A Hybrid Artificial Intelligence and Human Pipeline to Map the Over Thirty-Seven Years Immunomodulatory Legacy of Lactobacillus rhamnosus GG

Lactobacillus rhamnosus GG (LGG) is one of the most studied probiotic strains, with an immunological fingerprint that has evolved over three decades of research. The exponential growth of biomedical literature has created a scalability crisis exceeding human synthesis capacity. This study aimed to elucidate LGG’s immunomodulatory role using a zero-cost, high-speed, hybrid human-AI workflow, leveraging free Model-platform systems as a scalable screening tool accessible to any researcher regardless of institutional affiliation. An operative pipeline based on four specialized prompts was developed to interrogate three Model-platform systems architectures (Gemini 3 Flash, Perplexity Academic, and Claude Sonnet 4.6), screening 37 years of PubMed literature (1989–2026). Performance was benchmarked against a human-validated Gold Standard using Sensitivity, Specificity, and Spearman Correlation, with a “Semantic Floor” analysis investigating False Negatives. A paradigm shift emerged: historical studies (pre-2019) focused on mucosal barrier integrity and IgA production, while recent research (2019–2026) emphasizes complex molecular signaling (IL-22, Type-I Interferons, Inflammasome modulation). A consistent core fingerprint persisted, characterized by TNF-α/IL-6 suppression and IL-10 upregulation, while IFNg showed context-dependent dual modulation. Gemini 3 Flash showed superior sensitivity (0.93–0.97), while Perplexity Academic achieved near-perfect specificity (0.99) due to its Retrieval-Augmented Generation (RAG) architecture which mitigated hallucinations. The Spearman Heatmap revealed a correlation coefficient near zero between Gemini and Perplexity sessions, reflecting their divergent scoring dynamics. LGG research has shifted from mucosal barrier protection to complex molecular signaling. Synergy between different model-platform systems architectures allows researchers to act as AI-orchestrators, focusing on critical interpretation rather than mechanical extraction. Established knowledge on this subject. Lactobacillus rhamnosus GG (LGG) is one of the most studied probiotic strains, with a well-documented immunomodulatory profile. Biomedical literature is growing exponentially and model-platform systems are emerging as tools for accelerating evidence synthesis, but their reliability and complementarity in biomedical research remain poorly characterized. Significant and/or new findings of this study. We validated a zero-cost, hybrid human-AI pipeline using three distinct model-platform systems architectures to screen 37 years of PubMed literature on LGG. We identified a shift in LGG research, from mucosal barrier/IgA focus to a more recent interest in complex molecular signaling (IL-22, Type I IFN, inflammasome). A consistent core immunological fingerprint (TNF-α/IL-6 suppression, IL-10/IFN-γ upregulation) persisted across three decades. We defined a "Semantic Floor," including a novel "Title Trap" phenomenon, highlighting key limitations requiring human oversight in AI-assisted synthesis.

Authors

Institutions

Publication Details

Journal
Probiotics and Antimicrobial Proteins
Published
2026-11-19
DOI
https://doi.org/10.1007/s12602-026-11290-6
Primary Topic
Probiotics and Fermented Foods
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Hybrid Artificial Intelligence and Human Pipeline to Map the Over Thirty-Seven Years Immunomodulatory Legacy of Lactobacillus rhamnosus GG

Chiara Amoroso, Maurizio Vecchi, Federica Facciotti, Flavio Caprioli et al.
Probiotics and Antimicrobial Proteins
Probiotics and Fermented Foods
article

A Hybrid Artificial Intelligence and Human Pipeline to Map the Over Thirty-Seven Years Immunomodulatory Legacy of Lactobacillus rhamnosus GG

Chiara Amoroso, Maurizio Vecchi, Federica Facciotti, Flavio Caprioli, Daniele Noviello, Melissa Rocca
article en

Abstract

Lactobacillus rhamnosus GG (LGG) is one of the most studied probiotic strains, with an immunological fingerprint that has evolved over three decades of research. The exponential growth of biomedical literature has created a scalability crisis exceeding human synthesis capacity. This study aimed to elucidate LGG’s immunomodulatory role using a zero-cost, high-speed, hybrid human-AI workflow, leveraging free Model-platform systems as a scalable screening tool accessible to any researcher regardless of institutional affiliation. An operative pipeline based on four specialized prompts was developed to interrogate three Model-platform systems architectures (Gemini 3 Flash, Perplexity Academic, and Claude Sonnet 4.6), screening 37 years of PubMed literature (1989–2026). Performance was benchmarked against a human-validated Gold Standard using Sensitivity, Specificity, and Spearman Correlation, with a “Semantic Floor” analysis investigating False Negatives. A paradigm shift emerged: historical studies (pre-2019) focused on mucosal barrier integrity and IgA production, while recent research (2019–2026) emphasizes complex molecular signaling (IL-22, Type-I Interferons, Inflammasome modulation). A consistent core fingerprint persisted, characterized by TNF-α/IL-6 suppression and IL-10 upregulation, while IFNg showed context-dependent dual modulation. Gemini 3 Flash showed superior sensitivity (0.93–0.97), while Perplexity Academic achieved near-perfect specificity (0.99) due to its Retrieval-Augmented Generation (RAG) architecture which mitigated hallucinations. The Spearman Heatmap revealed a correlation coefficient near zero between Gemini and Perplexity sessions, reflecting their divergent scoring dynamics. LGG research has shifted from mucosal barrier protection to complex molecular signaling. Synergy between different model-platform systems architectures allows researchers to act as AI-orchestrators, focusing on critical interpretation rather than mechanical extraction. Established knowledge on this subject. Lactobacillus rhamnosus GG (LGG) is one of the most studied probiotic strains, with a well-documented immunomodulatory profile. Biomedical literature is growing exponentially and model-platform systems are emerging as tools for accelerating evidence synthesis, but their reliability and complementarity in biomedical research remain poorly characterized. Significant and/or new findings of this study. We validated a zero-cost, hybrid human-AI pipeline using three distinct model-platform systems architectures to screen 37 years of PubMed literature on LGG. We identified a shift in LGG research, from mucosal barrier/IgA focus to a more recent interest in complex molecular signaling (IL-22, Type I IFN, inflammasome). A consistent core immunological fingerprint (TNF-α/IL-6 suppression, IL-10/IFN-γ upregulation) persisted across three decades. We defined a "Semantic Floor," including a novel "Title Trap" phenomenon, highlighting key limitations requiring human oversight in AI-assisted synthesis.

Probiotics and Antimicrobial Proteins
University of Milan (IT), Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT), University of Milano-Bicocca (IT)
Fondazione Cariplo, Ministero della Salute, Associazione Italiana per la Ricerca sul Cancro
Good health and well-being
Probiotics and Fermented Foods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon