1
|
Lee MH, Zea R, Garrett JW, Summers RM, Pickhardt PJ. AI-based abdominal CT measurements of orthotopic and ectopic fat predict mortality and cardiometabolic disease risk in adults. Eur Radiol 2024:10.1007/s00330-024-10935-w. [PMID: 38995381 DOI: 10.1007/s00330-024-10935-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2024] [Revised: 04/27/2024] [Accepted: 05/31/2024] [Indexed: 07/13/2024]
Abstract
OBJECTIVES To evaluate the utility of CT-based abdominal fat measures for predicting the risk of death and cardiometabolic disease in an asymptomatic adult screening population. METHODS Fully automated AI tools quantifying abdominal adipose tissue (L3 level visceral [VAT] and subcutaneous [SAT] fat area, visceral-to-subcutaneous fat ratio [VSR], VAT attenuation), muscle attenuation (L3 level), and liver attenuation were applied to non-contrast CT scans in asymptomatic adults undergoing CT colonography (CTC). Longitudinal follow-up documented subsequent deaths, cardiovascular events, and diabetes. ROC and time-to-event analyses were performed to generate AUCs and hazard ratios (HR) binned by octile. RESULTS A total of 9223 adults (mean age, 57 years; 4071:5152 M:F) underwent screening CTC from April 2004 to December 2016. 549 patients died on follow-up (median, nine years). Fat measures outperformed BMI for predicting mortality risk-5-year AUCs for muscle attenuation, VSR, and BMI were 0.721, 0.661, and 0.499, respectively. Higher visceral, muscle, and liver fat were associated with increased mortality risk-VSR > 1.53, HR = 3.1; muscle attenuation < 15 HU, HR = 5.4; liver attenuation < 45 HU, HR = 2.3. Higher VAT area and VSR were associated with increased cardiovascular event and diabetes risk-VSR > 1.59, HR = 2.6 for cardiovascular event; VAT area > 291 cm2, HR = 6.3 for diabetes (p < 0.001). A U-shaped association was observed for SAT with a higher risk of death for very low and very high SAT. CONCLUSION Fully automated CT-based measures of abdominal fat are predictive of mortality and cardiometabolic disease risk in asymptomatic adults and uncover trends that are not reflected in anthropomorphic measures. CLINICAL RELEVANCE STATEMENT Fully automated CT-based measures of abdominal fat soundly outperform anthropometric measures for mortality and cardiometabolic risk prediction in asymptomatic patients. KEY POINTS Abdominal fat depots associated with metabolic dysregulation and cardiovascular disease can be derived from abdominal CT. Fully automated AI body composition tools can measure factors associated with increased mortality and cardiometabolic risk. CT-based abdominal fat measures uncover trends in mortality and cardiometabolic risk not captured by BMI in asymptomatic outpatients.
Collapse
Affiliation(s)
- Matthew H Lee
- Departments of Radiology and Medical Physics, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA.
| | - Ryan Zea
- Departments of Radiology and Medical Physics, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA
| | - John W Garrett
- Departments of Radiology and Medical Physics, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA
| | - Ronald M Summers
- National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Perry J Pickhardt
- Departments of Radiology and Medical Physics, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA
| |
Collapse
|
2
|
Zeng F, Jiang W, Chang X, Yang F, Luo X, Liu R, Lei Y, Li J, Pan C, Huang X, Sun H, Lan Y. Sarcopenia is associated with short- and long-term mortality in patients with acute-on-chronic liver failure. J Cachexia Sarcopenia Muscle 2024. [PMID: 38965993 DOI: 10.1002/jcsm.13501] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 03/21/2024] [Accepted: 04/08/2024] [Indexed: 07/06/2024] Open
Abstract
BACKGROUND While sarcopenia is recognized as a predictor of mortality in cirrhosis, its influence on acute-on-chronic liver failure (ACLF) remains uncertain. Despite multiple studies examining the impact of sarcopenia on short-term mortality in patients with ACLF, the sample size of these studies was limited, and their outcomes were inconsistent. Therefore, this study aimed to explore the impact of sarcopenia on both short- and long-term mortality in patients with ACLF. METHODS This retrospective cohort study included 414 patients with ACLF that were treated between January 2016 and September 2022. Sarcopenia was diagnosed based on the measurement of the skeletal muscle index at the third lumbar vertebra (L3-SMI). Subsequently, the patients were divided into sarcopenia and non-sarcopenia groups. We analysed the basic clinical data of the two groups. Multivariate Cox proportional analysis was used to analyse short-term (28 days) and long-term (1 year and overall) mortality rates. RESULTS A total of 414 patients were included, with a mean age of 52.88 ± 13.41 years. Among them, 318 (76.8%) were male, and 239 (57.7%) had sarcopenia. A total of 280 (67.6%) patients died during the study period. Among them, 153 patients died within 28 days (37%) and 209 patients died within 1 year (50.5%). We found that the 28-day, 1-year and overall mortality rates in the sarcopenia group were significantly higher than those in the non-sarcopenia group (37% vs. 22.3%, P < 0.01; 50.5% vs. 34.9%, P < 0.01; and 67.6% vs. 53.1%, P < 0.01, respectively). Multivariate Cox regression analysis revealed that sarcopenia was significantly associated with increased mortality. The hazard ratios for sarcopenia were 2.05 (95% confidence interval [CI] 1.41-3.00, P < 0.01) for 28-day mortality, 1.81 (95% CI 1.29-2.54, P < 0.01) for 1-year mortality and 1.82 (95% CI 1.30-2.55, P < 0.01) for overall mortality. In addition, muscle density and international normalized ratio were associated with short- and long-term mortality. CONCLUSIONS Sarcopenia is associated with both short- and long-term mortality in patients with ACLF. Therefore, regular monitoring for sarcopenia is important for these patients.
Collapse
Affiliation(s)
- Fan Zeng
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Wei Jiang
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
- Clinical Medicine School of Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Xiujun Chang
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
- Clinical Medicine School of Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Fuxun Yang
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Xiaoxiu Luo
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Rongan Liu
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Yu Lei
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Jiajia Li
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Chun Pan
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Xiaobo Huang
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Huaiqiang Sun
- Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
| | - Yunping Lan
- Department of Intensive Care Unit, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| |
Collapse
|
3
|
Swartz AZ, Robles ME, Park S, Esfandiari H, Bradshaw M, Koethe JR, Silver HJ. Cardiometabolic Characteristics of Obesity Phenotypes in Persons With HIV. Open Forum Infect Dis 2024; 11:ofae376. [PMID: 39035569 PMCID: PMC11259191 DOI: 10.1093/ofid/ofae376] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Accepted: 07/02/2024] [Indexed: 07/23/2024] Open
Abstract
Background In the general population, it is established that adipose tissue depots pose various risks for cardiometabolic diseases. The interaction among obesity, HIV, and antiretroviral treatment promotes even greater risk for persons with HIV (PWH). As obesity is a heterogeneous condition, determining the specific obesity phenotypes present and their characteristics is critical to personalize care in PWH. Methods Visceral, sarcopenic, myosteatotic, hepatosteatotic, and metabolically healthy obesity phenotypes were determined by pre-established cut points after segmentation of computed tomography scans at the L3 vertebra. Multivariable linear regression modeling included anthropometrics, clinical biomarkers, and inflammatory factors while controlling for age, sex, race, and body mass index (BMI). Results Of 187 PWH, 86% were male, and the mean ± SD age and BMI were 51.2 ± 12.3 years and 32.6 ± 6.3 kg/m2. Overall, 59% had visceral obesity, 11% sarcopenic obesity, 25% myosteatotic obesity, 9% hepatosteatotic obesity, and 32% metabolically healthy obesity. The strongest predictor of visceral obesity was an elevated triglyceride:high-density lipoprotein (HDL) ratio. Increased subcutaneous fat, waist circumference, and HDL cholesterol were predictors of sarcopenic obesity. Diabetes status and elevated interleukin 6, waist circumference, and HDL cholesterol predicted myosteatotic obesity. An increased CD4+ count and a decreased visceral:subcutaneous adipose tissue ratio predicted hepatosteatotic obesity, though accounting for only 28% of its variability. Participants with metabolically healthy obesity were on average 10 years younger, had higher HDL, lower triglyceride:HDL ratio, and reduced CD4+ counts. Conclusions These findings show that discrete obesity phenotypes are highly prevalent in PWH and convey specific risk factors that measuring BMI alone does not capture. These clinically relevant findings can be used in risk stratification and optimization of personalized treatment regimens. This study is registered at ClinicalTrials.gov (NCT04451980).
Collapse
Affiliation(s)
- Alison Z Swartz
- School of Medicine, Vanderbilt University, Nashville, Tennessee, USA
| | - Michelle E Robles
- Division of Gastroenterology, Hepatology, and Nutrition, Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Seungweon Park
- School of Medicine, Vanderbilt University, Nashville, Tennessee, USA
| | - Helia Esfandiari
- College of Arts and Sciences, University of Tennessee, Knoxville, Tennessee, USA
| | - Marques Bradshaw
- Department of Veterans Affairs, Tennessee Valley Healthcare System, Nashville, Tennessee, USA
| | - John R Koethe
- Department of Veterans Affairs, Tennessee Valley Healthcare System, Nashville, Tennessee, USA
- Division of Infectious Diseases, Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Heidi J Silver
- Division of Gastroenterology, Hepatology, and Nutrition, Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA
- Department of Veterans Affairs, Tennessee Valley Healthcare System, Nashville, Tennessee, USA
| |
Collapse
|
4
|
Chang YY, Cheng B. Prognostic impact of myosteatosis in patients with colorectal cancer undergoing curative surgery: an updated systematic review and meta-analysis. Front Oncol 2024; 14:1388001. [PMID: 38962266 PMCID: PMC11219791 DOI: 10.3389/fonc.2024.1388001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Accepted: 05/16/2024] [Indexed: 07/05/2024] Open
Abstract
Background Colorectal cancer (CRC) is a global health concern, and identifying prognostic factors can improve outcomes. Myosteatosis is fat infiltration into muscles and is a potential predictor of the survival of patients with CRC. Methods This systematic review and meta-analysis aimed to assess the prognostic role of myosteatosis in CRC. PubMed, Embase, and Cochrane CENTRAL were searched up to 1 August 2023, for relevant studies, using combinations of the keywords CRC, myosteatosis, skeletal muscle fat infiltration, and low skeletal muscle radiodensity. Case-control, prospective, and retrospective cohort studies examining the association between myosteatosis and CRC outcomes after curative intent surgery were eligible for inclusion. Primary outcomes were overall survival (OS), disease-free survival (DFS), and cancer-specific survival (CSS). Results A total of 10 studies with a total of 9,203 patients were included. The pooled hazard ratio (HR) for OS (myosteatosis vs. no myosteatosis) was 1.52 [95% confidence interval (CI), 1.38-1.67); for CSS, 1.67 (95% CI, 1.40-1.99); and for DFS, 1.89 (95% CI, 1.35-2.65). Conclusion In patients with CRC undergoing curative intent surgery, myosteatosis is associated with worse OS, CSS, and DFS. These findings underscore the importance of evaluating myosteatosis in patients with CRC to improve outcomes.
Collapse
Affiliation(s)
- Yu-Yao Chang
- Division of Colon and Rectal Surgery, Department of Surgery, Changhua Christian Hospital, Changhua, Taiwan
- Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung, Taiwan
| | - Bill Cheng
- Graduate Institute of Biomedical Engineering, National Chung-Hsing University, Taichung, Taiwan
| |
Collapse
|
5
|
Tang H, Wang R, Hu N, Wang J, Wei Z, Gao X, Xie C, Qiu Y, Chen X. The association between computed tomography-based osteosarcopenia and osteoporotic vertebral fractures: a longitudinal study. J Endocrinol Invest 2024:10.1007/s40618-024-02415-1. [PMID: 38890220 DOI: 10.1007/s40618-024-02415-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/25/2024] [Accepted: 06/14/2024] [Indexed: 06/20/2024]
Abstract
PURPOSE Osteoporosis and sarcopenia usually coexist in older population. The concept of osteosarcopenia has been proposed in recent years. However, studies on the relationship between osteosarcopenia and the risk of fracture are rare, and the association is unclear at present. This study aimed to investigate the association between osteosarcopenia evaluated based on chest computed tomography (CT) and osteoporotic vertebral fracture (OVF). METHODS This study recruited 7906 individuals aged 50 years and older who did not have OVFs and underwent chest CT for physical examination between July 2016 and September 2019. Subjects were followed up annually until June 2023. Osteosarcopenia was defined by a low muscle area of the erector spinae (< 25.4 cm2) and the bone attenuation (Hounsfield unit, HU < 135). Genant's grades were used to define OVFs. Control subjects were selected by Propensity Score Matching at a ratio 20:1. Cox proportional hazards models were used to assess the associations between osteosarcopenia and OVFs. RESULTS Of the 7906 participants included, 95 had a new OVF within a median follow-up of 3 years. A total of 1900 control subjects were matched. Individuals in the osteosarcopenia group had a higher prevalence of spinal fractures than those in normal group (16.4% vs. 0.4%, P < 0.001). Osteosarcopenia was independently associated with OVF (adjusted hazard ratio (aHR): 12.67, 95% confidence interval (CI) 3.79-42.40) and severe OVF (aHR = 14.07, 95% CI 1.84-107.66). Similar trends were observed in males, females and those subjects aged older than 60 years. Osteosarcopenia had good predictive efficacy for OVF (area under the curve = 0.836). A nomogram was also developed for clinical application. CONCLUSION Osteosarcopenia assessed based on chest CT was associated with OVF, and osteosarcopenia has good performance for vertebral fracture prediction.
Collapse
Affiliation(s)
- H Tang
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - R Wang
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - N Hu
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - J Wang
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - Z Wei
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - X Gao
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China
| | - C Xie
- Center for Musculoskeletal Research, School of Medicine and Dentistry, University of Rochester, Rochester, NY, 14642, USA
| | - Y Qiu
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China.
| | - X Chen
- Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, 155 Hanzhong Road, Nanjing, 210029, China.
| |
Collapse
|
6
|
Nault JC, Calderaro J, Ronot M. Integration of new technologies in the multidisciplinary approach to primary liver tumours: The next-generation tumour board. J Hepatol 2024:S0168-8278(24)02310-9. [PMID: 38871125 DOI: 10.1016/j.jhep.2024.05.041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/04/2024] [Revised: 05/27/2024] [Accepted: 05/28/2024] [Indexed: 06/15/2024]
Abstract
Primary liver tumours, including benign liver tumours, hepatocellular carcinoma and cholangiocarcinoma, present a multifaceted challenge, necessitating a collaborative approach, as evidenced by the role of the multidisciplinary tumour board (MDTB). The approach to managing primary liver tumours involves specialised teams, including surgeons, radiologists, oncologists, pathologists, hepatologists, and radiation oncologists, coming together to propose individualised treatment plans. The evolving landscape of primary liver cancer treatment introduces complexities, particularly with the expanding array of systemic and locoregional therapies, alongside the potential integration of molecular biology and artificial intelligence (AI) into MDTBs in the future. Precision medicine demands collaboration across disciplines, challenging traditional frameworks. In the next decade, we anticipate the convergence of AI, molecular biology, pathology, and advanced imaging, requiring adaptability in MDTB structure to incorporate these cutting-edge technologies. Navigating this evolution also requires a focus on enhancing basic, translational, and clinical research, as well as boosting clinical trials through an upgraded use of MDTBs as hubs for scientific collaboration and raising literacy about AI and new technologies. In this review, we will delineate the current unmet needs in the clinical management of primary liver cancers, discuss our perspective on the future role of MDTBs in primary liver cancers ("next generation" MDTBs), and unravel the potential power and limitations of novel technologies that may shape the multidisciplinary care landscape for primary liver cancers in the coming decade.
Collapse
Affiliation(s)
- Jean-Charles Nault
- Liver unit, Hôpital Avicenne, Hôpitaux Universitaires Paris-Seine-Saint-Denis, Assistance-Publique Hôpitaux de Paris, Bobigny, France; Unité de Formation et de Recherche Santé Médecine et Biologie Humaine, Université Paris 13, Communauté d'Universités et Etablissements Sorbonne Paris Cité, Paris, France; Centre de Recherche des Cordeliers, Sorbonne Université, Inserm, Université de Paris, team « Functional Genomics of Solid Tumors », F-75006 Paris, France.
| | - Julien Calderaro
- Université Paris Est Créteil, INSERM, IMRB, F-94010, Créteil, France; Assistance Publique-Hôpitaux de Paris, Henri Mondor-Albert Chenevier University Hospital, Department of Pathology, Créteil, France; MINT-Hep, Mondor Integrative Hepatology, Créteil, France
| | - Maxime Ronot
- Université de Paris, INSERM U1149 "Centre de Recherche sur l'inflammation", CRI, Paris, France; Department of Radiology, AP-HP, Hôpital Beaujon APHP.Nord, Clichy, France
| |
Collapse
|
7
|
Pickhardt PJ. Abdominal CT-Based Body Composition Biomarkers for Phenotypic Biologic Aging. Mayo Clin Proc 2024; 99:858-860. [PMID: 38839185 DOI: 10.1016/j.mayocp.2024.04.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/26/2024] [Accepted: 04/19/2024] [Indexed: 06/07/2024]
Affiliation(s)
- Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI.
| |
Collapse
|
8
|
Moeller AR, Garrett JW, Summers RM, Pickhardt PJ. Adjusting for the effect of IV contrast on automated CT body composition measures during the portal venous phase. Abdom Radiol (NY) 2024:10.1007/s00261-024-04376-8. [PMID: 38744704 DOI: 10.1007/s00261-024-04376-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2024] [Revised: 05/04/2024] [Accepted: 05/06/2024] [Indexed: 05/16/2024]
Abstract
OBJECTIVE Fully-automated CT-based algorithms for quantifying numerous biomarkers have been validated for unenhanced abdominal scans. There is great interest in optimizing the documentation and reporting of biophysical measures present on all CT scans for the purposes of opportunistic screening and risk profiling. The purpose of this study was to determine and adjust the effect of intravenous (IV) contrast on these automated body composition measures at routine portal venous phase post-contrast imaging. METHODS Final study cohort consisted of 1,612 older adults (mean age, 68.0 years; 594 women) all imaged utilizing a uniform CT urothelial protocol consisting of pre-contrast, portal venous, and delayed excretory phases. Fully-automated CT-based algorithms for quantifying numerous biomarkers, including muscle and fat area and density, bone mineral density, and solid organ volume were applied to pre-contrast and portal venous phases. The effect of IV contrast upon these body composition measures was analyzed. Regression analyses, including square of the Pearson correlation coefficient (r2), were performed for each comparison. RESULTS We found that simple, linear relationships can be derived to determine non-contrast equivalent values from the post-contrast CT biomeasures. Excellent positive linear correlation (r2 = 0.91-0.99) between pre- and post-contrast values was observed for all automated soft tissue measures, whereas moderate positive linear correlation was observed for bone attenuation (r2 = 0.58-0.76). In general, the area- and volume-based measurement require less adjustment than attenuation-based measures, as expected. CONCLUSION Fully-automated quantitative CT-biomarker measures at portal venous phase abdominal CT can be adjusted to a non-contrast equivalent using simple, linear relationships.
Collapse
Affiliation(s)
- Alexander R Moeller
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA
| | - John W Garrett
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA.
| |
Collapse
|
9
|
Cho SW, Baek S, Han S, Kim CO, Kim HC, Rhee Y, Hong N. Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults. J Cachexia Sarcopenia Muscle 2024. [PMID: 38649795 DOI: 10.1002/jcsm.13487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 03/06/2024] [Accepted: 03/21/2024] [Indexed: 04/25/2024] Open
Abstract
BACKGROUND Computed tomography (CT) body compositions reflect age-related metabolic derangements. We aimed to develop a multi-outcome deep learning model using CT multi-level body composition parameters to detect metabolic syndrome (MS), osteoporosis and sarcopenia by identifying metabolic clusters simultaneously. We also investigated the prognostic value of metabolic phenotyping by CT model for long-term mortality. METHODS The derivation set (n = 516; 75% train set, 25% internal test set) was constructed using age- and sex-stratified random sampling from two community-based cohorts. Data from participants in the individual health assessment programme (n = 380) were used as the external test set 1. Semi-automatic quantification of body compositions at multiple levels of abdominal CT scans was performed to train a multi-layer perceptron (MLP)-based multi-label classification model. External test set 2 to test the prognostic value of the model output for mortality was built using data from individuals who underwent abdominal CT in a tertiary-level institution (n = 10 141). RESULTS The mean ages of the derivation and external sets were 62.8 and 59.7 years, respectively, without difference in sex distribution (women 50%) or body mass index (BMI; 23.9 kg/m2). Skeletal muscle density (SMD) and bone density (BD) showed a more linear decrement across age than skeletal muscle area. Alternatively, an increase in visceral fat area (VFA) was observed in both men and women. Hierarchical clustering based on multi-level CT body composition parameters revealed three distinctive phenotype clusters: normal, MS and osteosarcopenia clusters. The L3 CT-parameter-based model, with or without clinical variables (age, sex and BMI), outperformed clinical model predictions of all outcomes (area under the receiver operating characteristic curve: MS, 0.76 vs. 0.55; osteoporosis, 0.90 vs. 0.79; sarcopenia, 0.85 vs. 0.81 in external test set 1; P < 0.05 for all). VFA contributed the most to the MS predictions, whereas SMD, BD and subcutaneous fat area were features of high importance for detecting osteoporosis and sarcopenia. In external test set 2 (mean age 63.5 years, women 79%; median follow-up 4.9 years), a total of 907 individuals (8.9%) died during follow-up. Among model-predicted metabolic phenotypes, sarcopenia alone (adjusted hazard ratio [aHR] 1.55), MS + sarcopenia (aHR 1.65), osteoporosis + sarcopenia (aHR 1.83) and all three combined (aHR 1.87) remained robust predictors of mortality after adjustment for age, sex and comorbidities. CONCLUSIONS A CT body composition-based MLP model detected MS, osteoporosis and sarcopenia simultaneously in community-dwelling and hospitalized adults. Metabolic phenotypes predicted by the CT MLP model were associated with long-term mortality, independent of covariates.
Collapse
Affiliation(s)
- Sang Wouk Cho
- Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
- Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea
| | - Seungjin Baek
- Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Sookyeong Han
- Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
- Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea
| | - Chang Oh Kim
- Division of Geriatric Medicine, Department of Internal Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Hyeon Chang Kim
- Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea
- Department of Preventive Medicine, Yonsei University College of Medicine, Seoul, South Korea
| | - Yumie Rhee
- Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
- Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea
| | - Namki Hong
- Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
- Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea
| |
Collapse
|
10
|
Quint EE, Liu Y, Shafaat O, Ghildayal N, Crosby H, Kamireddy A, Pol RA, Orandi BJ, Segev DL, Weiss CR, McAdams-DeMarco MA. Abdominal computed tomography measurements of body composition and waitlist mortality in kidney transplant candidates. Am J Transplant 2024; 24:591-605. [PMID: 37949413 PMCID: PMC10982050 DOI: 10.1016/j.ajt.2023.11.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Revised: 10/10/2023] [Accepted: 11/02/2023] [Indexed: 11/12/2023]
Abstract
Body mass index is often used to determine kidney transplant (KT) candidacy. However, this measure of body composition (BC) has several limitations, including the inability to accurately capture dry weight. Objective computed tomography (CT)-based measures may improve pre-KT risk stratification and capture physiological aging more accurately. We quantified the association between CT-based BC measurements and waitlist mortality in a retrospective study of 828 KT candidates (2010-2022) with clinically obtained CT scans using adjusted competing risk regression. In total, 42.5% of candidates had myopenia, 11.4% had myopenic obesity (MO), 68.8% had myosteatosis, 24.8% had sarcopenia (probable = 11.2%, confirmed = 10.5%, and severe = 3.1%), and 8.6% had sarcopenic obesity. Myopenia, MO, and sarcopenic obesity were not associated with mortality. Patients with myosteatosis (adjusted subhazard ratio [aSHR] = 1.62, 95% confidence interval [CI]: 1.07-2.45; after confounder adjustment) or sarcopenia (probable: aSHR = 1.78, 95% CI: 1.10-2.88; confirmed: aSHR = 1.68, 95% CI: 1.01-2.82; and severe: aSHR = 2.51, 95% CI: 1.12-5.66; after full adjustment) were at increased risk of mortality. When stratified by age, MO (aSHR = 2.21, 95% CI: 1.28-3.83; P interaction = .005) and myosteatosis (aSHR = 1.95, 95% CI: 1.18-3.21; P interaction = .038) were associated with elevated risk only among candidates <65 years. MO was only associated with waitlist mortality among frail candidates (adjusted hazard ratio = 2.54, 95% CI: 1.28-5.05; P interaction = .021). Transplant centers should consider using BC metrics in addition to body mass index when a CT scan is available to improve pre-KT risk stratification at KT evaluation.
Collapse
Affiliation(s)
- Evelien E Quint
- Division of Transplant Surgery, Department of Surgery, University Medical Center Groningen, Groningen, The Netherlands
| | - Yi Liu
- Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA
| | - Omid Shafaat
- Division of Vascular and Interventional Radiology, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Nidhi Ghildayal
- Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA
| | - Helen Crosby
- Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA
| | - Arun Kamireddy
- Division of Vascular and Interventional Radiology, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Robert A Pol
- Division of Transplant Surgery, Department of Surgery, University Medical Center Groningen, Groningen, The Netherlands
| | - Babak J Orandi
- Division of Endocrinology, Joan & Sanford Weill Medical College of Cornell University, New York, NY, USA
| | - Dorry L Segev
- Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA; Department of Population Health, New York University Grossman School of Medicine, New York, NY, USA
| | - Clifford R Weiss
- Division of Vascular and Interventional Radiology, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Mara A McAdams-DeMarco
- Department of Surgery, New York University Grossman School of Medicine, New York, NY, USA; Department of Population Health, New York University Grossman School of Medicine, New York, NY, USA.
| |
Collapse
|
11
|
Pickhardt PJ. Invited Commentary: Metabolic Syndrome: The Urgent Need for an Imaging-based Definition. Radiographics 2024; 44:e230230. [PMID: 38329902 DOI: 10.1148/rg.230230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/10/2024]
Affiliation(s)
- Perry J Pickhardt
- From the Department of Radiology, The University of Wisconsin School of Medicine and Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252
| |
Collapse
|
12
|
Spytek M, Krzyziński M, Langbein SH, Baniecki H, Wright MN, Biecek P. survex: an R package for explaining machine learning survival models. Bioinformatics 2023; 39:btad723. [PMID: 38039146 PMCID: PMC11025379 DOI: 10.1093/bioinformatics/btad723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2023] [Revised: 11/10/2023] [Accepted: 11/29/2023] [Indexed: 12/03/2023] Open
Abstract
SUMMARY Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications. AVAILABILITY AND IMPLEMENTATION survex is available under the GPL3 public license at https://github.com/modeloriented/survex and on CRAN with documentation available at https://modeloriented.github.io/survex.
Collapse
Affiliation(s)
- Mikołaj Spytek
- MI2.AI, Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
| | - Mateusz Krzyziński
- MI2.AI, Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
| | - Sophie Hanna Langbein
- Leibniz Institute for Prevention Research and Epidemiology—BIPS, Bremen, Germany
- Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany
| | - Hubert Baniecki
- MI2.AI, Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
- MI2.AI, Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland
| | - Marvin N Wright
- Leibniz Institute for Prevention Research and Epidemiology—BIPS, Bremen, Germany
- Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany
- Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, Denmark
| | - Przemysław Biecek
- MI2.AI, Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
- MI2.AI, Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw, Poland
| |
Collapse
|
13
|
Friedman RS, Tarasova A, Jain VR, Ye K, Mansour A, Haramati LB. Predictive Value of CT Biomarkers in Lung Transplantation Survival: Preliminary Investigation in a Diverse, Underserved, Urban Population. Lung 2023; 201:581-590. [PMID: 37917190 DOI: 10.1007/s00408-023-00650-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Accepted: 10/09/2023] [Indexed: 11/04/2023]
Abstract
INTRODUCTION Survival following lung transplant is low. With limited donor lung availability, predicting post-transplant survival is key. We investigated the predictive value of pre-transplant CT biomarkers on survival. METHODS In this single-center retrospective cohort study of adults in a diverse, underserved, urban lung transplant program (11/8/2017-5/20/2022), chest CTs were analyzed using TeraRecon to assess musculature, fat, and bone. Erector spinae and pectoralis muscle area and attenuation were analyzed. Sarcopenia thresholds were 34.3 (women) and 38.5 (men) Hounsfield Units (HU). Visceral and subcutaneous fat area and HU, and vertebral body HU were measured. Demographics and pre-transplant metrics were recorded. Survival analyses included Kaplan-Meier and Cox proportional hazard. RESULTS The study cohort comprised 131 patients, 50 women, mean age 60.82 (SD 10.15) years, and mean follow-up 1.78 (SD 1.23) years. Twenty-nine percent were White. Mortality was 32.1%. Kaplan-Meier curves did not follow the proportional hazard assumption for sex, so analysis was stratified. Pre-transplant EMR metrics did not predict survival. Women without sarcopenia at erector spinae or pectoralis had 100% survival (p = 0.007). Sarcopenia did not predict survival in men and muscle area did not predict survival in either sex. Men with higher visceral fat area and HU had decreased survival (p = 0.02). Higher vertebral body density predicted improved survival in men (p = 0.026) and women (p = 0.045). CONCLUSION Pre-transplantation CT biomarkers had predictive value in lung transplant survival and varied by sex. The absence of sarcopenia in women, lower visceral fat attenuation and area in men, and higher vertebral body density in both sexes predicted survival in our diverse, urban population.
Collapse
Affiliation(s)
- Renee S Friedman
- Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA.
| | - Anna Tarasova
- Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Vineet R Jain
- Department of Radiology, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Kenny Ye
- Department of Epidemiology and Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Ali Mansour
- Department of Cardiothoracic and Vascular Surgery and Department of Medicine, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Linda B Haramati
- Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| |
Collapse
|
14
|
Petroff D, Wiegand J, Karlas T. Editorial: Let your muscles do the talking-what can muscle quality tell us about hepatic fibrosis? Aliment Pharmacol Ther 2023; 58:372-373. [PMID: 37452590 DOI: 10.1111/apt.17618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/18/2023]
Affiliation(s)
- David Petroff
- Clinical Trial Centre, Leipzig University, Leipzig, Germany
| | - Johannes Wiegand
- Division of Hepatology, Department of Medicine II, Leipzig University Medical Center, Leipzig, Germany
| | - Thomas Karlas
- Division of Gastroenterology, Department of Medicine II, University Hospital Leipzig, Leipzig, Germany
| |
Collapse
|