Tango-Tiger

Have you ever been asked by a doctor what is more than 10 things?Pain tolerance is a highly subjective matter, which can make it difficult for doctors to determine why someone's pain is as high as they say.My five could be your seven, or a 10 mine could be your three.A new study published in Nature Medicine is looking to fix this.The researchers used artificial intelligence techniques to analyze X-rays of the knee to "Predict patient experience pain" for people with osteoarthritisThis involved 36,369 observations gathered from 4,172 patients.Computer analysis can choose what radiologists may have missed.We're not training algorithms to predict what doctors are going to say about X-rays," said Ziad Obermeyer, Berkeley assistant professor and co-author of the study.We train to predict what patients will say about their knee pain.He said the algorithm could explain more about the pain people feel.This is important because the way doctors judge pain is linked to discrimination and even racism.


Competitive bias

Studies have highlighted the health care inequality between white and black patients in the สล็อต United States for years.It seems that doctors are less concerned with certain groups of people when they say they are hurt. For example, studies indicate that black patients tend to have too low pain levels and can adversely affect treatment.I think many black people take a lot of time to see a doctor," said Paulah Wheeler, co-founder of BLKHLTH, an organization working to challenge racism and its impact on black health.Having such a situation when you are there and you are not heard or heard and you are being disrespectful and mistreated, you know it's just putting the point even further.One of the key points in the study is to explore the "mystery" of why "black patients experience higher levels of pain".The study found that radiologists who examined seemingly similar arthritis cases found that black patients reported more pain than white patients.

But the algorithm argues that the cases are less similar than they appear.Taking into account the additional undiagnosed features that doctors would overlook using commonly used radiographic sequencing systems.And because of the patients who reported severe pain and scored high on their own algorithmic measurements, the results showed. But the low on the official scoring system tends to be black, thus suggesting that traditional diagnoses may be poor in community service.What we found is that algorithms can explain more of the pain people feel, ”said Prof Obermeyer.So it's better to find out what hurts everyone's knee.The benefit of the additional expository power is great for black patients.This also applies to patients with lower socioeconomic status, with low education, and those who did not speak English as their first language.The researchers accepted two important reservations.Due to the "black-box" nature of how deep learning works, it is unclear which features in the X-ray the AI ​​picked up that would normally be missed.And as a result, it is not yet known whether offering surgery to those who miss this opportunity will provide them with additional benefits.


Racial prejudice

The study is interesting because AI itself is often accused of discrimination.This is often because the algorithmic dataset is trained about suffering from accidental bias.Imagine you have a small population," said Jimeng Sun, a professor of computer science at the University of Illinois at Urbana-Champaign.Your model will then be trained on very few datasets.He explained that the resulting algorithm is likely to be less accurate when applied to a smaller cohort than the one that makes up the majority of the population.Essentially, the cost is that AI systems are often faced with prejudice, as they've learned to identify patterns in whites' habits and traits, which may not work as well when applied to people with skin tones. OtherA.I.M.The use of AI in healthcare is not a substitute for doctors.

It's more about assisting doctors, especially with tasks that are often tiring or not directly related to caring for the sick.Dr. Sandra Hobson, assistant professor of orthopedics at Emory University, thinks the study has great promises and that many of them involve a wide variety of data groups used.Historically, studies have looked at different patients and sometimes the studies did not include women, or sometimes the studies did not include patients from different backgrounds," she explains.I think AI has an opportunity to help integrate information that includes patients from all backgrounds of countries around the world and help them understand them all.