Machine Learning-Based Exploratory Clinical Decision Support for Newly Diagnosed Patients With Acute Myeloid Leukemia Treated With 7 + 3 Type Chemotherapy or Venetoclax/Azacitidine.

Autor:	Islam N; Optum Labs, Minnetonka, MN., Reuben JS; UCHealth, Aurora, CO., Dale J; Department of Medicine, University of Colorado, Aurora, CO., Gutman J; Department of Medicine, University of Colorado, Aurora, CO., McMahon CM; Department of Medicine, University of Colorado, Aurora, CO., Amaya M; Department of Medicine, University of Colorado, Aurora, CO., Goodman B; Optum Labs, Minnetonka, MN., Toninato J; Optum Labs, Minnetonka, MN., Gasparetto M; Department of Medicine, University of Colorado, Aurora, CO., Stevens B; Department of Medicine, University of Colorado, Aurora, CO., Pei S; Department of Medicine, University of Colorado, Aurora, CO., Gillen A; Department of Medicine, University of Colorado, Aurora, CO., Staggs S; Department of Medicine, University of Colorado, Aurora, CO., Engel K; Department of Medicine, University of Colorado, Aurora, CO., Davis S; Department of Medicine, University of Colorado, Aurora, CO., Hull M; Health Data Compass, Colorado Center for Personalized Medicine, University of Colorado, Aurora, CO., Burke E; UCHealth, Aurora, CO., Larchick L; UCHealth, Aurora, CO., Zane R; UCHealth Care Innovations and Department of Emergency Medicine, University of Colorado, Aurora, CO., Weller G; Optum Labs, Minnetonka, MN., Jordan C; Department of Medicine, University of Colorado, Aurora, CO., Smith C; Department of Medicine, University of Colorado, Aurora, CO.
Jazyk:	angličtina
Zdroj:	JCO clinical cancer informatics [JCO Clin Cancer Inform] 2022 Sep; Vol. 6, pp. e2200030.
DOI:	10.1200/CCI.22.00030
Abstrakt:	Purpose: There are currently limited objective criteria to help assist physicians in determining whether an individual patient with acute myeloid leukemia (AML) is likely to do better with induction with either standard 7 + 3 chemotherapy or targeted therapy with venetoclax plus azacitidine. The study goal was to address this need by developing exploratory clinical decision support methods. Patients and Methods: Univariable and multivariable analysis as well as comparison of a range of machine learning (ML) predictors were performed using cohorts of 120 newly diagnosed 7 + 3-treated AML patients compared with 101 venetoclax plus azacitidine-treated patients. Results: A variety of features in the two patient cohorts were identified that may potentially correlate with short- and long-term outcomes, toxicities, and other considerations. A subset of these diagnostic features was then used to develop ML-based predictors with relatively high areas under the curve of short- and long-term outcomes, hospital stays, transfusion requirements, and toxicities for individual patients treated with either venetoclax/azacitidine or 7 + 3. Conclusion: Potential ML-based approaches to clinical decision support to help guide individual patients with newly diagnosed AML to either 7 + 3 or venetoclax plus azacitidine induction therapy were identified. Larger cohorts with separate test and validation studies are necessary to confirm these initial findings. Competing Interests: Grant WellerEmployment: UnitedHealth Group, BioIntelliSense, IncStock and Other Ownership Interests: UnitedHealth Group Joseph ToninatoEmployment: Cityblock Health, UnitedHealth GroupStock and Other Ownership Interests: UnitedHealth Group, Cityblock Health Sarah StaggsResearch Funding: argenx, ElevateBio, Syros Pharmaceuticals, Kura Oncology Richard ZaneUncompensated Relationships: Riva, Arrive Health Austin GillenResearch Funding: Syros Pharmaceuticals, argenx, Kura Oncology, ElevateBio Justin DaleEmployment: UnitedHealth GroupStock and Other Ownership Interests: UnitedHealth Group Bruce GoodmanEmployment: OptumStock and Other Ownership Interests: UnitedHealth GroupResearch Funding: Optum Nazmul IslamEmployment: Optum/UnitedHealth GroupStock and Other Ownership Interests: Optum/UnitedHealth Group Christine M. McMahonConsulting or Advisory Role: Arcellx, TG Therapeutics, AbbVieResearch Funding: Syros Pharmaceuticals (Inst) Clay SmithResearch Funding: argenx, Syros Pharmaceuticals, Kura 11/21Patents, Royalties, Other Intellectual Property: Patents pending: (1) compositions and methods for reducing cancer stem cells (2) methods for treating acute myeloid leukemia (3) machine language predictor of AML patient responsiveness to treatment with venetoclax and hypomethylating agents (4) subject specific treatments for venetoclax resistant AML Shanshan PeiStock and Other Ownership Interests: CRISPR Therapeutics, Teladoc, Iterum, Abeona TherapeuticsSpeakers' Bureau: AbbViePatents, Royalties, Other Intellectual Property: A pending patent related to detecting and treating venetoclax-resistant AML patientsNo other potential conflicts of interest were reported.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu