EUVIMEDOpdag EUVIMED
Klinische Studie (Phase III)Multizentrische StudieRandomisierte kontrollierte Studie

Digital Pathology–Based Multimodal Artificial Intelligence Scores and Outcomes in a Randomized Phase III Trial in Men With Nonmetastatic Castration-Resistant Prostate Cancer

Digital Pathology–basierte multimodale KI-Scores und Outcomes in einer randomisierten Phase-III-Studie bei Männern mit nichtmetastasiertem kastrationsresistentem Prostatakarzinom

Felix Y Feng iD, Matthew R Smith, Fred Saad iD, Pooya Mobadersany iD, Shaozhou K Tian, Stephen S F Yip, Joel Greshock, Najat Khan, Margaret K Yu iD, Sharon McCarthy, Sabine D Brookman-May, Ariel B Bourla iD and 9 more

JCO Precision Oncology · 2025-01 · (9)

DOI: 10.1200/po-24-00653 ↗

Auf einen Blick

In der SPARTAN-Studie war ein digitaler Histopathologie-basierter MMAI-Score mit ungünstigeren Outcomes assoziiert. Bei MMAI-Hochrisikopatienten war Apalutamid mit besseren Ergebnissen verbunden.

Fragestellung

Welche Assoziation besteht zwischen einem digital pathologie-basierten MMAI-Score und klinischen Outcomes in der SPARTAN-Studie zu nmCRPC?

Methode

Analyse von Tumor-HE-Schnitten aus SPARTAN; digitale Histopathologie und Baseline-Klinikparameter zur MMAI-Berechnung; Einteilung in Non-High-Risk und High-Risk; Cox-Analysen für MFS, PFS2 und OS sowie Interaktion mit der Behandlung.

Ergebnisse

420 auswertbare Patient:innen. MMAI-Hochrisiko: 63 % (n = 266), Non-High-Risk: 37 % (n = 154). Höherer MMAI-Score war mit kürzerem MFS (HR 1,72), PFS2 (HR 1,57) und OS (HR 1,41) assoziiert. In der Hochrisikogruppe verbesserte Apalutamid MFS (HR 0,19), PFS2 (HR 0,47) und OS (HR 0,6).

Einschränkungen

Patient:innen mit fehlenden klinischen Daten oder unzureichenden Histopathologie-Bildern wurden ausgeschlossen; zusätzliche Validierung erforderlich.

Schlussfolgerung der Autor:innen

MMAI ist ein prognostischer Marker bei nmCRPC und könnte ein prädiktiver Biomarker sein, wobei Hochrisikopatient:innen am meisten von Apalutamid profitieren. Die Autor:innen sehen weitere Validierung als nötig an.

Kernaussagen

  • MMAI-Score war mit kürzerem MFS, PFS2 und OS assoziiert
  • Apalutamid zeigte in der Hochrisikogruppe stärkere Effekte
  • Weitere Validierung des MMAI-Klassifikators wird gefordert

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Klinische Studie (Phase III) in JCO Precision Oncology, 2025-01. Written by Felix Y Feng and 20 co-authors. Institution: Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA. Major MEDLINE topics: Artificial Intelligence, Prostatic Neoplasms, Castration-Resistant, Thiohydantoins. Cited 15 times so far (Crossref); 14 references.

Auf einen BlickAbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

PURPOSE The SPARTAN trial demonstrated that the addition of apalutamide to androgen deprivation therapy improves outcomes among patients with nonmetastatic castration-resistant prostate cancer (nmCRPC). We applied a previously reported digital histopathology–based multimodal artificial intelligence (MMAI) algorithm to estimate clinical outcomes in SPARTAN. METHODS Patients with available hematoxylin and eosin-stained slides from the primary tumor were included. Histopathology slides were digitized. MMAI scores ranging from 0 to 1 were generated from digital histopathology and baseline clinical parameters. Patients were categorized into MMAI non–high-risk and high-risk groups using previously validated cutoffs. Kaplan-Meier estimates were calculated for metastasis-free survival (MFS), second progression-free survival (PFS2), and overall survival (OS); comparisons were performed using Cox proportional hazards regression for treatment arms and MMAI risk. The interaction between treatment arm and risk group was evaluated using a Cox proportional hazards model. RESULTS The study included 420 evaluable patients after excluding those with missing clinical data or inadequate histopathology images. Of these, 63% (n = 266) were MMAI high risk and 37% (n = 154) were non–high risk. MMAI risk score was associated with shorter MFS (hazard ratio [HR], 1.72; P < .005), PFS2 (HR, 1.57; P < .005), and OS (HR, 1.41; P = .02). MMAI high-risk patients receiving apalutamide demonstrated significant improvement in MFS (HR, 0.19; P < .005), PFS2 (HR, 0.47; P < .005), and OS (HR, 0.6; P = .01). The interaction between MMAI risk score and treatment for MFS ( P = .01) and PFS2 ( P = .03) was significant, indicating greater benefit from apalutamide treatment in MMAI high-risk patients. CONCLUSION MMAI is a prognostic marker in nmCRPC and may serve as a predictive biomarker with high-risk patients deriving the greatest benefit from treatment with apalutamide. These results represent the first extension of an MMAI classifier to patients with castration-resistant prostate cancer, warranting additional validation.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceProstatic Neoplasms, Castration-ResistantThiohydantoinsAgedHumansMaleMiddle AgedAndrogen AntagonistsTreatment Outcome

Substances

Androgen AntagonistsapalutamideThiohydantoins

Authors and institutions

  • Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA.
  • Massachusetts General Hospital Cancer Center, Boston, MA.
  • Centre Hospitalier de l'Université de Montréal, Université de Montréal, Montréal, QC, Canada.
  • Janssen Research & Development, New Brunswick, NJ.
  • LMU, University of Munich, Munich, Germany.
  • Artera Inc, Los Altos, CA.

ORCID profiles: Felix Y Feng, Fred Saad, Pooya Mobadersany, Margaret K Yu, Ariel B Bourla, Trevor J Royce, Eric J Small

Cite

APA

Feng, F. Y., Smith, M. R., Saad, F., Mobadersany, P., Tian, S. K., Yip, S. S. F., Greshock, J., Khan, N., Yu, M. K., McCarthy, S., Brookman-May, S. D., Bourla, A. B., Todorovic, T., Yamashita, R., Huang, H. C., Royce, T. J., Showalter, T. N., Griffin, J., Mitani, A., …, & Small, E. J. (2025). Digital Pathology–Based Multimodal Artificial Intelligence Scores and Outcomes in a Randomized Phase III Trial in Men With Nonmetastatic Castration-Resistant Prostate Cancer. JCO Precision Oncology. https://doi.org/10.1200/po-24-00653

Vancouver

Feng FY, Smith MR, Saad F, Mobadersany P, Tian SK, Yip SSF, et al. Digital Pathology–Based Multimodal Artificial Intelligence Scores and Outcomes in a Randomized Phase III Trial in Men With Nonmetastatic Castration-Resistant Prostate Cancer. JCO Precision Oncology. 2025. doi:10.1200/po-24-00653

BibTeX
@article{Feng2025,
  author = {Feng, Felix Y and Smith, Matthew R and Saad, Fred and Mobadersany, Pooya and Tian, Shaozhou K and Yip, Stephen S F and Greshock, Joel and Khan, Najat and Yu, Margaret K and McCarthy, Sharon and Brookman-May, Sabine D and Bourla, Ariel B and Todorovic, Tamara and Yamashita, Rikiya and Huang, Huei-Chung and Royce, Trevor J and Showalter, Timothy N and Griffin, Jacqueline and Mitani, Akinori and Esteva, Andre and Small, Eric J},
  title = {Digital Pathology–Based Multimodal Artificial Intelligence Scores and Outcomes in a Randomized Phase III Trial in Men With Nonmetastatic Castration-Resistant Prostate Cancer},
  journal = {JCO Precision Oncology},
  year = {2025},
  number = {9},
  doi = {10.1200/po-24-00653}
}
Start for free →