The steatosis-associated fibrosis estimator (SAFE) score: A tool to detect low-risk NAFLD in primary care

Abstract

Background: NAFLD is common in primary care. Liver fibrosis stage 2 or higher (≥F2) increases future risk of morbidity and mortality. We developed and validated a score to aid in the initial assessment of liver fibrosis for NAFLD in primary care.

Methods: Data from patients with biopsy-proven NAFLD were extracted from the NASH Clinical Research Network observational study ( n = 676). Using logistic regression and machine-learning methods, we constructed prediction models to distinguish ≥F2 from F0/1. The models were tested in participants in a trial ("FLINT," n = 280) and local patients with NAFLD with magnetic resonance elastography data ( n = 130). The final model was applied to examinees in the National Health and Nutrition Examination Survey (NHANES) III ( n = 11,953) to correlate with long-term mortality.

Results: A multivariable logistic regression model was selected as the Steatosis-Associated Fibrosis Estimator (SAFE) score, which consists of age, body mass index, diabetes, platelets, aspartate and alanine aminotransferases, and globulins (total serum protein minus albumin). The model yielded areas under receiver operating characteristic curves ≥0.80 in distinguishing F0/1 from ≥F2 in testing data sets, consistently higher than those of Fibrosis-4 and NAFLD Fibrosis Scores. The negative predictive values in ruling out ≥F2 at SAFE of 0 were 88% and 92% in the two testing sets. In the NHANES III set, survival up to 25 years of subjects with SAFE < 0 was comparable to that of those without steatosis ( p = 0.34), whereas increasing SAFE scores correlated with shorter survival with an adjusted HR of 1.53 ( p < 0.01) for subjects with SAFE > 100.

Conclusion: The SAFE score, which uses widely available variables to estimate liver fibrosis in patients diagnosed with NAFLD, may be used in primary care to recognize low-risk NAFLD.

Figure 1.

Overall study plan

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 2.

P-splines describing relationship between significant fibrosis and predictor variables.

Figure 3.

Areas under the receiver operating characteristics (AUROC) curves of prediction models. The upper and lower bar in each column represent 95% confidence interval of AUROCs. A. New models derived in the training set, applied to testing set #1. Dashed line is the AUROC level of FIB-4. B. Logistic model compared to FIB-4 and NFS in the training set, testing set #1, and testing set #2. P<0.01 for all comparisons between SAFE and the other two models except SAFE versus NFS in testing set #2 (p=0.03)

Figure 3.

Areas under the receiver operating characteristics (AUROC) curves of prediction models. The upper and lower bar in each column represent 95% confidence interval of AUROCs. A. New models derived in the training set, applied to testing set #1. Dashed line is the AUROC level of FIB-4. B. Logistic model compared to FIB-4 and NFS in the training set, testing set #1, and testing set #2. P<0.01 for all comparisons between SAFE and the other two models except SAFE versus NFS in testing set #2 (p=0.03)

Figure 4.

Probabilities of F0/1, F2, F3/4 at SAFE scores −200 to 400 derived from the model training data set.

Figure 5.

Kaplan-Meier Survival for NHANES III participants according to NAFLD and SAFE score tiers