Years ago, a friend was a nurse working nights at a hospital. She accidentally administered the wrong drug to a patient. I do not remember all the details, but the patient became distressed and had to be monitored. The next morning the empty vial was identified verifying it was the wrong drug. This mistake did not ultimately end in tragedy but that is not always the case. By some estimates 5% of patients experience a medical mistake. NBC News reported on a new method using artificial intelligence could reduce medication errors:
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.
This type of system is sometimes created using what is called human factors analysis or ergonomics. I took an industrial psychology class in graduate school that dealt with human factors design.
According to polls, 90% of anesthesiologists admit to causing a medical error at some point in their careers. (The other 10% are probably lying). A frequent problem is vial swaps. Injectable drugs come in vials that are then transferred to syringe. This can create opportunities for medication errors. The wrong drug may be transferred to a vial, and possibly the wrong dosage.
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.
Scientists are looking at artificial intelligence – using a type of eyewear scanner – that could verify the correct drug is used.
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.
In a study published late last year, Michaelsen reported that the device detected vial swap errors with 99.6% accuracy. All that is 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.
This technique sounds good but there is still room for medication errors. Hospital employees could get more careless if they think technology will take the guesswork out of which vial to inject. Of course, a vial could be loaded with the wrong drug at the pharmacy. All hospitals have pharmacies and pharmacy techs who load carts. Melissa Sheldrick, a patient safety advocate from Ontario shared her 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.
Medical errors and medical failures do not often result from simple mistakes. Most are the result of a series of failures that lead to serious errors. By the way, the same is true of plane crashes. A simple technical fix is unlikely to solve the problem of incorrect medication errors. A comprehensive system of risk analysis from the pharmacy to the hospital floor or operating room will be necessary to eliminate medication errors.
Read more at NBC News: Medical errors are still harming patients. AI could help change that.