BACKGROUND
Recurrence is a key oncologic endpoint but is difficult to automatically capture from electronic health records (EHR).
METHODS
We evaluated rule-based algorithms to detect recurrence and its timing using a publicly available clinico-genomic database of patients with breast, colorectal, non-small cell lung, or pancreatic cancer. Algorithms evaluated varying anchor dates, defined as the time at which patients were assumed eligible to recur for the purposes of the algorithm, including diagnosis and four-, six-, and twelve-months post-diagnosis, as well as varying criteria for subsequent evidence of cancer from radiology, pathology, medical oncology assessments, or cancer-directed regimen initiation. Algorithm-derived recurrence results were compared with manually curated institutional data. Performance was measured by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and concordance of recurrence timing.
RESULTS
The best algorithms, anchored at six months post-diagnosis and requiring two reports demonstrated high sensitivity (≥0.95), PPV (≥0.81), and NPV (≥0.84), reasonable specificity (≥0.75), and estimated recurrence within a median of one month of institutional reference data.
CONCLUSIONS
This scalable method enables derivation of real-world endpoints from EHR-based data.
IMPACT
The algorithm may be used to characterize outcomes for patients treated outside of prospective clinical trials and may inform the creation of synthetic control cohorts to support regulatory approvals for new drugs in rare tumor or biomarker defined populations.
Jessica A. Lavery, Samantha Brown, Chelsea Nichols et al.· Cancer Epidemiology, Biomark...· 0 citations
Progress in precision oncology, including biomarker discovery and individualized treatment selection, is limited by the complexity of clinico-genomic data and the scarcity of large multimodal patient cohorts. Here, we introduce PanoraOnc, a pan-cancer artificial intelligence (AI) model pretrained on real-world clinical, genomic, and imaging data from 84,131 patients spanning 66 cancer types. PanoraOnc enables transferable treatment outcome prediction through pan-cancer pretraining and generalizes to unseen cohorts across cancer types, institutions, and therapeutic settings. Evaluation and fine-tuning were performed on cohorts comprising diverse modalities, including clinical features, targeted gene panels, immunofluorescence imaging, whole-exome sequencing, and transcriptomic profiles. Across these settings, PanoraOnc consistently outperforms statistical, machine-learning, survival, and AI baselines, with the largest improvements observed in zero- and few-shot scenarios, demonstrating that large-scale clinico-genomic pretraining enables robust and generalizable outcome predictions across previously unseen conditions. In addition, PanoraOnc supports biomarker discovery through explainable AI, revealing both established and underappreciated features, including tumor-infiltrating clonal hematopoiesis, oncogenic signaling pathways, and DNA damage response mechanisms in immunotherapy-treated melanoma and non-small cell lung cancer. Furthermore, PanoraOnc enables the identification of patient subgroups potentially benefitting from alternative treatments by estimating personalized treatment outcomes across therapeutic scenarios. These findings establish pan-cancer multimodal pretraining as a scalable paradigm for AI-assisted discovery in precision oncology.
M. Schuerch, J. Geisberg, C. T. Flower et al.· medRxiv· 0 citations
Open-source LLMs, when fine-tuned using labeled data, can effectively automate the ascertainment of key radiophenotypic variables using only the impression section of radiology reports, without the full report text, suggesting that these models may provide a scalable approach for phenotypic characterization of patients with cancer in real-world clinical settings.
S. A. Naqvi, I. Riaz, Amir Saeidi et al.· JCO Clinical Cancer Informat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
