Zihe Zheng1, Sushrut S Waikar2, Insa M Schmidt2, J Richard Landis3, Chi-Yuan Hsu4, Tariq Shafi5, Harold I Feldman3, Amanda H Anderson6, Francis P Wilson7, Jing Chen8, Hernan Rincon-Choles9, Ana C Ricardo10, Georges Saab11, Tamara Isakova12, Radhakrishna Kallem13, Jeffrey C Fink14, Panduranga S Rao15, Dawei Xie3, Wei Yang3. 1. Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania zihez@upenn.edu. 2. Section of Nephrology, Boston Medical Center and Boston University School of Medicine, Boston, Massachusetts. 3. Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 4. Division of Nephrology, University of California, San Francisco, California. 5. Nephrology Division, The University of Mississippi Medical Center, Jackson, Mississippi. 6. Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, Louisiana. 7. Section of Nephrology, Yale University School of Medicine, New Haven, Connecticut. 8. Section of Nephrology & Hypertension, Tulane University School of Medicine, New Orleans, Louisiana. 9. Department of Nephrology and Hypertension, Cleveland Clinic, Cleveland, Ohio. 10. Division of Nephrology, University of Illinois Chicago College of Medicine, Chicago, Illinois. 11. Nephrology Division, MetroHealth, Cleveland, Ohio. 12. Nephrology and Hypertension Division, Northwestern University Feinberg School of Medicine, Chicago, Illinois. 13. Renal Electrolyte and Hypertension Division, Department of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 14. Division of General Internal Medicine, University of Maryland School of Medicine, Baltimore, Maryland. 15. Nephrology Division, University of Michigan School of Medicine, Ann Arbor, Michigan.
Abstract
BACKGROUND: CKD is a heterogeneous condition with multiple underlying causes, risk factors, and outcomes. Subtyping CKD with multidimensional patient data holds the key to precision medicine. Consensus clustering may reveal CKD subgroups with different risk profiles of adverse outcomes. METHODS: We used unsupervised consensus clustering on 72 baseline characteristics among 2696 participants in the prospective Chronic Renal Insufficiency Cohort (CRIC) study to identify novel CKD subgroups that best represent the data pattern. Calculation of the standardized difference of each parameter used the cutoff of ±0.3 to show subgroup features. CKD subgroup associations were examined with the clinical end points of kidney failure, the composite outcome of cardiovascular diseases, and death. RESULTS: The algorithm revealed three unique CKD subgroups that best represented patients' baseline characteristics. Patients with relatively favorable levels of bone density and cardiac and kidney function markers, with lower prevalence of diabetes and obesity, and who used fewer medications formed cluster 1 (n=1203). Patients with higher prevalence of diabetes and obesity and who used more medications formed cluster 2 (n=1098). Patients with less favorable levels of bone mineral density, poor cardiac and kidney function markers, and inflammation delineated cluster 3 (n=395). These three subgroups, when linked with future clinical end points, were associated with different risks of CKD progression, cardiovascular disease, and death. Furthermore, patient heterogeneity among predefined subgroups with similar baseline kidney function emerged. CONCLUSIONS: Consensus clustering synthesized the patterns of baseline clinical and laboratory measures and revealed distinct CKD subgroups, which were associated with markedly different risks of important clinical outcomes. Further examination of patient subgroups and associated biomarkers may provide next steps toward precision medicine.
BACKGROUND: CKD is a heterogeneous condition with multiple underlying causes, risk factors, and outcomes. Subtyping CKD with multidimensional patient data holds the key to precision medicine. Consensus clustering may reveal CKD subgroups with different risk profiles of adverse outcomes. METHODS: We used unsupervised consensus clustering on 72 baseline characteristics among 2696 participants in the prospective Chronic Renal Insufficiency Cohort (CRIC) study to identify novel CKD subgroups that best represent the data pattern. Calculation of the standardized difference of each parameter used the cutoff of ±0.3 to show subgroup features. CKD subgroup associations were examined with the clinical end points of kidney failure, the composite outcome of cardiovascular diseases, and death. RESULTS: The algorithm revealed three unique CKD subgroups that best represented patients' baseline characteristics. Patients with relatively favorable levels of bone density and cardiac and kidney function markers, with lower prevalence of diabetes and obesity, and who used fewer medications formed cluster 1 (n=1203). Patients with higher prevalence of diabetes and obesity and who used more medications formed cluster 2 (n=1098). Patients with less favorable levels of bone mineral density, poor cardiac and kidney function markers, and inflammation delineated cluster 3 (n=395). These three subgroups, when linked with future clinical end points, were associated with different risks of CKD progression, cardiovascular disease, and death. Furthermore, patient heterogeneity among predefined subgroups with similar baseline kidney function emerged. CONCLUSIONS: Consensus clustering synthesized the patterns of baseline clinical and laboratory measures and revealed distinct CKD subgroups, which were associated with markedly different risks of important clinical outcomes. Further examination of patient subgroups and associated biomarkers may provide next steps toward precision medicine.
Authors: Sanjiv J Shah; Daniel H Katz; Senthil Selvaraj; Michael A Burke; Clyde W Yancy; Mihai Gheorghiade; Robert O Bonow; Chiang-Ching Huang; Rahul C Deo Journal: Circulation Date: 2014-11-14 Impact factor: 29.690
Authors: R G Nelson; P H Bennett; G J Beck; M Tan; W C Knowler; W E Mitch; G H Hirschman; B D Myers Journal: N Engl J Med Date: 1996-11-28 Impact factor: 91.245
Authors: Nisha Bansal; Amanda Hyre Anderson; Wei Yang; Robert H Christenson; Christopher R deFilippi; Rajat Deo; Daniel L Dries; Alan S Go; Jiang He; John W Kusek; James P Lash; Dominic Raj; Sylvia Rosas; Myles Wolf; Xiaoming Zhang; Michael G Shlipak; Harold I Feldman Journal: J Am Soc Nephrol Date: 2014-10-02 Impact factor: 10.121
Authors: James Fotheringham; Nicholas Weatherley; Bisher Kawar; Damian G Fogarty; Timothy Ellam Journal: Kidney Int Date: 2014-04-09 Impact factor: 10.612
Authors: Julia Carracedo; Matilde Alique; Carmen Vida; Guillermo Bodega; Noemí Ceprián; Enrique Morales; Manuel Praga; Patricia de Sequera; Rafael Ramírez Journal: Front Cell Dev Biol Date: 2020-03-20
Authors: Charat Thongprayoon; Michael A Mao; Andrea G Kattah; Mira T Keddis; Pattharawin Pattharanitima; Stephen B Erickson; John J Dillon; Vesna D Garovic; Wisit Cheungpasitporn Journal: Clin Kidney J Date: 2021-10-12
Authors: Charat Thongprayoon; Pradeep Vaitla; Voravech Nissaisorakarn; Michael A Mao; Jose L Zabala Genovez; Andrea G Kattah; Pattharawin Pattharanitima; Saraschandra Vallabhajosyula; Mira T Keddis; Fawad Qureshi; John J Dillon; Vesna D Garovic; Kianoush B Kashani; Wisit Cheungpasitporn Journal: Med Sci (Basel) Date: 2021-09-24