Slashdot Mirror
Hospitals May Turn To Algorithms To Fight Fatal Infections (scientificamerican.com)
An anonymous reader quotes a report from Scientific American: Clostridium difficile, a deadly bacterium spread by physical contact with objects or infected people, thrives in hospitals, causing 453,000 cases a year and 29,000 deaths in the United States, according to a 2015 study in the New England Journal of Medicine. Traditional methods such as monitoring hygiene and warning signs often fail to stop the disease. But what if it were possible to systematically target those most vulnerable to C-diff? Erica Shenoy, an infectious-disease specialist at Massachusetts General Hospital, and Jenna Wiens, a computer scientist and assistant professor of engineering at the University of Michigan, did just that when they created an algorithm to predict a patient's risk of developing a C-diff infection, or CDI. Using patients' vital signs and other health records, this method -- still in an experimental phase -- is something both researchers want to see integrated into hospital routines.
The CDI algorithm -- based on a form of artificial intelligence called machine learning -- is at the leading edge of a technological wave starting to hit the U.S. health care industry. After years of experimentation, machine learning's predictive powers are well-established, and it is poised to move from labs to broad real-world applications, said Zeeshan Syed, who directs Stanford University's Clinical Inference and Algorithms Program. Shenoy and Wiens' CDI algorithm analyzed a data set from 374,000 inpatient admissions to Massachusetts General Hospital and the University of Michigan Health System, seeking connections between cases of CDI and the circumstances behind them. The records contained over 4,000 distinct variables. As it repeatedly analyzes this data, the ML process extracts warning signs of disease that doctors may miss -- constellations of symptoms, circumstances and details of medical history most likely to result in infection at any point in the hospital stay.
The CDI algorithm -- based on a form of artificial intelligence called machine learning -- is at the leading edge of a technological wave starting to hit the U.S. health care industry. After years of experimentation, machine learning's predictive powers are well-established, and it is poised to move from labs to broad real-world applications, said Zeeshan Syed, who directs Stanford University's Clinical Inference and Algorithms Program. Shenoy and Wiens' CDI algorithm analyzed a data set from 374,000 inpatient admissions to Massachusetts General Hospital and the University of Michigan Health System, seeking connections between cases of CDI and the circumstances behind them. The records contained over 4,000 distinct variables. As it repeatedly analyzes this data, the ML process extracts warning signs of disease that doctors may miss -- constellations of symptoms, circumstances and details of medical history most likely to result in infection at any point in the hospital stay.
Isn't fighting a fatal infection somewhat of a waste of resources?
Let's make like a bird... and get the flock outta here.
We are already doing that. We use predictive analytics that processes dozens of data elements on each patient in the hospital and scores them for sepsis risk. The system then can do many things with that score. The most popular is paging to the attending provider and care team. This helps to reduce the cases of septic shock significantly.
will see you now.
anything which can be grabbed is better than what you have now. You are still in a shit creek. More heathly Americans die going to hospital each year than died in the Korean, Vietnam, and Middle East/Southwest Asia wars combined. 800,000 each and every year. Went in healthy - not in danger of dying - to cold stone dead.
"After years of experimentation, machine learning's predictive powers are well-established"
I hate when their prediction insists on a word, even changing what I typed several types into the word their algorithm thinks I must have really meant to type.
Went in healthy - not in danger of dying - to cold stone dead.
Well, that kind of shit will happen when you see what that place charges for ice cream.
We need a exciting new frontier in computation called the "Artificially Obvious".
Almost all infections are the result, even if the patient has 'whatever' level of risk, to transmission and re-transmission by human beings, and almost always the staff. Some of these interventions are over a hundreds year old now, like quarantine and hand washing ( Ignaz Semmelweis, 1848 ). See "Hand Hygiene in Health Care: First Global Patient Safety Challenge Clean Care Is Safer Care "https://www.ncbi.nlm.nih.gov/books/NBK144018/
Get 6 sigma on this issue, then the apply the A.I.
I really thought there was going to be medical blockchains somewhere in the story. Maybe next week...
Serenity now, insanity later.
https://www.youtube.com/watch?...
And that video was from 2013.
But really, aren't "algorithms" what are used by humans anyway? Input data, apply logic and other constraints, eliminate some options, rinse and repeat until a 'best course of action' is shown? Or, is Watson "AI" and thus totally different? Or, is this a matter of deep learning, with blockchain technology being integrated next quarter?
I know buzzword bingo is nothing new, but it really, really feels like nobody remembers anything anymore.
"Traditional methods such as monitoring hygiene and warning signs often fail to stop the disease."
THAT is why this won't work. This "solution" does not address THAT. This "solution" does not fix THAT. So no, it isn't gonna do a damned thing outside clinical trials.
On the other hand, when hospitals stop abusing antibiotics, and start actually maintaining cleanliness among hospital staff, infections go down, supebug development goes down, and hospital stays shorten, allowing the hospital to serve more patients. Not gonna link, look up the Netherlands or Holland, they ran this live and got incredible results.
Stop putting lots of sick people in a same building. Hospitals are becoming like those high-density pig or chicken farm where the animals are injected with antibiotics because it's cheaper than cleaning their shit. Smaller clusters = less problems.
lucm, indeed.
1. Hire top quality staff who know how to do medicine and who got educated to that nations standards about hygiene.
2. Clean wards and equipment. Have systems in place to ensure that is always done.
3. Dont allow your nation to deal with really high risk patients. Have a centre for tropical medicine ready to accept for the really interesting people.
4. Stop bringing really sick people into your nation. Have a visa system that demands medical results before a person gets to enter the nation.
List the conditions a person will not be allowed to enter the nation with.
5. Find out why people are getting really sick in a clean hospital. Is it from their own conditions, other patients, equipment, staff problems?
6. Dont accept medical experts who have not passed your state, nations medical exams.
7. If a doctor cant get good results all the time have systems in place to find who and why not. Dont keep a doctor who cant do their work as well as the best doctors in that nation can all the time.
Track every result, every person, every operation. Have other professionals do real reviews and have oversight on all tests.
Use all the experts a nation has to find out what is going wrong.
8. Have a way of getting sick people to a hospital quickly. Helicopter flights that can work day and night nation wide so a sick person can make it to a top hospital sooner and to the very best experts.
Once in hospital make sure they don't get sicker with below average staff. Study who is getting sicker and why. Stop that problem for all who use the health care system.
Advanced nations have most of the medical skills and tracking systems in place not to have 'infection" issues all the time.
Domestic spying is now "Benign Information Gathering"
They aren't clean. It was a while ago but I doubt the attitudes have changed. I worked in the laundry and we failed our health inspection every time. Management didn't care. The inspector would come in and we wouldn't have fixed any of the things he sited us for the last time. We were a critical resource or some bullshit like that so the health inspector couldn't shut us down. The mopping of the floors and cleaning of the beds was superficial. Spraying disinfectant isn't cleaning, you actually have to remove the human excrement and fluids so the bacteria doesn't have a place to immediately repopulate.
Details:
KW Hospital - Kitchener, Ontario, Canada, laundry department
Years - 1987 -1989
Faulty practices - putting clean laundry on dirty laundry carts, staff covered in filth handling clean laundry, staff covered in filth delivering laundry, no fire or safety training (7 high school students got left in the building during a fire), no metal detector for sharp objects.
quicksort?
(That got really dark)
I hadn't the slightest objection to his spending his time planning massacres for the bourgeoisie... (P.G. Wodehouse)
Cost tradeoffs.
Pull up the international comparisons for hospital infections by country.
If you break down by top private hospitals - risks have a cost association.
My private hospital swabbed me on admission, then gave me a chemical use once sponge to wash myself down. Pathology results protect them too.
Oh , this costs money, something public hospitals may not do. private room, less germ sharing. And they can hire/fire staff associated with poor outcomes - or doctors for that matter.
Surgeons use dermabond, a kind of superglue to seal wounds.
Most hospitals have infection control staff/nazis to control outbreaks. They also sense who are the real risks - suck as foreign operation candidates, or a deplorable.
AI will be nonsense - who is going to label the nurse/patient/doctors so the ones with unlucky outcomes get fired.
Good news is private hospitals generally avoid the more risky patients that public hospitals cannot turn away.
https://science.slashdot.org/s...
Recent development has indicated a popular "harmless" sugar additive as a likely culprit of causing two explosions in the occurrence of two nasty infections. Clostridium being one of them.
Start tackling that shit as prevention.
And yes, hand hygiene helps a lot, but is hard to do, as you would need to wash (with soap, not just alcohol) 100 times a day. That would cause a severe disturbance in the biotope on the nurses/doctors hands by itself!.
Why are other peoples sig's always more witty ???
... next up: "blockchain."
It little behooves the best of us to comment on the rest of us.
... and Al Gore have got no rhythm.
It little behooves the best of us to comment on the rest of us.
Crybaby.
machine learning's predictive powers are well-established, and it is poised to move from labs to broad real-world applications
Yeah, he's right! We need to start using this "machine learning" in the real world instead of confining it to the lab. /sarcasm
That is the only thing I can think of, with stories like this.
Like in the 60s, everything was "atom ...". ..." in movies and "smart ..." in products.
And now it is "quantum
Just wait ... in a few years, your Chinese soup kitchen will offer "algorithm soup".
But don't forget to use your algorithm toothbrush!
They aren't clean. It was a while ago but I doubt the attitudes have changed. I worked in the laundry and we failed our health inspection every time. Management didn't care. The inspector would come in and we wouldn't have fixed any of the things he sited us for the last time. We were a critical resource or some bullshit like that so the health inspector couldn't shut us down. The mopping of the floors and cleaning of the beds was superficial. Spraying disinfectant isn't cleaning, you actually have to remove the human excrement and fluids so the bacteria doesn't have a place to immediately repopulate.
Details:
KW Hospital - Kitchener, Ontario, Canada, laundry department
Years - 1987 -1989
Faulty practices - putting clean laundry on dirty laundry carts, staff covered in filth handling clean laundry, staff covered in filth delivering laundry, no fire or safety training (7 high school students got left in the building during a fire), no metal detector for sharp objects.
Staff leadership. Even when they train new staff members correctly at a school for nursing, etc..., if the staff culture encourages bad work, the patients are screwed. While there are a few good hospitals in Ontario cities, the rural hospitals I've heard about tend to have serious problems. And Canadian healthcare means they try to force you to go to the local hospital, because on paper it's capable of doing thing X.