Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2023 Apr 21:rs.3.rs-2790858.
doi: 10.21203/rs.3.rs-2790858/v1.

Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer

Affiliations

Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer

Daniel E Spratt et al. Res Sq. .

Update in

  • Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer.
    Spratt DE, Tang S, Sun Y, Huang HC, Chen E, Mohamad O, Armstrong AJ, Tward JD, Nguyen PL, Lang JM, Zhang J, Mitani A, Simko JP, DeVries S, van der Wal D, Pinckaers H, Monson JM, Campbell HA, Wallace J, Ferguson MJ, Bahary JP, Schaeffer EM, Sandler HM, Tran PT, Rodgers JP, Esteva A, Yamashita R, Feng FY. Spratt DE, et al. NEJM Evid. 2023 Aug;2(8):EVIDoa2300023. doi: 10.1056/EVIDoa2300023. Epub 2023 Jun 29. NEJM Evid. 2023. PMID: 38320143 Free PMC article.

Abstract

Background: Androgen deprivation therapy (ADT) with radiotherapy can benefit patients with localized prostate cancer. However, ADT can negatively impact quality of life and there remain no validated predictive models to guide its use.

Methods: Digital pathology image and clinical data from pre-treatment prostate tissue from 5,727 patients enrolled on five phase III randomized trials treated with radiotherapy +/- ADT were used to develop and validate an artificial intelligence (AI)-derived predictive model to assess ADT benefit with the primary endpoint of distant metastasis. After the model was locked, validation was performed on NRG/RTOG 9408 (n = 1,594) that randomized men to radiotherapy +/- 4 months of ADT. Fine-Gray regression and restricted mean survival times were used to assess the interaction between treatment and predictive model and within predictive model positive and negative subgroup treatment effects.

Results: In the NRG/RTOG 9408 validation cohort (14.9 years of median follow-up), ADT significantly improved time to distant metastasis (subdistribution hazard ratio [sHR] = 0.64, 95%CI [0.45-0.90], p = 0.01). The predictive model-treatment interaction was significant (p-interaction = 0.01). In predictive model positive patients (n = 543, 34%), ADT significantly reduced the risk of distant metastasis compared to radiotherapy alone (sHR = 0.34, 95%CI [0.19-0.63], p < 0.001). There were no significant differences between treatment arms in the predictive model negative subgroup (n = 1,051, 66%; sHR = 0.92, 95%CI [0.59-1.43], p = 0.71).

Conclusions: Our data, derived and validated from completed randomized phase III trials, show that an AI-based predictive model was able to identify prostate cancer patients, with predominately intermediate-risk disease, who are likely to benefit from short-term ADT.

Keywords: AI; Prostate cancer; deep learning; digital pathology; phase III clinical trials; predictive biomarker.

PubMed Disclaimer

Conflict of interest statement

S.T., H.H., E.C., J.Z., A. M., D.v.d.W., H.P., R.Y. and A.E. are employees at ArteraD.E.S. reports personal fees from AstraZeneca, Bayer, Boston Scientific, Blue Earth, Elekta, Pfizer, Gamma Tile, Myovant, Novartis, Janssen, and Varian. A.J.A received research funding from Dendreon, Bayer, Pfizer, Novartis, Janssen Oncology, Astellas Pharma, Gilead Sciences, Roche/Genentech, Bristol-Myers Squibb, Constellation Pharmaceuticals, Merck, AstraZeneca, BeiGene, Amgen, and Forma Therapeutics; consulting fees from Bayer, Dendreon, Pfizer, Astellas, AstraZeneca, Merck, Bristol-Myers Squibb, Janssen, FORMA Therapeutics, Novartis, Exelixis, Myovant Sciences, and GoodRx; travel support from Astellas; has patents for circulating tumor cell novel capture technology. J.D.T received research funding from Bayer and Myriad. Personal fees from Myriad, Myovant, and Boston Scientific. P.L.N. received personal fees from Janssen, Boston Scientific, Bayer, Blue Earth, and Nanocan, equity in Nanocan, and research Funding from Astellas, Bayer, Janssen. J.L. received consulting fees from Janssen Oncology, Astellas Pharma, Gilead Sciences, Pfizer, Arvinas, 4D Pharma, Sanofi-Aventis, AstraZeneca. J.P.S. received research funding from Intuitive Surgical and has stock in Protean Biosciences, Alpenglow Biosciences and Triopsy Medical. E.M.S. is a consultant for Lantheus, Pfizer, Astellas. J.P. is an expert for the advocacy group Coalition Priorité Cancer. L.S. reports personal fees from Varian. L.B. reports personal fees from Blue Earth and Pfizer; travel and meeting support from SWOG and ASTRO. H.M.S. reports consulting fees from Janssen and serves as Board Member and President-Elect on the Board of Directors for ASTRO. P.T.T. received research funding from Astellas, Bayer Healthcare, and RefleXion Medical Inc; personal fees from Bayer Healthcare, RefleXion, Noxopharm, Janssen-Taris Biomedical, Myovant and AstraZeneca; and has a patent 9114158 - Compounds and Methods of Use in Ablative Radiotherapy licensed to Natsar Pharm. F.Y.F is an advisor to and holds equity in Artera and is a consultant for Janssen, Myovant, SerImmune, Bayer, Novartis, Tempus, Varian, Blue Earth Diagnostics and Exact Sciences. No other potential conflict of interest relevant to this article was reported.

Figures

Figure 1
Figure 1
CONSORT flow diagram for NRG/RTOG 9408 (validation set). ST-ADT = short-term androgen-deprivation therapy; RT = radiotherapy.
Figure 2
Figure 2
Cumulative incidence in the validation cohort, NRG/RTOG 9408, histopathology-imaged patients by AI-predictive model subgroups for A) distant metastasis and B) prostate cancer-specific mortality. Est. = estimated; DM = distant metastasis; sHR = subdistribution hazard ratio; CI = confidence interval; p = p-value; RT = radiotherapy; ST-ADT = short-term androgen-deprivation therapy; PCSM = prostate cancer-specific mortality.
Figure 3
Figure 3
Forest plots for all endpoints in positive and negative predictive model groups of NRG/RTOG 9408 (validation set) for all patients. RT = radiation therapy; ST-ADT = short-term androgen-deprivation therapy; yr = year; RMST = restricted mean survival time; sHR = subdistribution hazard ratio; CI = confidence interval; N = number of patients; DM = distant metastasis; PCSM = prostate cancer-specific mortality.

References

    1. Jones CU, Pugh SL, Sandler HM, et al. Adding Short-Term Androgen Deprivation Therapy to Radiation Therapy in Men With Localized Prostate Cancer: Long-Term Update of the NRG/RTOG 9408 Randomized Clinical Trial. Int J Radiat Oncol Biol Phys [Internet] 2021;Available from:10.1016/j.ijrobp.2021.08.031 - DOI - PMC - PubMed
    1. Pilepich MV, Winter K, Lawton CA, et al. Androgen suppression adjuvant to definitive radiotherapy in prostate carcinoma–long-term results of phase III RTOG 85 – 31. Int J Radiat Oncol Biol Phys 2005;61(5):1285–90. - PubMed
    1. D’Amico AV, Chen M-H, Renshaw A, Loffredo M, Kantoff PW. Long-term Follow-up of a Randomized Trial of Radiation With or Without Androgen Deprivation Therapy for Localized Prostate Cancer [Internet]. JAMA. 2015;314(12):1291. Available from: 10.1001/jama.2015.8577 - DOI - PubMed
    1. Bolla M, Neven A, Maingon P, et al. Short Androgen Suppression and Radiation Dose Escalation in Prostate Cancer: 12-Year Results of EORTC Trial 22991 in Patients With Localized Intermediate-Risk Disease. J Clin Oncol 2021;39(27):3022–33. - PubMed
    1. Kishan AU, Sun Y, Hartman H, et al. Androgen deprivation therapy use and duration with definitive radiotherapy for localised prostate cancer: an individual patient data meta-analysis. Lancet Oncol [Internet] 2022. [cited 2022 Aug 29];23(2). Available from:https://pubmed.ncbi.nlm.nih.gov/35051385/ - PubMed

Publication types