MASLD, hepatic steatosis and fibrosis are associated with the prevalence of chronic kidney disease and retinopathy in adults with type 1 diabetes mellitus

Machine Learning Identifies Metabolic Dysfunction-Associated Steatotic Liver Disease in Patients With Diabetes Mellitus

CONTEXT

The presence of metabolic dysfunction-associated steatotic liver disease (MASLD) in patients with diabetes mellitus (DM) is associated with a high risk of cardiovascular disease, but is often underdiagnosed.

OBJECTIVE

To develop machine learning (ML) models for risk assessment of MASLD occurrence in patients with DM.

METHODS

Feature selection determined the discriminative parameters, utilized to classify DM patients as those with and without MASLD. The performance of the multiple logistic regression model was quantified by sensitivity, specificity, and percentage of correctly classified patients, and receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) assessed the model's net benefit for alternative treatments.

RESULTS

We studied 2000 patients with DM (mean age 58.85 ± 17.37 years; 48% women). Eight parameters: age, body mass index, type of DM, alanine aminotransferase, aspartate aminotransferase, platelet count, hyperuricaemia, and treatment with metformin were identified as discriminative. The experiments for 1735 patients show that 744/991 (75.08%) and 586/744 (78.76%) patients with/without MASLD were correctly identified (sensitivity/specificity: 0.75/0.79). The area under ROC (AUC) was 0.84 (95% CI, 0.82-0.86), while DCA showed a higher clinical utility of the model, ranging from 30% to 84% threshold probability. Results for 265 test patients confirm the model's generalizability (sensitivity/specificity: 0.80/0.74; AUC: 0.81 [95% CI, 0.76-0.87]), whereas unsupervised clustering identified high-risk patients.

CONCLUSION

A ML approach demonstrated high performance in identifying MASLD in patients with DM. This approach may facilitate better risk stratification and cardiovascular risk prevention strategies for high-risk patients with DM at risk of MASLD.

Metabolic dysfunction-associated steatotic liver disease-related hepatic fibrosis increases risk of insulin resistance, type 2 diabetes, and chronic kidney disease

Metabolic dysfunction-associated steatotic liver disease (MASLD) (previously called nonalcoholic fatty liver disease, NAFLD) is associated with cardiometabolic risk factors and chronic kidney disease (CKD). However, evidence is lacking regarding whether the severity of fibrosis is affected by these risk factors and diseases and to what degree. We aimed to determine the correlation between these factors and vibration-controlled transient elastography-determined liver stiffness measurements (LSMs) and controlled attenuation parameter (CAP) values in a sample of the US population. Data from the 2017-2018 cycle of the National Health and Nutrition Examination Survey were pooled. The association between LSM and cardiometabolic risk factors and CKD was assessed using generalized linear or logistic regression analyses. In multivariate regression analyses, CAP and BMI were adjusted as confounders. Of 3647 participants, 2079 (57.1%) had NAFLD/MASLD [weighted prevalence 54.8%; 95% confidence interval (CI) 51.8-57.9%]; the weighted prevalence of significant fibrosis (LSM ≥ 7.9 kPa) was 9.7% (95% CI 8.2-11.3%). Log LSM was associated with higher levels of homeostatic model assessment of insulin resistance ( β  = 2.19; P  = 0.017), hepatic steatosis (CAP > 248 dB/m) [odds ratio (OR) 3.66; 95% CI 2.22-6.02], type 2 diabetes (OR 2.69; 95% CI 1.72-4.20), and CKD (OR 1.70; 95% CI 1.24-2.34). These correlations did not change notably after adjustments were made for waist circumference, CAP, and BMI. LSM and CAP, although influenced by waist circumference and BMI, are good indicators of hepatic fibrosis and steatosis. LSM is associated with insulin resistance, diabetes, and CKD independent of hepatic steatosis and obesity.

Increased risk of chronic kidney disease and mortality in a cohort of people diagnosed with metabolic dysfunction associated steatotic liver disease with hepatic fibrosis

BACKGROUND AND AIMS

Metabolic dysfunction associated steatotic liver disease (MASLD) increases the risk of incident chronic kidney disease (CKD). However, the relative risk of CKD associated with increasing hepatic fibrosis, and consequent mortality risk, remains underexplored in real-world cohorts. In this study, we sought to establish whether hepatic fibrosis is associated with increased CKD risk and explore differences in mortality risk in a cohort of people living with MASLD, contingent on liver fibrosis and CKD status.

METHODS

This was an observational study of people who underwent routine liver function testing in Tayside, Scotland. MASLD was defined as: elevated ALT (>30 U/L) or GGT (>73 U/L); presence of diabetes, and/or hypertension, and/or obesity; weekly alcohol consumption <14 units (112g (+/-8g) alcohol); and negative screen for other aetiologies. Data was collected from digital health records. We used log-binomial models to quantify the risk of CKD among those with and without fibrosis, and Cox regression models to estimate differences in mortality risk dependent on fibrosis and CKD.

RESULTS

In our cohort (n = 2,046), 1,448 (70.8%) people had MASLD without fibrosis and 598 (29.2%) with fibrosis; 161 (11.1%) and 117 (19.6%) respectively also had CKD. After excluding individuals with structural, autoimmune, or malignant CKD (n = 22), liver fibrosis (n = 593; 18.9% with CKD) was associated with increased CKD risk (aRR = 1.31, 1.04-1.64, p = 0.021). Increased mortality risk was observed for those with liver fibrosis (aHR = 2.30, 1.49-3.56, p = <0.001) and was higher again among people with both fibrosis and CKD (aHR = 5.07, 3.07-8.39, p = <0.014).

CONCLUSIONS

Liver fibrosis was an independent risk factor for CKD in this cohort of people living with MASLD. Furthermore, those with MASLD with liver fibrosis had higher risk for mortality and this risk was further elevated among those with co-morbid CKD. Given the increased risk of CKD, and consequent mortality risk, among people living with MASLD fibrosis, renal function screening should be considered within liver health surveillance programmes and guidelines.

Elevated FIB-4 Is Associated with Higher Rates of Cardiovascular Disease and Extrahepatic Cancer History in Patients with Type 2 Diabetes Mellitus

BACKGROUND

Type 2 diabetes mellitus (T2DM) is often complicated by steatotic liver disease, cardiovascular disease (CVD), and extrahepatic cancer. We investigated whether FIB-4, an indicator of liver fibrosis, is associated with a higher risk of CVD and extrahepatic cancer history in T2DM.

METHODS

Two hundred and nine of 244 diabetics admitted to our center in one year were included and retrospectively evaluated.

RESULTS

One hundred and fifty-two (72.7%) were males and 57 (27.3%) females. The mean age and FIB-4 were 64.3 ± 11 years, and 1.15 ± 0.5, respectively. One hundred and fifty patients (71.8%) had FIB-4 ≤ 1.3, and 59 (28.2%) had FIB-4 > 1.3. A history of CVD was presented in 76 (36.4%) patients, and of extrahepatic cancer in 39 (18.7%). Patients with CVD were significantly older than those without (68.4 ± 8.5 vs. 63.2 ± 11.5 years; p = 0.002), with significantly higher FIB-4 (1.26 ± 0.5 vs. 1.08 ± 0.5; p = 0.012). Patients with cancer were older, with higher FIB-4 compared to those without (68.2 ± 9.5 vs. 64.4 ± 10.9 years; p = 0.098 and 1.37 ± 0.6 vs. 1.1 ± 0.5; p = 0.004, respectively). FIB-4 > 1.3 was associated with a 2.1-fold probability for CVD (χ2 = 5.810; p = 0.025) and 2.7-fold probability for cancer history (χ2 = 7.603; p = 0.01).

CONCLUSIONS

FIB-4 ≥ 1.3 is associated with a higher probability of CVD or extrahepatic cancer history. FIB-4 could potentially discriminate patients at risk, justifying stricter surveillance.

2024 UPDATE: the Brazilian Diabetes Society position on the management of metabolic dysfunction-associated steatotic liver disease (MASLD) in people with prediabetes or type 2 diabetes

BACKGROUND

Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most common liver disease affecting 30% of the world's population and is often associated with metabolic disorders such as metabolic syndrome, type 2 diabetes (T2D), and cardiovascular disease. This review is an update of the Brazilian Diabetes Society (Sociedade Brasileira de Diabetes [SBD]) evidence-based guideline for the management of MASLD in clinical practice.

METHODS

The methodology was published previously and was defined by the internal institutional steering committee. The SBD Metabolic Syndrome and Prediabetes Department drafted the manuscript, selecting key clinical questions for a narrative review using MEDLINE via PubMed with the MeSH terms [diabetes] and [fatty liver]. The best available evidence was reviewed, including randomized clinical trials (RCTs), meta-analyses, and high-quality observational studies related to MASLD.

RESULTS AND CONCLUSIONS

The SBD Metabolic Syndrome and Prediabetes Department formulated 9 recommendations for the management of MASLD in people with prediabetes or T2D. Screening for the risk of advanced fibrosis associated with MASLD is recommended in all adults with prediabetes or T2D. Lifestyle modification (LSM) focusing on a reduction in body weight of at least 5% is recommended as the first choice for these patients. In situations where LSMs are insufficient to achieve weight loss, the use of anti-obesity medications is recommended for those with a body mass index (BMI) ≥ 27 kg/m2. Pioglitazone and glucagon-like peptide-1 receptor agonists (GLP-1RA) monotherapy are the first-line pharmacological treatments for steatohepatitis in people with T2D, and sodium-glucose cotransporter-2 (SGLT2) inhibitors may be considered in this context. The combination of these agents may be considered in the treatment of steatohepatitis and/or fibrosis, and bariatric surgery should be considered in patients with a BMI ≥ 35 kg/m2, in which the combination of LSM and pharmacotherapy has not been shown to be effective in improving MASLD.