A cure-rate model for Q-learning: Estimating an adaptive immunosuppressant treatment strategy for allogeneic hematopoietic cell transplant patients

Erica E.M. Moodie, David A. Stephens, Shomoita Alam, Mei Jie Zhang, Brent Logan, Mukta Arora, Stephen Spellman, Elizabeth F. Krakow

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    Cancers treated by transplantation are often curative, but immunosuppressive drugs are required to prevent and (if needed) to treat graft-versus-host disease. Estimation of an optimal adaptive treatment strategy when treatment at either one of two stages of treatment may lead to a cure has not yet been considered. Using a sample of 9563 patients treated for blood and bone cancers by allogeneic hematopoietic cell transplantation drawn from the Center for Blood and Marrow Transplant Research database, we provide a case study of a novel approach to Q-learning for survival data in the presence of a potentially curative treatment, and demonstrate the results differ substantially from an implementation of Q-learning that fails to account for the cure-rate.

    Original languageEnglish (US)
    Pages (from-to)442-453
    Number of pages12
    JournalBiometrical Journal
    Volume61
    Issue number2
    DOIs
    StatePublished - Mar 2019

    Fingerprint

    Cure Rate Model
    Q-learning
    Transplantation
    Cell
    Blood
    Cancer
    Survival Data
    Bone
    Drugs
    Strategy
    Demonstrate

    Keywords

    • Q-learning
    • adaptive treatment strategy
    • cure-rate
    • dynamic treatment regime
    • survival data

    PubMed: MeSH publication types

    • Journal Article
    • Research Support, N.I.H., Extramural
    • Research Support, Non-U.S. Gov't

    Cite this

    A cure-rate model for Q-learning : Estimating an adaptive immunosuppressant treatment strategy for allogeneic hematopoietic cell transplant patients. / Moodie, Erica E.M.; Stephens, David A.; Alam, Shomoita; Zhang, Mei Jie; Logan, Brent; Arora, Mukta; Spellman, Stephen; Krakow, Elizabeth F.

    In: Biometrical Journal, Vol. 61, No. 2, 03.2019, p. 442-453.

    Research output: Contribution to journalArticle

    Moodie, Erica E.M. ; Stephens, David A. ; Alam, Shomoita ; Zhang, Mei Jie ; Logan, Brent ; Arora, Mukta ; Spellman, Stephen ; Krakow, Elizabeth F. / A cure-rate model for Q-learning : Estimating an adaptive immunosuppressant treatment strategy for allogeneic hematopoietic cell transplant patients. In: Biometrical Journal. 2019 ; Vol. 61, No. 2. pp. 442-453.
    @article{cd20f53bf97946269ab4dc18bf31683d,
    title = "A cure-rate model for Q-learning: Estimating an adaptive immunosuppressant treatment strategy for allogeneic hematopoietic cell transplant patients",
    abstract = "Cancers treated by transplantation are often curative, but immunosuppressive drugs are required to prevent and (if needed) to treat graft-versus-host disease. Estimation of an optimal adaptive treatment strategy when treatment at either one of two stages of treatment may lead to a cure has not yet been considered. Using a sample of 9563 patients treated for blood and bone cancers by allogeneic hematopoietic cell transplantation drawn from the Center for Blood and Marrow Transplant Research database, we provide a case study of a novel approach to Q-learning for survival data in the presence of a potentially curative treatment, and demonstrate the results differ substantially from an implementation of Q-learning that fails to account for the cure-rate.",
    keywords = "Q-learning, adaptive treatment strategy, cure-rate, dynamic treatment regime, survival data",
    author = "Moodie, {Erica E.M.} and Stephens, {David A.} and Shomoita Alam and Zhang, {Mei Jie} and Brent Logan and Mukta Arora and Stephen Spellman and Krakow, {Elizabeth F.}",
    year = "2019",
    month = "3",
    doi = "10.1002/bimj.201700181",
    language = "English (US)",
    volume = "61",
    pages = "442--453",
    journal = "Biometrical Journal",
    issn = "0323-3847",
    publisher = "Wiley-VCH Verlag",
    number = "2",

    }

    TY - JOUR

    T1 - A cure-rate model for Q-learning

    T2 - Estimating an adaptive immunosuppressant treatment strategy for allogeneic hematopoietic cell transplant patients

    AU - Moodie, Erica E.M.

    AU - Stephens, David A.

    AU - Alam, Shomoita

    AU - Zhang, Mei Jie

    AU - Logan, Brent

    AU - Arora, Mukta

    AU - Spellman, Stephen

    AU - Krakow, Elizabeth F.

    PY - 2019/3

    Y1 - 2019/3

    N2 - Cancers treated by transplantation are often curative, but immunosuppressive drugs are required to prevent and (if needed) to treat graft-versus-host disease. Estimation of an optimal adaptive treatment strategy when treatment at either one of two stages of treatment may lead to a cure has not yet been considered. Using a sample of 9563 patients treated for blood and bone cancers by allogeneic hematopoietic cell transplantation drawn from the Center for Blood and Marrow Transplant Research database, we provide a case study of a novel approach to Q-learning for survival data in the presence of a potentially curative treatment, and demonstrate the results differ substantially from an implementation of Q-learning that fails to account for the cure-rate.

    AB - Cancers treated by transplantation are often curative, but immunosuppressive drugs are required to prevent and (if needed) to treat graft-versus-host disease. Estimation of an optimal adaptive treatment strategy when treatment at either one of two stages of treatment may lead to a cure has not yet been considered. Using a sample of 9563 patients treated for blood and bone cancers by allogeneic hematopoietic cell transplantation drawn from the Center for Blood and Marrow Transplant Research database, we provide a case study of a novel approach to Q-learning for survival data in the presence of a potentially curative treatment, and demonstrate the results differ substantially from an implementation of Q-learning that fails to account for the cure-rate.

    KW - Q-learning

    KW - adaptive treatment strategy

    KW - cure-rate

    KW - dynamic treatment regime

    KW - survival data

    UR - http://www.scopus.com/inward/record.url?scp=85047468536&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85047468536&partnerID=8YFLogxK

    U2 - 10.1002/bimj.201700181

    DO - 10.1002/bimj.201700181

    M3 - Article

    C2 - 29766558

    AN - SCOPUS:85047468536

    VL - 61

    SP - 442

    EP - 453

    JO - Biometrical Journal

    JF - Biometrical Journal

    SN - 0323-3847

    IS - 2

    ER -