Evidence map›Paper›PMID 40803139›Full record

ArticleClinical imaging2025

A multimodal automated deep learning-based model for predicting biochemical recurrence of prostate cancer following prostatectomy from baseline MRI, Presurgical clinical covariates.

Benjamin D Simon, Stephanie A Harmon, Katie M Merriman, Jesse Tetreault, Omer T Esengur, Hunter Stecko, Enis C Yilmaz, Lei Clifton, Anshul Thakur, Zoë Blake and 10 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Clinical imaging, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
3citing papers in PubMed, 1 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

3 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Article
  3. The potential of artificial intelligence in clinical trials.European journal of clinical investigation · 2026
    Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

20 authors.

Benjamin D SimonMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA; Institute of Biomedical Engineering, University of Oxford, UK.
Stephanie A HarmonMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Katie M MerrimanMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Jesse TetreaultNVIDIA Corporation, Santa Clara, CA, USA.
Omer T EsengurMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Hunter SteckoMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Enis C YilmazMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Lei CliftonNuffield Department of Population Health, University of Oxford, UK; Big Data Institute, University of Oxford, UK.
Anshul ThakurInstitute of Biomedical Engineering, University of Oxford, UK.
Zoë BlakeUrology Oncology Branch, NCI, NIH, Bethesda, MD, USA.
Maria J MerinoLaboratory of Pathology, NCI, NIH, Bethesda, MD, USA.
Julie Y AnDepartment of Radiology, University of California, San Diego, CA, USA.
Jamie MarkoDepartment of Radiology, Johns Hopkins University, Baltimore, MD, USA.
Yan Mee LawDepartment of Radiology, Singapore General Hospital, Singapore.
Sandeep GurramUrology Oncology Branch, NCI, NIH, Bethesda, MD, USA.
David CliftonInstitute of Biomedical Engineering, University of Oxford, UK.
Bradford J WoodCenter for Interventional Oncology, NCI, NIH, Bethesda, MD, USA; Department of Radiology, Clinical Center, NIH, Bethesda, MD, USA.
Peter L ChoykeMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA.
Peter A PintoUrology Oncology Branch, NCI, NIH, Bethesda, MD, USA.
Baris TurkbeyMolecular Imaging Branch, NCI, NIH, Bethesda, MD, USA. Electronic address: turkbeyi@mail.nih.gov.

Funding

Imaging, image guided biopsy and treatment of prostate cancerZIABC012062 · NCI · DIVISION OF BASIC SCIENCES - NCI · PI TÜRKBEY, BARIS · 2021 to 2025
$1.3M
Intramural NIH HHS ZIA BC012062
6 · The paper itself

Abstract

purposeTo develop a multimodal deep learning-based AI algorithm and investigate its ability to predict BCR of PCa after radical prostatectomy (RP) using MRI and clinical data.

methodsPCa patients (n = 311) underwent prostate MRI prior to RP between January 2008 and December 2018. For each patient, CAPRA-S was calculated. Quantitative imaging features were extracted using methods developed in a previous study. Test set results were assessed independently for each model in the study, using cross-validation of the training set to tune hyperparameters and select features. DeLong's test compared AUROC curve values, and log-rank tests compared BCR-free survival curves.

resultsAcross all patients, the AUROC of the automated multimodal model was 0.74, compared to 0.66 for CAPRA-S. This model had the highest sensitivity at 75 %, with CAPRA-S at 37 %. BCR-free survival curves for the test set were generated for each model. Log-rank tests indicated each model differentiated between patient outcomes (p < 0.05). The automated multimodal model was the only model with p < 0.01. Focusing on intermediate risk patients (CAPRA-S scores 3-5), this automated model was the only model which maintained the ability to differentiate between outcomes (p < 0.01), while all other models and CAPRA-S failed to differentiate intermediate risk BCR outcomes (p > 0.05).

conclusionDevelopment of a multimodal model using quantitative imaging features and clinical covariates revealed that an automated multimodal AI approach most effectively predicts BCR in PCa patients. Based on AUROC and the ability to differentiate between BCR-free survival outcomes with statistical significance in intermediate risk patients, this model outperforms the gold standard postsurgical CAPRA-S risk scores.

Indexed as

Deep LearningMagnetic Resonance ImagingNeoplasm Recurrence, LocalProstatectomyProstatic NeoplasmsAgedHumansMaleMiddle AgedPredictive Value of TestsRetrospective StudiesArtificial intelligenceBiochemical recurrenceMultimodalProstate cancerRadical prostatectomy

Identifiers

PMID40803139
PMCPMC12415651

What OpenQuestion holds

Textmetadata
LicenceTDM
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.