News & Events

The University of Illinois Cancer Center strengthened its Data Integration Shared Resource (DISR) with new capabilities designed to speed research and provide more insight.

The latest DISR additions include using Pangaea to extract information from clinical notes and other unstructured text data, as well as deploying AskOmix©, a natural language AI Chatbot for researchers created in-house by DISR developers.

Pangaea

Pangaea extracts key information from unstructured text. Based on the guardrails DISR provides, Pangaea helps to extract tumor characteristics, biomarkers, staging elements, and narrative findings, and turns unstructured text into research‑ready data. This strengthens registry accuracy, supports precision oncology studies, and makes downstream analytics far more reliable. Pangaea can also extract data on social drivers of health (SDOH), helping cancer researchers understand the real-world factors that shape cancer risk and access to treatment. Integrating data on SDOH with clinical and pathology data allows researchers to study health disparities and design interventions that improve cancer outcomes for all.

AskOmix©

The introduction of AskOmix© makes it simpler for cancer researchers to explore complex -omics data. Researchers can ask the Chatbot questions in plain language (such as “show me germline dataset distributions by age and race” or “plot the number of adenocarcinoma patients by gender and age group”), and it quickly generates visualizations and summaries, as well as offering other insights.

As 1 of 6 shared resources at the Cancer Center, DISR fosters innovation at the intersection of patient and population-level data, clinical and public health research, and data analytics. The Cancer Center is part of the University of Illinois Chicago (UIC), and DISR supports cancer researchers in leveraging data to conduct studies across the cancer control continuum that address community needs.