ConcertAI will spotlight its new and expanded multimodal and real-world data management offerings with Cara AI and the TeraRecon Oncology Suite at the American Society of Clinical Oncology (ASCO)'s annual meeting this week.
Both products are designed to enhance research capabilities and support complex clinical study workflows, according to ConcertAI.
Cara AI can combine radiological imaging studies, digital pathology, and structured and unstructured real-world data (RWD). The system also provides an open AI framework that enables scientists to embed and orchestrate AI algorithms (third party, first party, or open source) for retrospective and prospective image and data processing. ConcertAI also noted Cara AI includes:
- Advanced AI orchestrations across large language models (LLMs), natural language processing (NLP), and predictive AI
- Oncology- and hematology-specific LLMs
- Predictive AI operating on healthcare electronic medical records (EMR)-derived data, molecular radiological imaging, and digital pathology
- An industry-first, multi-modal data management platform optimized for predictive and generative AI
"Over the past two years, we have focused on the importance of multi-modal data AI model development, validation, stability monitoring, and deployment for insights, as part of clinical trials and, ultimately, clinical care," said ConcertAI CEO Jeff Elton, PhD. "Multi-modal data enable causal inferences and elimination of confounders for interpretations and predictions."
Also to be featured at ASCO 2024, the TeraRecon Oncology Suite is a new integrated set of AI-powered diagnostic tools designed for lung cancer detection, prostate cancer identification, and brain tumor characterization, to enhance early detection and accurate diagnosis. ConcertAI said the product enables management of cancer patients across the entire care pathway, provides innovative oncology-centric solutions to support and guide care delivery, and integrates seamlessly into existing workflows.
In 2021, TeraRecon joined the ConcertAI network to establish a single integrated network and AI-enabled workflows for clinical research and clinical decision support applications.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
