Semaglutide has shown benefit in metabolic dysfunction-associated steatohepatitis (MASH), but real-world evidence across longitudinal liver phenotypes remains limited, particularly regarding how liver remodeling relates to weight loss and dose exposure. Using a de-identified federated electronic health record network spanning more than 29 million patients in the United States, including 489,785 semaglutide-treated adults, we analyzed 6,734 patients with baseline liver disease burden. We find that higher attained pre-landmark (0-2 years) semaglutide dose was associated with lower post-landmark (2-4 years) risk of steatohepatitis, alcoholic liver disease, and all-cause mortality, whereas greater pre-landmark weight loss was associated with lower post-landmark risk of steatohepatitis, steatotic liver disease, and hepatorenal syndrome, indicating distinct dose- and weight-linked patterns of long-term liver benefits. These associations were notable because semaglutide prescribing was generally lower during the post-landmark period, raising the possibility of durable benefit beyond peak exposure. Towards better understanding mechanistic bases for liver protection, we performed a complementary longitudinal study of 326 adults with paired noninvasive liver elastography measurements before and after treatment initiation. Median liver stiffness decreased from 4.85 [3.02 - 7.20] to 3.9 [2.6 - 5.8] kPa after semaglutide initiation (median change = −0.38 kPa; p<0.001), with 194 of 326 patients (59.5%) showing lower follow-up stiffness. A clinically meaningful reduction of at least 20% was observed in 133 of 326 patients (40.8%), and 69 of 326 (21.2%) shifted to a lower fibrosis stage by prespecified elastography thresholds. Larger improvements were also seen in patients with higher baseline stiffness (p<0.001); notably 80% of patients with cirrhosis-range baseline stiffness (≥12.5 kPa) achieved ≥20% improvement versus 29.5% with minimal baseline disease (p <0.001). The proportion achieving at least 20% stiffness improvement was similar across weight-loss strata, including patients with no weight loss or weight gain and those with at least 10% weight loss (38.0% in each group), and liver stiffness change showed negligible correlation with changes in weight, BMI, HBA1c, alanine aminotransferase, or aspartate aminotransferase. To provide biological context, single cell RNA analyses demonstrated sparse overall hepatic GLP1R expression (0.0239%), with enrichment in non-parenchymal niches including cholangiocytes, intrahepatic cholangiocytes, liver sinusoidal endothelial cells, and hepatic stellate cells implicated in fibrogenesis and vascular remodeling. Together, this real-world evidence suggests diverse liver benefits for semaglutide beyond weight-loss with intricate dose response relationships.

The authors are employees of nference, inc., which conducts research collaborations with various biopharmaceutical companies whose therapeutic products are included in this study. None of these companies, nor any other nference collaborator, funded, supported, or had any role in the independent study design, data acquisition, analysis, interpretation, manuscript preparation, or the decision to submit this work for publication. All analyses were conducted by the authors using de-identified electronic health record data. The authors declare no additional competing interests.

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Prior to analysis, all EHR data were de-identified under an expert determination consistent with the Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule (45 CFR 164.514(b)(1)). The de-identification methodology employed a multi-layered transformation approach to both structured and unstructured data fields. In structured data, direct identifiers including patient names and precise geographic locations were excluded entirely, while indirect identifiers underwent specific transformations: patient identifiers, medical record numbers, and accession numbers were replaced with one-way cryptographic hashes using confidential salts to preserve linkage across patient encounters; all dates were shifted backward by patient-specific random offsets (1-31 days) to preserve temporal relationships while obscuring exact event timing; the ZIP codes were truncated to two-digit state-level resolution; and continuous variables including age, height, weight, and body mass index were thresholded to prevent identification of extreme values (for example, ages ≥89 years transformed to '89+' and BMI >40 transformed to '40+'). In unstructured clinical text, an ensemble de-identification system that combines attention-based deep learning models with rule-based methods achieved an estimated >99% recall for personally identifiable information (PII) detection, with detected identifiers replaced by plausible fictional surrogates.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

This study involves the analysis of de-identified Electronic Health Record (EHR) data via the nference nSights Federated Clinical Analytics Platform (nSights). Data shown and reported in this manuscript were extracted from this environment using an established protocol for data extraction, aimed at preserving patient privacy. The data has been de-identified pursuant to an expert determination in accordance with the HIPAA Privacy Rule. Any data beyond what is reported in the manuscript, including but not limited to the raw EHR data, cannot be shared or released due to the parameters of the expert determination to maintain the data de-identification. The corresponding author should be contacted for additional details regarding nSights.