Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: WFRF:(Papatheodoridis G.) > (2023) > Machine learning al...

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

Lee, Jenny (author): Amsterdam UMC, Netherlands

Westphal, Max (author): Fraunhofer Inst Digital Med MEVIS, Germany

Vali, Yasaman (author): Amsterdam UMC, Netherlands

Boursier, Jerome (author): Angers Univ Hosp, France

Petta, Salvatorre (author): Univ Palermo, Italy

Ostroff, Rachel (author): SomaLogic Inc, CO USA

Alexander, Leigh (author): SomaLogic Inc, CO USA

Chen, Yu (author): Eli Lilly & Co Ltd LLY, IN USA

Fournier, Celine (author): Echosens, France

Geier, Andreas (author): Wurzburg Univ Hosp, Germany

Francque, Sven (author): Univ Antwerp, Belgium

Wonders, Kristy (author): Newcastle Univ, England

Tiniakos, Dina (author): Newcastle Univ, England; Natl & Kapodistrian Univ Athens, Greece

Bedossa, Pierre (author): Newcastle Univ, England

Allison, Mike (author): Cambridge Univ NHS Fdn Trust, England

Papatheodoridis, Georgios (author): Natl & Kapodistrian Univ Athens, Greece

Cortez-Pinto, Helena (author): Univ Lisbon, Portugal

Pais, Raluca (author): Sorbonne Univ, France

Dufour, Jean-Francois (author): Univ Bern, Switzerland

Leeming, Diana Julie (author): Nordic Biosci AS, Denmark

Harrison, Stephen (author): John Radcliffe Hosp, England

Cobbold, Jeremy (author): John Radcliffe Hosp, England

Holleboom, Adriaan G. (author): Amsterdam Univ Med Ctr, Netherlands

Yki-Jarvinen, Hannele (author): Univ Helsinki, Finland; Helsinki Univ Hosp, Finland; Minerva Fdn, Finland

Crespo, Javier (author): Univ Hosp Marques Valdecilla, Spain

Ekstedt, Mattias (author): Linköpings universitet,Avdelningen för diagnostik och specialistmedicin,Medicinska fakulteten,Region Östergötland, Mag- tarmmedicinska kliniken

Aithal, Guruprasad P. (author): Nottingham Univ Hosp NHS Trust, England; Univ Nottingham, England

Bugianesi, Elisabetta (author): Univ Turin, Italy

Romero-Gomez, Manuel (author): Univ Seville, Spain

Torstenson, Richard (author): AstraZeneca, Sweden

Karsdal, Morten (author): Nordic Biosci AS, Denmark

Yunis, Carla (author): Pfizer Inc, NY USA

Schattenberg, Joern M. (author): Univ Med Ctr Mainz, Germany

Schuppan, Detlef (author): Univ Med Ctr Mainz, Germany; Univ Med Ctr Mainz, Germany; Harvard Med Sch, MA USA

Ratziu, Vlad (author): Sorbonne Univ, France

Brass, Clifford (author): Novartis Pharmaceut, NJ USA

Duffin, Kevin (author): Eli Lilly & Co Ltd LLY, IN USA

Zwinderman, Koos (author): Amsterdam UMC, Netherlands

Pavlides, Michael (author): Univ Oxford, England

Anstee, Quentin M. (author): Univ Antwerp, Belgium; Newcastle Upon Tyne Hosp NHS Trust, England

Bossuyt, Patrick M. (author): Amsterdam UMC, Netherlands

show less...

(creator_code:org_t)

LIPPINCOTT WILLIAMS & WILKINS, 2023
2023
English.
In: Hepatology. - : LIPPINCOTT WILLIAMS & WILKINS. - 0270-9139 .- 1527-3350. ; 78:1, s. 258-271

Related links:: https://urn.kb.se/re...; show more...; https://doi.org/10.1...; show less...

Journal article (peer-reviewed)

Abstract Subject headings

Background and Aims: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F >= 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. Approach and Results: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS >= 4;53%), at-risk NASH (NASH with F >= 2;35%), significant (F >= 2;47%), and advanced fibrosis (F >= 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). Conclusions: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Find in a library

Hepatology (Search for host publication in LIBRIS)

To the university's database

Find more in SwePub

By the author/editor: Lee, Jenny; Westphal, Max; Vali, Yasaman; Boursier, Jerome; Petta, Salvatorr ...; Ostroff, Rachel; show more...; Alexander, Leigh; Chen, Yu; Fournier, Celine; Geier, Andreas; Francque, Sven; Wonders, Kristy; Tiniakos, Dina; Bedossa, Pierre; Allison, Mike; Papatheodoridis, ...; Cortez-Pinto, He ...; Pais, Raluca; Dufour, Jean-Fra ...; Leeming, Diana J ...; Harrison, Stephe ...; Cobbold, Jeremy; Holleboom, Adria ...; Yki-Jarvinen, Ha ...; Crespo, Javier; Ekstedt, Mattias; Aithal, Gurupras ...; Bugianesi, Elisa ...; Romero-Gomez, Ma ...; Torstenson, Rich ...; Karsdal, Morten; Yunis, Carla; Schattenberg, Jo ...; Schuppan, Detlef; Ratziu, Vlad; Brass, Clifford; Duffin, Kevin; Zwinderman, Koos; Pavlides, Michae ...; Anstee, Quentin ...; Bossuyt, Patrick ...; show less...

About the subject

MEDICAL AND HEALTH SCIENCES: MEDICAL AND HEAL ...; and Clinical Medicin ...; and Gastroenterology ...

Articles in the publication: Hepatology

By the university: Linköping University

Search outside SwePub

Extend your search to:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

Subject headings

Publication and Content Type

Find in a library

To the university's database

Find more in SwePub

Search outside SwePub