That investigation, now published as a case report and literature review in BMC Pediatrics, describes how an isolated, initially mild but progressive rise in liver enzymes turned out to be the first visible signal of childhood-onset primary Sjögren’s syndrome, a rare autoimmune disease that most clinicians associate with dry eyes and dry mouth rather than hepatic inflammation. The report, authored by Kai Li, Chenling Zhang, Na Zeng, and Mingwu Chen and colleagues at Anhui Provincial Hospital and the University of Science and Technology of China, is a striking reminder that autoimmune diseases in children can announce themselves through organ systems that seem, on the surface, entirely unrelated to their usual targets.

The biochemical details of the case are worth unpacking, because they illustrate why the diagnosis was so elusive. For roughly the first twenty months of the boy’s illness, his alanine aminotransferase, or ALT, and his gamma-glutamyl transferase, or GGT, two of the standard enzymes clinicians use to gauge liver injury, hovered below twice the upper limit of normal. That is a level many guidelines classify as mild, and it is exactly the range in which clinicians often suspect fatty liver, residual viral infection, or simply laboratory noise. His creatine kinase, an enzyme that rises when muscle is damaged, was repeatedly normal, which helped rule out a muscular origin for the enzyme elevations. Abdominal ultrasound showed only mild hepatic steatosis, a fatty change in the liver that could plausibly have absorbed the blame.

The team worked systematically through the usual suspects. Infectious causes were excluded, as was any drug-related injury, and a panel of autoantibodies associated with autoimmune liver disease, including those linked to autoimmune hepatitis, primary biliary cholangitis, and primary sclerosing cholangitis, came back negative. That negativity matters, because autoimmune liver diseases are the standard explanations for unexplained chronic enzyme elevation in a child, and their serological fingerprints were absent. What remained was a slowly smoldering process with no obvious address, the kind of clinical limbo in which patients can drift for years while the underlying disease advances unchecked.

The turning point came when the boy’s immune profile was tested more broadly. He proved strongly positive for anti-SSA, anti-SSB, and anti-Ro52 antibodies, a trio of autoantibodies that serve as hallmark markers of Sjögren’s syndrome, an autoimmune condition in which the body’s exocrine glands, particularly the salivary and lacrimal glands, come under lymphocytic attack. Critically, the boy had no sicca symptoms at all, no dry eyes, no dry mouth, none of the complaints that typically define the disease in adults. A salivary gland biopsy sealed the diagnosis, revealing focal lymphocytic sialadenitis with a focus score of at least one aggregate of immune cells per four square millimeters, the histological threshold used in international classification criteria for the disease.

Childhood-onset primary Sjögren’s syndrome is genuinely rare, and its presentation in children is notoriously heterogeneous. While adults usually present with the glandular dryness that gives the disease its name, children more often show non-specific or extraglandular features, including recurrent parotitis, arthritis, rash, or, as this case demonstrates, laboratory abnormalities in distant organs. Hepatic involvement in pediatric Sjögren’s has been reported only infrequently, and it is especially unusual for liver enzyme elevation to be the very first manifestation, preceding any glandular symptoms by years. The authors reviewed the existing literature to place their case in context, and the picture that emerges is one of a disease that pediatricians rarely have on their differential when the presenting complaint is an abnormal liver panel.

The report is also candid about the limits of what could be proven. Liver biopsy and magnetic resonance cholangiopancreatography, the imaging technique used to visualize the bile ducts, were not performed, which means the precise mechanism of the boy’s liver injury remains incompletely characterized. The authors explicitly note that a causal relationship between the Sjögren’s syndrome and the hepatic abnormalities could not be definitively established, and they recommend continued follow-up to reassess alternative or coexisting diagnoses. This kind of epistemic honesty is important in case reports, where the temptation to draw a clean narrative line between diagnosis and treatment response can outpace the evidence. The mild steatosis seen on ultrasound, for instance, raises the possibility that metabolic factors contributed to the enzyme elevations even if they did not tell the whole story.

Treatment, however, appeared to vindicate the autoimmune hypothesis. The boy received tofacitinib, a Janus kinase inhibitor that blocks intracellular signaling pathways used by immune cells to drive inflammation, along with hydroxychloroquine, an antimalarial drug with immunomodulatory effects that is a mainstay of systemic autoimmune disease therapy, and a short course of diammonium glycyrrhizinate, a licorice-derived compound with anti-inflammatory activity used in China for liver protection. The response was decisive. His liver biochemistry normalized and remained within reference ranges throughout eight months of follow-up, a sustained remission that, while not proof of causation, is difficult to dismiss as coincidence.

The choice of tofacitinib is itself noteworthy. Janus kinase inhibitors have become one of the most closely watched drug classes in immunology, praised for their oral convenience and broad anti-inflammatory reach, and their expanding use in pediatric rheumatology reflects growing confidence in targeted immune modulation. In this case, the combination of a JAK inhibitor with hydroxychloroquine addressed the systemic autoimmune process rather than treating the liver in isolation, a therapeutic philosophy that only becomes available once the correct diagnosis is in hand. Had the boy remained labeled as a fatty liver case, he might never have received immunosuppressive therapy at all.

For clinicians, the practical lesson is that isolated, persistent, slowly progressive liver enzyme elevation in a child, even when mild, deserves a diagnostic strategy that extends beyond hepatology. The authors suggest that when infectious, drug-related, and autoimmune liver causes have been excluded, and especially when the biochemical pattern evolves over months to years, clinicians should consider systemic autoimmune diseases, including Sjögren’s syndrome, even in the complete absence of sicca symptoms. Simple serological tests for anti-SSA, anti-SSB, and anti-Ro52 antibodies are widely available, and a positive result can redirect an entire diagnostic workup. For researchers, the case adds to the small but growing literature on extraglandular manifestations of pediatric Sjögren’s and underscores how much remains unknown about the disease’s hepatic dimension. For families, it is a reminder that a child’s body rarely reads the textbook, and that the answer to one organ’s quiet distress may lie in an immune system attacking somewhere no one thought to look.

Subject of Research: Childhood-onset primary Sjögren's syndrome presenting as isolated progressive liver enzyme elevation

Article Title: The diagnostic dilemma of isolated, initially mild but progressive liver enzyme elevation as an initial manifestation of childhood-onset primary Sjögren’s syndrome: a case report and literature review

Article References: Li, K., Zhang, C., Zeng, N., & Chen, M. (2026). The diagnostic dilemma of isolated, initially mild but progressive liver enzyme elevation as an initial manifestation of childhood-onset primary Sjögren’s syndrome: a case report and literature review. BMC Pediatrics. https://doi.org/10.1186/s12887-026-07734-1

Image Credits: AI Generated

DOI: 10.1186/s12887-026-07734-1

Keywords: Sjögren's syndrome, pediatrics, liver enzymes, autoimmune disease, hepatic involvement, anti-SSA antibodies, tofacitinib, case report, JAK inhibitor, childhood-onset, autoimmune hepatitis, liver biopsy

Liver biopsy is a cornerstone of cancer diagnosis, but it is far from trivial. The liver is a crowded, vascular organ hemmed in by ribs, lungs, bowel, and major blood vessels, and the needle must reach a target lesion while avoiding all of these hazards. Today, that planning rests almost entirely on the experience and judgment of individual interventional radiologists, which introduces meaningful variability between operators. Standardized AI-assisted planning has been proposed as a way to reduce that variability, particularly at centers with less experienced staff, but the field remains preliminary. The Memorial Sloan Kettering team set out to test the most basic building block of such a system: could a generative AI model, given nothing but a single axial CT slice and a standardized prompt, propose an entry angle that experienced reviewers would rate as potentially safe?

The study design was deliberately simple. The researchers retrospectively collected de-identified CT images from 30 consecutive CT-guided liver biopsies performed between February and June 2025 by sixteen board-certified interventional radiologists with a median of eight years of experience. The patient group included 20 women and 10 men with a median age of 56, and their lesions spanned liver segments 1 through 8 under the Couinaud classification. Crucially, the AI never touched a patient. It worked only on the initial planning CT image, after the fact, and only in two dimensions, while the actual procedures had already been completed safely by human hands.

The preprocessing workflow was strikingly low-tech for a study of cutting-edge AI. Each CT image was cropped to remove patient identifiers, magnified without rescaling, and overlaid with a radial grid created in GIMP, the free open-source image editor. The grid consisted of 36 radial lines at 10-degree intervals with concentric circles spaced 10 millimeters apart, calibrated to known anatomical landmarks. The annotated images were saved as PNG files and fed to GPT-4.1 through a standardized prompt. The model operated entirely on its baseline training, with no fine-tuning on medical data, and a fresh chat was started for every case to prevent contamination between cases.

The researchers tested two conditions that differed in how much hand-holding the AI received. In the first condition, two study authors manually annotated each image with a blue circle marking the lesion and a red line delineating sensitive structures to avoid, essentially handing the model a pre-drawn map of the danger zones. In the second, more demanding condition, only the blue circle was drawn, forcing the AI to identify critical structures on its own. For each case, the model was allowed up to four iterations: if its proposed trajectory failed safety criteria, it was re-prompted within that limit. Two independent reviewers then rated every AI-generated trajectory using consensus methodology, judging safety, avoidance of organs, vessels, and bone, whether the path crossed the midline or excessive tissue, and whether the approach would be comfortable and clinically reasonable.

The headline numbers were encouraging, with important caveats. In the first condition, the AI needed a median of two iterations and produced trajectories rated potentially safe in 27 of 30 cases, or 90 percent. In the second condition, without the red-line annotations, it needed a median of just one iteration and scored 28 of 30, or 93 percent. The difference between conditions was not statistically significant, and the model’s proposed entry angles differed significantly from the angles actually used by clinicians, with mean differences reaching statistical significance in both conditions. Only 23 percent of cases in condition one and 33 percent in condition two showed strong concordance, defined as entry angles within 10 degrees with similar liver traversal patterns, meaning the AI was often safe but not necessarily matching human choices.

The failures are as instructive as the successes. In three cases in the first condition, the AI proposed paths crossing bone, the midline, or the marked red line, even after four attempts. One of these involved a patient with ascites, fluid in the abdomen that complicated the anatomy; another involved a patient whose prior surgery had removed the left hepatic lobe, creating atypical anatomy; and a third targeted a high-lying segment 2 lesion where the model routed the needle through costal cartilage. Cartilage proved a recurring blind spot: in the second condition, both unsafe trajectories involved bone or cartilage, suggesting the model struggles to recognize structures with intermediate radiodensity. The authors note that excluding these inadequate cases from distance calculations introduces selection bias that may flatter the AI’s performance.

On the metric of liver tissue traversed, the AI actually looked competitive. In condition one, its paths crossed a median of 31.6 millimeters of liver versus 48.25 millimeters for the manual paths, and in condition two, 39.35 versus 48.25 millimeters, though neither difference reached statistical significance. Interestingly, the AI’s longer median distances in the unannotated condition hint at a conservative streak: without predefined avoidance zones, it may favor longer but safer routes. A power analysis indicated the 30-case sample could only detect large effect sizes, so smaller but clinically meaningful differences would require larger cohorts to detect.

The authors are refreshingly blunt about what these results do not mean. This was a proof of concept, nothing more. The workflow does not address a real clinical need: interventional radiologists can identify safe trajectories in seconds using native console capabilities with full three-dimensional visualization, whereas the AI pipeline required manual image export, GIMP annotation, and chatbot prompting, all while discarding the three-dimensional spatial information that real planning depends on. A human planner scrolls through multiple slices, uses multiplanar reconstruction, and mentally constructs 3D anatomy, capabilities entirely absent from a static 2D analysis. The AI also required continuous human supervision, with iterative re-prompting in most cases, which undermines any claim of autonomy. And because the AI trajectories were never actually executed, they remain theoretical, while the manual paths were proven safe by successful, complication-free procedures, a comparison that cannot establish equivalence.

Looking forward, the researchers see a path, if a long one. Future systems would need automated lesion identification, since current generative models lack the segmentation capabilities required for precise localization, and integration with dedicated segmentation architectures such as U-Net could enable fully autonomous planning from raw CT images. Three-dimensional volumetric analysis, quantitative vascular proximity measurements, phantom studies, and prospective multicenter trials would all be prerequisites before any clinical consideration. The authors also point toward applications in tumor ablation and margin assessment, and note that many liver biopsies worldwide are performed under ultrasound guidance, where real-time, operator-dependent imaging poses an even harder challenge for AI. For now, the message is measured: generative AI can look at a liver CT slice and propose a plausible needle angle most of the time, but the 7 to 10 percent of cases where it fails, sometimes by routing a needle through bone or cartilage, are exactly the cases where a patient would be harmed. In medicine, that margin is everything.

Subject of Research: Feasibility of generative AI for planning CT-guided liver biopsy needle trajectories

Article Title: Feasibility of generative AI for CT-guided liver biopsy trajectory planning: a pilot study

Article References: Feasibility of generative AI for CT-guided liver biopsy trajectory planning: a pilot study. (n.d.). https://doi.org/10.1007/s44343-026-00041-7

Image Credits: AI Generated

DOI: 10.1007/s44343-026-00041-7

Keywords: generative AI, GPT-4.1, liver biopsy, CT guidance, interventional radiology, trajectory planning, pilot study, medical imaging, needle biopsy, proof of concept, Memorial Sloan Kettering, artificial intelligence