A novel diagnostic tool, the steatosis-associated fibrosis estimator (SAFE) algorithm, may revolutionize the early detection of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH). NAFLD, a common liver condition, often remains undiagnosed until advanced stages. The SAFE algorithm offers promising potential to enhance patient identification, enabling proactive healthcare interventions and alleviating the burden on specialists, according to GlobalData, a leading data and analytics company.

NAFLD7, a result of excess fat buildup in the liver, is one of the most common causes of liver disease in the US. If left untreated, the scarring (fibrosis) becomes more severe, leading to a more advanced liver disease known as NASH.

Sravani Meka, Senior Immunology Analyst at GlobalData, comments: “With the increasing prevalence and public health impact of NAFLD, there is an urgent need for systematic approaches to lessen its consequences on the healthcare system.”

“Given that most patients with NAFLD/NASH are typically diagnosed in the later stages of the disease, they are also commonly burdened with several comorbidities, including type 2 diabetes (T2D), obesity, cardiovascular disease (CVD), and chronic kidney disease (CKD).”

Therefore, these patients see a wide variety of healthcare specialists, such as endocrinologists, cardiologists, pharmacists, nutritionists/dietitians, hepatologists, and gastroenterologists, in addition to their primary care physician (PCP).

Meka continues: “Although such a large multidisciplinary team is required to effectively treat patients with NAFLD/NASH in the later stages of disease, it is not practical to assume that hepatologists and gastroenterologists can keep up with the increasing volume of NAFLD/NASH patients.”

Certainly, patients who are diagnosed with severe liver disease should be referred to specialized care to decelerate or halt disease progression, prevent end-stage liver disease (ESLD), or handle complications.

The SAFE score was developed by researchers from Stanford University School of Medicine to detect clinically significant fibrosis in patients with NAFLD and is calculated using multivariable logistic regression and machine-learning methods using data such as age, body mass index (BMI), diabetes as a binary variable, aspartate and alanine aminotransferases, total globulin, and platelets from the NASH Clinical Research Network (CRN) observational study.

Following validation, the prognostic performance of the SAFE algorithm was investigated using data from the National Health and Nutrition Examination Survey (NHANES) for 2017–20. Overall, when SAFE scores were compared to those of established diagnostic models (FIB-4 and NAFLD fibrosis scores), researchers found that the SAFE scores outperformed the latter set of scores in both the derivation and validation cohorts.

Meka concludes: “Despite the positive performance of the SAFE scores, it should be noted that the model is not yet ready to be applied to the wider primary care population. As a diagnostic or prediction model should be developed in cohorts where it would be applied, it appears further revision of the SAFE score model should be considered as the current model was developed and validated using data from secondary care populations (NASH CRN observational study and FLINT study data).

“However, if the SAFE algorithm can be successfully integrated into primary care, it can not only help improve the identification of at-risk patients and implement proactive measures to enhance liver health, but also potentially aid in the reduction of the burden faced by specialists in healthcare systems.”