1
|
Rule AD, Grossardt BR, Weston AD, Garner HW, Kline TL, Chamberlain AM, Allen AM, Erickson BJ, Rocca WA, St Sauver JL. Older Tissue Age Derived From Abdominal Computed Tomography Biomarkers of Muscle, Fat, and Bone Is Associated With Chronic Conditions and Higher Mortality. Mayo Clin Proc 2024; 99:878-890. [PMID: 38310501 PMCID: PMC11153040 DOI: 10.1016/j.mayocp.2023.09.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Revised: 09/12/2023] [Accepted: 09/18/2023] [Indexed: 02/05/2024]
Abstract
OBJECTIVE To determine whether body composition derived from medical imaging may be useful for assessing biologic age at the tissue level because people of the same chronologic age may vary with respect to their biologic age. METHODS We identified an age- and sex-stratified cohort of 4900 persons with an abdominal computed tomography scan from January 1, 2010, to December 31, 2020, who were 20 to 89 years old and representative of the general population in Southeast Minnesota and West Central Wisconsin. We constructed a model for estimating tissue age that included 6 body composition biomarkers calculated from abdominal computed tomography using a previously validated deep learning model. RESULTS Older tissue age associated with intermediate subcutaneous fat area, higher visceral fat area, lower muscle area, lower muscle density, higher bone area, and lower bone density. A tissue age older than chronologic age was associated with chronic conditions that result in reduced physical fitness (including chronic obstructive pulmonary disease, arthritis, cardiovascular disease, and behavioral disorders). Furthermore, a tissue age older than chronologic age was associated with an increased risk of death (hazard ratio, 1.56; 95% CI, 1.33 to 1.84) that was independent of demographic characteristics, county of residency, education, body mass index, and baseline chronic conditions. CONCLUSION Imaging-based body composition measures may be useful in understanding the biologic processes underlying accelerated aging.
Collapse
Affiliation(s)
- Andrew D Rule
- Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN; Division of Nephrology and Hypertension.
| | - Brandon R Grossardt
- Division of Clinical Trials and Biostatistics, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN
| | - Alexander D Weston
- Department of Quantitative Health Sciences, Mayo Clinic, Jacksonville, FL
| | - Hillary W Garner
- Division of Musculoskeletal Radiology, Department of Radiology, Mayo Clinic, Jacksonville, FL
| | | | - Alanna M Chamberlain
- Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN
| | - Alina M Allen
- Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN
| | - Bradley J Erickson
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, Rochester, MN
| | - Walter A Rocca
- Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN; Department of Neurology, Mayo Clinic, Rochester, MN; Women's Health Research Center, Mayo Clinic, Rochester, MN
| | - Jennifer L St Sauver
- Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN; The Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, MN
| |
Collapse
|
2
|
Zalay O, Bontempi D, Bitterman DS, Birkbak N, Shyr D, Haugg F, Qian JM, Roberts H, Perni S, Prudente V, Pai S, Dekker A, Haibe-Kains B, Guthier C, Balboni T, Warren L, Krishan M, Kann BH, Swanton C, Ruysscher DD, Mak RH, Aerts HJWL. Decoding biological age from face photographs using deep learning. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.09.12.23295132. [PMID: 37745558 PMCID: PMC10516042 DOI: 10.1101/2023.09.12.23295132] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/26/2023]
Abstract
Because humans age at different rates, a person's physical appearance may yield insights into their biological age and physiological health more reliably than their chronological age. In medicine, however, appearance is incorporated into medical judgments in a subjective and non-standardized fashion. In this study, we developed and validated FaceAge, a deep learning system to estimate biological age from easily obtainable and low-cost face photographs. FaceAge was trained on data from 58,851 healthy individuals, and clinical utility was evaluated on data from 6,196 patients with cancer diagnoses from two institutions in the United States and The Netherlands. To assess the prognostic relevance of FaceAge estimation, we performed Kaplan Meier survival analysis. To test a relevant clinical application of FaceAge, we assessed the performance of FaceAge in end-of-life patients with metastatic cancer who received palliative treatment by incorporating FaceAge into clinical prediction models. We found that, on average, cancer patients look older than their chronological age, and looking older is correlated with worse overall survival. FaceAge demonstrated significant independent prognostic performance in a range of cancer types and stages. We found that FaceAge can improve physicians' survival predictions in incurable patients receiving palliative treatments, highlighting the clinical utility of the algorithm to support end-of-life decision-making. FaceAge was also significantly associated with molecular mechanisms of senescence through gene analysis, while age was not. These findings may extend to diseases beyond cancer, motivating using deep learning algorithms to translate a patient's visual appearance into objective, quantitative, and clinically useful measures.
Collapse
Affiliation(s)
- Osbert Zalay
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
- Division of Radiation Oncology, Queen’s University, Kingston, Canada
| | - Dennis Bontempi
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, The Netherlands
- Department of Radiation Oncology (MAASTRO), Maastricht University, Maastricht, The Netherlands
| | - Danielle S Bitterman
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Nicolai Birkbak
- Department of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
- Bioinformatics Research Center, Aarhus University, Aarhus, Denmark
| | - Derek Shyr
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston
| | - Fridolin Haugg
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Jack M Qian
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Hannah Roberts
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Subha Perni
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Vasco Prudente
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, The Netherlands
| | - Suraj Pai
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, The Netherlands
| | - Andre Dekker
- Department of Radiation Oncology (MAASTRO), Maastricht University, Maastricht, The Netherlands
| | - Benjamin Haibe-Kains
- Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
| | - Christian Guthier
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Tracy Balboni
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Laura Warren
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Monica Krishan
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Benjamin H Kann
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Charles Swanton
- Cancer Research UK Lung Cancer Centre of Excellence, University College London Cancer Institute, London, UK
- Cancer Evolution and Genome Instability Laboratory, The Francis Crick Institute, London, UK
| | - Dirk De Ruysscher
- Department of Radiation Oncology (MAASTRO), Maastricht University, Maastricht, The Netherlands
| | - Raymond H Mak
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
| | - Hugo JWL Aerts
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States of America
- Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States of America
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, The Netherlands
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, United States of America
| |
Collapse
|
3
|
Kuma A, Kato A. Lifestyle-Related Risk Factors for the Incidence and Progression of Chronic Kidney Disease in the Healthy Young and Middle-Aged Population. Nutrients 2022; 14:nu14183787. [PMID: 36145162 PMCID: PMC9506421 DOI: 10.3390/nu14183787] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Revised: 09/10/2022] [Accepted: 09/11/2022] [Indexed: 11/16/2022] Open
Abstract
The prevalence of chronic kidney disease (CKD) increased by 88% from 1990 to 2016. Age of onset of lifestyle-related diseases (such as hypertension, diabetes mellitus, obesity, dyslipidemia, and hyperuricemia), which are risk factors for incident CKD, is lower now compared with the past. Thus, we aimed to evaluate the risk factors for the incidence and progression of CKD in the young and middle-aged population. There are differences in the risk for CKD among the young, middle-aged, and elderly populations. We aimed to assess obesity (which is basic component of metabolic syndrome), waist circumference, and abdominal adiposity, which are predictive factors of CKD in the younger population. Furthermore, we described the management and clinical evidence of hypertension, diabetes mellitus, dyslipidemia, and hyperuricemia for young and middle-aged patients, along with diet management and nutrients associated with kidney function. Kidney function in the young and middle-aged population is mostly normal, and they are considered a low-risk group for incident CKD. Thus, we expect this review to be useful in reducing the prevalence of CKD.
Collapse
Affiliation(s)
- Akihiro Kuma
- Kidney Center, Hospital of the University of Occupational and Environmental Health, 1-1 Iseigaoka, Yahatanishi-ku, Kitakyushu 807-8556, Fukuoka, Japan
| | - Akihiko Kato
- Blood Purification Unit, Hamamatsu University Hospital, 1-20-1 Handayama, Higashi-ku, Hamamatsu 431-3125, Shizuoka, Japan
- Correspondence:
| |
Collapse
|
4
|
Kuma A, Mafune K, Uchino B, Ochiai Y, Enta K, Kato A. Development of chronic kidney disease influenced by serum urate and body mass index based on young-to-middle-aged Japanese men: a propensity score-matched cohort study. BMJ Open 2022; 12:e049540. [PMID: 35131815 PMCID: PMC8823083 DOI: 10.1136/bmjopen-2021-049540] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
OBJECTIVE To investigate the association between serum uric acid (SUA) level and body mass index (BMI) on the development of chronic kidney disease (CKD) in working men aged 20-60 years. DESIGN Retrospective cohort study. SETTING Data from employees' annual health check-ups were collected from two companies in 2009 and 2014. PARTICIPANTS A total of 16 708 working men were recruited. We excluded participants with missing essential data (N=7801), who had basal estimated glomerular filtration rate (eGFR) <60.0 mL/min/1.73 m2 and/or proteinuria (N=698) or with the absence of follow-up data (N=2). PRIMARY OUTCOME eGFR <60 mL/min/1.73 m2 and/or proteinuria (≥1+) in 2014 (defined as incident CKD). RESULTS The cut-off values of SUA for incident CKD were 6.6 mg/dL in both young (20-39 years old) and middle-aged (40-60 years old) men analysed by receiver operator characteristics. ORs for incident CKD were assessed on propensity score-matched (1:1) cohorts. In young participants (N=1938), after propensity score matching, a coexistence of high-level SUA (≥6.6 mg/dL) and overweight (BMI ≥25 kg/m2) was a significant risk factor of incident CKD (OR=2.18, 95% CI 1.10 to 4.31, p=0.025), but high-level SUA was not an independent risk factor without overweight status (p=0.174). In middle-aged participants (N=2944) after propensity score matching, high-level SUA was a significant risk factor of incident CKD both with or without overweight (OR=1.44, 95% CI 1.02 to 2.04, p=0.037; OR=1.32, 95% CI 1.01 to 1.73, p=0.041, respectively). CONCLUSION These findings suggest that high-level SUA is strongly associated with incident CKD in overweight young adult men.
Collapse
Affiliation(s)
- Akihiro Kuma
- Kidney Centre, Hospital of the University of Occupational and Environmental Health, Kitakyushu, Fukuoka, Japan
- Blood Purification Unit, Hamamatsu University Hospital, Hamamatsu, Shizuoka, Japan
| | - Kosuke Mafune
- Department of Mental Health, Institution of Industrial Ecological Sciences, University of Occupational and Environmental Health, Kitakyushu, Fukuoka, Japan
| | - Bungo Uchino
- Health Promotion Centre, Yamaha Motor Co Ltd, Iwata, Shizuoka, Japan
| | - Yoko Ochiai
- Health Promotion Centre, Yamaha Motor Co Ltd, Iwata, Shizuoka, Japan
| | - Kazuhiko Enta
- Health Care Centre, Central Japan Railway Company, Nagoya, Aichi, Japan
| | - Akihiko Kato
- Blood Purification Unit, Hamamatsu University Hospital, Hamamatsu, Shizuoka, Japan
| |
Collapse
|
6
|
Orlov NV, Coletta C, van Asten F, Qian Y, Ding J, AlGhatrif M, Lakatta E, Chew E, Wong W, Swaroop A, Fiorillo E, Delitala A, Marongiu M, Goldberg IG, Schlessinger D. Age-related changes of the retinal microvasculature. PLoS One 2019; 14:e0215916. [PMID: 31048908 PMCID: PMC6497255 DOI: 10.1371/journal.pone.0215916] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2018] [Accepted: 04/10/2019] [Indexed: 01/17/2023] Open
Abstract
Purpose Blood vessels of the retina provide an easily-accessible, representative window into the condition of microvasculature. We investigated how retinal vessel structure captured in fundus photographs changes with age, and how this may reflect features related to patient health, including blood pressure. Results We used two approaches. In the first approach, we segmented the retinal vasculature from fundus photographs and then we correlated 25 parameterized aspects ("traits")—comprising 15 measures of tortuosity, 7 fractal ranges of self-similarity, and 3 measures of junction numbers—with participant age and blood pressure. In the second approach, we examined entire fundus photographs with a set of algorithmic CHARM features. We studied 2,280 Sardinians, ages 20–28, and an U.S. based population from the AREDS study in 1,178 participants, ages 59–84. Three traits (relating to tortuosity, vessel bifurcation number, and vessel endpoint number) showed significant changes with age in both cohorts, and one additional trait (relating to fractal number) showed a correlation in the Sardinian cohort only. When using second approach, we found significant correlations of particular CHARM features with age and blood pressure, which were stronger than those detected when using parameterized traits, reflecting a greater signal from the entire photographs than was captured in the segmented microvasculature. Conclusions These findings demonstrate that automated quantitative image analysis of fundus images can reveal general measures of patient health status.
Collapse
Affiliation(s)
- Nikita V. Orlov
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
- * E-mail: ,
| | - Cristopher Coletta
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Freekje van Asten
- Division of Epidemiology and Clinical Applications, National Eye Institute/National Institutes of Health, Baltimore, Maryland, United States of America
- Neurobiology, Neurodegeneration and Repair Laboratory, National Eye Institute/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Yong Qian
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Jun Ding
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Majd AlGhatrif
- Laboratory of Cardiovascular Science, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Edward Lakatta
- Laboratory of Cardiovascular Science, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Emily Chew
- Division of Epidemiology and Clinical Applications, National Eye Institute/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Wai Wong
- Division of Epidemiology and Clinical Applications, National Eye Institute/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Anand Swaroop
- Neurobiology, Neurodegeneration and Repair Laboratory, National Eye Institute/National Institutes of Health, Baltimore, Maryland, United States of America
| | - Edoardo Fiorillo
- Istituto di Ricerca Genetica e Biomedica, Consiglio Nazionale delle Ricerche (CNR), Monserrato, Cagliari, Italy
| | - Alessandro Delitala
- Department of Clinical and Experimental Medicine, Azienda Ospedaliero Universitaria di Sassari, Sassari, Italy
| | - Michele Marongiu
- Istituto di Ricerca Genetica e Biomedica, Consiglio Nazionale delle Ricerche (CNR), Monserrato, Cagliari, Italy
| | - Ilya G. Goldberg
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| | - David Schlessinger
- Laboratory of Genetics & Genomics, National Institute on Aging/National Institutes of Health, Baltimore, Maryland, United States of America
| |
Collapse
|