Nikolaus Schultz

Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology

Abstract Clinical decision-making in oncology is complex, requiring the integration of multimodal data and multidomain expertise. We developed and evaluated an autonomous clinical artificial intelligence (AI) agent leveraging GPT-4 with multimodal precision oncology tools to support personalized clinical decision-making. The system incorporates vision transformers for detecting microsatellite instability and KRAS and BRAF mutations from histopathology slides, MedSAM for radiological image segmentation and web-based search tools such as OncoKB, PubMed and Google. Evaluated on 20 realistic multimodal patient cases, the AI agent autonomously used appropriate tools with 87.5% accuracy, reached correct clinical conclusions in 91.0% of cases and accurately cited relevant oncology guidelines 75.5% of the time. Compared to GPT-4 alone, the integrated AI agent drastically improved decision-making accuracy from 30.3% to 87.2%. These findings demonstrate that integrating language models with precision oncology and search tools substantially enhances clinical accuracy, establishing a robust foundation for deploying AI-driven personalized oncology support systems.

Distinct Genomic Landscapes in Early-Onset and Late-Onset Endometrial Cancer

PURPOSEThe spectrum of somatic mutations among women with endometrial cancer (EC) younger than 50 years (early-onset EC) remains unknown. We investigated distinct somatic mutation patterns among early-onset and late-onset (age ≥ 50 years) EC patients.METHODSThis cohort study included individuals age 18+ years diagnosed with pathologically confirmed EC in the American Association of Cancer Research (AACR) Genomics Evidence Neoplasia Information Exchange (GENIE, v9.1) consortium. We explored tumor mutational burden (TMB) and genomic patterns of EC by age at clinical sequencing using multivariable regression models adjusted for race, ethnicity, histology, sequencing assay, sample type, and TMB.RESULTSAmong 2,425 women with EC, 176 (7.3%) had early-onset EC and 1,923 (79.3%) had nonhypermutated (< 17.78 mutations/Mb) tumors. TMB significantly differed across age and histology groups. Among nonhypermutated ECs, early-onset patients had significantly lower odds of presenting with nonsilent FGFR2 and PIK3R1 somatic mutations compared with late-onset EC patients in adjusted models ( FGFR2: odds ratio [OR] = 0.18, 95% CI, 0.04 to 0.76; PIK3R1: OR = 0.54, 95% CI, 0.31 to 0.92). By contrast, early-onset EC patients had increased odds of presenting with nonsilent CTNNB1 and BRCA2 mutations compared with late-onset patients ( CTNNB1: OR = 3.32, 95% CI, 2.14 to 5.16; BRCA2: OR = 4.01, 95% CI, 1.55 to 10.38). Subsequent analyses stratified by race, ethnicity, and tumor histology identified distinct patterns of APC, KMT2D, KMT2C, and KRAS by race, ethnicity, and PTEN and APC patterns by histologic subtypes.CONCLUSIONEarly-onset EC harbors a unique genomic landscape compared with late-onset disease. A distinct molecular phenotype of early-onset EC provides novel insights into a unique etiology and may yield clinical implications for developing targeted treatment modalities for younger patients.

Multimodal Spatial Profiling Reveals Immune Suppression and Microenvironment Remodeling in Fallopian Tube Precursors to High-Grade Serous Ovarian Carcinoma

Abstract High-grade serous ovarian cancer (HGSOC) originates from fallopian tube (FT) precursors. However, the molecular changes that occur as precancerous lesions progress to HGSOC are not well understood. To address this, we integrated high-plex imaging and spatial transcriptomics to analyze human tissue samples at different stages of HGSOC development, including p53 signatures, serous tubal intraepithelial carcinomas (STIC), and invasive HGSOC. Our findings reveal immune modulating mechanisms within precursor epithelium, characterized by chromosomal instability, persistent IFN signaling, and dysregulated innate and adaptive immunity. FT precursors display elevated expression of MHC class I, including HLA-E, and IFN-stimulated genes, typically linked to later-stage tumorigenesis. These molecular alterations coincide with progressive shifts in the tumor microenvironment, transitioning from immune surveillance in early STICs to immune suppression in advanced STICs and cancer. These insights identify potential biomarkers and therapeutic targets for HGSOC interception and clarify the molecular transitions from precancer to cancer. Significance: This study maps the immune response in FT precursors of HGSOC, highlighting localized IFN signaling, chromosomal instability, and competing immune surveillance and suppression along the progression axis. It provides an explorable public spatial profiling atlas for investigating precancer mechanisms, biomarkers, and early detection and interception strategies. See related commentary by Recouvreux and Orsulic, p. 1093

Obesity-dependent selection of driver mutations in cancer

Obesity is a risk factor for cancer, but whether obesity is linked to specific genomic subtypes of cancer is unknown. We examined the relationship between obesity and tumor genotype in two clinicogenomic corpora. Obesity was associated with specific driver mutations in lung adenocarcinoma, endometrial carcinoma and cancers of unknown primaries, independent of clinical covariates, demographic factors and genetic ancestry. Obesity is therefore a driver of etiological heterogeneity in some cancers.