- Dan Crenshaw roasted after attacking Sanders’ call for veteran care 11 Months Ago
- How to stream NXT for its USA network debut 11 Months Ago
- This website will show you how AI classifies you 11 Months Ago
- School tells Black 4-year-old to cut his hair or wear a dress Today 3:17 PM
- Lizzo called a ‘snitch’ for accusing Postmates runner of stealing food Today 2:30 PM
- Government sues Edward Snowden for breaking a non-disclosure agreement Today 2:21 PM
- How to stream Tottenham Hotspur vs. Olympiacos in the Champions League Today 1:56 PM
- ‘Love Island’ star’s Instagram photo doctored for MAGA hat ad Today 1:16 PM
- Los Tigres del Norte carry on Johnny Cash’s legacy in stellar Folsom Prison concert film Today 1:05 PM
- Keke Palmer’s ‘sorry to this man’ meme is perfect Today 12:59 PM
- Hoodies with fake bullet holes from prominent school shootings spark outrage Today 12:44 PM
- Instagram apologizes for censoring pictures of fish Today 12:40 PM
- George R.R. Martin clarifies some things about the ‘Game of Thrones’ Targaryen prequel Today 12:20 PM
- Bill Mitchell, the Trump-loving QAnon scammer, is pushing ammunition for a civil war Today 11:53 AM
- How to stream Tigres vs. Cruz Azul in the Leagues Cup final Today 11:48 AM
AI sepsis diagnosis more reliable than physicians, study finds
We may be getting closer to diagnosis by computer.
Even though the methods aren’t yet ready for use on human patients, the positive results emerging from the study could prompt real-life trials in the UK.
“The model is not specific to sepsis or intensive care,” Matthieu Komorowski, a PhD student at Imperial College London who headed the research, said in a phone interview with the Daily Dot. “It could be used to any clinical environment where you have lots of data.”
The system, called AI Clinician, looked at treatment strategies from the records of about 100,000 former intensive care patients. AI Clinician predicted the best patient strategy, outperforming the human clinicians.
Sepsis, or blood poisoning, is a potentially fatal complication of an infection, and affects more than 30 million people worldwide every year, potentially leading to 6 million deaths, according to data from the World Health Organization.
AI Clinician learned the best treatment strategy for a patient by analyzing the records of patients who had suffered from the disease to train the machines and identified 48 variables that were relevant to treating the life-threatening complication. Some of these were demographic, such as age and gender, and others related to their treatment. For Komorowski, the study also means that the medical field could benefit from more collaboration between health and computer science professionals.
“The secret recipe to this project is close collaboration between clinician and computer science expert,” Komorowski said. “This is why we succeeded in going further than the current state of the art.”
But the end note of the study comes back to the importance of human-based judgment.
“Physicians will always need to make subjective clinical judgments about treatment strategies,” the study’s authors warned.
Eventually, however, Komorowski believes the science could be precise enough to be led solely by computers: “It is possible in theory that we get enough evidence that the system is working appropriately and we can bypass human steps,” he said. “Just like jetplanes, where pilots are here for safety—most of the time they are not needed, but we’d need more evidence before we can do this.”
H/T Ars Technica
Stéphanie Fillion is a French-Canadian journalist covering politics and foreign affairs in Montreal, Canada. She has worked for Radio-Canada in Vancouver and was a San Paolo fellow at La Stampa in Turin. In 2015, she won the Eu-Canada Young Journalist Award. She holds an M.A. in Journalism, Politics and Global Affairs from Columbia Journalism School and a B.A. in Comparative Politics, History and Italian Studies from McGill University. Her work appeared in outlets such as Quartz, Vice News, Ipolitics, and PassBlue.