AngloFaza

Difficulty Level: C1

Source URL: https://www.bbc.com/news/articles/c9q7zqy1xlpo

Toggle Tooltips

Health medicine disease healthcare

How AI can spot diseases that doctors aren't looking for

How AI can spot diseases that doctors aren't looking for

This is the sixth featureartykuł in a six-part seriesseria składająca się z sześciu części that is looking at how AI is changing medical research and treatments.

B1

When 58-year-old Will Studholme ended upskończył in accident and emergencyizba przyjęć at an NHS hospital in Oxford in 2023 with gastrointestinalżołądkowo-jelitowy symptoms, he wasn't expecting a diagnosis of osteoporosisosteoporoza.

B2

The disease, strongly associatedzwiązany with age, causes bones to become weak and fragilekruche, increasing the risk of fracturezłamanie.

B2

It turned outokazało się that Mr Studholme had a severe case of food poisoning, but early in his ailmentdolegliwość's investigation, he received an abdominal CT scantomografia komputerowa jamy brzusznej.

B2

That scan was then later run throughprzeanalizować artificial intelligence (AI) technology which identified a collapsed vertebrakręg in Mr Studholme's spine, a common early indicatorwczesny wskaźnik of osteoporosisosteoporoza.

C1

Further testing ensuednastąpiło, and Mr Studholme emerged not only with his diagnosis, but a simple treatmentpojawił się nie tylko z diagnozą, ale i prostym leczeniem: an annual infusioninfuzja of an osteoporosisosteoporoza drug that is expected to improve his bone density.

B2

"I feel very lucky," says Mr Studholme, "I don't think this would have been picked upwykryte without the AI technologytechnologia."

B1

It isn't unheard ofnie jest niespotykane that a radiologist might note something incidentalprzypadkowy in a patient's imaging – an undetectedniewykryty tumour, a concern with a particular tissue or organ – outside of what they had originally been checking for.

C1

But applying AI in the backgroundw tle to systematicallysystematycznie comb throughprzeszukiwać scans and automatically identify early signswczesne oznaki of common preventablemożliwy do zapobieżenia chronic diseases that might be brewing – regardless of the reason the scan was originally ordered – is new.

C1

The clinical use of AI for opportunisticoportunistyczny screening or opportunisticoportunistyczny imaging, as it is called, "is just beginning" notes Perry Pickhardt, a professor of radiology and medical physics at the University of Wisconsin-Madison, who is among those developing the algorithmsalgorytmy.

C1

It is considered opportunisticoportunistyczny because it takes advantage ofwykorzystuje imaging that has already been done for another clinical purposecel kliniczny – be it suspected cancer, chest infection, appendicitis or belly pain.

C1

It has the potential to catchpotencjał do wykrycia previously undiagnosedniediagnozowany diseases in the early stages, before onsetpoczątek of symptoms, when they are easier to treat or prevent from progressingzapobiec postępowi. "We can avoid a lot of the lack of prevention that we have missed out onprzegapić previously," says Prof Pickhardt.

C1

Regular physicalsbadania lekarskie or blood tests often fail to pick upwykryć these diseases, he adds.

B1

There's a lot of datadużo danych in CT scans related to body tissues and organstkanki i narządy ciała that we don't really useużywać, notes Miriam Bredella, a radiologistradiolog at NYU Langone who is also developing algorithmsalgorytmy in the field.

C1

And while analysis of it could theoreticallyteoretycznie be done without AI by radiologists making measurements – it would be time consumingczasochłonny.

B2

There are also benefits of the technology in terms ofpod względem reducing biasstronniczość, she notes.

B1

A disease like osteoporosisosteoporoza, for example, is thought of asuważany za mostly affecting thin, elderly white women – so doctors don't always think to lookpomyśleć, żeby spojrzeć outside of that population.

B2

Opportunisticoportunistyczny imaging, on the other handz drugiej strony, doesn't discriminate that way.

C1

Mr Studholme's case is a good exampledobry przykład. Being relatively young for osteoporosisosteoporoza, male and with no history of broken bones, it is unlikely he would have been diagnosed without AI.

B2

In addition to osteoporosis, AI is being trained to help opportunisticallyoportunistycznie identify heart disease, fatty liver disease, age-related muscle lossutrata mięśni związana z wiekiem and diabetes.

B2

While the main focusgłówny nacisk is on CT scans, for example of the abdomen or chest, work is taking placeodbywać się to opportunisticallyoportunistycznie gleanzbierać information from other types of imaging too, including chest x-rays and mammograms.

C1

The algorithmsalgorytmy are trained on many thousands of tagged previous scans, and it is important the training data includes scans from a wide swathezakres of ethnic groups if the technology is going to be deployedwdrożony on a diverse range of peoplezróżnicowana grupa ludzi, stress the experts.

C1

And there is supposed to be a level of human reviewpoziom przeglądu przez człowieka – if the AI finds something suspectpodejrzane it would be sent to radiologists to confirm before it is then reported onprzekazane to doctors.

B2

The AI technology used to examine Mr Studholme's scan belongs to Israeli company Nanox.AI, which is one of only a handful of companies working on AI for opportunisticoportunistyczny screening - far more are focused onskupiony na using AI to assist in the accurate and swift diagnosesdiagnozy of the specific conditions the scans are actually conducted for.

C1

Nanox.AI offers three opportunisticoportunistyczny screening products aimed at helping identify osteoporosisosteoporoza, heart disease and fatty liver disease respectivelyodpowiednio from routine CT scans.

B2

Oxford NHS hospitals began triallingtestowanie Nanox.AI's osteoporosis focused productprodukt skoncentrowany na osteoporozie in 2018 before officially rolling it outwprowadzać na rynek in 2020.

B2

Results from Oxford hospitals show an up to six-fold increasesześciokrotny wzrost above the NHS average in the number of patients being identified with vertebralkręgowy fractures – patients that can then be checked forsprawdzeni pod kątem osteoporosisosteoporoza, and start treatmentrozpocząć leczenie to combat the diseasezwalczać chorobę, says Kassim Javaid, a professor of osteoporosisosteoporoza and rare bone diseases at the University of Oxford who has spearheadedzainicjował the algorithm's introduction.

C1

Further trials of the algorithmalgorytm are also now underwayw toku at hospitals in Cambridge, Cardiff, Nottingham, Southampton and Bradford. "We want to build the evidencezebrać dowody to use it across the NHS," says Prof Javaid.

B2

Yet while the technology can benefit individualsprzynosić korzyści jednostkom, there are wider ramificationskonsekwencje that need to be considered says Sebastien Ourselin, a professor of healthcare engineering at Kings College London, who heads the AI Centre for Value Based Healthcare.

C1

A big problem that needs to be balancedzrównoważony, he notes, is the extra patient numbers that the use of the technology can create. "This is increasing the demandzapotrzebowanie on the healthcare system not reducing it," he says.

B2

First, people who are flagged byoznaczeni przez the opportunisticoportunistyczny screening as potentially having a disease will likely need further confirmatorypotwierdzający testing, which takes resourceswymaga zasobów. And, if the AI is inaccurate or too sensitive, that could result in a lot of unnecessary testingniepotrzebne testowanie.

C1

Then services need to be in placedostępne for those extra people that do end upskończyć being diagnosedzdiagnozowany.

B2

The extra loaddodatkowe obciążenie is a challengewyzwanie that comes withwiąże się z the technology admits Prof Javaid – but there are solutions.

B2

Patients confirmed to have the fractures in Oxford are routedkierowani for follow upkontynuacja to a largely nurse delivered fracture prevention service so as not to overloadprzeciążać doctors. "The AI does force you to change your pathwayzmienić swoją ścieżkę," he says.

B2

And in the long runna dłuższą metę, believes Prof Javaid, to have a greater number of people with early-stage osteoporosisosteoporoza identified and receiving the preventativezapobiegawczy treatment they need will save the NHS money. "Fracture is one of the top reasons people end upskończyć in hospital," he says.

B2

Mr Studholme has seen the devastationzniszczenie of osteoporosisosteoporoza first handz pierwszej ręki: it led to his mother breaking both her hips. It used to just be considered an old person's conditionchoroba starszych ludzi with nothing that could be done, he says. "I feel quite privilegedczuć się dość uprzywilejowanym I can do something before my bones turn intozamienić się w chalk," he says.

B2