Research priorities in chronic lung allograft dysfunction: A machine learning-assisted bibliometric analysis
Abstract
Background: Chronic lung allograft dysfunction (CLAD), the leading cause of death beyond year one post-transplant, encompasses bronchiolitis obliterans syndrome (BOS), restrictive allograft syndrome (RAS), and mixed allograft syndrome (MAS), formalized by the 2019 ISHLT consensus. How thematic priorities have evolved and whether research effort tracks phenotype burden have not been systematically examined. Methods: From 1,851 CLAD-related papers (Web of Science, 1990-2025) assembled after AI-assisted relevance screening (validated against blinded expert adjudication), machine learning-based topic modeling using a biomedical language model identified thematic clusters; temporal trajectories were classified by statistical trend analysis; and a phenotype representation index (RI = corpus proportion ÷ clinical prevalence) was computed against 2 reference cohorts with bootstrap confidence intervals. Results: Twenty-four thematic clusters were identified (13 declining, 8 stable, 3 rising, 1 emerging). Rising topics included DSA/antibody-mediated rejection (119 papers), restrictive phenotype classification (126 papers), and translational CLAD pathogenesis (143 papers), reflecting momentum predating the 2019 consensus. Donor-derived cell-free DNA was the sole emerging topic (21 papers). Among 950 phenotype-focused papers, BOS was proportionally represented (RI 1.13 vs Leuven; 1.05 vs Toronto). RAS representation was denominator-dependent (RI 0.75-0.99). MAS was substantially under-represented in both cohorts (RI 0.33 vs Leuven; 0.41 vs Toronto). Conclusions: Transformer-based topic modeling reveals a directional shift toward immunological mechanisms and phenotype-specific research that classical keyword approaches cannot resolve. Research effort is broadly proportionate to clinical burden for BOS but substantially below for MAS, a gap possibly attributable to pathophysiological differences, diagnostic complexity, limited case volume, and recency of phenotype formalization that multicenter studies may address.
Related
- Case Report: Late-onset BK polyomavirus-associated nephropathy with encephalitis, antibody-mediated rejection, and atypical hemolytic uremic syndrome: a rare overlap causing allograft dysfunction, therapeutic challenges, and multidisciplinary management
- The clinical significance of baseline lung allograft dysfunction in single and bilateral lung transplant recipients
- Evolution of knee osteoarthritis biomechanics research, 2005–2025: bibliometric mapping and machine-learning-assisted topic modeling
- Possible baseline lung allograft dysfunction within the first year defines a high-risk and potentially reversible state after lung transplantation
- Pentraxin-3 dynamics during liver transplantation and association with early allograft dysfunction
BibTeX
@article{husseini2026research,
title = {{Research priorities in chronic lung allograft dysfunction: A machine learning-assisted bibliometric analysis}},
author = {Kinan El Husseini and Margot Delin and Sixtine Decaux and Tiphaine Goletto and Lise Morer and Domitille Mouren and Mathilde Salpin and Gaëlle Weisenburger and Benjamin Coiffard and Claire Merveilleux Du Vignaux and Jérôme Le Pavec and Benjamin Renaud-Picard and Antoine Roux and Adrien Tissot and Thomas Villeneuve and Arnaud Roussel and Pierre Mordant and Olivier Brugière and Hervé Mal and Vincent Bunel},
journal = {JHLT Open},
year = {2026},
month = oct,
doi = {10.1016/j.jhlto.2026.100645},
url = {https://inserm.hal.science/inserm-05778736v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Research priorities in chronic lung allograft dysfunction: A machine learning-assisted bibliometric analysis
AU - Kinan El Husseini
AU - Margot Delin
AU - Sixtine Decaux
AU - Tiphaine Goletto
AU - Lise Morer
AU - Domitille Mouren
AU - Mathilde Salpin
AU - Gaëlle Weisenburger
AU - Benjamin Coiffard
AU - Claire Merveilleux Du Vignaux
AU - Jérôme Le Pavec
AU - Benjamin Renaud-Picard
AU - Antoine Roux
AU - Adrien Tissot
AU - Thomas Villeneuve
AU - Arnaud Roussel
AU - Pierre Mordant
AU - Olivier Brugière
AU - Hervé Mal
AU - Vincent Bunel
PY - 2026
DA - 2026/10/05
JO - JHLT Open
DO - 10.1016/j.jhlto.2026.100645
UR - https://inserm.hal.science/inserm-05778736v1
AB - Background: Chronic lung allograft dysfunction (CLAD), the leading cause of death beyond year one post-transplant, encompasses bronchiolitis obliterans syndrome (BOS), restrictive allograft syndrome (RAS), and mixed allograft syndrome (MAS), formalized by the 2019 ISHLT consensus. How thematic priorities have evolved and whether research effort tracks phenotype burden have not been systematically examined. Methods: From 1,851 CLAD-related papers (Web of Science, 1990-2025) assembled after AI-assisted relevance screening (validated against blinded expert adjudication), machine learning-based topic modeling using a biomedical language model identified thematic clusters; temporal trajectories were classified by statistical trend analysis; and a phenotype representation index (RI = corpus proportion ÷ clinical prevalence) was computed against 2 reference cohorts with bootstrap confidence intervals. Results: Twenty-four thematic clusters were identified (13 declining, 8 stable, 3 rising, 1 emerging). Rising topics included DSA/antibody-mediated rejection (119 papers), restrictive phenotype classification (126 papers), and translational CLAD pathogenesis (143 papers), reflecting momentum predating the 2019 consensus. Donor-derived cell-free DNA was the sole emerging topic (21 papers). Among 950 phenotype-focused papers, BOS was proportionally represented (RI 1.13 vs Leuven; 1.05 vs Toronto). RAS representation was denominator-dependent (RI 0.75-0.99). MAS was substantially under-represented in both cohorts (RI 0.33 vs Leuven; 0.41 vs Toronto). Conclusions: Transformer-based topic modeling reveals a directional shift toward immunological mechanisms and phenotype-specific research that classical keyword approaches cannot resolve. Research effort is broadly proportionate to clinical burden for BOS but substantially below for MAS, a gap possibly attributable to pathophysiological differences, diagnostic complexity, limited case volume, and recency of phenotype formalization that multicenter studies may address.
SN - 2950-1334
ER -