Beyond MELD Score: Association of Machine Learning-derived CT Body Composition with 90-Day Mortality Post Transjugular Intrahepatic Portosystemic Shunt Placement.

Artificial intelligence CT body composition Machine learning TIPS prognostication

Journal

Cardiovascular and interventional radiology
ISSN: 1432-086X
Titre abrégé: Cardiovasc Intervent Radiol
Pays: United States
ID NLM: 8003538

Informations de publication

Date de publication:
29 Oct 2024
Historique:
received: 01 04 2024
accepted: 05 10 2024
medline: 30 10 2024
pubmed: 30 10 2024
entrez: 30 10 2024
Statut: aheadofprint

Résumé

To determine the association of machine learning-derived CT body composition and 90-day mortality after transjugular intrahepatic portosystemic shunt (TIPS) and to assess its predictive performance as a complement to Model for End-Stage Liver Disease (MELD) score for mortality risk prediction. This retrospective multi-center cohort study included patients who underwent TIPS from 1995 to 2018 and had a contrast-enhanced CT abdomen within 9 months prior to TIPS and at least 90 days of post-procedural clinical follow-up. A machine learning algorithm extracted CT body composition metrics at L3 vertebral level including skeletal muscle area (SMA), skeletal muscle index (SMI), skeletal muscle density (SMD), subcutaneous fat area (SFA), subcutaneous fat index (SFI), visceral fat area (VFA), visceral fat index (VFI), and visceral-to-subcutaneous fat ratio (VSR). Independent t-tests, logistic regression models, and ROC curve analysis were utilized to assess the association of those metrics in predicting 90-day mortality. A total of 122 patients (58 ± 11.8, 68% male) were included. Patients who died within 90 days of TIPS had significantly higher MELD (18.9 vs. 11.9, p < 0.001) and lower SMA (123 vs. 144.5, p = 0.002), SMI (43.7 vs. 50.5, p = 0.03), SFA (122.4 vs. 190.8, p = 0.009), SFI (44.2 vs. 66.7, p = 0.04), VFA (105.5 vs. 171.2, p = 0.003), and VFI (35.7 vs. 57.5, p = 0.02) compared to those who survived past 90 days. There were no significant associations between 90-day mortality and BMI (26 vs. 27.1, p = 0.63), SMD (30.1 vs. 31.7, p = 0.44), or VSR (0.97 vs. 1.03, p = 0.66). Multivariable logistic regression showed that SMA (OR = 0.97, p < 0.01), SMI (OR = 0.94, p = 0.03), SFA (OR = 0.99, p = 0.01), and VFA (OR = 0.99, p = 0.02) remained significant predictors of 90-day mortality when adjusted for MELD score. ROC curve analysis demonstrated that including SMA, SFA, and VFA improves the predictive power of MELD score in predicting 90-day mortality after TIPS (AUC, 0.84; 95% CI: 0.77, 0.91; p = 0.02). CT body composition is positively predictive of 90-day mortality after TIPS and improves the predictive performance of MELD score. Level 3, Retrospective multi-center cohort study.

Identifiants

pubmed: 39472315
doi: 10.1007/s00270-024-03886-8
pii: 10.1007/s00270-024-03886-8
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© 2024. The Author(s).

Références

O’Brien A, Williams R. Nutrition in end-stage liver disease: principles and practice. Gastroenterology. 2008;134:1729–40. https://doi.org/10.1053/j.gastro.2008.02.001 .
doi: 10.1053/j.gastro.2008.02.001 pubmed: 18471550
Lamarti E, Hickson M. The contribution of ascitic fluid to body weight in patients with liver cirrhosis, and its estimation using girth: a cross-sectional observational study. J Hum Nutr Diet. 2020;33:404–13. https://doi.org/10.1111/jhn.12721 .
doi: 10.1111/jhn.12721 pubmed: 31775184
Center for disease control and prevention. Body mass index: considerations for practitioners. Cdc [ https://stacks.cdc.gov/view/cdc/25368 ].
Ariya M, Koohpayeh F, Ghaemi A, Osati S, Davoodi SH, Razzaz JM, et al. Assessment of the association between body composition and risk of non-alcoholic fatty liver. PLoS ONE. 2021;16: e0249223. https://doi.org/10.1371/journal.pone.0249223 .
doi: 10.1371/journal.pone.0249223 pubmed: 33793621 pmcid: 8016222
Zou WY, Enchakalody BE, Zhang P, Shah N, Saini SD, Wang NC, et al. Automated measurements of body composition in abdominal CT scans using artificial intelligence can predict mortality in patients with cirrhosis. Hepatol Commun. 2021;5:1901–10. https://doi.org/10.1002/hep4.1768 .
doi: 10.1002/hep4.1768 pubmed: 34558818 pmcid: 8557320
Pickhardt PJ, Graffy PM, Zea R, Lee SJ, Liu J, Sandfort V, et al. Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study. Lancet Digit Health. 2020;2:e192–200. https://doi.org/10.1016/S2589-7500(20)30025-X .
doi: 10.1016/S2589-7500(20)30025-X pubmed: 32864598 pmcid: 7454161
Brown JC, Caan BJ, Prado CM, Weltzien E, Xiao J, Cespedes Feliciano EM, et al. Body composition and cardiovascular events in patients with colorectal cancer: a population-based retrospective cohort study. JAMA Oncol. 2019;5:967–72. https://doi.org/10.1001/jamaoncol.2019.0695 .
doi: 10.1001/jamaoncol.2019.0695 pubmed: 31095251 pmcid: 6537811
Manabe S, Kataoka H, Mochizuki T, Iwadoh K, Ushio Y, Kawachi K, et al. Impact of visceral fat area in patients with chronic kidney disease. Clin Exp Nephrol. 2021;25:608–20. https://doi.org/10.1007/s10157-021-02029-4 .
doi: 10.1007/s10157-021-02029-4 pubmed: 33595731
Toledo DO, Carvalho AM, Oliveira AMRR, Toloi JM, Silva AC, de Mattos F, Farah J, et al. The use of computed tomography images as a prognostic marker in critically ill cancer patients. Clin Nutr ESPEN. 2018;25:114–20. https://doi.org/10.1016/j.clnesp.2018.03.122 .
doi: 10.1016/j.clnesp.2018.03.122 pubmed: 29779805
Vrieling A, Kampman E, Knijnenburg NC, Mulders PF, Sedelaar JPM, Baracos VE, et al. Body composition in relation to clinical outcomes in renal cell cancer: a systematic review and meta-analysis. Eur Urol Focus. 2018;4:420–34. https://doi.org/10.1016/j.euf.2016.11.009 .
doi: 10.1016/j.euf.2016.11.009 pubmed: 28753824
Schaffler-Schaden D, Mittermair C, Birsak T, Weiss M, Hell T, Schaffler G, et al. Skeletal muscle index is an independent predictor of early recurrence in non-obese colon cancer patients. Langenbecks Arch Surg. 2020;405:469–77. https://doi.org/10.1007/s00423-020-01901-3 .
doi: 10.1007/s00423-020-01901-3 pubmed: 32504206 pmcid: 7359173
Su H, Ruan J, Chen T, Lin E, Shi L. CT-assessed sarcopenia is a predictive factor for both long-term and short-term outcomes in gastrointestinal oncology patients: a systematic review and meta-analysis. Cancer Imaging. 2019;19:82. https://doi.org/10.1186/s40644-019-0270-0 .
doi: 10.1186/s40644-019-0270-0 pubmed: 31796090 pmcid: 6892174
Pickhardt PJ, Graffy PM, Perez AA, Lubner MG, Elton DC, Summers RM. Opportunistic screening at abdominal CT: use of automated body composition biomarkers for added cardiometabolic value. Radiographics. 2021;41:524–42. https://doi.org/10.1148/rg.2021200056 .
doi: 10.1148/rg.2021200056 pubmed: 33646902
Bunnell KM, Thaweethai T, Buckless C, Shinnick DJ, Torriani M, Foulkes AS, et al. Body composition predictors of outcome in patients with COVID-19. Int J Obes (Lond). 2021;45:2238–43. https://doi.org/10.1038/s41366-021-00907-1 .
doi: 10.1038/s41366-021-00907-1 pubmed: 34244597
Papaconstantinou D, Vretakakou K, Paspala A, Misiakos EP, Charalampopoulos A, Nastos C, et al. The impact of preoperative sarcopenia on postoperative complications following esophagectomy for esophageal neoplasia: a systematic review and meta-analysis. Dis Esophagus. 2020. https://doi.org/10.1093/dote/doaa002 .
doi: 10.1093/dote/doaa002 pubmed: 32193528
Yao S, Kamo N, Taura K, Miyachi Y, Iwamura S, Hirata M, et al. Muscularity defined by the combination of muscle quantity and quality is closely related to both liver hypertrophy and postoperative outcomes following portal vein embolization in cancer patients. Ann Surg Oncol. 2022;29:301–12. https://doi.org/10.1245/s10434-021-10525-w .
doi: 10.1245/s10434-021-10525-w pubmed: 34333707
Best TD, Mercaldo SF, Bryan DS, Marquardt JP, Wrobel MM, Bridge CP, et al. Multilevel body composition analysis on chest computed tomography predicts hospital length of stay and complications after lobectomy for lung cancer: a multicenter study. Ann Surg. 2022;275:e708–15. https://doi.org/10.1097/SLA.0000000000004040 .
doi: 10.1097/SLA.0000000000004040 pubmed: 32773626
Bridge CP, Best TD, Wrobel MM, Marquardt JP, Magudia K, Javidan C, et al. A fully automated deep learning pipeline for multi-vertebral level quantification and characterization of muscle and adipose tissue on chest CT scans. Radiol Artif Intell. 2022;4: e210080. https://doi.org/10.1148/ryai.210080 .
doi: 10.1148/ryai.210080 pubmed: 35146434 pmcid: 8823460
Nowak S, Faron A, Luetkens JA, Geißler HL, Praktiknjo M, Block W, et al. Fully automated segmentation of connective tissue compartments for CT-based body composition analysis: a deep learning approach. Invest Radiol. 2020;55:357–66. https://doi.org/10.1097/RLI.0000000000000647 .
doi: 10.1097/RLI.0000000000000647 pubmed: 32369318
Weston AD, Korfiatis P, Kline TL, Philbrick KA, Kostandy P, Sakinis T, et al. Automated abdominal segmentation of CT scans for body composition analysis using deep learning. Radiology. 2019;290:669–79. https://doi.org/10.1148/radiol.2018181432 .
doi: 10.1148/radiol.2018181432 pubmed: 30526356
Ha J, Park T, Kim H-K, Shin Y, Ko Y, Kim DW, et al. Development of a fully automatic deep learning system for L3 selection and body composition assessment on computed tomography. Sci Rep. 2021;11:21656. https://doi.org/10.1038/s41598-021-00161-5 .
doi: 10.1038/s41598-021-00161-5 pubmed: 34737340 pmcid: 8568923
Montgomery A, Ferral H, Vasan R, Postoak DW. MELD score as a predictor of early death in patients undergoing elective transjugular intrahepatic portosystemic shunt (TIPS) procedures. Cardiovasc Radiol. 2005;28:307–12. https://doi.org/10.1007/s00270-004-0145-y .
doi: 10.1007/s00270-004-0145-y
Yin L, Chu S-L, Lv W-F, Zhou C-Z, Liu K-C, Zhu Y-J, et al. Contributory roles of sarcopenia and myosteatosis in development of overt hepatic encephalopathy and mortality after transjugular intrahepatic portosystemic shunt. World J Gastroenterol. 2023;29:2875–87. https://doi.org/10.3748/wjg.v29.i18.2875 .
doi: 10.3748/wjg.v29.i18.2875 pubmed: 37274064 pmcid: 10237102
Mongan J, Moy L, Kahn CE Jr. Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell. 2020;2(2):e200029.
doi: 10.1148/ryai.2020200029 pubmed: 33937821 pmcid: 8017414
Magudia K, Bridge CP, Bay CP, Babic A, Fintelmann FJ, Troschel FM, et al. Population-scale CT-based body composition analysis of a large outpatient population using deep learning to derive age-, sex-, and race-specific reference curves. Radiology. 2021;298:319–29. https://doi.org/10.1148/radiol.2020201640 .
doi: 10.1148/radiol.2020201640 pubmed: 33231527
Prado CMM, Lieffers JR, McCargar LJ, Reiman T, Sawyer MB, Martin L, et al. Prevalence and clinical implications of sarcopenic obesity in patients with solid tumours of the respiratory and gastrointestinal tracts: a population-based study. Lancet Oncol. 2008;9:629–35. https://doi.org/10.1016/S1470-2045(08)70153-0 .
doi: 10.1016/S1470-2045(08)70153-0 pubmed: 18539529
DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837–45. https://doi.org/10.2307/2531595 .
doi: 10.2307/2531595 pubmed: 3203132
Jahangiri Y, Pathak P, Tomozawa Y, Li L, Schlansky BL, Farsad K. Muscle gain after transjugular intrahepatic portosystemic shunt creation: time course and prognostic implications for survival in cirrhosis. J Vasc Interv Radiol. 2019;30:866-872.e4. https://doi.org/10.1016/j.jvir.2019.01.005 .
doi: 10.1016/j.jvir.2019.01.005 pubmed: 31053265
Paris MT. Body composition analysis of computed tomography scans in clinical populations: the role of deep learning. Lifestyle Genom. 2020;13:28–31. https://doi.org/10.1159/000503996 .
doi: 10.1159/000503996 pubmed: 31822001
Bhanji RA, Moctezuma-Velazquez C, Duarte-Rojo A, Ebadi M, Ghosh S, Rose C, et al. Myosteatosis and sarcopenia are associated with hepatic encephalopathy in patients with cirrhosis. Hepatol Int. 2018;12:377–86. https://doi.org/10.1007/s12072-018-9875-9 .
doi: 10.1007/s12072-018-9875-9 pubmed: 29881992
Nardelli S, Lattanzi B, Torrisi S, Greco F, Farcomeni A, Gioia S, et al. Sarcopenia is risk factor for development of hepatic encephalopathy after transjugular intrahepatic portosystemic shunt placement. Clin Gastroenterol Hepatol. 2017;15:934–6. https://doi.org/10.1016/j.cgh.2016.10.028 .
doi: 10.1016/j.cgh.2016.10.028 pubmed: 27816756
Perisetti A, Goyal H, Yendala R, Chandan S, Tharian B, Thandassery RB. Sarcopenia in hepatocellular carcinoma: current knowledge and future directions. World J Gastroenterol. 2022;28:432–48. https://doi.org/10.3748/wjg.v28.i4.432 .
doi: 10.3748/wjg.v28.i4.432 pubmed: 35125828 pmcid: 8790553
Tuifua TS, Kapoor B, Partovi S, Shah SN, Bullen JA, Enders J, Laique S, Levitin A, Gadani S. Prediction of mortality and hepatic encephalopathy after transjugular intrahepatic portosystemic shunt placement: baseline and longitudinal body composition measurement. J Vasc Interv Radiol. 2024;35(5):648-657.e1. https://doi.org/10.1016/j.jvir.2024.01.012 .
doi: 10.1016/j.jvir.2024.01.012 pubmed: 38244917
Hwang GL, Sze DY. Survival in cirrhotic patients with high MELD scores: The TIPping point. Digest Diseases and Sci. 2017;62(2):296–8. https://doi.org/10.1007/s10620-016-4376-y .
doi: 10.1007/s10620-016-4376-y
Stockhoff L, Schneider H, Tergast TL, Cornberg M, Maasoumy B. Freiburg index of post-TIPS survival (FIPS) a valid prognostic score in patients with cirrhosis but also an advisor against TIPS? J Hepatol. 2021;75(2):487–9. https://doi.org/10.1016/j.jhep.2021.02.031 .
doi: 10.1016/j.jhep.2021.02.031 pubmed: 33716088
Summers RM. Nomograms for automated body composition analysis: a crucial step for routine clinical implementation. Radiology. 2021;298(2):330–1.
doi: 10.1148/radiol.2020203956 pubmed: 33236958

Auteurs

Tarig Elhakim (T)

Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA. Tarigelhakim@gmail.com.
Massachusetts General Hospital, Boston, MA, USA. Tarigelhakim@gmail.com.

Arian Mansur (A)

Harvard Medical School, Boston, MA, USA.

Jordan Kondo (J)

Brigham and Womens, Boston, MA, USA.

Omar Moustafa Fathy Omar (OMF)

University of Connecticut School of Medicine, Farmington, CT, USA.

Khalid Ahmed (K)

University of Minnesota School of Medicine, Minneapolis, MN, USA.

Azadeh Tabari (A)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Allison Brea (A)

Tufts University School of Medicine, Boston, MA, USA.

Gabriel Ndakwah (G)

Massachusetts Institute of Technology, Boston, USA.

Shams Iqbal (S)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Andrew S Allegretti (AS)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Florian J Fintelmann (FJ)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Eric Wehrenberg-Klee (E)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Christopher Bridge (C)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Dania Daye (D)

Massachusetts General Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.

Classifications MeSH