Artificial intelligence (AI) helped spot breast cancers earlier and was linked to fewer dangerous cases emerging between routine screenings in a Swedish trial of more than 100,000 women.
The findings suggested AI could improve screening by reducing the number of breast cancers that are missed and diagnosed later, when they are often more aggressive and harder to treat.
Interval cancers — those diagnosed after a woman has received a clear screening result and before her next routine test — are “a very good measure on how effective the screening method is,” said lead author Kristina Lang, a breast radiologist and clinical researcher at Lund University. “Since it takes a long time to evaluate breast cancer mortality, interval cancer rate has been used as a surrogate measure.”
Photo: AFP
The trial is the first randomized controlled study to examine how AI affects breast cancer screening outcomes and is the largest test of AI in cancer screening to date. Earlier results from the same project showed the technology could increase cancer detection while reducing the workload for radiologists.
What had remained unclear was whether those gains meant fewer cancers would appear later, after screening appeared to show no disease.
The results come from a trial embedded in Sweden’s national breast cancer screening program. About 106,000 women were assigned to either standard screening, in which mammograms were read independently by two radiologists, or to screening supported by AI.
In the AI group, software reviewed images alongside radiologists, flagging higher-risk scans for extra scrutiny while allowing lower-risk images to be read once instead of twice.
Over the two years following screening, fewer women in the AI group were diagnosed with breast cancer after a clear scan. The rate of such cases was about 12 percent lower than among women whose mammograms were read without AI.
Women screened with AI support were also less likely to be diagnosed later with invasive tumors or aggressive cancer subtypes, the researchers found.
Importantly, using AI did not worsen screening performance or increase false alarms. The rate of false positives was similar in both groups.
“Our study does not support replacing healthcare professionals with AI,” said Jessie Gommers, a doctoral candidate at Radboud University Medical Center and first author of the paper. “However, our results potentially justify using AI to ease the substantial pressure on radiologists’ workloads.”
Whether AI-supported screening is worth the cost remains an open question. Previous modeling from Norway suggested the technology could be cost-effective if it helped prevent even a small share of cancers from being missed.
The Swedish trial showed a larger drop than that benchmark, although a full economic analysis of the data is still under way, Lang said.
The researchers said the study has limitations. It was conducted within Sweden’s screening program, using a single type of mammography machine and one AI system, and involved mostly experienced radiologists. The results would need to be confirmed in other countries and health systems, they said.
Further follow-up would also be needed to understand the long-term effects of AI-supported screening, including whether earlier detection reduces the need for aggressive treatment over time.
PRECARIOUS RELATIONS: Commentators in Saudi Arabia accuse the UAE of growing too bold, backing forces at odds with Saudi interests in various conflicts A Saudi Arabian media campaign targeting the United Arab Emirates (UAE) has deepened the Gulf’s worst row in years, stoking fears of a damaging fall-out in the financial heart of the Middle East. Fiery accusations of rights abuses and betrayal have circulated for weeks in state-run and social media after a brief conflict in Yemen, where Saudi airstrikes quelled an offensive by UAE-backed separatists. The United Arab Emirates is “investing in chaos and supporting secessionists” from Libya to Yemen and the Horn of Africa, Saudi Arabia’s al-Ekhbariya TV charged in a report this week. Such invective has been unheard of
US President Donald Trump on Saturday warned Canada that if it concludes a trade deal with China, he would impose a 100 percent tariff on all goods coming over the border. Relations between the US and its northern neighbor have been rocky since Trump returned to the White House a year ago, with spats over trade and Canadian Prime Minister Mark Carney decrying a “rupture” in the US-led global order. During a visit to Beijing earlier this month, Carney hailed a “new strategic partnership” with China that resulted in a “preliminary, but landmark trade agreement” to reduce tariffs — but
Chinese President Xi Jinping’s (習近平) purge of his most senior general is driven by his effort to both secure “total control” of his military and root out corruption, US Ambassador to China David Perdue said told Bloomberg Television yesterday. The probe into Zhang Youxia (張又俠), Xi’s second-in-command, announced over the weekend, is a “major development,” Perdue said, citing the family connections the vice chair of China’s apex military commission has with Xi. Chinese authorities said Zhang was being investigated for suspected serious discipline and law violations, without disclosing further details. “I take him at his word that there’s a corruption effort under
China executed 11 people linked to Myanmar criminal gangs, including “key members” of telecom scam operations, state media reported yesterday, as Beijing toughens its response to the sprawling, transnational industry. Fraud compounds where scammers lure Internet users into fake romantic relationships and cryptocurrency investments have flourished across Southeast Asia, including in Myanmar. Initially largely targeting Chinese speakers, the criminal groups behind the compounds have expanded operations into multiple languages to steal from victims around the world. Those conducting the scams are sometimes willing con artists, and other times trafficked foreign nationals forced to work. In the past few years, Beijing has stepped up cooperation
RSS