{"slug": "making-medical-ai-more-reliable", "title": "Making Medical AI More Reliable", "summary": "USC researcher Ruishan Liu has launched a three-year, nearly $900,000 National Science Foundation-funded project to build a traceable, cost-aware AI framework for medical data curation, aiming to automate the detection and repair of data errors that cause AI model failures in clinical settings. The framework, tested in radiation oncology, uses reasoning-based large language models to propose root-cause hypotheses and a provenance infrastructure with Bloom filters to log data histories, with a human-in-the-loop feature for expert review. Collaborators include Virginia Tech researchers Ruoxi Jia and Wenjie Xiong.", "body_md": "Medical AI technologies are changing how doctors make clinical decisions and significantly reducing the time clinicians spend on manual tasks.\n\nHowever, these AI systems are only as reliable as the data used to train them.\n\nWhen these models fail, researchers currently must perform slow, manual and nonreproducible investigations to determine why. There is no automated, systematic way to trace a model’s poor performance back to specific errors in the data pipeline. Troubleshooting data errors manually is not only labor-intensive but also costly, and it can slow the entire clinical workflow, causing patients to wait longer for critical treatments.\n\nUnlike general AI, medical data is also precious and expensive to collect because it requires patient consent and high levels of clinical expertise. Simply discarding “bad” data is often not a viable option.\n\nUSC researcher [Ruishan Liu](https://viterbi.usc.edu/directory/faculty/Liu/Ruishan) aims to build a traceable, cost-aware and end-to-end AI framework for data curation in an upcoming study funded by the [National Science Foundation (NSF)](https://www.nsf.gov/).\n\nLaunched this month, the three-year project received nearly $900,000 in funding.\n\nLiu is a WiSE Gabilan assistant professor from [USC Viterbi School of Engineering](https://viterbi.usc.edu/)’s [Thomas Lord Department of Computer Science](https://www.cs.usc.edu/) and [USC Mark and Mary Stevens School of Computing and AI](https://stevens-computing-ai.usc.edu/), with joint-appointments at [USC Dornsife](https://dornsife.usc.edu/)’s [quantitative and computational biology department](https://www.qcb-dornsife.usc.edu/) and [Keck School of Medicine of USC](https://www.keckmedicine.org/)‘s [radiation oncology department](https://keck.usc.edu/radiation-oncology/).\n\nTeaming up with [Virginia Tech](https://www.vt.edu/index.html) researchers [Ruoxi Jia](https://ece.vt.edu/people/profile/jiar.html) and [Wenjie Xiong](https://ece.vt.edu/people/profile/xiong.html), Liu will combine her background in computer science, biomedical data science and radiation oncology with her collaborators’ expertise in algorithms and computer systems.\n\nThe primary test bed for the study is radiation oncology, a field that relies heavily on complex, multimodal data, including medical imaging such as CT and MRI scans, radiation treatment planning and longitudinal electronic health records. Liu emphasized that the framework could also be applied across a wide range of medical specialties.\n\n“Our goal is to include a human-in-the-loop feature in the tool,” Liu said. “We want to design a framework that allows medical experts to review key decisions.”\n\n## How This New AI Tool Works\n\nLiu said the tool is essentially a framework consisting of three primary components, or “thrusts.”\n\nThe first focuses on algorithmic foundations. This part of the framework identifies which data is responsible for a model failure (attribution), why it is responsible (diagnosis) and how best to fix it (intervention selection). It uses reasoning-based large language models (LLMs) to propose root-cause hypotheses. This component replaces manual troubleshooting with an automated pipeline that traces model failures to specific data-level root causes and recommends the most cost-effective repairs. It tackles the challenge of maintaining model reliability in complex medical workflows, where data is scarce and errors are often context-dependent.\n\nThe second component is the provenance infrastructure. It acts as a “traceability” layer by logging the complete history and transformation of every data sample. It uses efficient structures such as Bloom filters, a fast probabilistic data structure used to test whether an item belongs to a set, to enable rapid querying of data origins. This provides a scalable, sample-level history of every data point, addressing the information-gap limitations of current medical AI systems. In turn, it transforms the AI “black box” into a transparent system where model failures can be traced to specific scanner protocols, data-processing steps or human errors.\n\nThe final component is the Integrated Curation Agent, an end-to-end system that orchestrates the algorithms and infrastructure into a closed-loop workflow. It includes a human-in-the-loop feature that allows medical experts to review and approve high-stakes remediation decisions while managing context-dependent medical data failures that traditional tools cannot detect.\n\n## How This Study Could Change the Medical AI Landscape\n\nThe tool developed from this study will be open source, making it available for medical researchers and clinicians to use.\n\nOne of the biggest advantages the tool could bring is improved efficiency. It has the potential to reduce the manual labor required for researchers and clinical data scientists to identify and troubleshoot data issues.\n\nThe framework introduced in the study also promotes standardization by establishing a replicable methodology for maintaining data integrity that can be applied to high-stakes domains beyond medical imaging.\n\nUltimately, the tool could help medical institutions deploy AI systems with greater trust, accountability and transparency.\n\nPublished on August 6th, 2026\n\nLast updated on August 6th, 2026", "url": "https://wpnews.pro/news/making-medical-ai-more-reliable", "canonical_source": "https://viterbischool.usc.edu/news/2026/08/making-medical-ai-more-reliable/", "published_at": "2026-08-06 20:37:35+00:00", "updated_at": "2026-08-09 09:49:21.191844+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-tools", "ai-ethics"], "entities": ["Ruishan Liu", "National Science Foundation", "USC Viterbi School of Engineering", "Thomas Lord Department of Computer Science", "USC Mark and Mary Stevens School of Computing and AI", "Virginia Tech", "Ruoxi Jia", "Wenjie Xiong"], "alternates": {"html": "https://wpnews.pro/news/making-medical-ai-more-reliable", "markdown": "https://wpnews.pro/news/making-medical-ai-more-reliable.md", "text": "https://wpnews.pro/news/making-medical-ai-more-reliable.txt", "jsonld": "https://wpnews.pro/news/making-medical-ai-more-reliable.jsonld"}}