Document Processing
Lifespan needed to make surgical consent forms easier for patients to understand because the documents were still written at a college reading level and could undermine health literacy during emotionally difficult care decisions.
Reported impact
Lifespan made consent forms more accessible for patients, reduced document length and complexity, and created a repeatable AI-assisted workflow for simplifying other forms across the health system.
Lifespan built a tightly governed document-simplification workflow around GPT-4 to rewrite surgical consent forms into plain language without changing meaning. Medical residents first identified that consent forms remained too complex for many patients, then used a simple prompt to ask GPT-4 to preserve content while rewriting the text to the average American reading level. The model produced an initial draft at roughly a sixth-grade reading level, after which legal and medical reviewers checked the output to mitigate hallucination and bias before deployment. That human-in-the-loop flow let Lifespan move from dense three-page documents toward simpler one-page forms, then extend the same process to other clinical paperwork such as intake and chemotherapy consent forms. The result is an implementation that keeps AI as the first-pass drafting layer while clinicians and legal staff remain the final authority on what reaches patients.
Lifespan feeds an existing surgical consent form and a simplification prompt into GPT-4, receives a plain-language draft, routes that draft through legal and medical review, and then deploys the approved version across the health system as patient-facing documentation.
GPT-4 generated a draft of the surgical consent form at approximately a 6th grade reading level with a 25 percent reduction in word count
In September 2023, Lifespan began deploying the revised surgical consent forms, reduced from three pages to one page
Lifespan has now replicated this GPT-4 assisted process to deploy simplified medical documentation across its healthcare system
Lifespan leadership created a system where GPT-4 would do a first pass, and then legal and medical reviewers would check the output
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The page says "Statistics are from fiscal year 2025" and "Employees: 19,469".
Related
OpenAI Sample May 29, 2026 Boston Children's Hospital Boston Children's needed to reduce the administrative burden of supply-chain, billing, and scheduling work while also helping clinicians reason through rare-disease cases where fragmented genetic data, incomplete… About 60,000 hours in time savings co-pilot geneticist · enterprise AI layer · secure internal ChatGPT environment OpenAI Sample May 21, 2026 AdventHealth AdventHealth needed to reduce administrative and documentation burden across clinical and operational teams so staff could handle more demand without sacrificing quality or clinician time with patients. 80% reduction in time spent on administrative tasks ChatGPT Enterprise · ChatGPT for Healthcare OpenAI Sample Sep 26, 2024 Promega Promega's manufacturing operations are complex. With the manufacture of 4,000 products, readiness means constant planning in advance. Linton immediately recognized its potential to help employees manage the company’s thousands of products and… OpenAI API · custom GPTs 