---
title: "ASD-FER benchmark: Facial emotion recognition in children with ASD using ViT, Swin‑T, and HybridT"
id: "biorxiv-5-asd-fer-an-annotated-multi-class-benchmark-and-comparative-study-for-facial"
canonical_url: "https://medichelpline.com/clinical-feed/biorxiv-5-asd-fer-an-annotated-multi-class-benchmark-and-comparative-study-for-facial"
content_type: "clinical_feed_article"
specialty: "Pediatrics"
source_name: "bioRxiv (Biomedical Preprints)"
source_url: "https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1?rss=1"
published_at: "2026-10-20T12:00:00.000Z"
evidence_level: "Verified Feed"
license: "CC-BY-NC-4.0 / Informational Use"
---
# ASD-FER benchmark: Facial emotion recognition in children with ASD using ViT, Swin‑T, and HybridT
## Provenance & Clinical Metadata
- **Canonical URL:** https://medichelpline.com/clinical-feed/biorxiv-5-asd-fer-an-annotated-multi-class-benchmark-and-comparative-study-for-facial
- **Specialty:** [Pediatrics](https://medichelpline.com/clinical-feed/pediatrics.md)
- **Primary Source:** bioRxiv (Biomedical Preprints)
- **Source URL:** [Original Journal Publication](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1?rss=1)
- **Published At:** 2026-10-20T12:00:00.000Z
- **Evidence Rating:** Verified Feed
## Executive GIST (TL;DR)
- The authors assembled **ASD-FER**, a labeled image benchmark of 2,779 facial images of children diagnosed with Autism Spectrum Disorder (ASD). - Images were annotated into six emotion categories by three independent annotators; final labels were assigned by majority voting. - The team evaluated nine classifiers: CNN, SVM, AlexNet, ResNet34, **ResNet50**, MobileNetV2, and three backbone configurations of a task-specific architecture named **EQFormer** (ViT, Swin‑T, HybridT). - Two evaluation schemas were used: stratified 10‑fold cross‑validation and a held‑out 90/10 split. - Under mean cross‑validation accuracy, ResNet50 led traditional models (84.89%), while transformer backbones outperformed with ViT at 88.27%, Swin‑T at 88.02% and HybridT at 86.58%. - On the held‑out set ViT reached 91.01% overall accuracy; Swin‑T delivered the highest balanced accuracy (74.47%) and the top macro‑F1 (0.7078). - The compact HybridT maintained competitive accuracy (89.57%) while using far fewer parameters (reported at 2.66M). - Grad‑CAM visualizations indicated model attention concentrated on emotion‑relevant facial regions — eyes, eyebrows, and mouth — with Swin‑T providing the most spatially focused maps. - The authors flagged persistent issues: class imbalance within ASD‑FER and limited cross‑dataset generalization. - Data and code availability are linked by the authors on GitHub; the preprint has not been peer reviewed.
## Clinical Analysis & Structured Key Points
[Skip to main content](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1?rss=1#main-content) [![bioRxiv](https://www.biorxiv.org/sites/default/files/biorxiv_article_logo.jpg)](https://www.biorxiv.org/) * [Home](https://www.biorxiv.org/) * [Submit](https://www.biorxiv.org/submit-a-manuscript) * [FAQ](https://www.biorxiv.org/about/FAQ) * [Blog](https://connect.biorxiv.org/news/) * [ALERTS / RSS](https://www.biorxiv.org/content/alertsrss) * [Resources](https://connect.biorxiv.org/resources/) * [About](https://www.biorxiv.org/content/about-biorxiv) * [Channels](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1?rss=1) * [4D Nucleome](https://connect.biorxiv.org/relate/content/66) * [Academia Sinica](https://connect.biorxiv.org/group/content/38) * [Advances in Genome Biology and Technology (AGBT) General Meeting 2016 #AGBT16](https://connect.biorxiv.org/relate/content/10) * [Albert Einstein College of Medicine](https://connect.biorxiv.org/group/content/4) * [Aligning Science Across Parkinson's (ASAP)](https://connect.biorxiv.org/relate/content/195) * [Allen Institute for Cell Science](https://connect.biorxiv.org/relate/content/71) * [Arc Institute](https://connect.biorxiv.org/relate/content/224) * [Babraham Institute](https://connect.biorxiv.org/relate/content/197) * [BICCN/BICAN](https://connect.biorxiv.org/relate/content/208) * [BioImaging North America](https://connect.biorxiv.org/relate/content/194) * [Biology of Genomes 2016 #BOG16](https://connect.biorxiv.org/relate/content/19) * [Breakthrough Discoveries for Thriving with Bipolar Disorder](https://connect.biorxiv.org/relate/content/236) * [Brown University](https://connect.biorxiv.org/group/content/9) * [California Institute of Technology](https://connect.biorxiv.org/group/content/32) * [Carnegie Mellon University](https://connect.biorxiv.org/group/content/19) * [Case Western Reserve University](https://connect.biorxiv.org/group/content/36) * [Central Oxford Structural Microscopy and Imaging](https://connect.biorxiv.org/relate/content/143) * [Centre for Microbiology and Environmental Systems Science](https://connect.biorxiv.org/relate/content/190) * [Chan Zuckerberg Biohub](https://connect.biorxiv.org/relate/content/121) * [Columbia University](https://connect.biorxiv.org/group/content/27) * [Donders Institute for Brain, Cognition and Behaviour](https://connect.biorxiv.org/relate/content/184) * [DREAM](https://connect.biorxiv.org/relate/content/153) * [Drug Development and Clinical Therapeutics](https://connect.biorxiv.org/relate/content/52) * [ENCODE](https://connect.biorxiv.org/relate/content/177) * [Ernst Strüngmann Institute (ESI) for Neuroscience](https://connect.biorxiv.org/relate/content/211) * [European Molecular Biology Laboratory (EMBL)](https://connect.biorxiv.org/relate/content/159) * [Francis Crick Institute](https://connect.biorxiv.org/relate/content/88) * [Fred Hutchinson Cancer Center](https://connect.biorxiv.org/group/content/28) * [Georgia Institute of Technology](https://connect.biorxiv.org/group/content/20) * [Harvard Program in Therapeutic Sciences](https://connect.biorxiv.org/relate/content/151) * [The Howard Hughes Medical Institute (HHMI)](https://connect.biorxiv.org/relate/content/227) * [Human Cell Atlas](https://connect.biorxiv.org/relate/content/163) * [Human Pangenome Reference Consortium (HPRC)](https://connect.biorxiv.org/relate/content/215) * [IMO Workshop](https://connect.biorxiv.org/relate/content/8) * [Impact of Genomic Variation on Function (IGVF)](https://connect.biorxiv.org/relate/content/214) * [Institut Pasteur](https://connect.biorxiv.org/relate/content/235/channel) * [Institute of Science and Technology Austria](https://connect.biorxiv.org/group/content/12) * [International Human Epigenome Consortium (IHEC)](https://connect.biorxiv.org/relate/content/219) * [International Mouse Phenotyping Consortium (IMPC)](https://connect.biorxiv.org/relate/content/185) * [Iowa State University](https://connect.biorxiv.org/group/content/6) * [Johns Hopkins University](https://connect.biorxiv.org/group/content/47) * [Mathematical Oncology](https://connect.biorxiv.org/relate/content/1) * [Micron Oxford](https://connect.biorxiv.org/relate/content/116) * [Michigan State University](https://connect.biorxiv.org/group/content/7) * [Morgridge Institute](https://connect.biorxiv.org/group/content/57) * [National Taiwan University](https://connect.biorxiv.org/group/content/39) * [NCI Cancer Systems Biology Consortium](https://connect.biorxiv.org/relate/content/210) * [NF Open Science Initiative](https://connect.biorxiv.org/relate/content/213) * [NCI Human Tumor Atlas Network](https://connect.biorxiv.org/relate/content/171) * [Neuromatch Conference](https://connect.biorxiv.org/relate/content/209) * [NeurotechEU](https://connect.biorxiv.org/relate/content/189) * [North Carolina State University](https://connect.biorxiv.org/group/content/37) * [Northeastern University](https://connect.biorxiv.org/group/content/54) * [Oregon Health & Sciences University](https://connect.biorxiv.org/group/content/22) * [RNA Therapeutics Institute at UMass Chan Med School](https://connect.biorxiv.org/relate/content/243) * [Rosetta Commons](https://connect.biorxiv.org/relate/content/191) * [Rutgers University](https://connect.biorxiv.org/group/content/31) * [SeroNet](https://connect.biorxiv.org/relate/content/192) * [Simons Foundation Autism Research Initiative (SFARI)](https://connect.biorxiv.org/relate/content/74) * [Society for Molecular Biology and Evolution #SMBE2016](https://connect.biorxiv.org/relate/content/29) * [Somatic Cell Genome Editing Program](https://connect.biorxiv.org/relate/content/167) * [Somatic Mosaicism across the Human Tissues Network](https://connect.biorxiv.org/relate/content/222) * [SPARC](https://connect.biorxiv.org/relate/content/187) * [Stowers Institute for Medical Research](https://connect.biorxiv.org/group/content/3) * [Stockholm University](https://connect.biorxiv.org/group/content/14) * [Tel Aviv University](https://connect.biorxiv.org/group/content/8) * [The Michael J. Fox Foundation](https://connect.biorxiv.org/relate/content/207) * [The Rockefeller University](https://connect.biorxiv.org/group/content/2) * [The Sainsbury Laboratory](https://connect.biorxiv.org/relate/content/98) * [The Whitehead Institute](https://connect.biorxiv.org/relate/content/212) * [University of Connecticut Health Center](https://connect.biorxiv.org/group/content/16) * [University of California, Berkeley](https://connect.biorxiv.org/group/content/13) * [University of California, San Diego](https://connect.biorxiv.org/group/content/41) * [University of California, San Francisco](https://connect.biorxiv.org/group/content/10) * [University of Chicago](https://connect.biorxiv.org/group/content/42) * [University of Geneva](https://connect.biorxiv.org/group/content/26) * [University of Guelph](https://connect.biorxiv.org/group/content/23) * [University of Hong Kong](https://connect.biorxiv.org/group/content/29) * [University of Illinois Chicago](https://connect.biorxiv.org/group/content/43) * [University of Iowa](https://connect.biorxiv.org/group/content/24) * [University of Kansas](https://connect.biorxiv.org/group/content/33) * [University of Massachusetts Chan Medical School](https://connect.biorxiv.org/group/content/44) * [University of New South Wales](https://connect.biorxiv.org/group/content/25) * [University of Ottawa](https://connect.biorxiv.org/group/content/35) * [University of Sydney](https://connect.biorxiv.org/group/content/50) * [Vanderbilt University](https://connect.biorxiv.org/group/content/30) * [Vienna BioCenter](https://connect.biorxiv.org/relate/content/186) * [Washington University in St. Louis](https://connect.biorxiv.org/group/content/11) * [Weizmann Institute of Science](https://connect.biorxiv.org/group/content/15) * [Yale University](https://connect.biorxiv.org/group/content/53) Search for this keyword [Advanced Search](https://www.biorxiv.org/search) New Results Follow this preprint # ASD-FER: An Annotated Multi-Class Benchmark and Comparative Study for Facial Emotion Recognition in Children with Autism Spectrum Disorder [ View ORCID Profile](http://orcid.org/0009-0006-3821-3644)Shahana Yasmin Chowdhury, Bithi Banik, Tracey Ann Knaus, Christopher David Moore, Henry Fordjour Ansah, Huda Hammad, Pranish Ghimire, Md Tamjidul Hoque, Shreya Banerjee doi: https://doi.org/10.64898/2026.10.14.754143 This article is a preprint and has not been certified by peer review [[what does this mean?](https://www.biorxiv.org/about/FAQ#unrefereed)]. Shahana Yasmin Chowdhury 1 Department of Computer Science, LSU New Orleans, New Orleans, Louisiana, USA; * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Shahana%2BYasmin%2BChowdhury%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Chowdhury%20SY&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AShahana%2BYasmin%2BChowdhury%2B) * [ORCID record for Shahana Yasmin Chowdhury](http://orcid.org/0009-0006-3821-3644 "Open in new tab") * For correspondence: sychowdh@lsuneworleans.edu Bithi Banik 2 Kristiania University of Applied Sciences, Oslo, Norway; * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Bithi%2BBanik%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Banik%20B&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3ABithi%2BBanik%2B) Tracey Ann Knaus 3 Department of Psychology, LSU New Orleans, New Orleans, Louisiana, USA; * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Tracey%2BAnn%2BKnaus%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Knaus%20TA&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3ATracey%2BAnn%2BKnaus%2B) Christopher David Moore 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Christopher%2BDavid%2BMoore%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Moore%20CD&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AChristopher%2BDavid%2BMoore%2B) Henry Fordjour Ansah 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Henry%2BFordjour%2BAnsah%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Ansah%20HF&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AHenry%2BFordjour%2BAnsah%2B) Huda Hammad 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Huda%2BHammad%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Hammad%20H&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AHuda%2BHammad%2B) Pranish Ghimire 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Pranish%2BGhimire%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Ghimire%20P&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3APranish%2BGhimire%2B) Md Tamjidul Hoque 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Md%2BTamjidul%2BHoque%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Hoque%20MT&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AMd%2BTamjidul%2BHoque%2B) Shreya Banerjee 4 Department of Computer Science LSU New Orleans, New Orleans, Louisiana, USA * [Find this author on Google Scholar](https://www.biorxiv.org/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=Shreya%2BBanerjee%2B "Open in new tab") * [Find this author on PubMed](https://www.biorxiv.org/lookup/external-ref?access_num=Banerjee%20S&link_type=AUTHORSEARCH "Open in new tab") * [Search for this author on this site](https://www.biorxiv.org/search/author1%3AShreya%2BBanerjee%2B) * [Abstract](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1)[](https://www.biorxiv.org/panels_ajax_tab/biorxiv_tab_art/node:5885768/1) * [Info/History](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.article-info)[](https://www.biorxiv.org/panels_ajax_tab/biorxiv_tab_info/node:5885768/1) * [Metrics](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.article-metrics)[](https://www.biorxiv.org/panels_ajax_tab/article_tab_metrics/node:5885768/1) * [Data/Code](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.external-links)[](https://www.biorxiv.org/panels_ajax_tab/article_tab_data_code/node:5885768/1) * [ Preview PDF](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.full.pdf+html)[](https://www.biorxiv.org/panels_ajax_tab/biorxiv_tab_pdf/node:5885768/1) ![Loading](https://www.biorxiv.org/sites/all/modules/contrib/panels_ajax_tab/images/loading.gif) ## Abstract Autism Spectrum Disorder (ASD) affects social interaction and communication, and automatically recognizing emotions from the facial expressions of children with ASD remains challenging. A key barrier to _facial emotion recognition_ (FER) in children with ASD is the absence of ASD-specific datasets with proper emotion-level annotations. To address this, we present **ASD-FER** , a benchmark of 2,779 facial images of children with ASD annotated across six emotion categories by three independent annotators using majority voting. We evaluate nine models — CNN, SVM, AlexNet, ResNet34, ResNet50, MobileNetV2, and three backbone configurations of our proposed task-specific architecture, **EQFormer** : ViT, Swin-T, and a compact Hybrid CNN-Transformer (HybridT) — under stratified 10-fold cross-validation and a held-out 90/10 evaluation. ResNet50 led conventional models at 84.89% mean cross-validation accuracy; among transformer-based models, ViT led with 88.27%, followed by Swin-T at 88.02% and HybridT at 86.58%. On the held-out set, ViT achieved the highest overall accuracy (91.01%), while Swin-T obtained the best balanced accuracy (74.47%) and macro-F1 (0.7078); HybridT remained competitive at 89.57% accuracy with a fraction of the parameters. To support explainability, Grad-CAM visualizations highlighted attention on emotion-relevant facial regions — eyes, eyebrows, and mouth — with Swin-T the most spatially focused and the HybridT the most parameter-efficient (2.66M). Class imbalance and cross-dataset generalization remain open challenges. ### Competing Interest Statement The authors have declared no competing interest. ## Footnotes * ## Funder Information Declared Louisiana Department of Health, Bureau of Health Services Financing,, 10000411 National Institute of General Medical Sciences (NIGMS), NIH — Institutional Development Award (IDeA) National Institute of General Medical Sciences (NIGMS), NIH — Data Science Block Grant Copyright The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a [CC-BY 4.0 International license](http://creativecommons.org/licenses/by/4.0/). bioRxiv and medRxiv thank the following for their generous financial support: > The Chan Zuckerberg Initiative, Cold Spring Harbor Laboratory, the Sergey Brin Family Foundation, California Institute of Technology, Centre National de la Recherche Scientifique, Fred Hutchinson Cancer Center, Imperial College London, Massachusetts Institute of Technology, Stanford University, The University of Edinburgh, University of Washington, and Vrije Universiteit Amsterdam. [Donate to openRxiv ](https://www.zeffy.com/en-US/donation-form/donate-to-make-a-difference-10981) [ Back to top](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1?rss=1#page) [ Previous](https://www.biorxiv.org/content/10.64898/2026.10.19.760013v1 "Antenna cells of ascidian larvae are gravity-sensing neurons")[Next ](https://www.biorxiv.org/content/10.64898/2026.10.19.760083v1 "Plant cell-based 4D engineered living materials") Posted October 20, 2026. [ Download PDF](https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.full.pdf) Print/Save Options [Download PDF](https://www.biorxiv.org/content/biorxiv/early/2026/10/20/2026.10.14.754143.full.pdf)Full Text & In-line FiguresXML [More Info](https://www.biorxiv.org/about/FAQ#PrintOptions "More Information on Print/Save Options") [ Data/Code](https://www.biorxiv.org/content/early/2026/10/20/2026.10.14.754143.external-links) [ Email](https://www.biorxiv.org/ "Email this Article") [ Share](https://www.biorxiv.org/) ASD-FER: An Annotated Multi-Class Benchmark and Comparative Study for Facial Emotion Recognition in Children with Autism Spectrum Disorder Shahana Yasmin Chowdhury, Bithi Banik, Tracey Ann Knaus, Christopher David Moore, Henry Fordjour Ansah, Huda Hammad, Pranish Ghimire, Md Tamjidul Hoque, Shreya Banerjee bioRxiv 2026.10.14.754143; doi: https://doi.org/10.64898/2026.10.14.754143 This article is a preprint and has not been certified by peer review [[what does this mean?](https://www.biorxiv.org/about/FAQ#unrefereed)]. Share This Article: Copy [![Twitter logo](https://www.biorxiv.org/sites/all/modules/highwire/highwire/images/twitter.png)](https://www.biorxiv.org/highwire_log/share/twitter?link=http%3A%2F%2Ftwitter.com%2Fshare%3Furl%3Dhttps%253A%2F%2Fwww.biorxiv.org%2Fcontent%2F10.64898%2F2026.10.14.754143v1%26text%3DASD-FER%253A%2520An%2520Annotated%2520Multi-Class%2520Benchmark%2520and%2520Comparative%2520Study%2520for%2520Facial%2520Emotion%2520Recognition%2520in%2520Children%2520with%2520Autism%2520Spectrum%2520Disorder "Share this on Twitter") [![Facebook logo](https://www.biorxiv.org/sites/all/modules/highwire/highwire/images/fb-blue.png)](https://www.biorxiv.org/highwire_log/share/facebook?link=http%3A%2F%2Fwww.facebook.com%2Fsharer.php%3Fu%3Dhttps%253A%2F%2Fwww.biorxiv.org%2Fcontent%2F10.64898%2F2026.10.14.754143v1%26t%3DASD-FER%253A%2520An%2520Annotated%2520Multi-Class%2520Benchmark%2520and%2520Comparative%2520Stud
## Related Clinical Research

- [Spatial profiling links STING to Kawasaki disease cardiac inflammation](https://medichelpline.com/clinical-feed/biorxiv-2-spatial-profiling-of-kawasaki-disease-cardiac-inflammation-identifies-sting-as.md)
- [DFCP1 membrane coat forms a diffusion barrier that concentrates PI3P for lysosome repair](https://medichelpline.com/clinical-feed/biorxiv-18-structure-and-function-of-the-dfcp1-membrane-barrier-responsible-for-er.md)
- [Mitochondrial dysfunction in neurology: biomarkers for diagnosis, stratification and monitoring](https://medichelpline.com/clinical-feed/nature-reviews-neurology-0-mitochondrial-dysfunction-in-neurology-biomarkers-and-clinical-implications.md)
- [Olive oil before carbs and blood sugar: what the mouse study found](https://medichelpline.com/clinical-feed/medical-news-today-0-olive-oil-shot-trend-what-science-really-says-about-fat-and-glucose-response.md)
- [Fatty liver in lean patients and five other research briefs](https://medichelpline.com/clinical-feed/bmj-2-leaning-into-fatty-liver-findings-and-other-research.md)

## Navigation
- [← Back to Pediatrics Feed](https://medichelpline.com/clinical-feed/pediatrics.md)
- [← All Clinical Specialties](https://medichelpline.com/clinical-feed.md)
## Medical & Regulatory Disclaimer

> [!CAUTION]
> MedicHelpline content is structured for research, educational, and professional discovery purposes. It does not constitute individual medical advice, clinical diagnosis, or treatment recommendations.
> Always verify dosing, contraindications, and regulatory alerts against official product labeling and primary regulatory sources before clinical decision-making.