30 juni 2025: Bron: Journal of Clinical Oncology april 2025

Een biomarker verkregen door Kunstmatige Intelligentie (afgekort MMAI) kan bij prostaatkankerpatiënten met hoog risico het standaard langjarige gebruik van hormoontherapie van 2 tot 3 jaar naast radiotherapie / bestraling terugbrengen naar een half jaar als zij de biomarker niet bij zich dragen. Dat blijkt uit het toetsen van de MMAI-biomarker in een vergelijkende studie van 6.423 prostaatkankerpatiënten  met hoog risico uit 6 gerandomiseerde fase III studies die werden vergeleken met prostaatkankerpatiënten  met hoog risico van de RTOG-9202 studie over 15 jaar follow-up.

Van de volledige controlegroep was 66% (785 patiënten) MMAI-biomarkerpositief; bij deze patiënten was het percentage uitzaaiingen op afstand (DM) significant lager met langdurige hormoontherapie vergeleken met kortdurende hormoontherapie (HR 0,55; 95% BI [0,41; 0,73]; p < 0,001).
Bij MMAI-biomarkernegatieve mannen (407 patiënten) werd geen dergelijk voordeel waargenomen (HR 1,06; 95% BI [0,61; 1,84]; p = 0,84).
Het 15-jaars risicoverschil tussen langdurige en kortdurende hormoontherapie bedroeg 14% bij MMAI-biomarkerpositieve mannen, vergeleken met een verschil van 0% tussen de behandelduur bij biomarker negatieve patiënten. 
De MMAI-biomarker was op zichzelf ook prognostisch voor uitzaaiingen op afstand (DM), ongeacht de behandelingsduur (HR 2,35; 95% BI [1,72; 3,19]; p < .001).
Het 15-jaars DM-percentage in de biomarker-negatieve groep was 11%, vergeleken met 26% in de biomarker-positieve groep (p < .001).

Uit de perspresentatie een stukje vertaald:

"Een standaardbehandeling voor mannen met een hoog risico op prostaatkanker is 2 tot 3 jaar hormoontherapie plus bestraling, maar dergelijke langdurige hormoontherapie gaat gepaard met een reeks bijwerkingen, waaronder een verhoogd cardiovasculair risico, metabolisch risico, vermoeidheid en spierverlies, osteoporose en fractuurrisico, en opvliegers", aldus Andrew J. Armstrong, MD, FACP, van het Duke Cancer Institute, die de nieuwe studie leidde.

"Het ontwikkelen van een biomarker om de mannen te identificeren die deze intensievere behandeling echt nodig hebben, kan nuttig zijn om meer precisie medische benaderingen mogelijk te maken voor het gebruik van hormoontherapie in deze setting."
De van het MMAI afgeleide biomarker, voegde hij eraan toe, is de eerste gevalideerde voorspellende biomarker die de duur van hormoontherapie bij prostaatkanker kan helpen bepalen.
"Ongeveer een derde van de mannen met een hoog risico op gelokaliseerde prostaatkanker heeft geen 2 tot 3 jaar hormoontherapie nodig en heeft uitstekende resultaten met een kortere behandelperiode van 6 maanden in combinatie met bestraling", aldus Dr. Armstrong. “Deze kortere behandeling voor AI-biomarker-negatieve patiënten brengt de genezingspercentages niet in gevaar en verhoogt de risico's op uitzaaiingen op afstand niet. Bovendien heeft deze behandeling duidelijke voordelen voor het verminderen van de toxiciteit en bijwerkingen van langdurige hormoontherpie”.

het abstract is summier maar onder bepaalde voorwaarden is het wel verkrijgbaar, zie in abstract:

Development and Validation of an Artificial Intelligence Digital Pathology Biomarker to Predict Benefit of Long-Term Hormonal Therapy and Radiotherapy in Men With High-Risk Prostate Cancer Across Multiple Phase III Trials

PublicationJournal of Clinical Oncology


Abstract

Purpose

Long-term androgen deprivation therapy (ADT) improves survival in men with high-risk localized prostate cancer (PCa) receiving radiotherapy (RT). Predictive biomarkers are needed to guide ADT duration.

Methods

A multimodal artificial intelligence (MMAI)–derived predictive biomarker was trained for long-term (LT) versus short-term (ST) ADT using pretreatment digital prostate biopsy images and clinical data (age, prostate-specific antigen, Gleason, and T stage) from six NRG Oncology phase III randomized radiotherapy trials. The novel MMAI-derived biomarker was developed to predict the differential benefit of LT-ADT on the primary end point, distant metastasis (DM). MMAI predictive utility was validated on a seventh randomized trial, RTOG 9202 (N = 1,192), which randomly assigned men to RT + ST-ADT (4 months) versus RT + LT-ADT (28 months). Fine-Gray and cumulative incidence analyses for DM, and secondarily, death with DM, were performed. Deaths without DM were treated as competing risks.

Results

In the validation cohort (median follow-up, 17.2 years), LT-ADT significantly improved DM from 26% to 17% (subdistribution hazard ratio , 0.64 [95% CI, 0.50 to 0.82], P < .001). A significant biomarker-treatment predictive interaction was observed (P = .04) for DM, whereby MMAI biomarker–positive men (n = 785, 66%) had reduced DM with LT-ADT versus ST-ADT (sHR, 0.55 [95% CI, 0.41 to 0.73], P < .001), whereas no treatment benefit was observed for MMAI biomarker–negative men (n = 407; sHR, 1.06 [95% CI, 0.61 to 1.84], P = .84). The estimated 15-year DM risk difference between RT + LT-ADT and RT + ST-ADT was 14% in MMAI biomarker–positive men and 0% in MMAI biomarker–negative men. The MMAI biomarker was also prognostic for DM, irrespective of treatment (sHR, 2.35 [95% CI, 1.72 to 3.19], P < .001).

Conclusion

To our knowledge, the MMAI model is the first validated predictive biomarker to guide ADT duration with RT in localized/locally advanced PCa. Approximately one third of men with high-risk PCa could safely be spared the additional 24 months of ADT and the associated morbidity.

Get full access to this article

View all available purchase options and get full access to this article.

Data Sharing Statement

Data Supplement

Authors retain all rights in any data supplements associated with their articles.

The ideas and opinions expressed in this Data Supplement do not necessarily reflect those of the American Society of Clinical Oncology (ASCO). The mention of any product, service, or therapy in this Data Supplement should not be construed as an endorsement of the products mentioned. It is the responsibility of the treating physician or other health care provider, relying on independent experience and knowledge of the patient, to determine drug dosages and the best treatment for the patient. Readers are advised to check the appropriate medical literature and the product information currently provided by the manufacturer of each drug to be administered to verify approved uses, the dosage, method, and duration of administration, or contraindications. Readers are also encouraged to contact the manufacturer with questions about the features or limitations of any products. ASCO and JCO assume no responsibility for any injury or damage to persons or property arising out of or related to any use of the material contained in this publication or to any errors or omissions. Readers should contact the corresponding author with any comments related to Data Supplement materials.

Support

Supported by grants U10CA180822 (NRG Oncology SDMC), UG1CA189867 (NCORP), U10CA180868 (NRG Oncology Operations), U24CA196067 (NRG Specimen Bank) from the National Cancer Institute (NCI). A.J.A.'s contributions were funded, in part, by NCI R01: 5R01CA233585-05. This work was also funded by Artera, Inc.

Clinical Trial Information

Data Sharing Statement

A data sharing statement provided by the authors is available with this article at DOI https://doi.org/10.1200/JCO.24.00365. All data will be made available per the National Clinical Trials Network Data Archive rules. The link for the archive is https://nctn-data-archive.nci.nih.gov/. The source code may be made available, subject to intellectual property constraints, by contacting A.E. (aesteva@artera.ai), A.J.A. (andrew.armstrong@duke.edu), or P.L.N. (paul_nguyen@dfci.harvard.edu).

Authors' Disclosures of Potential Conflicts of Interest

Development and Validation of an Artificial Intelligence Digital Pathology Biomarker to Predict Benefit of Long-Term Hormonal Therapy and Radiotherapy in Men With High-Risk Prostate Cancer Across Multiple Phase III Trials

The following represents disclosure information provided by authors of this manuscript. All relationships are considered compensated unless otherwise noted. Relationships are self-held unless noted. I = Immediate Family Member, Inst = My Institution. Relationships may not relate to the subject matter of this manuscript. For more information about ASCO's conflict of interest policy, please refer to www.asco.org/rwc or ascopubs.org/jco/authors/author-center.
Open Payments is a public database containing information reported by companies about payments made to US-licensed physicians (Open Payments).

Andrew J. Armstrong

Consulting or Advisory Role: Bayer, Pfizer, Astellas Scientific and Medical Affairs Inc, AstraZeneca, Merck, Bristol-Myers Squibb, Janssen, Novartis, Exelixis, Myovant Sciences, GoodRx, Cytogen
Research Funding: Bayer (Inst), Pfizer (Inst), Novartis (Inst), Janssen Oncology (Inst), Astellas Pharma (Inst), Bristol-Myers Squibb (Inst), Merck (Inst), AstraZeneca (Inst), Bristol-Myers Squibb (Inst), Amgen (Inst), Syntrix Biosystems (Inst)
Patents, Royalties, Other Intellectual Property: Circulating tumor cell novel capture technology (Inst)
Travel, Accommodations, Expenses: Astellas Scientific and Medical Affairs Inc

Vinnie Y.T. Liu

Employment: Artera, Decipher Biosciences
Stock and Other Ownership Interests: Artera, Decipher Biosciences
Research Funding: Artera, Decipher Biosciences
Travel, Accommodations, Expenses: Artera, Decipher Biosciences

Emmalyn Chen

Employment: Artera, Inc
Stock and Other Ownership Interests: Artera, Inc

Jeffry P. Simko

Stock and Other Ownership Interests: Protean Biodiagnostics, Alpenglow biosciences, Triopsy Medical Inc
Consulting or Advisory Role: Uro-1
Research Funding: Intuitive Surgical (Inst)

Sandy DeVries

Employment: University of California, San Francisco

Oliver Sartor

Stock and Other Ownership Interests: Lilly, Abbvie, Cardinal Health, United Health Group, Clarity Pharmaceuticals, Convergent Therapeutics, Ratiopharm, Telix Pharmaceuticals, Abbott Laboratories, BioNTech SE, Perspective, ARTbio
Honoraria: Lantheus Medical Imaging, Intellisphere, Clarity Pharmaceuticals, Advancell, Telix Pharmaceuticals, Sanofi, Pfizer, AstraZeneca, Ratiopharm, Actinium Pharmaceuticals, Convergent Therapeutics, Point Therapeutics
Consulting or Advisory Role: Bayer, Sanofi, AstraZeneca, Pfizer, Astellas Pharma, Novartis, Clarity Pharmaceuticals, Fusion Pharmaceuticals, Isotopen Technologien, Janssen, Point Biopharma, Telix Pharmaceuticals, Amgen, Ratiopharm, Advancell, Lantheus Medical Imaging, Telix Pharmaceuticals, ARTbio, Actinium Pharmaceuticals
Research Funding: Bayer (Inst), Merck (Inst), InVitae (Inst), AstraZeneca (Inst), Janssen, Lantheus Medical Imaging (Inst), Sanofi (Inst), Novartis (Inst), POINT Biopharma (Inst)
Expert Testimony: Sanofi
Travel, Accommodations, Expenses: Bayer, Sanofi, Lantheus Medical Imaging

Howard M. Sandler

Consulting or Advisory Role: Janssen
Other Relationship: Caribou Publishing

Osama Mohamad

Employment: MD Anderson Cancer Center
Honoraria: Private Medical

Huei-Chung Huang

Employment: Artera Inc, Los Altos, CA
Stock and Other Ownership Interests: Artera Inc, Los Altos, CA

Jacqueline Griffin

Employment: Artera
Stock and Other Ownership Interests: Artera

Rikiya Yamashita

Employment: Artera
Stock and Other Ownership Interests: Artera

Andre Esteva

Employment: Artera
Leadership: Artera
Stock and Other Ownership Interests: Artera
Patents, Royalties, Other Intellectual Property: Artera's founding IP - multi-modal AI technology for cancer therapy personalization, using digital pathology
Travel, Accommodations, Expenses: Artera

Phuoc T. Tran

Honoraria: Reflexion Medical
Consulting or Advisory Role: Astellas Pharma, Regeneron, GenomeDx, Reflexion Medical, Dendreon, Reflexion Medical, Noxopharm, Janssen, Myovant Sciences, AstraZeneca, Bayer Health, Lantheus Medical Imaging
Research Funding: Astellas Pharma (Inst), Reflexion Medical (Inst), Bayer Health (Inst)
Patents, Royalties, Other Intellectual Property: Compounds and Methods of Use in Ablative Radiotherapy. Patent filed 3/9/2012. PCT/US2012/028475. PCT/WO/2012/122471
Travel, Accommodations, Expenses: Reflexion Medical

Daniel E. Spratt

Consulting or Advisory Role: Janssen Oncology, AstraZeneca, Boston Scientific, Bayer, Blue Earth Diagnostics, Pfizer, Astellas Scientific and Medical Affairs Inc, Novartis
Research Funding: Janssen (Inst)
Uncompensated Relationships: NCCN

Steve P. Lee

Honoraria: Novocure
Travel, Accommodations, Expenses: Galera Therapeutics

Rana McKay

Consulting or Advisory Role: Janssen, Novartis, Tempus, Exelixis, Pfizer, Bristol-Myers Squibb, Astellas Medivation, Dendreon, Bayer, Sanofi, Merck, Vividion Therapeutics, Calithera Biosciences, AstraZeneca, Myovant Sciences, Caris Life Sciences, Sorrento Therapeutics, AVEO, Seagen, Telix Pharmaceuticals, Lilly, Blue Earth Diagnostics, Ambrx, Arcus Biosciences, Sumitomo Pharma Oncology, Ambrx, Esiai, NeoMorph
Research Funding: Bayer (Inst), Tempus (Inst), AstraZeneca (Inst), Exelixis (Inst), Bristol Myers Squibb (Inst), Oncternal Therapeutics (Inst), Artera (Inst)

Todd Morgan

Consulting or Advisory Role: Stratify Genomics, Tempus, Foundation Medicine, ClevelandDx
Research Funding: MDxHealth (Inst)

Felix Y. Feng

Stock and Other Ownership Interests: Artera, Serimmune, Bluestar Genomics
Consulting or Advisory Role: Janssen Biotech, Astellas Pharma, SerImmune, Foundation Medicine, Exact Sciences, Bristol Myers Squibb, Varian Medical Systems, Novartis, Roivant, Bayer, BlueStar Genomics, Myovant Sciences, Tempus, Artera, Bristol Myers Squibb (BMS), POINT Biopharma
Research Funding: Zenith Epigenetics

Paul L. Nguyen

Stock and Other Ownership Interests: Volatilyx (I), Nanocan Therapeutics, Stratagen Bio, Reversal Therapeutics, Telerad Oncology
Consulting or Advisory Role: Bayer, Blue Earth Diagnostics, Boston Scientific, Janssen Oncology, Myovant Sciences, Nanocan Therapeutics, AIQ Solutions, Novartis, Theranano
Research Funding: Astellas Pharma, Janssen, Bayer
Patents, Royalties, Other Intellectual Property: Wife has a patent on volatile diagnostics of infections (I)
No other potential conflicts of interest were reported.

References:

  1. Armstrong AJ, Liu VYT, Selvaraju RR, et al. Development and validation of an AI digital pathology biomarker to predict benefit of long-term hormonal therapy and radiotherapy in men with high-risk prostate cancer across multiple phase 3 trials. J Clin Oncol. Published online April 16, 2025.
  2. Esteva A, Feng J, van der Wal D, et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digit Med. 2022;5(1):71.
  3. Spratt DE, Tang S, Sun Y, et al. Artificial intelligence predictive model for hormone therapy use in prostate cancer. NEJM Evid. 2023;2(8):a2300023.


Plaats een reactie ...

Reageer op "Biomarker via kunstmatige intelligentie verkregen kan de behandelingsduur van hormoontherapie van patiënten met prostaatkanker met een hoog risico verkorten"


Gerelateerde artikelen
 

Gerelateerde artikelen

Biomarker via kunstmatige >> Intermitterende hormoontherapie >> Hormoontherapie plus palbociclib >> Hormoontherapie na radiotherapie >> Hormoonbehandeling regelmatig >> Hormoontherapie plus bestraling >> APD - Androgen Deprivation >> Hormoontherapie bij patiënten >> Hormoontherapie bij oudere >> Hormoontherapie bij mannen >>