess whether the test produces clinically meaningful shifts in probability. This approach is recommended in the Cochrane Handbook for Diagnostic Test Accuracy Reviews (Macaskill et al., 2023).
The positive likelihood ratio (LR+) quantifies the increase in odds of disease following a positive test result. It is calculated as sensitivity divided by (1 minus specificity), or equivalently, the true positive rate divided by the false positive rate. A high LR+ means that a positive test result is much more likely in patients with disease than in those without, producing a large upward shift on the nomogram. The negative likelihood ratio (LR-) quantifies the decrease in odds following a negative result. It equals (1 minus sensitivity) divided by specificity. A low LR- means a negative test result is much less likely in diseased patients, producing a large downward shift.
Clinicians and researchers should select pre-test probability carefully, as it fundamentally determines the clinical impact of any test result. For screening applications, the pre-test probability typically equals the disease prevalence in the screened population. For diagnostic applications, it reflects the clinician's assessment after initial history and examination. Clinical prediction rules, such as the Wells score for pulmonary embolism or the Centor score for streptococcal pharyngitis, provide validated estimates of pre-test probability that can be used directly with the nomogram.
A common pitfall in diagnostic reasoning is the base rate neglect, where clinicians anchor on test sensitivity and specificity without considering the pre-test probability. A test with 99% sensitivity and 99% specificity applied to a population with 0.1% prevalence still produces a positive predictive value of only about 9%. The Fagan nomogram makes this counterintuitive result visually obvious: the line from a very low pre-test probability through even a high likelihood ratio arrives at a surprisingly modest post-test probability.
For a complete diagnostic test accuracy assessment, combine this tool with our diagnostic test accuracy calculator for computing sensitivity, specificity, predictive values, and likelihood ratios from 2x2 tables. Assess the quality of diagnostic accuracy studies using our QUADAS-2 risk of bias tool. Visualize pooled diagnostic accuracy estimates on an SROC curve with our SROC curve generator. Present your meta-analysis results using the forest plot generator.
A Fagan nomogram is a graphical tool introduced by Fagan (1975) for applying Bayes theorem to diagnostic test results. It consists of three vertical scales: pre-test probability on the left, likelihood ratio in the center, and post-test probability on the right. By drawing a straight line from the pre-test probability through the likelihood ratio, you can read the resulting post-test probability on the right scale. The nomogram provides an intuitive visual representation of how a diagnostic test result changes the probability of disease, making Bayesian reasoning accessible without manual calculation.
To read a Fagan nomogram, start at the left scale with your estimated pre-test probability (the probability of disease before testing, often based on prevalence or clinical judgment). Draw a line through the center scale at the value of the positive likelihood ratio (LR+) for a positive test result, or the negative likelihood ratio (LR-) for a negative test result. Where this line intersects the right scale gives you the post-test probability. A higher LR+ shifts the line upward, increasing the post-test probability substantially. A lower LR- shifts the line downward, decreasing the post-test probability. Likelihood ratios near 1.0 produce minimal change.
Likelihood ratios quantify how much a test result changes the odds of disease. The positive likelihood ratio (LR+) equals sensitivity divided by (1 minus specificity), and represents how much more likely a positive test result is in someone with the disease compared to someone without it. The negative likelihood ratio (LR-) equals (1 minus sensitivity) divided by specificity, and represents how much less likely a negative test result is in someone with the disease. An LR+ greater than 10 or an LR- less than 0.1 provides strong evidence for ruling in or ruling out disease, respectively. Values between 0.5 and 2.0 are considered clinically uninformative.
Pre-test probability should be estimated before interpreting any diagnostic test result. It represents the clinician's best estimate of the probability that the patient has the condition in question, based on clinical findings, patient history, prevalence in the relevant population, and results of previous tests. Common sources for pre-test probability include disease prevalence in the patient's demographic group, validated clinical prediction rules, and expert clinical judgment. The choice of pre-test probability substantially affects the post-test probability: the same test applied to a high-prevalence population yields very different post-test probabilities compared to a low-prevalence screening context.
Diagnostic accuracy studies estimate sensitivity and specificity (or equivalently, likelihood ratios) of a test by comparing its results against a reference standard. These accuracy measures are the input to the Fagan nomogram. In a diagnostic test accuracy meta-analysis, sensitivity and specificity are pooled across multiple studies, and the resulting summary estimates can be fed into the nomogram to assess the clinical utility of the test at different pre-test probability thresholds. The Fagan nomogram thus bridges the gap between the statistical results of a diagnostic accuracy study and the clinical decision at the bedside.
The Fagan nomogram assumes that the test result is binary (positive or negative) and that the likelihood ratio is constant across the range of pre-test probabilities. In practice, some tests produce continuous results (such as biomarker levels), and the likelihood ratio may vary at different cut-off thresholds. The nomogram also requires accurate estimates of sensitivity and specificity, which can be affected by spectrum bias, verification bias, and heterogeneity across studies. Additionally, the nomogram applies Bayes theorem under the assumption that the test is conditionally independent of prior information, which may not hold if the pre-test probability was estimated partly from the same clinical features that influence the test result.
Compute sensitivity, specificity, predictive values, and likelihood ratios from a 2x2 table using our diagnostic test accuracy calculator. Assess risk of bias in diagnostic accuracy studies with our QUADAS-2 risk of bias tool. Generate summary ROC curves for diagnostic test accuracy meta-analysis with our SROC curve generator.
Reviewed by
Dr. Sarah Mitchell holds a PhD in Biostatistics from Johns Hopkins Bloomberg School of Public Health and has over 15 years of experience in systematic review methodology and meta-analysis. She has authored or co-authored 40+ peer-reviewed publications in journals including the Journal of Clinical Epidemiology, BMC Medical Research Methodology, and Research Synthesis Methods. A former Cochrane Review Group statistician and current editorial board member of Systematic Reviews, Dr. Mitchell has supervised 200+ evidence synthesis projects across clinical medicine, public health, and social sciences. She reviews all Research Gold tools to ensure statistical accuracy and compliance with Cochrane Handbook and PRISMA 2020 standards.
Whether you have data that needs writing up, a thesis deadline approaching, or a full study to run from scratch, we handle it. Average turnaround: 2-4 weeks.