Proteomics and machine learning in the prediction and explanation of low pectoralis muscle area
-
期刊论文
-
出版模式：
开放获取
-
发表日期：
2024年8月3日
- Nicholas A. Enzer,
- Joe Chiles,
- Stefanie Mason,
- Toru Shirahata,
- Victor Castro,
- Elizabeth Regan,
- Bina Choi,
- Nancy F. Yuan,
- Alejandro A. Diaz,
- George R. Washko,
- Merry-Lynn McDonald,
- Raúl San José Estépar,
- Samuel Y. Ash,
- Nicola A. Hanania,
- Mustafa Atik,
- Laura Bertrand,
- Aladin Boriek,
- Thomas Monaco,
- Dharani Narendra,
- Francesca Polverino,
- Veronica V. Lenge de Rosen,
- Paula Sierra Salas,
- Tianshi David Wu,
- Dawn L. DeMeo,
- Craig P. Hersh,
- Alejandro A. Diaz,
- Staci M. Gagne,
- Francine L. Jacobson,
- Kathryn Marentette,
- George R. Washko,
- Seth Wilson,
- Jeong H. Yun,
- R. Graham Barr,
- John H. M. Austin,
- Maria Lorena Gomez Blum,
- Belinda M. D’Souza,
- Emilay Florez,
- Valeria Lopez,
- Wanda Pecheco,
- Byron Thomashow,
- Chris H. Wendt,
- Arianne Baldomero,
- Miranda Hassler,
- Ken M. Kunisaki,
- David MacDonald,
- Charlene McEvoy,
- Nell Adams,
- Barbara Heinz,
- Jonathan Phelan,
- Cheryl Sasse,
- Eric L. Flenaugh,
- Judith Delancy,
- Marilyn G. Foreman,
- Hirut Gebrekristos,
- Willi Howell,
- Dominique Lawson,
- Mario Ponce,
- Gloria Westney,
- Russell P. Bowler,
- Sophia Addi,
- Elena Engel,
- Jay Finigan,
- Claire Guo,
- Seth Kligerman,
- David A. Lynch,
- Elizabeth Regan,
- Lisa Ruvuna,
- Richard Rosiello,
- Jean Champagne,
- Mary Charpentier,
- Theodore Girard,
- Jon Jaksha,
- Diane Kirk,
- Laurie Kuck,
- Mohammed Quraishi,
- Lucia Sears,
- Gerard J. Criner,
- Elise Cortese,
- Chandra Dass,
- Laurie Jameson,
- Nathaniel Marchetti,
- Francine McGonagle,
- Lauren Miller,
- Kim Selwood,
- Kartik Shenoy,
- Regina Sheridan,
- Shubhra Srivastava-Malhotra,
- Surya P. Bhatt,
- William C. Bailey,
- Sandeep Bodduluri,
- Joe W. Chiles,
- Mark T. Dransfield,
- Scott Grumley,
- Sonya Hardy,
- Anand Iyer,
- David C. LaFon,
- Padma Manapragada,
- Merry-Lynn McDonald,
- Hrudaya Nath,
- Gabriela Oates,
- Satinder P. Singh,
- Raymond C. Wade,
- Mike Wells,
- Abigail West,
- Douglas Conrad,
- Jeffrey Barry,
- Marissa Gil,
- Albert Hsiao,
- Amber Martineau,
- Jenna Mielke,
- Gabriel Querido,
- Xavier Soler,
- Rajat Suri,
- Sean Swenson,
- Angela Wang,
- Andrew Yen,
- Alejandro Comellas,
- Eric Bruening,
- Sidney Davis,
- Nick Feeley,
- Spyridon Fortis,
- Devon Foster,
- Eric Garcia,
- Kaitlyn Glosser,
- Karin F. Hoth,
- Justin D. Kuhn,
- Archana Laroia,
- Changhyun Lee,
- Jeni Michelson,
- Kim Sprenger,
- Katelyn Wilensky,
- Alejandro Comellas,
- Eric Bruening,
- Sidney Davis,
- Nick Feeley,
- Spyridon Fortis,
- Devon Foster,
- Eric Garcia,
- Kaitlyn Glosser,
- Karin F. Hoth,
- Justin D. Kuhn,
- Archana Laroia,
- Changhyun Lee,
- Jeni Michelson,
- Kim Sprenger,
- Katelyn Wilensky,
- MeiLan K. Han,
- Gretchen Bautista,
- Jeffrey L. Curtis,
- Crystal Cutlip,
- Craig J. Galban,
- Jaide Hawn,
- Ella Kazerooni,
- Wassim Labaki,
- Lisa McCloskey,
- Kelly Rysso,
- Liujian Zhao,
- Joanne Billings,
- Tadashi L. Allen,
- Mary P. Bailey,
- Anne Duesterbeck,
- Nate Gaeckle,
- Brooke Noren,
- Kyong Yun,
- Frank Sciurba,
- Daniel Arminavage,
- P. Takis Benos,
- Jessica Bon,
- Divay Chandra,
- Paula Consolaro,
- Tiffany Ditter,
- Jason Duin,
- Robert Gregg,
- Chad Karoleski,
- Zehavit Kirshenboim,
- Rhonda Lincoln,
- Antonio Anzueto,
- Sandra G. Adams,
- Diego Maselli-Caceres,
- Mario E. Ruiz
摘要
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.