PMID- 36413412 OWN - NLM STAT- MEDLINE DCOM- 20230109 LR - 20240202 IS - 1097-0142 (Electronic) IS - 0008-543X (Print) IS - 0008-543X (Linking) VI - 129 IP - 3 DP - 2023 Feb 1 TI - Sarcopenia identified by computed tomography imaging using a deep learning-based segmentation approach impacts survival in patients with newly diagnosed multiple myeloma. PG - 385-392 LID - 10.1002/cncr.34545 [doi] AB - BACKGROUND: Sarcopenia increases with age and is associated with poor survival outcomes in patients with cancer. By using a deep learning-based segmentation approach, clinical computed tomography (CT) images of the abdomen of patients with newly diagnosed multiple myeloma (NDMM) were reviewed to determine whether the presence of sarcopenia had any prognostic value. METHODS: Sarcopenia was detected by accurate segmentation and measurement of the skeletal muscle components present at the level of the L3 vertebrae. These skeletal muscle measurements were further normalized by the height of the patient to obtain the skeletal muscle index for each patient to classify them as sarcopenic or not. RESULTS: The study cohort consisted of 322 patients of which 67 (28%) were categorized as having high risk (HR) fluorescence in situ hybridization (FISH) cytogenetics. A total of 171 (53%) patients were sarcopenic based on their peri-diagnosis standard-dose CT scan. The median overall survival (OS) and 2-year mortality rate for sarcopenic patients was 44 months and 40% compared to 90 months and 18% for those not sarcopenic, respectively (p < .0001 for both comparisons). In a multivariable model, the adverse prognostic impact of sarcopenia was independent of International Staging System stage, age, and HR FISH cytogenetics. CONCLUSIONS: Sarcopenia identified by a machine learning-based convolutional neural network algorithm significantly affects OS in patients with NDMM. Future studies using this machine learning-based methodology of assessing sarcopenia in larger prospective clinical trials are required to validate these findings. CI - (c) 2022 American Cancer Society. FAU - Nandakumar, Bharat AU - Nandakumar B AUID- ORCID: 0000-0002-5399-9116 AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Baffour, Francis AU - Baffour F AD - Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Abdallah, Nadine H AU - Abdallah NH AUID- ORCID: 0000-0001-9195-1589 AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Kumar, Shaji K AU - Kumar SK AUID- ORCID: 0000-0001-5392-9284 AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Dispenzieri, Angela AU - Dispenzieri A AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Buadi, Francis K AU - Buadi FK AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Dingli, David AU - Dingli D AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Lacy, Martha Q AU - Lacy MQ AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Hayman, Suzanne R AU - Hayman SR AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Kapoor, Prashant AU - Kapoor P AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Leung, Nelson AU - Leung N AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. AD - Division of Nephrology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Fonder, Amie AU - Fonder A AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Hobbs, Miriam AU - Hobbs M AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Hwa, Yi Lisa AU - Hwa YL AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Muchtar, Eli AU - Muchtar E AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Warsame, Rahma AU - Warsame R AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Kourelis, Taxiarchis V AU - Kourelis TV AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Go, Ronald S AU - Go RS AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Kyle, Robert A AU - Kyle RA AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Gertz, Morie A AU - Gertz MA AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Rajkumar, S Vincent AU - Rajkumar SV AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Klug, Jason AU - Klug J AD - Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Korfiatis, Panagiotis AU - Korfiatis P AD - Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA. FAU - Gonsalves, Wilson I AU - Gonsalves WI AD - Division of Hematology, Mayo Clinic, Rochester, Minnesota, USA. LA - eng GR - P50 CA186781/CA/NCI NIH HHS/United States GR - R01 CA254961/CA/NCI NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural PT - Research Support, Non-U.S. Gov't DEP - 20221122 PL - United States TA - Cancer JT - Cancer JID - 0374236 SB - IM MH - Humans MH - *Sarcopenia/complications/diagnostic imaging MH - *Multiple Myeloma/complications/diagnostic imaging/pathology MH - Prospective Studies MH - *Deep Learning MH - In Situ Hybridization, Fluorescence MH - Retrospective Studies MH - Tomography, X-Ray Computed/methods MH - Muscle, Skeletal/diagnostic imaging MH - Prognosis PMC - PMC9822865 MID - NIHMS1850433 OTO - NOTNLM OT - artificial intelligence OT - multiple myeloma OT - prognostic factors in multiple myeloma OT - sarcopenia OT - survival outcomes in multiple myeloma COIS- CONFLICT OF INTEREST DISCLOSURE: These authors declare no competing financial interests. EDAT- 2022/11/23 06:00 MHDA- 2023/01/10 06:00 PMCR- 2024/02/01 CRDT- 2022/11/22 12:03 PHST- 2022/09/02 00:00 [revised] PHST- 2022/07/11 00:00 [received] PHST- 2022/09/26 00:00 [accepted] PHST- 2022/11/23 06:00 [pubmed] PHST- 2023/01/10 06:00 [medline] PHST- 2022/11/22 12:03 [entrez] PHST- 2024/02/01 00:00 [pmc-release] AID - 10.1002/cncr.34545 [doi] PST - ppublish SO - Cancer. 2023 Feb 1;129(3):385-392. doi: 10.1002/cncr.34545. Epub 2022 Nov 22.