External Validation of the Bone Metastases Ensemble Trees for Survival (BMETS) Machine Learning Model to Predict Survival in Patients With Symptomatic Bone Metastases
The Bone Metastases Ensemble Trees for Survival (BMETS) model uses a machine learning algorithm to estimate survival time following consultation for palliative radiation therapy for symptomatic bone metastases (SBM). BMETS was developed at a tertiary-care, academic medical center, but its validity a...
Saved in:
Published in | JCO clinical cancer informatics Vol. 5; p. 304 |
---|---|
Main Authors | , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
01.03.2021
|
Subjects | |
Online Access | Get more information |
Cover
Loading…
Abstract | The Bone Metastases Ensemble Trees for Survival (BMETS) model uses a machine learning algorithm to estimate survival time following consultation for palliative radiation therapy for symptomatic bone metastases (SBM). BMETS was developed at a tertiary-care, academic medical center, but its validity and stability when applied to external data sets are unknown.
Patients treated with palliative radiation therapy for SBM from May 2013 to May 2016 at two hospital-based community radiation oncology clinics were included, and medical records were retrospectively reviewed to collect model covariates and survival time. The Kaplan-Meier method was used to estimate overall survival from consultation to death or last follow-up. Model discrimination was estimated using time-dependent area under the curve (tAUC), which was calculated using survival predictions from BMETS based on the initial training data set.
A total of 216 sites of SBM were treated in 182 patients. Most common histologies were breast (27%), lung (23%), and prostate (23%). Compared with the BMETS training set, the external validation population was older (mean age, 67
62 years;
< .001), had more primary breast (27%
19%;
= .03) and prostate cancer (20%
12%;
= .01), and survived longer (median, 10.7
6.4 months). When the BMETS model was applied to the external data set, tAUC values at 3, 6, and 12 months were 0.82, 0.77, and 0.77, respectively. When refit with data from the combined training and external validation sets, tAUC remained
0.79.
BMETS maintained high discriminative ability when applied to an external validation set and when refit with new data, supporting its generalizability, stability, and the feasibility of dynamic modeling. |
---|---|
AbstractList | The Bone Metastases Ensemble Trees for Survival (BMETS) model uses a machine learning algorithm to estimate survival time following consultation for palliative radiation therapy for symptomatic bone metastases (SBM). BMETS was developed at a tertiary-care, academic medical center, but its validity and stability when applied to external data sets are unknown.
Patients treated with palliative radiation therapy for SBM from May 2013 to May 2016 at two hospital-based community radiation oncology clinics were included, and medical records were retrospectively reviewed to collect model covariates and survival time. The Kaplan-Meier method was used to estimate overall survival from consultation to death or last follow-up. Model discrimination was estimated using time-dependent area under the curve (tAUC), which was calculated using survival predictions from BMETS based on the initial training data set.
A total of 216 sites of SBM were treated in 182 patients. Most common histologies were breast (27%), lung (23%), and prostate (23%). Compared with the BMETS training set, the external validation population was older (mean age, 67
62 years;
< .001), had more primary breast (27%
19%;
= .03) and prostate cancer (20%
12%;
= .01), and survived longer (median, 10.7
6.4 months). When the BMETS model was applied to the external data set, tAUC values at 3, 6, and 12 months were 0.82, 0.77, and 0.77, respectively. When refit with data from the combined training and external validation sets, tAUC remained
0.79.
BMETS maintained high discriminative ability when applied to an external validation set and when refit with new data, supporting its generalizability, stability, and the feasibility of dynamic modeling. |
Author | Smith, Thomas J DeWeese, Theodore L LaVigne, Anna W Elledge, Christen R Fiksel, Jacob Kleinberg, Lawrence R Hu, Chen Zeger, Scott Wright, Jean L McNutt, Todd Alcorn, Sara R |
Author_xml | – sequence: 1 givenname: Christen R orcidid: 0000-0002-6047-3219 surname: Elledge fullname: Elledge, Christen R organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 2 givenname: Anna W orcidid: 0000-0001-6872-9357 surname: LaVigne fullname: LaVigne, Anna W organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 3 givenname: Jacob orcidid: 0000-0001-7067-1334 surname: Fiksel fullname: Fiksel, Jacob organization: Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD – sequence: 4 givenname: Jean L surname: Wright fullname: Wright, Jean L organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 5 givenname: Todd surname: McNutt fullname: McNutt, Todd organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 6 givenname: Lawrence R orcidid: 0000-0003-2473-2305 surname: Kleinberg fullname: Kleinberg, Lawrence R organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 7 givenname: Chen orcidid: 0000-0003-4672-1981 surname: Hu fullname: Hu, Chen organization: Department of Oncology, Johns Hopkins School of Medicine, Baltimore, MD – sequence: 8 givenname: Thomas J orcidid: 0000-0003-3040-6434 surname: Smith fullname: Smith, Thomas J organization: Department of Oncology, Johns Hopkins School of Medicine, Baltimore, MD – sequence: 9 givenname: Scott orcidid: 0000-0001-8907-1603 surname: Zeger fullname: Zeger, Scott organization: Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD – sequence: 10 givenname: Theodore L surname: DeWeese fullname: DeWeese, Theodore L organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD – sequence: 11 givenname: Sara R orcidid: 0000-0003-4620-5047 surname: Alcorn fullname: Alcorn, Sara R organization: Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33760638$$D View this record in MEDLINE/PubMed |
BookMark | eNpdkFFLwzAUhYMobs69-Sx51IfONO2a9FFL1cGKg019HGly6yJtOpJsuD_k7zSgIggXLvfAdw73nKFj0xtA6CImk5gSclMUswklE0Jiyo_QkKYsiVLKsgEaO_dOgs7TNEvzUzRIEpaRLOFD9Fl-eLBGtPhFtFoJr3uD-wb7DeC74I8r8MKFAYdL46CrW8ArC-FseouXO7vX-0Bf3VXlanmNKyE3OmBzENZo84arXkGLfY8XFpSW_g_RBi9CHhjv8Kv2G7w8dFvfd0GT_7PP0UkjWgfjnz1Cz_flqniM5k8Ps-J2Hkmaxz4KbzEGFBLJmIynYppzlUDMKM1Iw5Na1TWXjeSEq0zxaZrnQONQSS5VTWsl6Qhdfvtud3UHar21uhP2sP4tjH4BYt1vVw |
CitedBy_id | crossref_primary_10_1016_j_semradonc_2022_11_002 crossref_primary_10_1111_jep_13652 crossref_primary_10_3390_cancers15051596 crossref_primary_10_1016_j_semradonc_2023_01_003 crossref_primary_10_1097_SPC_0000000000000645 crossref_primary_10_1200_CCI_22_00082 |
ContentType | Journal Article |
DBID | CGR CUY CVF ECM EIF NPM |
DOI | 10.1200/CCI.20.00128 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) |
DatabaseTitleList | MEDLINE |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | no_fulltext_linktorsrc |
EISSN | 2473-4276 |
ExternalDocumentID | 33760638 |
Genre | Journal Article |
GroupedDBID | 0R~ 53G ABDBF ALMA_UNASSIGNED_HOLDINGS C45 CGR CUY CVF DIWNM EBS ECM EIF FBNNL H13 NPM O9- OVD RLZ RUC TEORI |
ID | FETCH-LOGICAL-c291t-37677e2e3c77c15a598d3e172260f83bdbb8cfc808d6d85499e216499cdb2bdc2 |
IngestDate | Tue Aug 27 13:49:08 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c291t-37677e2e3c77c15a598d3e172260f83bdbb8cfc808d6d85499e216499cdb2bdc2 |
ORCID | 0000-0002-6047-3219 0000-0001-7067-1334 0000-0001-8907-1603 0000-0001-6872-9357 0000-0003-4672-1981 0000-0003-4620-5047 0000-0003-3040-6434 0000-0003-2473-2305 |
PMID | 33760638 |
ParticipantIDs | pubmed_primary_33760638 |
PublicationCentury | 2000 |
PublicationDate | 2021-03-00 |
PublicationDateYYYYMMDD | 2021-03-01 |
PublicationDate_xml | – month: 03 year: 2021 text: 2021-03-00 |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States |
PublicationTitle | JCO clinical cancer informatics |
PublicationTitleAlternate | JCO Clin Cancer Inform |
PublicationYear | 2021 |
SSID | ssj0001844649 |
Score | 2.2469983 |
Snippet | The Bone Metastases Ensemble Trees for Survival (BMETS) model uses a machine learning algorithm to estimate survival time following consultation for palliative... |
SourceID | pubmed |
SourceType | Index Database |
StartPage | 304 |
SubjectTerms | Aged Bone Neoplasms - mortality Humans Machine Learning Palliative Care Retrospective Studies |
Title | External Validation of the Bone Metastases Ensemble Trees for Survival (BMETS) Machine Learning Model to Predict Survival in Patients With Symptomatic Bone Metastases |
URI | https://www.ncbi.nlm.nih.gov/pubmed/33760638 |
Volume | 5 |
hasFullText | |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEF6lRUK9oFa8yqOaAwdQ5JCsX-sjRK5K1BSkpqW3yvtwZdE4UWMO8IP4MfwqZtbe2KQgFS6W5dV6V55P429m58HYKyqgIoXRXpKr3AuCLPKS0Aw9yXWcRyEP_IwSnKcn0dFZMLkIL3q9n52opa-VHKjvf8wr-R-p4jOUK2XJ_oNk1y_FB3iP8sUrShivd5Jx2pRw7p8jm9Zr8mfP_BfIHqemypD9rcyqn5YrM6csqdmNMbYGA-oMVBO4HSKZ76fp7JQ8BFMbXGlc3dUr2yztmhjqpxs606naaUVJBf4LmyL3mdy5p9_my2pR14DdWP83Djz-2CZkKkIdhcQ35LmNvU-vra-vrYBgyja68Tg7L64aZ2xZZv21p-iw-LKqAw8mqOvlbSfEhI4ejrvODt6J9hoYqxR5EPtewOueMU6Dhx0N7NfdjG_9Gbhtej0efxhwCuYb1SnpHZAs5xYlPkUJRf4dRjfqdLuhLbYVC9K1J43fyHr7BJrdQdJkXuBe3nZ3ssPuu9kb1o1lObNd9qAxT-BdjbU91jPlQ_bD4QxanMEiB8QZkJyhlTM4nIHFGaBUwQEGXluUvYEGY-AwBhZjUC2gwVg7pSjBYQwIY9DB2Obaj9jZYTobH3lNfw9P8WRU0b8tjg03vopjNQqzMBHaN8io0cbOhS-1lELlSgyFjrQgR4bhaN0nidKSS634Y7Zd4kpPGWQikUh2Jfd1FGgzlMhboyAbxWgARfGQ77Mn9We9XNZFXC7dB3_215HnbKeF4At2L0etYV4iBa3kgZXuLw6IicM |
link.rule.ids | 786 |
linkProvider | National Library of Medicine |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=External+Validation+of+the+Bone+Metastases+Ensemble+Trees+for+Survival+%28BMETS%29+Machine+Learning+Model+to+Predict+Survival+in+Patients+With+Symptomatic+Bone+Metastases&rft.jtitle=JCO+clinical+cancer+informatics&rft.au=Elledge%2C+Christen+R&rft.au=LaVigne%2C+Anna+W&rft.au=Fiksel%2C+Jacob&rft.au=Wright%2C+Jean+L&rft.date=2021-03-01&rft.eissn=2473-4276&rft.volume=5&rft.spage=304&rft_id=info:doi/10.1200%2FCCI.20.00128&rft_id=info%3Apmid%2F33760638&rft_id=info%3Apmid%2F33760638&rft.externalDocID=33760638 |