Disclaimer notice: It is important to bear in mind that this is not a medical device and creators are not responsible for the use of the algorithm in a clinical setting.
Individuals with 1 or more of the following conditions:
International Diabetes Federation (IDF) definition (2005)  
Central obesity  Waist circumference ≥ 94/80 cm in men/women (European ancestry) or BMI > 30 kg/m²  
Plus any two of the following:  
Triglycerides  ≥ 1.7 mmol/L (150 mg/dL) or specific treatment for this lipid abnormality  
HDL cholesterol 


Blood pressure  Systolic ≥ 130 mmHg or diastolic ≥ 85 mmHg or treatment of previously diagnosed hypertension  
Fasting plasma glucose  ≥ 5.6 mmol/L (100 mg/dL) or previously diagnosed type 2 diabetes 
• Fibrotic NASH: histological diagnosis of NASH + elevated NAS score (NAS≥4) + significant fibrosis (F≥2)
The score was developed in the derivation cohort (264 morbidly obese individuals) using a bootstrapping stepwise logistic regression model (2000 bootstrap samples). The score was derived based on the final predictors and the corresponding regression coefficients. Performance for fibrotic NASH was assessed by the receiver operating characteristic curve (AUROC). Ruleout and rulein cutoffs were derived based on sensitivity ≥0.89 and specificity ≥0.90, respectively.
The FNI is a predicted probability score derived from a logistic regression model, and it ranges from 0 to 1.
N  264 
Fibrotic NASH, n (%)  54 (20.5) 
AUROC (95% CI)  0.78 (0.710.85) 
FNI ≤ 0.10 (Ruleout zone)  
n (%)  83 (31.4) 
Sensitivity  0.89 
Specificity  0.37 
PPV  0.27 
NPV  0.93 
FNI ≥ 0.33 (Rulein zone)  
n (%)  49 (18.6) 
Sensitivity  0.52 
Specificity  0.90 
PPV  0.57 
NPV  0.88 
Stefano Romeo, MD, PhD
Professor in Molecular and Clinical Medicine
University of Gothenburg, Institute of Medicine, Sahlgrenska Academy
Wallenberg Laboratory, Bruna Stråket 16
41345 Gothenburg, Sweden
Email: stefano [dot] romeo [at] wlab [dot] gu [dot] se