Machine-learning methodologies to predict disease progression in chronic hepatitis B in Africa

Hailemichael Desalegn; Xianchen Yang; Yi-Syuan Yen; Nega Berhe; Brooke Kenney; Geoffrey H Siwo; Weijing Tang; Ji Zhu; Akbar K Waljee; Asgeir Johannessen

doi:10.1097/HC9.0000000000000584

Machine-learning methodologies to predict disease progression in chronic hepatitis B in Africa

Hepatol Commun. 2024 Nov 15;8(12):e0584. doi: 10.1097/HC9.0000000000000584. eCollection 2024 Dec 1.

Authors

Hailemichael Desalegn^{1

2}, Xianchen Yang^{3

4}, Yi-Syuan Yen^{3

5}, Nega Berhe^{2

6}, Brooke Kenney^{7

8}, Geoffrey H Siwo^{9

10}, Weijing Tang^{3

11}, Ji Zhu³, Akbar K Waljee^{9

10

12}, Asgeir Johannessen^{2

13}

Affiliations

¹ Medical Department, St. Paul's Hospital Millennium Medical College, Addis Ababa, Ethiopia.
² Department of Infectious Diseases, Vestfold Hospital Trust, Tønsberg, Norway.
³ Department of Statistics, University of Michigan, Ann Arbor, Michigan, USA.
⁴ Department of Statistics, Stanford University, Stanford, California, USA.
⁵ Department of Statistics, University of California at Davis, Davis, California, USA.
⁶ Aklilu Lemma Institute of Pathobiology, Addis Ababa University, Addis Ababa, Ethiopia.
⁷ Menelik II Medical and Health Science College, Addis Ababa, Ethiopia.
⁸ Department of Surgery, University of Michigan, Ann Arbor, Michigan, USA.
⁹ Center for Global Health Equity, Michigan Medicine, University of Michigan, Ann Arbor, Michigan, USA.
¹⁰ Department of Learning Health Sciences, University of Michigan, Ann Arbor, Michigan, USA.
¹¹ Department of Statistics and Data Science, Carnegie Melon University, Pittsburgh, Pennsylvania, USA.
¹² Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan, USA.
¹³ Department of Infectious Diseases, Institute of Clinical Medicine, University of Oslo, Oslo, Norway.

PMID: 39774109
DOI: 10.1097/HC9.0000000000000584

Abstract

Background: Little is known about the determinants of disease progression among African patients with chronic HBV infection.

Methods: We used machine-learning models with longitudinal data to establish predictive algorithms in a well-characterized cohort of Ethiopian HBV-infected patients without baseline liver fibrosis. Disease progression was defined as an increase in liver stiffness to >7.9 kPa or initiation of treatment based on meeting the eligibility criteria.

Results: Twenty-four of 551 patients (4.4%) experienced disease progression after a median follow-up time of 69 months. A random forest model based on a combination of available laboratory tests (standard hematology and biochemistry) demonstrated the best predictive properties with the AUROC ranging from 0.82 to 0.88.

Conclusion: We conclude that combined metrics based on simple and available laboratory tests had good predictive properties and should be explored further in larger HBV cohorts.

MeSH terms

Adult
Algorithms
Disease Progression*
Elasticity Imaging Techniques
Ethiopia
Female
Hepatitis B, Chronic*
Humans
Liver Cirrhosis / virology
Longitudinal Studies
Machine Learning*
Male
Middle Aged
Predictive Value of Tests