Techno

GPs turn to AI to help with patient workload

Susan Byrne

Technology reporter

Deepali Misra-sharp Dr. Deepali Misra-Sharp lies at her work desk, with photos and cards behind her.Deepali Misra Sharp

Dr. Dipali Misra Sharp uses artificial intelligence to help take notes

This is the fifth feature in a six-part series examining how artificial intelligence will change medical research and treatments.

The difficulty of getting a GP appointment is a familiar drawback in the UK.

Even when an appointment is secured, The rising workload faced by physicians This means that these meetings can be shorter than the doctor or patient.

But Dr Dipali Misra Sharp, a GP partner in Birmingham, has found that AI has alleviated the administration part of her job, meaning she can focus more on patients.

Dr. Mirsa Sharp started using Heidi Health, a free, AI-assisted medical transcription tool that listens and transcribes patient appointments, about four months ago and says it has made a big difference.

“Usually when I’m with a patient, I write things down and take them out of the consultation,” she says. “This now means that I can spend my entire time locking eyes with the patient and actively listening. It makes for a more high-quality consultation.”

She says the technology reduces her workflow, saving her “two to three minutes per consultation, if not more.” It prevents other benefits: “It reduces the risk of errors and omissions in my medical note.”

With the workforce declining while the number of patients continues to grow, GPS is facing enormous pressure.

The full-time GP is now responsible for 2,273 patients, an increase of 17% since September 2015, According to the British Medical Association (BMA).

Could AI be the solution to help GPs cut down on administrative tasks and reduce burnout?

Some research suggests it can. 2019 report Health Education England estimated a minimum saving of one minute per patient from new technologies such as AI, equivalent to 5.7 million hours of GP time.

Meanwhile, Research from Oxford University In 2020, it found that 44% of all administrative work in general practice can now be either automated or fully automated, freeing up time to spend with patients.

Corti Corti founders Lars Mallo (left) and Andreas Kleiff stand with the sea behind them.Kurti

Lars Mallo (left) and Andreas Kleeve, founders of the Danish medical company Corti

One company working on this is Corti’s Denmark, which has developed an AI that can listen to healthcare consultations, either over the phone or in person, and suggest follow-up questions, prompts, and treatment options, as well as automated transcription.

Corti says the technology handles about 150,000 patient interactions per day across hospitals, GP surgeries and healthcare organizations across Europe and the US, totaling about 100 million encounters per year.

“The idea is that the doctor can spend more time with the patient,” says Lars Mallo, co-founder and chief technology officer at Corti. He says the technology can suggest questions based on previous conversations you’ve heard in other health care situations.

“The AI ​​has access to relevant conversations, and then it might think, in 10,000 similar conversations, most questions asked X and were not asked,” says Mr Maaløe.

“I imagine that GPS has one consultation after another, and therefore I have little time to consult with colleagues. It gives colleague advice.”

He also says he can look at a patient’s historical data. “You could ask, for example, ‘Did you remember to ask if the patient still has pain in the right knee?’

But do patients want to listen to technology and record their conversations?

“The data doesn’t leave the system,” says Mr Maaløe. He says it’s good practice to inform the patient.

“If a patient blinks, the doctor won’t be able to record it. We see some examples of this where the patient can see better documentation.”

Dr. Misra Sharp says she lets patients know she has a listening device to help her take notes. “I haven’t had anyone have a problem with that yet, but if they did, I wouldn’t do it.”

C tags on women in the office looking at tags programC marks

C The tagging software is used to analyze the patients’ medical record

Meanwhile, 1,400-year-old practices across England are using Tags, a platform that uses artificial intelligence to analyze patients’ medical records and check for various signs, symptoms and risk factors of cancer, and recommend what action should be taken.

Says CEO and Co-Founder Dr. B. GP.

The AI ​​was trained on published medical research papers.

“For example, it might say that a patient is at risk for pancreatic cancer and would benefit from pancreatic screening, and then the doctor will decide to indicate those pathways,” says Dr. Bakshi. “It won’t diagnose, but it can make it easier.”

It says it has conducted more than 400,000 cancer risk assessments in a real-world setting, where they detected more than 30,000 patients with cancer across more than 50 different types of cancer.

An AI report published by the BMA this year found that “AI should be expected to transform healthcare jobs, rather than replace them, by automating routine tasks and improving efficiency.”

In a statement, Dr Katie Bramall Steiner, Chair of the UK General Practice Committee at the CRC, said: “We recognize that AI has the potential to completely transform NHS care – but if it is not enacted safely, it could also cause significant harm. It is subject to bias and error, can introduce patient privacy, and is still largely a work.

“While AI can be used to enhance and complement what GPs can offer as another tool in their arsenal, it is not a silver bullet that is needed today.”

Banner

GPS needs to tread carefully when using artificial intelligence, warns Alison Dennis, a partner and associate in Taylor Wessing’s international life sciences law team.

“There is a very high risk of AI tools not providing complete or correct pathways or pathways, and even giving wrong diagnoses or treatment pathways, i.e. producing hallucinations or placing outputs on training data that are clinically incorrect,” says Dennis.

“AI tools that have been trained on reliable datasets and then fully validated for clinical use – which will certainly be a specific clinical use, are more appropriate in clinical practice.”

She says specialty medical products should be regulated and receive some form of official approval.

“The NHS will also want to ensure that all data entered into the tool is held securely within the NHS system infrastructure, and is not absorbed for further use by the tool provider as training data without a GDPR.” [General Data Protection Regulation] Guarantees in place.”

For now, for GPS like Misra-Sharp, they have turned their business around. “It got me back to enjoying my consultations again instead of feeling stressed.”

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button