Proteomics and machine learning in the prediction and explanation of low pectoralis muscle area.

Journal: Scientific reports
Published Date: Aug 3, 2024

Abstract

Low muscle mass is associated with numerous adverse outcomes independent of other associated comorbid diseases. We aimed to predict and understand an individual's risk for developing low muscle mass using proteomics and machine learning. We identified eight biomarkers associated with low pectoralis muscle area (PMA). We built three random forest classification models that used either clinical measures, feature selected biomarkers, or both to predict development of low PMA. The area under the receiver operating characteristic curve for each model was: clinical-only = 0.646, biomarker-only = 0.740, and combined = 0.744. We displayed the heterogenetic nature of an individual's risk for developing low PMA and identified two distinct subtypes of participants who developed low PMA. While additional validation is required, our methods for identifying and understanding individual and group risk for low muscle mass could be used to enable developments in the personalized prevention of low muscle mass.

Authors

  • Nicholas A Enzer
    Division of Pulmonary and Critical Care Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
  • Joe Chiles
    Division of Pulmonary, Allergy and Critical Care Medicine, Heersink School of Medicine, The University of Alabama at Birmingham, Birmingham, AL, USA.
  • Stefanie Mason
    Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA.
  • Toru Shirahata
    Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA.
  • Victor Castro
    Partners Healthcare Systems, Summerville, MA, USA.
  • Elizabeth Regan
    COPDGene Study Consortium, Denver, CO, USA.
  • Bina Choi
    Department of Medicine.
  • Nancy F Yuan
    Department of Biomedical Informatics, University of California at San Diego, San Diego, CA, USA.
  • Alejandro A Díaz
    From the Division of Pulmonary and Critical Care Medicine (A.A.D., W.R.D., A.T., J.L.O., G.R.W.), Department of Radiology (P.N., Rubén San José Estépar, Raúl San José Estépar), Division of Sleep Medicine and Circadian Disorders (W.W.), and Channing Division of Network Medicine (E.K.S.), Brigham and Women's Hospital, Harvard Medical School, 15 Francis St, Boston, MA 02115; Department of Radiology, University of California-San Diego, San Diego, Calif (A.Y., S.K.); Division of Pulmonary Diseases and Critical Care, University of Texas-San Antonio, San Antonio, Tex (D.J.M.); Department of Biomedical Sciences, Humanitas University, Milan, Italy (S.A.); Respiratory Unit, IRCCS Humanitas Research Hospital, Milan, Italy (S.A.); Department of Pulmonary Disease and Critical Care Medicine, Mayo Clinic, Rochester, Minn (T.R.A.); and Department of Epidemiology, Colorado School of Public Health, University of Colorado, Aurora, Colo (K.A.Y., G.L.K.).
  • George R Washko
    3 Division of Pulmonary and Critical Care Medicine, Department of Medicine, Brigham and Women's Hospital, Boston Massachusetts.
  • Merry-Lynn McDonald
    UAB Lung Health Center.
  • Raul San Jose Estepar
    Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
  • Samuel Y Ash
    3 Division of Pulmonary and Critical Care Medicine, Department of Medicine, Brigham and Women's Hospital, Boston Massachusetts.

Keywords

External Resources

Popular Topics
Recent Journals