Connect with us

Brand Stories

Artificial Intelligence Accurately Classifies Pancreatic Cysts

Published

on


Key Takeaways 

  • MRI and CT scans of nearly 1,000 adults were evaluated by ChatGPT-4 and the traditional manual approach for pancreatic cysts.  
  • The accuracy of AI was equivalent to human performance in identifying and classifying nine clinical variables used to monitor pancreatic cyst progression.  

CHICAGO — Artificial intelligence (AI) models such as ChatGPT are designed to rapidly process data. Using the AI ChatGPT-4 platform to extract and analyze specific data points from the Magnetic Resonance Imaging (MRI) and computed tomography (CT) scans of patients with pancreatic cysts, researchers found near-perfect accuracy when compared directly against the manual approach of chart review performed by radiologists, according to a studypublished in the Journal of the American College of Surgeons(JACS). 

“ChatGPT-4 is a much more efficient approach, is cost effective, and allows researchers to focus on data analysis and quality assurance rather than the process of reviewing chart after chart,” said study coauthor Kevin C. Soares, MD, MS, a hepatopancreatobiliary cancer surgeon at Memorial Sloan Kettering Cancer Center in New York City. “Our study established that this AI approach was essentially equally as accurate as the manual approach, which is the gold standard.”  

Using an existing database of nearly 1,000 adult patients with pancreatic lesions under surveillance between 2010 and 2024 at Memorial Sloan Kettering Cancer Center in New York City, ChatGPT-4 was deployed to identify nine clinical variables used to monitor cyst progression: cyst size, main pancreatic duct size, number of lesions, main pancreatic duct dilation, branch duct dilation, presence of solid component, calcific lesion, pancreatic atrophy, and pancreatitis. Pancreatic cysts are common and require ongoing surveillance because some develop into cancer and require surgery.  

Researchers evaluated ChatGPT-4’s ability to identify and classify these nine factors associated with increased risk for dysplasia and cancer. A manually annotated institutional cyst database was used as the standard for comparison.  

Key Findings  

  • The study involved 3,198 unique MRI and CT scans from 991 patients under long-term surveillance for premalignant lesions.  
  • ChatGPT-4 successfully extracted clinical variables with high accuracy. The accuracy rate ranged from 97% for a solid component, a high-risk variable, to 99% for calcific lesions.  
  • Accuracy was 92% for cyst size and 97% for main pancreatic duct size, other high-risk variables that may indicate cancer and require surgical resection, biopsy, or endoscopic ultrasound.    

“AI can help us expand medical research and improve patient outcomes,” Dr. Soares said. “The question I get asked most often is, ‘What is the chance that this cyst is going to develop into cancer?’ We now have an efficient way to look at the MRI and CT scans of thousands of patients and give our patients a better answer. This approach goes a long way to reduce anxiety and help patients feel more confident about their treatment decisions.”  

While this was a proof-of-concept study, moving forward the study authors say they would like to use AI to expand the number of research questions they ask to enhance patient care.  

“There is a lot of interest in understanding if AI can predict who is going to develop cancer. It’s important to understand who progresses and why, so we have a better chance at tailoring surveillance,” Dr. Soares said. “We want to limit the number of patient visits, costs to the health care industry, and ultimately provide a customized, rather than one-size-fits-all approach to surveillance.” 

The researchers caution that the study used only one AI source, ChatGPT-4, and results are limited to the data that was used. AI can only work with the information that is handed to it. These limitations may reduce the broader applicability of the findings.  

Coauthors are Ankur P. Choubey, MD, MPH; Emanuel Eguia, MD, MS; Alexander Hollingsworth, MS; Subrata Chatterjee, PhD; Remo Alessandris, MD; Misha T. Armstrong, MD, MPH; Emily Manin, MD; Lily V. Saadat, MD; Jennifer Flood, MSN; Avijit Chatterjee, PhD; Vinod P. Balachandran, MD, FACS; Jeffrey A. Drebin, MD, PhD, FACS; T. Peter Kingham, MD, FACS; Michael I. D’Angelica, MD, FACS; William R. Jarnagin, MD, FACS; Alice C. Wei, MD, MSc, FACS; Vineet S. Rolston, MD; Mark A. Schattner, MD; and Richard K. G. Do, MD, PhD. 

The study is published as an article in press on the JACS website.  

Author Disclosures: This work was funded in part by NIH/National Cancer Institute P30 CA008748 Cancer Center Support Grant. 

Citation: Large Language Models Enable Accurate Data Extraction and Curation from Radiology Reports for Pancreatic Cyst Surveillance. Journal of the American College of Surgeons. DOI: 10.1097/XCS.0000000000001478 

# # # 

 About the American College of Surgeons 

The American College of Surgeons (ACS) is a scientific and educational organization of surgeons that was founded in 1913 to raise the standards of surgical practice and improve the quality of care for all surgical patients. The ACS is dedicated to the ethical and competent practice of surgery. Its achievements have significantly influenced the course of scientific surgery in America and have established it as an important advocate for all surgical patients. The ACS has approximately 90,000 members and is the largest organization of surgeons in the world. “FACS” designates that a surgeon is a Fellow of the ACS.   

Follow the ACS on social media: X | Instagram | YouTube | LinkedIn | Facebook 





Source link

Continue Reading
Click to comment

You must be logged in to post a comment Login

Leave a Reply

Brand Stories

Americans May Have To Pay Much More For Electricity. Reason: Artificial Intelligence

Published

on

By


Artificial intelligence is reshaping the future — but not without a cost. A new report by the White House Council of Economic Advisors warns that AI and cloud computing may drive up electricity prices dramatically across the United States unless urgent investments are made in power infrastructure.

The study highlights a significant shift: after decades of minimal electricity demand growth, 2024 alone saw a 2% rise, largely attributed to the surge in AI-powered data centers. The International Energy Agency (IEA) projects that by 2030, data centers in the US could consume more electricity than the combined output of heavy industries such as aluminum, steel, cement, and chemicals.

Productivity Promises VS Power Pressures

Despite the looming challenges, the report does not discount AI’s potential benefits. If half of all US businesses adopt AI by 2034, labor productivity could rise by 1.5 percentage points annually, potentially boosting GDP growth by 0.4% that year. But that promise comes with a price.

To meet the surge in demand, especially when factoring in industrial electrification and efforts to reshore manufacturing, the US would need to invest an estimated 1.4 trillion Dollars between 2025 and 2030 in new electricity generation. That figure surpasses the industry’s investment over the past decade. The study cautions that without the emergence of lower-cost power providerssuch as renewables or advanced nuclearelectricity bills will rise sharply.



Source link

Continue Reading

Brand Stories

Delaware Firm to Evolve Defense Tech Org With Self-Growing AI

Published

on


Star26 Capital Inc. is collaborating with Delaware-based Synthetic Darwin to supercharge its defense tech developments through self-growing AI.

This partnership will utilize Darwinslab, an AI ecosystem where digital agents generate, assess, and cultivate other algorithms inspired by biological evolution.

The solution slashes the time needed to build or sustain complex AI systems, shrinking development cycles to days and enabling rapid adaptation to new data and mission needs.

Read the full story on our new publication, Military AI: Delaware Firm to Evolve New York Defense Tech Org Through Self-Growing AI



Source link

Continue Reading

Brand Stories

AI isn’t just for coders: 7 emerging non-tech career paths in artificial intelligence

Published

on

By


7 emerging non-tech career paths in artificial intelligence

Artificial intelligence is no longer the future. It’s already shaping how we live, work, and learn. From smart assistants to personalised learning apps and automated hiring tools, AI is now part of everyday life. But here’s something many students still don’t realise — you don’t have to be a computer science genius to build a meaningful career in AI.In 2025, AI needs more than just coders. It needs people who understand ethics, design, communication, psychology, policy, and human behaviour. Whether you’re studying law, liberal arts, design, economics, or media, there is space for you in this fast-growing field. These emerging roles are all about making AI more responsible, more human, and more useful.Here are seven exciting non-tech career paths in artificial intelligence that you can start exploring now.

AI ethics specialist

AI systems make decisions that can affect real lives — from who gets hired to who receives a loan. That’s why companies and governments need experts who can guide them on what’s fair, what’s biased, and what crosses a line. Ethics specialists work closely with developers, legal teams, and product leaders to make sure AI is built and used responsibly.Best suited for: Students from philosophy, sociology, law, or political science backgroundsWhere to work: Tech companies, research institutes, policy think tanks, or digital rights NGOs

AI UX and UI designer

AI tools need to be easy to use, intuitive, and accessible. That’s where design comes in. AI UX and UI designers focus on creating smooth, human-centered experiences, whether it’s a chatbot, a virtual assistant, or a smart home interface. They use design thinking to make sure AI works well for real users.Best suited for: Students of psychology, graphic design, human-computer interaction, or visual communicationWhere to work: Tech startups, health-tech and ed-tech platforms, voice and interface design labs

AI policy analyst

AI raises big questions about privacy, rights, and regulation. Governments and organisations are racing to create smart policies that balance innovation with safety. AI policy analysts study laws, write guidelines, and advise decision-makers on how to manage the impact of AI in sectors like education, defense, healthcare, and finance.Best suited for: Public policy, law, international relations, or development studies studentsWhere to work: Government agencies, global institutions, research bodies, and policy units within companies

AI behavioural researcher

AI tools influence human behaviour — from how long we scroll to what we buy. Behavioural researchers look at how people respond to AI and what changes when technology gets smarter. Their insights help companies design better products and understand the social effects of automation and machine learning.Best suited for: Students of psychology, behavioural economics, sociology, or educationWhere to work: Tech companies, research labs, social impact startups, or mental health platforms

AI content strategist and explainer

AI is complex, and most people don’t fully understand it. That’s why companies need writers, educators, and content creators who can break it down. Whether it’s writing onboarding guides for AI apps or creating videos that explain how algorithms work, content strategists make AI easier to understand for everyday users.Best suited for: Students of journalism, English, media studies, marketing, or communicationWhere to work: Ed-tech and SaaS companies, AI product teams, digital agencies, or NGOs

AI program manager

This role is perfect for big-picture thinkers who love connecting people, processes, and purpose. Responsible AI program managers help companies build AI that meets ethical, legal, and user standards. They coordinate between tech, legal, and design teams and ensure that AI development stays aligned with values and global standards.Best suited for: Business, liberal arts, management, or public administration studentsWhere to work: Large tech firms, AI consultancies, corporate ethics teams, or international development agencies

AI research associate (non-technical)

Not all AI research is about coding. Many labs focus on the social, psychological, or economic impact of AI. As a research associate, you could be studying how AI affects jobs, education, privacy, or cultural behaviour. Your work might feed into policy, academic papers, or product design.Best suited for: Students from linguistics, anthropology, education, economics, or communication studiesWhere to work: Universities, research labs, global think tanks, or ethics institutesThe world of AI is expanding rapidly, and it’s no longer just about math, code, and machines. It’s also about people, systems, ethics, and storytelling. If you’re a student with curiosity, critical thinking skills, and a passion for meaningful work, there’s a place for you in AI — even if you’ve never opened a programming textbook.TOI Education is on WhatsApp now. Follow us here.





Source link

Continue Reading

Trending

Copyright © 2025 AISTORIZ. For enquiries email at prompt@travelstoriz.com