ArticleJAMA surgery2025
Artificial Intelligence-Powered Spatial Analysis of Immune Phenotypes in Resected Pancreatic Cancer.
Article in JAMA surgery, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 8 papers.
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.
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.
Who cites it
8 citing papers in PubMed.
- Spatial Configuration of Pancreatic Cancer Is Associated with Disease Recurrence after Neoadjuvant Therapy and Curative-Intent Resection.Clinical cancer research : an official journal of the American Association for Cancer Research · 2026Article
- Agentic systems in computational pathology: architectures, evidence, and translational challenges.Journal of translational medicine · 2026Review
- Advances in deciphering intratumoral versus peritumoral heterogeneity of infiltrating lymphocytes in pancreatic cancer: a spatial perspective.Translational oncology · 2026Review
- Review
- Artificial Intelligence for Spatial Immunometabolic Analysis of the Tumor Microenvironment: Current Evidence and Future Directions.Current issues in molecular biology · 2026Review
- Artificial intelligence and immune topography transforming prognostication in pancreatic cancer.Gland surgery · 2026Article
- Epigenetic modulation to overcome immune suppression in pancreatic cancer.Clinical epigenetics · 2026Review
- Cancer-Associated Fibroblast-Targeted Nanomedicine in Solid Tumor Therapy: From Mechanisms of Therapeutic Resistance to Precision Stromal Modulation.International journal of nanomedicine · 2026Review
Corrections and comments
- Commented on by
- Commented on by
Authors and funding
24 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Importance: Although tumor-infiltrating lymphocytes (TILs) have been implicated as prognostic biomarkers across various malignancies, the clinical application remains challenging. This study evaluated the applicability of artificial intelligence (AI)-powered spatial mapping of TIL density for prognostic assessment in resected pancreatic ductal adenocarcinoma (PDAC). Objective: To evaluate the prognostic significance of AI-powered spatial TIL analysis in resected PDAC and its clinical applicability. Design, Setting, and Participants: This cohort study included patients with PDAC who underwent up-front R0 resection at a tertiary referral center between January 2017 and December 2020. Whole-slide images of retrospectively enrolled patients with PDAC and up-front R0 resection were analyzed. An AI-powered whole-slide image analyzer was used for spatial TIL quantification, segmentation of tumor and stroma, and immune phenotype classification as immune-inflamed phenotype, immune-excluded phenotype, or immune-desert phenotype. Study data were analyzed from January 2017 to August 2023. Exposure: Use of AI-powered spatial analysis of the tumor microenvironment in resected PDACs. Main Outcomes and Measures: Tumor microenvironment-related risk factors and their associations with overall survival (OS) and recurrence-free survival (RFS) outcomes were identified. Results: Among 304 patients, the mean (SD) age was 66.8 (9.4) years with 171 male patients (56.3%), and preoperative clinical stages I and II were represented by 54.3% patients (165 of 304) and 45.7% patients (139 of 304), respectively. The TILs in the tumor microenvironment were predominantly concentrated in the stroma, and the median intratumoral TIL and stromal TIL densities were 100.64/mm2 (IQR, 53.25-121.39/mm2) and 734.88/mm2 (IQR, 443.10-911.16/mm2), respectively. Overall, 9.9% of tumors (30 of 304) were immune inflamed, 85.2% (259 of 304) were immune excluded, and 4.9% (15 of 304) were immune desert. The immune-inflamed phenotype was associated with the most prolonged OS (median not reached; P < .001) and RFS (median not reached; P = .001), followed by immune-excluded phenotype and immune-desert phenotype. High intratumoral TIL density was associated with longer OS (median, 52.47 months; 95% CI, 41.98-62.96; P = .004) and RFS (median, 21.67 months; 95% CI, 14.43-28.91; P = .02). A combined analysis of the pathologic stage with immune phenotype predicted better survival of stage II PDAC stratified as immune-inflamed phenotype than stage I PDAC stratified as non-immune-inflamed phenotype. Conclusions and Relevance: Results of this cohort study suggest that the use of AI has markedly condensed the labor-intensive process of TIL assessment, potentially rendering the process more feasible and practical in clinical application. Importantly, the IP may be one of the most important prognostic biomarkers in resected PDACs.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
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.