John Wiederspan puts on an AI-powered wearable camera designed to detect medication errors. David Jaewon Oh for NBC News Health news Medical errors are still harming patients. AI could help change that. Medication mistakes — where the wrong drug or the wrong dosage is given to a patient — are among the most common errors in medicine.
May 25, 2025, 5:00 AM EDT
By David Cox
John Wiederspan is well aware of how things can go wrong in the high-pressure, high-stakes environment of an operating room.
'During situations such as trauma, or a patient doing poorly, there's a real rush to try and get emergency drugs into the patient as fast as possible,' said Wiederspan, a nurse anesthetist at UW Medicine in Seattle. 'And that's when mistakes can occur, when you're flustered, your adrenaline's rushing, you're drawing up drugs and you're trying to push them.'
Despite ongoing efforts to improve patient safety, it's estimated that at least 1 in 20 patients still experience medical mistakes in the health care system. One of the most common categories of mistakes is medication errors, where for one reason or another, a patient is given either the wrong dose of a drug or the wrong drug altogether. In the U.S., these errors injure approximately 1.3 million people a year and result in one death each day, according to the World Health Organization.
In response, many hospitals have introduced guardrails, ranging from color coding schemes that make it easier to differentiate between similarly named drugs, to barcode scanners that verify that the correct medicine has been given to the correct patient.
Despite these attempts, medication mistakes still occur with alarming regularity.
'I had read some studies that said basically 90% of anesthesiologists admit to having a medication error at some point in their career,' said Dr. Kelly Michaelsen, Wiederspan's colleague at UW Medicine and an assistant professor of anesthesiology and pain medicine at the University of Washington. She started to wonder whether emerging technologies could help.
As both a medical professional and a trained engineer, it struck her that spotting an error about to be made, and alerting the anesthesiologists in real time, should be within the capabilities of AI. 'I was like, 'This seems like something that shouldn't be too hard for AI to do,'' she said. 'Ninety-nine percent of the medications we use are these same 10-20 drugs, and so my idea was that we could train an AI to recognize them and act as a second set of eyes.'
The study
Michaelsen focused on vial swap errors, which account for around 20% of all medication mistakes.
All injectable drugs come in labeled vials, which are then transferred to a labeled syringe on a medication cart in the operating room. But in some cases, someone selects the wrong vial, or the syringe is labeled incorrectly, and the patient is injected with the wrong drug.
In one particularly notorious vial swap error, a 75-year-old woman being treated at Vanderbilt University Medical Center in Tennessee was injected with a fatal dose of the paralyzing drug vecuronium instead of the sedative Versed, resulting in her death and a subsequent high-profile criminal trial.
Michaelsen thought such tragedies could be prevented through 'smart eyewear' — adding an AI-powered wearable camera to the protective eyeglasses worn by all staff during operations. Working with her colleagues in the University of Washington computer science department, she designed a system that can scan the immediate environment for syringe and vial labels, read them and detect whether they match up.
'It zooms in on the label and detects, say, propofol inside the syringe, but ondansetron inside the vial, and so it produces a warning,' she said. 'Or the two labels are the same, so that's all good, move on with your day.'
Building the device took Michaelsen and her team more than three years, half of which was spent getting approval to use prerecorded video streams of anesthesiologists correctly preparing medications inside the operating room. Once given the green light, she was able to train the AI on this data, along with additional footage — this time in a lab setting — of mistakes being made.
'There's lots of issues with alarm fatigue in the operating room, so we had to make sure it works very well, it can do a near perfect job of detecting errors, and so [if used for real] it wouldn't be giving false alarms,' she said. 'For obvious ethical reasons, we couldn't be making mistakes on purpose with patients involved, so we did that in a simulated operating room.'
In a study published late last year, Michaelsen reported that the device detected vial swap errors with 99.6% accuracy. All that's left is to decide the best way for warning messages to be relayed and it could be ready for real-world use, pending Food and Drug Administration clearance. The study was not funded by AI tech companies.
'I'm leaning towards auditory feedback because a lot of the headsets like GoPro or Google Glasses have built-in microphones,' she said. 'Just a little warning message which makes sure people stop for a second and make sure they're doing what they think they're doing.'
Wiederspan has tested the device and said he's optimistic about its potential for improving patient safety, although he described the current GoPro headset as being a little bulky.
'Once it gets a bit smaller, I think you're going to get more buy-in from anesthesia providers to use it,' Wiederspan said. 'But I think it's going to be great. Anything that's going to make our job a little bit easier, spot any potential mistakes and help bring our focus back to the patient is a good thing.'
It isn't a fail-safe
Patient safety advocates have been calling for the implementation of error-preventing AI tools for some time. Dr. Dan Cole, vice chair of the anesthesiology department at UCLA Health and president of the Anesthesia Patient Safety Foundation, likened their potential for reducing risk to that of self-driving cars and improving road safety.
But while Cole is encouraged by the UW study and other AI-based research projects to prevent prescribing and dispensing errors in pharmacies, he said there are still questions surrounding the most effective ways to integrate these technologies into clinical care.
'The UW trial idea was indeed a breakthrough,' he said. 'As with driverless taxis, I'm a bit reluctant to use the technology at this point, but based on the potential for improved safety, I am quite sure I will use it in the future.'
Melissa Sheldrick, a patient safety advocate from Ontario who lost her 8-year-old son Andrew to a medication error in 2016, echoed those thoughts.
Sheldrick said that while technology can make a difference, the root cause of many medical errors is often a series of contributing factors, from lack of communication to vital data being compartmentalized within separate hospital departments or systems.
'Technology is an important layer in safety, but it's just one layer and cannot be relied upon as a fail-safe,' she said.
Others feel that AI can play a key role in preventing mistakes, particularly in demanding environments such as the operating room and emergency room, where creating more checklists and asking for extra vigilance has proved ineffective at stopping errors.
'These interventions either add friction or demand perfect attention from already overburdened providers in a sometimes chaotic reality with numerous distractions and competing priorities,' said Dr. Nicholas Cordella, an assistant professor of medicine at Boston University's Chobanian & Avedisian School of Medicine. 'AI-enabled cameras allow for passive monitoring without adding cognitive burden to clinicians and staff.'
AI is only going to be used more
AI tools are likely to be deployed to prevent errors in an even broader range of situations. At UW Medicine, Michaelsen is considering expanding her device to also detect the volume of the drug present in a syringe, as a way of preventing underdosing and overdosing errors.
'This is another area where harm can occur, especially in pediatrics, because you've got patients [in the same department] where there can be a hundredfold difference in size, from a brand-new premature baby to an overweight 18-year-old,' she said. 'Sometimes we have to dilute medications, but as you do dilutions there's chances for errors. It isn't happening to every single patient, but we do this enough times a day and to enough people that there is a possibility for people to get injured.'
Wiederspan said he can also see AI-powered wearable cameras being used in the emergency room and on the hospital floor to help prevent errors when dispensing oral medications.
'I know Kelly's currently working on using the system with intravenous drugs, but if it can be tailored to oral medications, I think that's going to help too,' Wiederspan said. 'I used to work in a cardiac unit, and sometimes these patients are on a plethora of drugs, a little cup full of all these pills. So maybe the AI can catch errors there as well.'
Of course, broader uses of AI throughout a hospital also come with data protection and privacy concerns, especially if the technology happens to be scanning patient faces and screens or documents containing their medical information. In UW Medicine's case, Michaelsen said this is not an issue as the tool is only trained to look for labels on syringes, and does not actively store any data.
'Privacy concerns represent a significant challenge with passive, always-on camera technology,' Cordella said. 'There needs to be clear standards with monitoring for breaches, and the technology should be introduced with full transparency to both patients and health care staff.'
He also noted the possibility of more insidious issues such as clinicians starting to excessively rely on AI, reducing their own vigilance and neglecting traditional safety practices.
'There's also a potential slippery slope here,' Cordella said. 'If this technology proves successful for medication error detection, there could be pressure to expand it to monitor other aspects of clinician behavior, raising ethical questions about the boundary between a supportive safety tool and intrusive workplace monitoring.'
But while the prospect of AI entering hospitals on a wider basis certainly presents the need for stringent oversight, many who work in the operating room feel it has enormous potential to do good by keeping patients safe and buying medical professionals valuable time in critical situations.
'Time is of the essence in an emergency situation where you're trying to give blood, lifesaving medications, checking vital signs, and you're trying to rush through these processes,' Wiederspan said. 'I think that's where this kind of wearable technology can really come into play, helping us shave off vital seconds and create more time where we can really focus on the patient.'
David Cox
David Cox is a freelance journalist focusing on all aspects of health, from fitness and nutrition to infectious diseases and future medicines. Prior to becoming a full-time journalist, he was a neuroscientist attempting to understand how and why the brain goes wrong.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Medical News Today
19 hours ago
- Medical News Today
Walking 100 minutes per day may help lower risk of chronic back pain
For many people, low back pain is chronic, meaning it is constant for at least three are several risk factors for chronic low back pain, such as not getting enough physical activity. A new study found that increasing the length of time and intensity of one's walks may help lower the risk of experiencing chronic low back to the World Health Organization (WHO), about 619 million people around the world were living with low back pain in 2020. This number is expected to hit 843 million by 2050. For many people, their low back pain is chronic, meaning it is constant for at least three months. And the pain is moderate to intense, affecting their daily lives. There are a number of risk factors for chronic low back pain. Some are not modifiable, such as age, genetics, and underlying medical conditions such as arthritis, spinal infections, spinal stenosis, osteoporosis, and fibromyalgia. However, several risk factors are modifiable, including obesity, improving lifting techniques, smoking, stress, and a sedentary lifestyle.'Low back pain is the leading cause of disability worldwide and accounts for the highest healthcare spending in the U.S.,' Rayane Haddadj, MS, a PhD candidate in the Department of Public Health and Nursing at the Norwegian University of Science and Technology in Norway, told Medical News Today. 'Identifying modifiable risk factors that can be targeted and easily implemented through public health policy and interventions is therefore of great importance.'Haddadj is the first author of a new study recently published in the journal JAMA Network Open that says increasing the length of time you walk, and its intensity, may help lower your risk for chronic low back pain. Walking 100+ minutes per day lowers low back pain riskFor this study, researchers analyzed medical data from more than 11,000 adult participants with an average age of about 55 from the Trøndelag Health (HUNT) Study in Norway, which ran from 2017 to 2019 with a follow-up in 2021 to 2023. At the start of the HUNT study, study participants did not have chronic low back pain. Researchers focused on the daily minutes each participant walked and their walking intensity, or how quickly they walked, which is calculated by using the metabolic equivalent of task (MET) per the study's conclusion, Haddadj and his team found that participants walking for more than 100 minutes per day were associated with a 23% lower risk of chronic low back pain, compared to those who walked less than 78 minutes per day.78 vs. 100 minutes a day'Our study shows that higher daily walking volume lowers the risk of developing chronic low back pain. The relationship was dose-dependent — meaning the more people walked, the lower their risk — up to about 100 minutes per day, after which the benefit leveled off. Even small increases in daily walking were associated with a decreased risk of chronic low back pain.' — Rayane Haddadj, MSWalking intensity also linked to lower pain riskAdditionally, researchers discovered that walking intensity was also associated with the risk of chronic low back pain, but to a lesser degree than walking volume. 'Our results suggest that a higher average walking intensity is associated with lower risk of chronic low back pain,' Haddadj said. 'However, the association was less pronounced than for walking volume. Further research, including a more robust assessment of walking intensity, could enhance our understanding of its association with the risk of chronic low back pain.''Our results reinforce a growing body of evidence showing that physical activity is essential for long-term health. Even small increases in daily activity can make a difference. Or as the World Health Organization puts it 'every move counts towards a better health'.'— Rayane Haddadj, MS'Walking is a simple, low cost, and accessible activity that can be promoted widely to reduce the burden of low back pain,' Haddadj added. 'Walking more could therefore be a simple yet powerful way to reduce risk of chronic low back pain and other diseases. Future studies investigating parameters such as timing and context of walking could enhance our understanding of the association between walking and risk of chronic low back pain.' Walking more may not always prevent back painMNT spoke with Neel Anand, MD, MCh Orth, a board certified orthopedic spine surgeon and director of the Cedars-Sinai Spine Center in Los Angeles, about this study. Anand commented that while he agrees with the study's findings that activity is better than no activity, he does not agree with the idea that if you walk, you will lower your risk for chronic back pain. 'Walking does not prevent back pain. Walking helps you get better because activity will help back pain always — it actually does. If you have chronic back pain, activity and walking actually makes it feel better than remaining stationary.' — Neel Anand, MD, MCh Orth'But the idea that you walk, you're not going to get back pain, makes no sense at all — that idea is not logical,' Anand continued. 'Back pain is a degenerative disorder. Yes, a couch potato has more chances of getting back pain than a person who's more active — that is correct. But to take that a step further and say, just because you walk, you're not going to get back pain is too far a reach. In my opinion, that's too far a conclusion to make.'
The Independent
4 days ago
- The Independent
What is new ‘Nimbus' Covid variant? Symptoms as cases grow in UK
Covid-19 is once again making headlines more than five years after the initial outbreak, with a new variant spreading in the UK and several countries across the globe. The new strain, named NB.1.8.1 and also known as 'Nimbus', now accounts for just over 10 per cent of global infections, with cases now confirmed in England and Northern Ireland. While there is no evidence that the new strain causes more severe symptoms, experts believe that it in can infect cells more efficiently and can trigger gastrointestinal symptoms such as diarrhoea, constipation and nausea. Since first being recognised in January 2025, the omicron variant has spread to several states across the US, Australia, Thailand and is the most dominant variant in China and Hong Kong. What is 'Nimbus' NB.1.8.1? The World Health Organisation has designated the NB.1.8.1 as a 'variant under monitoring', and comprises around 10.7 per cent of all submitted sequences. A WHO spokesperson said: " SARS-CoV-2 continues to evolve, and between January and May 2025, there were shifts in global SARS-CoV-2 variant dynamics. At the beginning of the year, the most prevalent variant tracked by WHO at the global level was XEC, followed by KP.3.1.1. "In February, circulation of XEC began to decline while that of LP.8.1 increased, with the latter becoming the most detected variant in mid-March. Since mid-April, the circulation of LP.8.1 has been slightly declining as NB.1.8.1 is increasingly being detected." While it first appeared in samples at the beginning of this year, data from GISAID, a global data of genetic sequences of major disease-causing viruses, show that the first known cases were registered at the end of April. What are the symptoms? While evidence has suggested that NB.1.8.1 may spread more easily than other variants, the WHO has not observed any signs that it has an increase in severity. "Data indicates that NB.1.8.1 does not lead to more severe illness compared to previous variants, although it appears to have a growth advantage, suggesting it may spread more easily," Subhash Verma, a professor of microbiology and immunology at the University of Nevada, Reno School of Medicine, told CBS News. "In other words, it is more transmissible." Common symptoms align with typical Omicron subvariants and include fatigue, fever and muscle aches. Dr Naveed Asif, GP at the London General Practice, warned the variant also has a distinctive symptom, a severe sore throat known as 'razor blade' throat, causing a sharp stabbing pain when you swallow, often at the back of the throat. So far, cases have been recorded in England, Northern Ireland and Wales, as well as in popular British tourist hotspots overseas. However, given the dwindling numbers of people testing for Covid-19, it has become increasingly difficult to know the true number of infections. Why has there been a global surge in cases? The 'Nimbus' variant, as it has been dubbed, does appear to be more transmissible than previous strains, with notable increases reported in India, Hong Kong, Singapore and Thailand. Dr Chun Tang, GP at UK private healthcare centre Pall Mall Medical, said: 'NB.1.8.1 isn't too different from the Omicron variant, but it does have some tweaks to its spike protein, which might make it spread a bit more easily or slip past some of our existing immunity. 'That said, early signs suggest it doesn't seem to cause more serious illness, but of course, we're still learning more about it.' Do the Covid vaccines work against NB.1.8.1?
The Independent
4 days ago
- The Independent
How ‘exercise snacking' can slash risk of diseases in just a few minutes
Technological advances and the habits of modern life have drastically reduced levels of physical activity around the world. The World Health Organisation (WHO) now warns that inactivity and sedentary lifestyles are one of the main risk factors for health problems and premature death. It is important, however, to draw a distinction between a sedentary lifestyle and physical inactivity. Inactivity is defined as a level of daily movement below the healthy recommendations (a minimum of 30 minutes a day of moderate exercise). Sedentary refers to the hours of the day when we are sitting or lying down. This includes time spent commuting and at work, or at home reading, using a phone or watching TV. Previously, people believed they just had to follow physical activity recommendations to stay healthy. However, research in recent years has shown that sedentary lifestyles can actually counteract the beneficial effects of regular physical activity. Even if a person completes their recommended 30 minutes of daily physical activity or 7,000 steps, sitting for 8 hours or more each day is still considered sedentary. A study published in the journal PLoS ONE highlights that, while vigorous exercise can help mitigate some of the negative effects of sedentary lifestyles, reducing total time spent sitting is also essential. Moreover, spending many hours sitting increases the overall risk of mortality by up to 40%, as highlighted by research published in the Journal of the American College of Cardiology. Active breaks and 'exercise snacks' Experts suggest that a good way to mitigate these risks is to take short breaks with movement throughout the day. According to a 2021 study, so-called 'active breaks' or ' exercise snacks ' improve cardiometabolic capacity. In 2024, a review concluded that taking 3 to 4 minute high-intensity active breaks three times a day decreased the risk of cardiovascular disease and death from cancer. An even more recent article confirmed that they are a practical and feasible way to improve cardiovascular fitness, metabolic capacity and muscle function. What kind of exercise is best? Until recently, it was not actually clear which type of exercise works best in this context. To answer this question, a recent study in the journal Medicine & Science in Sports compared the effectiveness of various activities for glucose control in overweight young men. The researchers divided volunteers into four groups: one group sat for 8 hours or more a day; another group took a 30-minute walking break; the third group went for a 3-minute walk every 45 minutes; and the fourth group did 10 squats every 45 minutes. They concluded that performing 10 squats or walking for 3 minutes every 45 minutes is more effective than walking for half an hour at a time in managing blood sugar levels. An accessible solution It is crucial to adopt more active lifestyle habits to mitigate the risks of a sedentary lifestyle. While the World Health Organisation recommends at least 150 minutes of moderate physical activity per week, it is also important to incorporate exercise and some strength work. But if this is not possible, then incorporate moderate to high intensity exercise snacks at home or in the office. Active breaks of 1 to 3 minutes every 45 minutes or every hour are sufficient. And in addition to the 10 squats, there are other alternatives, depending on each person's preferences: climbing stairs, taking short walks, jumping in place or even walking with long strides. Remember that these small daily doses of effort have great health benefits, improving cardiovascular function, metabolic capacity and muscle function. Beatriz Carpallo Porcar and Rita Galán Díaz are physiotherapists who are part of the teaching and research staff in physiotherapy at San Jorge University.
