Diagnostic Accuracy of the LiverRisk Score to Detect Increased Liver Stiffness Among a United States General Population and Subgroups
Bibliographic record
Abstract
Background: The LiverRisk score (LRS) has recently been proposed to predict liver fibrosis and future development of liver-related outcomes in the general population. Here, we performed an external validation of this score. Methods: We used data from National Health and Nutrition Examination Survey 2017-2020, a United States population-based cohort to assess the diagnostic accuracy of the LRS to detect a liver stiffness measurement (LSM) ≥8 and ≥12 kPa. Performance was tested among the entire general population and clinically relevant subgroups. Results: The cohort comprised 7,025 participants (aged 49 [33-63], 49% male), and 9.7% had an LSM ≥8 and 3.2% had an LSM ≥12 kPa. The area under the receiver characteristic operator curve (AUC) in the overall population was 0.73 (95% confidence interval [CI] :0.71-0.75) and 0.78 (95% CI: 0.74-0.81) to detect an LSM ≥8 and ≥ 12 kPa, respectively, significantly outperforming the fibrosis 4 index (FIB-4) but not the nonalcoholic fatty liver disease fibrosis score, steatosis-associated fibrosis estimator (SAFE), or metabolic dysfunction-associated fibrosis 5 (MAF-5). Performance was consistent among most subgroups, but AUC levels to detect an LSM ≥8 kPa decreased to <0.70 among participants aged 18-40 or 60-80 years, blacks, and individuals with diabetes or liver steatosis. The LRS categorized 80.5% as very low risk, 17.7% as low risk, and 1.8% as at risk, prevalence of an LSM ≥8 in these groups was 6.3%, 20.8%, and 50.5%, respectively. The sensitivity to detect an LSM ≥8 kPa was 47.3% in the overall population (but dropped to 21.3% for individuals aged 18-40 years) despite applying the lowest cut-off, which should yield the highest sensitivity. Conclusion: The LRS score is a promising new tool to predict liver fibrosis; however, its diagnostic accuracy attenuates especially among patients aged 18-40 or 60-80 years. The overall sensitivity was only 47.3% at the lowest LRS cut-off. Further studies assessing cost-benefit ratios according to the LRS compared to FIB-4 and other risk scores such as MAF-5 and SAFE are required to determine its usefulness in referral strategies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".