Mohammed Eslam1, Ahmed M Hashem2, Manuel Romero-Gomez3, Thomas Berg4, Gregory J Dore5, Alessandra Mangia6, Henry Lik Yuen Chan7, William L Irving8, David Sheridan9, Maria Lorena Abate10, Leon A Adams11, Martin Weltman12, Elisabetta Bugianesi10, Ulrich Spengler13, Olfat Shaker14, Janett Fischer15, Lindsay Mollison16, Wendy Cheng17, Jacob Nattermann13, Stephen Riordan18, Luca Miele19, Kebitsaone Simon Kelaeng1, Javier Ampuero3, Golo Ahlenstiel1, Duncan McLeod20, Elizabeth Powell21, Christopher Liddle1, Mark W Douglas1, David R Booth22, Jacob George23. 1. Storr Liver Centre, The Westmead Millennium Institute for Medical Research and Westmead Hospital, The University of Sydney, NSW, Australia. 2. Department of Systems and Biomedical Engineering, Faculty of Engineering, Minia University, Minia, Egypt. 3. Unit for The Clinical Management of Digestive Diseases and CIBERehd, Hospital Universitario de Valme, Sevilla, Spain. 4. Medizinische Klinik m.S. Hepatologie und Gastroenterologie, Charite, Campus Virchow-Klinikum, Universitätsmedizin Berlin, Germany; Department of Hepatology, Clinic for Gastroenterology and Rheumatology, University Clinic Leipzig, Leipzig, Germany. 5. Kirby Institute, The University of New South Wales, Sydney, NSW, Australia; St Vincent's Hospital, Sydney, NSW, Australia. 6. Division of Hepatology, Ospedale Casa Sollievo della Sofferenza, IRCCS, San Giovanni Rotondo, Italy. 7. Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong, China. 8. NIHR Biomedical Research Unit in Gastroenterology and the Liver, University of Nottingham, Nottingham, United Kingdom. 9. Liver Research Group, Institute of Cellular Medicine, Medical School, Newcastle University, Newcastle upon Tyne, United Kingdom; Institute of Translational and Stratified Medicine, Plymouth University, United Kingdom. 10. Division of Gastroenterology and Hepatology, Department of Medical Science, University of Turin, Turin, Italy. 11. School of Medicine and Pharmacology, Sir Charles Gairdner Hospital Unit, University of Western Australia, Nedlands, WA, Australia. 12. Department of Gastroenterology and Hepatology, Nepean Hospital, Sydney, NSW, Australia. 13. Department of Internal Medicine I, University of Bonn, Bonn, Germany. 14. Medical Biochemistry and Molecular Biology Department, Faculty of Medicine, Cairo University, Cairo, Egypt. 15. Medizinische Klinik m.S. Hepatologie und Gastroenterologie, Charite, Campus Virchow-Klinikum, Universitätsmedizin Berlin, Germany. 16. School of Medicine and Pharmacology, Fremantle Hospital, UWA, Fremantle, WA, Australia. 17. Department of Gastroenterology & Hepatology, Royal Perth Hospital, WA, Australia. 18. Gastrointestinal and Liver Unit, Prince of Wales Hospital and University of New South Wales, Sydney, NSW, Australia. 19. Department of Internal Medicine, Catholic University of the Sacred Heart, Rome, Italy. 20. Department of Anatomical Pathology, Institute of Clinical Pathology and Medical Research (ICPMR), Westmead Hospital, Sydney, Australia. 21. Princess Alexandra Hospital, Department of Gastroenterology and Hepatology, Woolloongabba, QLD, Australia; The University of Queensland, School of Medicine, Princess Alexandra Hospital, Woolloongabba, QLD, Australia. 22. Institute of Immunology and Allergy Research, Westmead Hospital and Westmead Millennium Institute, University of Sydney, NSW, Australia. 23. Storr Liver Centre, The Westmead Millennium Institute for Medical Research and Westmead Hospital, The University of Sydney, NSW, Australia. Electronic address: jacob.george@sydney.edu.au.
Abstract
BACKGROUND & AIMS: The extent of liver fibrosis predicts long-term outcomes, and hence impacts management and therapy. We developed a non-invasive algorithm to stage fibrosis using non-parametric, machine learning methods designed for predictive modeling, and incorporated an invariant genetic marker of liver fibrosis risk. METHODS: Of 4277 patients with chronic liver disease, 1992 with chronic hepatitis C (derivation cohort) were analyzed to develop the model, and subsequently validated in an independent cohort of 1242 patients. The model was assessed in cohorts with chronic hepatitis B (CHB) (n=555) and non-alcoholic fatty liver disease (NAFLD) (n=488). Model performance was compared to FIB-4 and APRI, and also to the NAFLD fibrosis score (NFS) and Forns' index, in those with NAFLD. RESULTS: Significant fibrosis (⩾F2) was similar in the derivation (48.4%) and validation (47.4%) cohorts. The FibroGENE-DT yielded the area under the receiver operating characteristic curve (AUROCs) of 0.87, 0.85 and 0.804 for the prediction of fast fibrosis progression, cirrhosis and significant fibrosis risk, respectively, with comparable results in the validation cohort. The model performed well in NAFLD and CHB with AUROCs of 0.791, and 0.726, respectively. The negative predictive value to exclude cirrhosis was>0.96 in all three liver diseases. The AUROC of the FibroGENE-DT performed better than FIB-4, APRI, and NFS and Forns' index in most comparisons. CONCLUSION: A non-invasive decision tree model can predict liver fibrosis risk and aid decision making.
BACKGROUND & AIMS: The extent of liver fibrosis predicts long-term outcomes, and hence impacts management and therapy. We developed a non-invasive algorithm to stage fibrosis using non-parametric, machine learning methods designed for predictive modeling, and incorporated an invariant genetic marker of liver fibrosis risk. METHODS: Of 4277 patients with chronic liver disease, 1992 with chronic hepatitis C (derivation cohort) were analyzed to develop the model, and subsequently validated in an independent cohort of 1242 patients. The model was assessed in cohorts with chronic hepatitis B (CHB) (n=555) and non-alcoholic fatty liver disease (NAFLD) (n=488). Model performance was compared to FIB-4 and APRI, and also to the NAFLD fibrosis score (NFS) and Forns' index, in those with NAFLD. RESULTS: Significant fibrosis (⩾F2) was similar in the derivation (48.4%) and validation (47.4%) cohorts. The FibroGENE-DT yielded the area under the receiver operating characteristic curve (AUROCs) of 0.87, 0.85 and 0.804 for the prediction of fast fibrosis progression, cirrhosis and significant fibrosis risk, respectively, with comparable results in the validation cohort. The model performed well in NAFLD and CHB with AUROCs of 0.791, and 0.726, respectively. The negative predictive value to exclude cirrhosis was>0.96 in all three liver diseases. The AUROC of the FibroGENE-DT performed better than FIB-4, APRI, and NFS and Forns' index in most comparisons. CONCLUSION: A non-invasive decision tree model can predict liver fibrosis risk and aid decision making.
Authors: Mohammed Eslam; Hashem B El-Serag; Sven Francque; Shiv K Sarin; Lai Wei; Elisabetta Bugianesi; Jacob George Journal: Nat Rev Gastroenterol Hepatol Date: 2022-06-16 Impact factor: 73.082
Authors: Mohammed Eslam; Duncan McLeod; Kebitsaone Simon Kelaeng; Alessandra Mangia; Thomas Berg; Khaled Thabet; William L Irving; Gregory J Dore; David Sheridan; Henning Grønbæk; Maria Lorena Abate; Rune Hartmann; Elisabetta Bugianesi; Ulrich Spengler; Angela Rojas; David R Booth; Martin Weltman; Lindsay Mollison; Wendy Cheng; Stephen Riordan; Hema Mahajan; Janett Fischer; Jacob Nattermann; Mark W Douglas; Christopher Liddle; Elizabeth Powell; Manuel Romero-Gomez; Jacob George Journal: Nat Genet Date: 2017-04-10 Impact factor: 38.330
Authors: Khaled Thabet; Anastasia Asimakopoulos; Maryam Shojaei; Manuel Romero-Gomez; Alessandra Mangia; William L Irving; Thomas Berg; Gregory J Dore; Henning Grønbæk; David Sheridan; Maria Lorena Abate; Elisabetta Bugianesi; Martin Weltman; Lindsay Mollison; Wendy Cheng; Stephen Riordan; Janett Fischer; Ulrich Spengler; Jacob Nattermann; Ahmed Wahid; Angela Rojas; Rose White; Mark W Douglas; Duncan McLeod; Elizabeth Powell; Christopher Liddle; David van der Poorten; Jacob George; Mohammed Eslam Journal: Nat Commun Date: 2016-09-15 Impact factor: 14.919
Authors: Naeimeh Atabaki-Pasdar; Mattias Ohlsson; Ana Viñuela; Francesca Frau; Hugo Pomares-Millan; Mark Haid; Angus G Jones; E Louise Thomas; Robert W Koivula; Azra Kurbasic; Pascal M Mutie; Hugo Fitipaldi; Juan Fernandez; Adem Y Dawed; Giuseppe N Giordano; Ian M Forgie; Timothy J McDonald; Femke Rutters; Henna Cederberg; Elizaveta Chabanova; Matilda Dale; Federico De Masi; Cecilia Engel Thomas; Kristine H Allin; Tue H Hansen; Alison Heggie; Mun-Gwan Hong; Petra J M Elders; Gwen Kennedy; Tarja Kokkola; Helle Krogh Pedersen; Anubha Mahajan; Donna McEvoy; Francois Pattou; Violeta Raverdy; Ragna S Häussler; Sapna Sharma; Henrik S Thomsen; Jagadish Vangipurapu; Henrik Vestergaard; Leen M 't Hart; Jerzy Adamski; Petra B Musholt; Soren Brage; Søren Brunak; Emmanouil Dermitzakis; Gary Frost; Torben Hansen; Markku Laakso; Oluf Pedersen; Martin Ridderstråle; Hartmut Ruetten; Andrew T Hattersley; Mark Walker; Joline W J Beulens; Andrea Mari; Jochen M Schwenk; Ramneek Gupta; Mark I McCarthy; Ewan R Pearson; Jimmy D Bell; Imre Pavo; Paul W Franks Journal: PLoS Med Date: 2020-06-19 Impact factor: 11.069