View in EDS

Machine Learning Algorithm Prospectively Predicts Survival for High-Risk Patients Undergoing Radiotherapy: A Survival Analysis of SHIELD-RT.

Saved in:
Bibliographic Details
Title: Machine Learning Algorithm Prospectively Predicts Survival for High-Risk Patients Undergoing Radiotherapy: A Survival Analysis of SHIELD-RT.
Authors: Natesan, D.1 (AUTHOR), Thomas, S.M.2 (AUTHOR), Eclov, N.1 (AUTHOR), Dalal, N.H.3 (AUTHOR), Stephens, S.J.1 (AUTHOR), Malicki, M.4 (AUTHOR), Shields, S.1 (AUTHOR), Cobb, A.1 (AUTHOR), Mowery, Y.M.1 (AUTHOR), Niedzwiecki, D.2 (AUTHOR), Tenenbaum, J.D.5 (AUTHOR), Palta, M.1 (AUTHOR), Hong, J.C.6 (AUTHOR)
Source: International Journal of Radiation Oncology, Biology, Physics. 2021 Supplement, Vol. 111 Issue 3, pS113-S113. 1p.
Subjects: Clinical prediction rules, Machine learning, Survival analysis (Biometry), Individualized medicine, Proportional hazards models, Head & neck cancer, Oncologists
Abstract: Purpose/objective(s): Mortality prediction is critical to appropriate cancer care planning. This has become a topic of interest, with machine learning (ML) tools demonstrating accurate binary predictions for mortality at specific time points. There are limited prospective data validating the clinical utility of health care ML tools. We previously developed a ML algorithm which predicts risk of acute care (ER visits or hospitalizations). SHIELD-RT was a randomized controlled study which demonstrated that a ML algorithm could direct supplemental clinic visits to reduce the rate of acute care during RT from 22% to 12%. While the algorithm was trained for acute care visits, we sought to determine whether ML risk would facilitate multiple clinical uses through survival prediction in this prospective study.Materials/methods: Patients who initiated RT from 1/7/2019-6/30/19 at a single institution were evaluated during the first week of treatment by the electronic health record-based ML algorithm. High risk patients (> 10% risk of acute visit) were randomized to standard weekly evaluations (S) or twice weekly evaluations (TW). Patient, disease, and treatment factors were collected prospectively. Survival was recorded retrospectively. Unadjusted OS was estimated with the Kaplan Meier method and compared between arms with the log rank test. Cox proportional hazards models were used to estimate the association of covariates with OS after adjustment for study arm. Hazard ratios (HRs) and 95% confidence intervals (CIs) are reported.Results: Patients undergoing 311 distinct courses were randomized to S (n = 157) or TW (n = 154) evaluations. The 1-year OS was similar for those who underwent S (58%, 95% CI 50%-65%) or TW (66%, 95% CI 58%-73%) evaluations, P = 0.35. ML risk on a continuous basis was significantly associated with survival (HR 4.27, 95% CI 0.98-18.6, P = 0.05). Other factors associated with OS included age (HR 1.01, 95% CI 1.00-1.03, P = 0.04), palliative treatment vs curative treatment (HR 6.59 (95% CI 4.62-9.41, < 0.001), widely metastatic disease vs no metastatic disease (HR 6.86, 95% CI 4.74-9.92, P < 0.001). Treatment of certain disease sites were also associated with OS: brain metastases (HR 5.00, 95% CI 3.16-7.93, P < 0.001), bone metastases (HR 4.69, 95% CI 3.09-7.12, P < 0.001), thoracic (HR 2.44, 95% CI 1.61-3.7, P < 0.001), head and neck cancer (HR 0.44, 95% CI 0.22-0.91, P = 0.03), genitourinary cancer (HR 0.32, 95% CI 0.12-0.85, P = 0.02). Admission during RT + 15 days was associated with decreased OS (HR 2.32, 95% CI 1.58-3.40, P < 0.001).Conclusion: Our ML algorithm, developed to predict acute care, also predicted OS. This supports the correlation between the two event types and demonstrates the utility of ML to provide multiple predictive functions. Implementation of predictive ML algorithms into oncology clinical workflows may aid in prognostication to guide personalized patient care and influence treatment decisions. (NCT03775265). [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Radiation Oncology, Biology, Physics is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 152497051
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Machine Learning Algorithm Prospectively Predicts Survival for High-Risk Patients Undergoing Radiotherapy: A Survival Analysis of SHIELD-RT.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Natesan%2C+D%2E%22&quot;&gt;Natesan, D.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Thomas%2C+S%2EM%2E%22&quot;&gt;Thomas, S.M.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Eclov%2C+N%2E%22&quot;&gt;Eclov, N.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Dalal%2C+N%2EH%2E%22&quot;&gt;Dalal, N.H.&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Stephens%2C+S%2EJ%2E%22&quot;&gt;Stephens, S.J.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Malicki%2C+M%2E%22&quot;&gt;Malicki, M.&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Shields%2C+S%2E%22&quot;&gt;Shields, S.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Cobb%2C+A%2E%22&quot;&gt;Cobb, A.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Mowery%2C+Y%2EM%2E%22&quot;&gt;Mowery, Y.M.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Niedzwiecki%2C+D%2E%22&quot;&gt;Niedzwiecki, D.&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Tenenbaum%2C+J%2ED%2E%22&quot;&gt;Tenenbaum, J.D.&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Palta%2C+M%2E%22&quot;&gt;Palta, M.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Hong%2C+J%2EC%2E%22&quot;&gt;Hong, J.C.&lt;/searchLink&gt;&lt;relatesTo&gt;6&lt;/relatesTo&gt; (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22International+Journal+of+Radiation+Oncology%2C+Biology%2C+Physics%22&quot;&gt;International Journal of Radiation Oncology, Biology, Physics&lt;/searchLink&gt;. 2021 Supplement, Vol. 111 Issue 3, pS113-S113. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Clinical+prediction+rules%22&quot;&gt;Clinical prediction rules&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Machine+learning%22&quot;&gt;Machine learning&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Survival+analysis+%28Biometry%29%22&quot;&gt;Survival analysis (Biometry)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Individualized+medicine%22&quot;&gt;Individualized medicine&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Proportional+hazards+models%22&quot;&gt;Proportional hazards models&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Head+%26+neck+cancer%22&quot;&gt;Head &amp; neck cancer&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Oncologists%22&quot;&gt;Oncologists&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: &lt;bold&gt;Purpose/objective(s): &lt;/bold&gt;Mortality prediction is critical to appropriate cancer care planning. This has become a topic of interest, with machine learning (ML) tools demonstrating accurate binary predictions for mortality at specific time points. There are limited prospective data validating the clinical utility of health care ML tools. We previously developed a ML algorithm which predicts risk of acute care (ER visits or hospitalizations). SHIELD-RT was a randomized controlled study which demonstrated that a ML algorithm could direct supplemental clinic visits to reduce the rate of acute care during RT from 22% to 12%. While the algorithm was trained for acute care visits, we sought to determine whether ML risk would facilitate multiple clinical uses through survival prediction in this prospective study.&lt;bold&gt;Materials/methods: &lt;/bold&gt;Patients who initiated RT from 1/7/2019-6/30/19 at a single institution were evaluated during the first week of treatment by the electronic health record-based ML algorithm. High risk patients (&gt; 10% risk of acute visit) were randomized to standard weekly evaluations (S) or twice weekly evaluations (TW). Patient, disease, and treatment factors were collected prospectively. Survival was recorded retrospectively. Unadjusted OS was estimated with the Kaplan Meier method and compared between arms with the log rank test. Cox proportional hazards models were used to estimate the association of covariates with OS after adjustment for study arm. Hazard ratios (HRs) and 95% confidence intervals (CIs) are reported.&lt;bold&gt;Results: &lt;/bold&gt;Patients undergoing 311 distinct courses were randomized to S (n = 157) or TW (n = 154) evaluations. The 1-year OS was similar for those who underwent S (58%, 95% CI 50%-65%) or TW (66%, 95% CI 58%-73%) evaluations, P = 0.35. ML risk on a continuous basis was significantly associated with survival (HR 4.27, 95% CI 0.98-18.6, P = 0.05). Other factors associated with OS included age (HR 1.01, 95% CI 1.00-1.03, P = 0.04), palliative treatment vs curative treatment (HR 6.59 (95% CI 4.62-9.41, &lt; 0.001), widely metastatic disease vs no metastatic disease (HR 6.86, 95% CI 4.74-9.92, P &lt; 0.001). Treatment of certain disease sites were also associated with OS: brain metastases (HR 5.00, 95% CI 3.16-7.93, P &lt; 0.001), bone metastases (HR 4.69, 95% CI 3.09-7.12, P &lt; 0.001), thoracic (HR 2.44, 95% CI 1.61-3.7, P &lt; 0.001), head and neck cancer (HR 0.44, 95% CI 0.22-0.91, P = 0.03), genitourinary cancer (HR 0.32, 95% CI 0.12-0.85, P = 0.02). Admission during RT + 15 days was associated with decreased OS (HR 2.32, 95% CI 1.58-3.40, P &lt; 0.001).&lt;bold&gt;Conclusion: &lt;/bold&gt;Our ML algorithm, developed to predict acute care, also predicted OS. This supports the correlation between the two event types and demonstrates the utility of ML to provide multiple predictive functions. Implementation of predictive ML algorithms into oncology clinical workflows may aid in prognostication to guide personalized patient care and influence treatment decisions. (NCT03775265). [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of International Journal of Radiation Oncology, Biology, Physics is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder&#39;s express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=152497051
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.ijrobp.2021.07.260
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: S113
    Subjects:
      – SubjectFull: Clinical prediction rules
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Survival analysis (Biometry)
        Type: general
      – SubjectFull: Individualized medicine
        Type: general
      – SubjectFull: Proportional hazards models
        Type: general
      – SubjectFull: Head & neck cancer
        Type: general
      – SubjectFull: Oncologists
        Type: general
    Titles:
      – TitleFull: Machine Learning Algorithm Prospectively Predicts Survival for High-Risk Patients Undergoing Radiotherapy: A Survival Analysis of SHIELD-RT.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Natesan, D.
      – PersonEntity:
          Name:
            NameFull: Thomas, S.M.
      – PersonEntity:
          Name:
            NameFull: Eclov, N.
      – PersonEntity:
          Name:
            NameFull: Dalal, N.H.
      – PersonEntity:
          Name:
            NameFull: Stephens, S.J.
      – PersonEntity:
          Name:
            NameFull: Malicki, M.
      – PersonEntity:
          Name:
            NameFull: Shields, S.
      – PersonEntity:
          Name:
            NameFull: Cobb, A.
      – PersonEntity:
          Name:
            NameFull: Mowery, Y.M.
      – PersonEntity:
          Name:
            NameFull: Niedzwiecki, D.
      – PersonEntity:
          Name:
            NameFull: Tenenbaum, J.D.
      – PersonEntity:
          Name:
            NameFull: Palta, M.
      – PersonEntity:
          Name:
            NameFull: Hong, J.C.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 02
              M: 11
              Text: 2021 Supplement
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 03603016
          Numbering:
            – Type: volume
              Value: 111
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: International Journal of Radiation Oncology, Biology, Physics
              Type: main
ResultId 1