Machine Learning Methods for Precision Dosing in Anticancer Drug Therapy: A Scoping Review.
Journal
Clinical pharmacokinetics
ISSN: 1179-1926
Titre abrégé: Clin Pharmacokinet
Pays: Switzerland
ID NLM: 7606849
Informations de publication
Date de publication:
17 Aug 2024
17 Aug 2024
Historique:
accepted:
04
08
2024
medline:
17
8
2024
pubmed:
17
8
2024
entrez:
17
8
2024
Statut:
aheadofprint
Résumé
In the last decade, various Machine Learning techniques have been proposed aiming to individualise the dose of anticancer drugs mostly based on a presumed drug effect or measured effect biomarkers. The aim of this scoping review was to comprehensively summarise the research status on the use of Machine Learning for precision dosing in anticancer drug therapy. This scoping review was conducted in accordance with the interim guidance by Cochrane and the Joanna Briggs Institute. We systematically searched the databases Medline (via PubMed), Embase and the Cochrane Library for research articles and reviews including results published after 2016. Results were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist. A total of 17 relevant studies was identified. In 12 of the included studies, Reinforcement Learning methods were used, including Classical, Deep, Double Deep and Conservative Q-Learning and Fuzzy Reinforcement Learning. Furthermore, classical Machine Learning methods were compared in terms of their performance and an artificial intelligence platform based on parabolic equations was used to guide dosing prospectively and retrospectively, albeit only in a limited number of patients. Due to the significantly different algorithm structures, a meaningful comparison between the various Machine Learning approaches was not possible. Overall, this review emphasises the clinical relevance of Machine Learning methods for anticancer drug dose optimisation, as many algorithms have shown promising results enabling model-free predictions with the potential to maximise efficacy and minimise toxicity when compared to standard protocols.
Identifiants
pubmed: 39153056
doi: 10.1007/s40262-024-01409-9
pii: 10.1007/s40262-024-01409-9
doi:
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Bundesministerium für Bildung und Forschung
ID : 16DHBK1022
Informations de copyright
© 2024. The Author(s).
Références
Hu PJH, Wei CP, Cheng TH, Chen JX. Predicting adequacy of vancomycin regimens: a learning-based classification approach to improving clinical decision making. Decis Support Syst. 2007;43:1226–41.
doi: 10.1016/j.dss.2006.02.003
Imai S, Takekuma Y, Miyai T, Sugawara M. A new algorithm optimized for initial dose settings of vancomycin using machine learning. Biol Pharm Bull. 2020;43:188–93.
pubmed: 31902925
doi: 10.1248/bpb.b19-00729
Tang J, Liu R, Zhang Y-L, et al. Application of machine-learning models to predict tacrolimus stable dose in renal transplant recipients. Sci Rep. 2017;7:42192.
Lu J, Deng K, Zhang X, et al. Neural-ODE for pharmacokinetics modeling and its advantage to alternative machine learning models in predicting new dosing regimens. iScience. 2021;24:102804.
pubmed: 34308294
pmcid: 8283337
doi: 10.1016/j.isci.2021.102804
You Dubout W. An algorithmic approach to personalized drug concentration predictions. Lausanne: EPFL; 2014.
Stankevičiūtė K, Woillard JB, Peck RW, et al. Bridging the worlds of pharmacometrics and machine learning. Clin Pharmacokinet. 2023;62:1551–65.
pubmed: 37803104
doi: 10.1007/s40262-023-01310-x
Chen S, Peng Y, Qin A, et al. MR-based synthetic CT image for intensity-modulated proton treatment planning of nasopharyngeal carcinoma patients. Acta Oncol. 2022;61:1417–24.
pubmed: 36305424
doi: 10.1080/0284186X.2022.2140017
The 2022 AAPM Annual Meeting Program. Med Phys. 2022;49:e113–e982.
Zhao J, Chen Z, Wang J, et al. MV CBCT-based synthetic CT generation using a Deep Learning method for rectal cancer adaptive radiotherapy. Front Oncol. 2021;11: 655325.
pubmed: 34136391
pmcid: 8201514
doi: 10.3389/fonc.2021.655325
Men K, Zhang T, Chen X, et al. Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning. Phys Med. 2018;50:13–9.
pubmed: 29891089
doi: 10.1016/j.ejmp.2018.05.006
Kawata Y, Arimura H, Ikushima K, et al. Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy. Phys Med. 2017;42:141–9.
pubmed: 29173908
doi: 10.1016/j.ejmp.2017.08.012
Kawula M, Purice D, Li M, et al. Dosimetric impact of deep learning-based CT auto-segmentation on radiation therapy treatment planning for prostate cancer. Radiat Oncol. 2022;17:21.
pubmed: 35101068
pmcid: 8805311
doi: 10.1186/s13014-022-01985-9
Osman AFI, Tamam NM. Attention-aware 3D U-Net convolutional neural network for knowledge-based planning 3D dose distribution prediction of head-and-neck cancer. J Appl Clin Med Phys. 2022;23: e13630.
pubmed: 35533234
pmcid: 9278691
doi: 10.1002/acm2.13630
Frederick A, Roumeliotis M, Grendarova P, Quirk S. Performance of a knowledge-based planning model for optimizing intensity-modulated radiotherapy plans for partial breast irradiation. J Appl Clin Med Phys. 2022;23: e13506.
pubmed: 34936195
doi: 10.1002/acm2.13506
de Dios NR, Moñino AM, Liu C, et al. Machine learning-based automated planning for hippocampal avoidance prophylactic cranial irradiation. Clin Transl Oncol. 2023;25:503–9.
doi: 10.1007/s12094-022-02963-z
Peters M, Godfrey C, McInerney P, Munn Z, Tricco A, Khalil H. Chapter 11: scoping reviews (2020 version). 2020. In: JBI manual for evidence synthesis. JBI; 2020. https://synthesismanual.jbi.global . Accessed 11 Dec 2023.
Tricco AC, Lillie E, Zarin W, et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med. 2018;169:467–73.
pubmed: 30178033
doi: 10.7326/M18-0850
Rayyan-AI powered tool for systematic literature reviews. https://www.rayyan.ai/ .
Teplytska O. Review protocol; 2023. https://osf.io/qm3yr/ .
Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372: n71.
pubmed: 33782057
pmcid: 8005924
doi: 10.1136/bmj.n71
Ribba B, Kaloshi G, Peyre M, et al. A tumor growth inhibition model for low-grade glioma treated with chemotherapy or radiotherapy. Clin Cancer Res. 2012;18:5071–80.
pubmed: 22761472
doi: 10.1158/1078-0432.CCR-12-0084
Yang CY, Shiranthika C, Wang CY, et al. Reinforcement learning strategies in cancer chemotherapy treatments: a review. Comput Methods Progr Biomed. 2023;229: 107280.
doi: 10.1016/j.cmpb.2022.107280
Poweleit EA, Vinks AA, Mizuno T. Artificial intelligence and machine learning approaches to facilitate therapeutic drug management and model-informed precision dosing. Ther Drug Monit. 2023;45:143–50.
pubmed: 36750470
pmcid: 10378651
doi: 10.1097/FTD.0000000000001078
Watkins CJ, Dayan P. Technical note: Q-learning. Mach Learn. 1992;8:279–92.
doi: 10.1007/BF00992698
Yazdjerdi P, Meskin N, Al-Naemi M, et al. Reinforcement learning-based control of tumor growth under anti-angiogenic therapy. Comput Methods Progr Biomed. 2019;173:15–26.
doi: 10.1016/j.cmpb.2019.03.004
Drexler DA, Sápi J, Szeles A, et al. Flat control of tumor growth with angiogenic inhibition. In: 7th IEEE International Symposium 2012. p. 179–83.
Sápi J, Drexler DA, Harmati I, et al. Linear state-feedback control synthesis of tumor growth control in antiangiogenic therapy. In: 10th IEEE International Symposium 2014. p. 143–8.
Drexler DA, Kovács L, Sápi J, et al. Model-based analysis and synthesis of tumor growth under angiogenic inhibition: a case study*. IFAC Proc Vol. 2011;44:3753–8.
doi: 10.3182/20110828-6-IT-1002.02107
Ebrahimi Zade A, Shahabi Haghighi S, Soltani M. Reinforcement learning for optimal scheduling of glioblastoma treatment with temozolomide. Comput Methods Progr Biomed. 2020;193: 105443.
doi: 10.1016/j.cmpb.2020.105443
Stamatakos GS, Antipas VP, Uzunoglu NK. A spatiotemporal, patient individualized simulation model of solid tumor response to chemotherapy in vivo: the paradigm of glioblastoma multiforme treated by temozolomide. IEEE Trans Biomed Eng. 2006;53:1467–77.
pubmed: 16916081
doi: 10.1109/TBME.2006.873761
de Carlo A, Tosca EM, Fantozzi M, Magni P. Reinforcement learning and PK-PD models integration to personalize the adaptive dosing protocol of erdafitinib in patients with metastatic urothelial carcinoma. Clin Pharmacol Ther. 2024.
Dosne AG, Valade E, Stuyckens K, et al. Population pharmacokinetics of total and free erdafitinib in adult healthy volunteers and cancer patients: analysis of phase 1 and phase 2 studies. J Clin Pharmacol. 2020;60:515–27.
pubmed: 31742712
doi: 10.1002/jcph.1547
Dosne AG, Valade E, Stuyckens K, et al. Erdafitinib’s effect on serum phosphate justifies its pharmacodynamically guided dosing in patients with cancer. CPT Pharmacometr Syst Pharmacol. 2022;11:569–80.
doi: 10.1002/psp4.12727
Janssen Pharmaceutical Companies. BALVERSA (erdafitinib) tablets, for oral use initial U.S. approval: 2019. 2019.
Padmanabhan R, Meskin N, Haddad WM. Reinforcement learning-based control of drug dosing for cancer chemotherapy treatment. Math Biosci. 2017;293:11–20.
pubmed: 28822813
doi: 10.1016/j.mbs.2017.08.004
Padmanabhan R, Meskin N, Haddad WM. Learning-based control of cancer chemotherapy treatment. IFAC-PapersOnLine. 2017;50:15127–32.
doi: 10.1016/j.ifacol.2017.08.2247
Padmanabhan R, Meskin N, Haddad WM. 9—Reinforcement learning-based control of drug dosing with applications to anesthesia and cancer therapy. In: Control applications for biomedical engineering systems. Academic Press: New York; 2020. p. 251–97.
doi: 10.1016/B978-0-12-817461-6.00009-3
Batmani Y, Khaloozadeh H. Optimal chemotherapy in cancer treatment: state dependent Riccati equation control and extended Kalman filter. Optim Control Appl Methods. 2013;34:562–77.
doi: 10.1002/oca.2039
de Pillis L, Radunskaya A. The dynamics of an optimally controlled tumor model: a case study. Math Comput Model. 2003;37:1221–44.
doi: 10.1016/S0895-7177(03)00133-X
Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 30th edn. 2016.
Yauney G, Shah P. Reinforcement learning with action-derived rewards for chemotherapy and clinical trial dosing regimen selection. In: Proceedings of the 3rd Machine Learning for Healthcare Conference. Reinforcement Learning with Action-Derived Rewards for Chemotherapy and Clinical Trial Dosing Regimen Selection. PMLR; 2018. p. 161–226.
Ribba B, Dudal S, Lavé T, Peck RW. Model-informed artificial intelligence: reinforcement learning for precision dosing. Clin Pharmacol Ther. 2020;107:853–7.
pubmed: 31955414
doi: 10.1002/cpt.1777
Ricard D, Kaloshi G, Amiel-Benouaich A, et al. Dynamic history of low-grade gliomas before and after temozolomide treatment. Ann Neurol. 2007;61:484–90.
pubmed: 17469128
doi: 10.1002/ana.21125
Peyre M, Cartalat-Carel S, Meyronet D, et al. Prolonged response without prolonged chemotherapy: a lesson from PCV chemotherapy in low-grade gliomas. Neuro Oncol. 2010;12:1078–82.
pubmed: 20488959
pmcid: 3018918
doi: 10.1093/neuonc/noq055
Eastman B, Przedborski M, Kohandel M. Reinforcement learning derived chemotherapeutic schedules for robust patient-specific therapy. Sci Rep. 2021;11:17882.
pubmed: 34504141
pmcid: 8429726
doi: 10.1038/s41598-021-97028-6
Panetta JC. A mathematical model of breast and ovarian cancer treated with paclitaxel. Math Biosci. 1997;146:89–113.
pubmed: 9348741
doi: 10.1016/S0025-5564(97)00077-1
Panetta JC, Adam J. A mathematical model of cycle-specific chemotherapy. Math Comput Model. 1995;22:67–82.
doi: 10.1016/0895-7177(95)00112-F
Huo L, Tang Y. Multi-objective deep reinforcement learning for personalized dose optimization based on multi-indicator experience replay. Appl Sci. 2023;13:325.
doi: 10.3390/app13010325
Mashayekhi H, Nazari M, Jafarinejad F, Meskin N. Deep reinforcement learning-based control of chemo-drug dose in cancer treatment. Comput Methods Progr Biomed. 2024;243: 107884.
doi: 10.1016/j.cmpb.2023.107884
Treesatayapun C, Muñoz-Vázquez AJ. Optimal drug-dosing of cancer dynamics with fuzzy reinforcement learning and discontinuous reward function. Eng Appl Artif Intell. 2023;120: 105851.
doi: 10.1016/j.engappai.2023.105851
Treesatayapun C, Muñoz-Vázquez AJ, Suyaroj N. Reinforcement learning optimal control with semi-continuous reward function and fuzzy-rules networks for drug administration of cancer treatment. Soft Comput. 2023;27:17347–56.
doi: 10.1007/s00500-023-08068-1
Ekpenyong ME, Etebong PI, Jackson TC, Udofa EM. Modelling drugs interaction in treatment-experienced patients on antiretroviral therapy. Soft Comput. 2020;24:17349–64.
doi: 10.1007/s00500-020-05024-1
Sharifi M, Moradi H. Nonlinear composite adaptive control of cancer chemotherapy with online identification of uncertain parameters. Biomed Signal Process Control. 2019;49:360–74.
doi: 10.1016/j.bspc.2018.07.009
Rihan FA, Velmurugan G. Dynamics of fractional-order delay differential model for tumor-immune system. Chaos Solitons Fractals. 2020;132: 109592.
doi: 10.1016/j.chaos.2019.109592
Babaei N, Salamci MU. Personalized drug administration for cancer treatment using model reference adaptive control. J Theor Biol. 2015;371:24–44.
pubmed: 25665717
doi: 10.1016/j.jtbi.2015.01.038
Alsaadi FE, Yasami A, Volos C, et al. A new fuzzy reinforcement learning method for effective chemotherapy. Mathematics. 2023;11:477.
doi: 10.3390/math11020477
Maier C, Hartung N, Kloft C, et al. Reinforcement learning and Bayesian data assimilation for model-informed precision dosing in oncology. CPT Pharmacometr Syst Pharmacol. 2021;10:241–54.
doi: 10.1002/psp4.12588
Joerger M, Kraff S, Huitema ADR, et al. Evaluation of a pharmacology-driven dosing algorithm of 3-weekly paclitaxel using therapeutic drug monitoring: a pharmacokinetic-pharmacodynamic simulation study. Clin Pharmacokinet. 2012;51:607–17.
pubmed: 22804749
doi: 10.1007/BF03261934
Shiranthika C, Chen K-W, Wang C-Y, et al. Supervised optimal chemotherapy regimen based on offline reinforcement learning. IEEE J Biomed Health Inform. 2022;26:4763–72.
pubmed: 35714083
doi: 10.1109/JBHI.2022.3183854
Kozłowska E, Suwiński R, Giglok M, et al. Mathematical model predicts response to chemotherapy in advanced non-resectable non-small cell lung cancer patients treated with platinum-based doublet. PLoS Comput Biol. 2020;16: e1008234.
pubmed: 33017420
pmcid: 7561182
doi: 10.1371/journal.pcbi.1008234
Nicolò C, Périer C, Prague M, et al. Machine learning and mechanistic modeling for prediction of metastatic relapse in early-stage breast cancer. JCO Clin Cancer Inform. 2020;4:259–74.
pubmed: 32213092
doi: 10.1200/CCI.19.00133
Yu Z, Ye X, Liu H, et al. Predicting lapatinib dose regimen using machine learning and deep learning techniques based on a real-world study. Front Oncol. 2022;12: 893966.
pubmed: 35719963
pmcid: 9203846
doi: 10.3389/fonc.2022.893966
Cauvin C, Bourguignon L, Carriat L, et al. Machine-learning exploration of exposure–effect relationships of cisplatin in head and neck cancer patients. Pharmaceutics. 2022;14:2509.
RECIST 1.1 criteria. https://recist.eortc.org/recist-1-1-2/ . Accessed 03 May 2024.
Common Terminology Criteria for Adverse Events (CTCAE) v5.0. https://ctep.cancer.gov/protocolDevelopment/electronic_applications/ctc.htm#ctc_60 . Accessed 27 Dec 2023.
Blasiak A, Khong J, Kee T. CURATE.AI: optimizing personalized medicine with artificial intelligence. SLAS Technol. 2020;25:95–105.
pubmed: 31771394
doi: 10.1177/2472630319890316
Lee DK, Chang VY, Kee T, et al. Optimizing combination therapy for acute lymphoblastic leukemia using a phenotypic personalized medicine digital health platform: retrospective optimization individualizes patient regimens to maximize efficacy and safety. SLAS Technol. 2017;22:276–88.
pubmed: 27920397
doi: 10.1177/2211068216681979
Pantuck AJ, Lee D-K, Kee T, et al. Modulating BET bromodomain inhibitor ZEN-3694 and enzalutamide combination dosing in a metastatic prostate cancer patient using CURATE.AI, an artificial intelligence platform. Adv Ther. 2018;1:1800104.
doi: 10.1002/adtp.201800104
Overview of the PRO-CTCAE. https://healthcaredelivery.cancer.gov/pro-ctcae/overview.html . Accessed 26 July 2024.
Mueller-Schoell A, Groenland SL, Scherf-Clavel O, et al. Therapeutic drug monitoring of oral targeted antineoplastic drugs. Eur J Clin Pharmacol. 2021;77:441–64.
pubmed: 33165648
doi: 10.1007/s00228-020-03014-8
Demoor-Goldschmidt C, de Vathaire F. Review of risk factors of secondary cancers among cancer survivors. Br J Radiol. 2019;92:20180390.
pubmed: 30102558
doi: 10.1259/bjr.20180390
Cheung WY. Difficult to swallow: issues affecting optimal adherence to oral anticancer agents. Am Soc Clin Oncol Educ Book. 2013;33:265–70.
Seiger K, Mostaghimi A, Silk AW, et al. Association of rising cost and use of oral anticancer drugs with Medicare part D spending from 2013 through 2017. JAMA Oncol. 2020;6:154–6.
pubmed: 31697307
doi: 10.1001/jamaoncol.2019.4906
Tosca EM, de Carlo A, Ronchi D, Magni P. Model-informed reinforcement learning for enabling precision dosing via adaptive dosing. Clin Pharmacol Ther. 2024. (Online ahead of print).