Clinical trials are how we discover new cures, and they can be a life-saving form of treatment. Paradigm(opens in a new window) is breaking down barriers in the healthcare industry with technology that brings clinical trials to more people, such as cancer patients, while reducing the paperwork burden for doctors and nurses to address clinician burnout.
## Clinical trial enrollment is broken
The evaluation of patient medical records is a major bottleneck for getting a patient enrolled in a clinical trial that might provide the best possible treatment option. Medical providers rarely have time to search through clinical trials, understand the details of the trial taking place, and then match and qualify patients. The result is that most clinical trials are filled by patients in close proximity to where the trial is taking place, creating bias in the selection process and preventing many patients from accessing the groundbreaking care that could save their lives.
To solve this, Paradigm deployed and optimized traditional best practice, healthcare domain-specific ML and NLP models to extract and interpret medical record data. These models were trained and evaluated on golden data sets curated by expert clinicians. However, this approach was slow and burdensome.
> “We deployed fine-tuned state-of-the-art healthcare models, which we then further optimized. You spend a lot of time, and you have to do everything use case by use case. You have to build, train, and validate a separate model for every piece of information.”
Jonathan Hirsch, Chief Strategy Officer at Paradigm
Because traditional models only worked so well, clinicians are required to manually review model output to verify that quality standards have been met.
## Using GPT-4 to evaluate clinical trial data sets
Paradigm believed that LLMs, with their ability to summarize unstructured text, could be a great fit for their use case and replace the approach of building one-off ML models. They explored two potential paths: integrating with a custom LLM trained on medical use cases, or integrating with GPT‑4 through OpenAI’s API.
Paradigm believed they would need a specialized medical model to get good results. They were “shocked” to find that GPT‑4 outperformed a team of highly trained human experts on complex data evaluation tasks.
Ultimately, they chose OpenAI for several reasons:
## GPT-4 improves product speed, data quality, and costs of operation
## Evaluating hundreds of patients per minute
Looking forward, Paradigm is excited about how they can leverage GPT‑4’s natural language understanding to further reduce the burden for clinicians. Rather than needing to write code to analyze data, clinical teams could have a dialog with ChatGPT about a patient’s data, to understand their eligibility for trials, missing information, and next steps.
Paradigm is excited about how they can continue to increase the patient screening rate. With GPT‑4, their platform can potentially evaluate hundreds of patients per minute. Compare this to a typical nurse research coordinator, who can manually review around 50 patients _per day_. These efficiency gains can lead to a world where patients have far better access to clinical trials, physicians and nurses can spend more time on patient care and less time on documentation, and new life-saving therapies are brought to market sooner.
## Interested in learning more about ChatGPT for business?
Embedding AI into developer software API Mar 21, 2024
Building a data-driven, efficient culture with AI ChatGPT Mar 18, 2024
Reimagining the email experience with AI API Mar 18, 2024
Our Research * Research Index * Research Overview * Research Residency * OpenAI for Science * Economic Research
Latest Advancements * GPT-5.3 Instant * GPT-5.3-Codex * GPT-5 * Codex
Safety * Safety Approach * Security & Privacy * Trust & Transparency
ChatGPT * Explore ChatGPT(opens in a new window) * Business * Enterprise * Education * Pricing(opens in a new window) * Download(opens in a new window)
Sora * Sora Overview * Features * Pricing * Sora log in(opens in a new window)
API Platform * Platform Overview * Pricing * API log in(opens in a new window) * Documentation(opens in a new window) * Developer Forum(opens in a new window)
For Business * Business Overview * Solutions * Contact Sales
Company * About Us * Our Charter * Foundation * Careers * Brand
Support * Help Center(opens in a new window)
More * News * Stories * Livestreams * Podcast * RSS
Terms & Policies * Terms of Use * Privacy Policy * Other Policies
(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)
OpenAI © 2015–2026 Manage Cookies
English United States
