GPs turn to AI to help with patient workloads.

This is the fifth feature in a six-part series looking at how AI is changing medical research and treatment.

Difficulty getting an appointment with a GP is a familiar gripe in the UK.

Even when an appointment is secured, The increasing workload faced by doctors That means those appointments may be shorter than the doctor or patient would like.

But Dr Deepali Misra Sharp, a GP partner in Birmingham, has found that AI has taken some of the administration out of her job, meaning she can focus more on patients.

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

“Usually when I’m with a patient, I write things down and it takes away from the consultation,” she says. “Now it means I can spend my entire time with the patient closing my eyes and actively listening. This leads to a more quality consultation.”

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

With workforce shortages while patient numbers continue to rise, GPs are under enormous pressure.

One full-time GP is now responsible for 2,273 patients, a 17% increase on September 2015. According to the British Medical Association (BMA)..

Could AI be the solution to reduce GP administrative tasks and help reduce burnout?

Some research suggests it might. 2019 report New technologies such as AI developed by Health Education England have been estimated to save as little as one minute per patient, equivalent to 5.7 million hours of GP time.

Meanwhile, Oxford University research In 2020, it was found that 44% of all administrative tasks in general practice could now be either mostly or fully automated, freeing up time to spend with patients.

One company working on this is Denmark’s Corti, which has developed AI that can listen to healthcare advice, over the phone or in person, and provide follow-up questions, indications, treatment options, as well as automated May also suggest taking notes.

Corti says its technology interacts with around 150,000 patients a day in hospitals, GP surgeries and healthcare institutions across Europe and the US, with around 100 million encounters per year.

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

“The AI ​​has access to relevant conversations and then it can figure out, well, in 10,000 similar conversations, most of the questions X has asked and those that haven’t been asked,” says Mr Malo.

“I imagine GPs have one-on-one consultations and therefore have very little time to consult with colleagues. It’s advising that colleague.”

They also say it can look at historical patient data. “It might ask, for example, do you remember to ask if the patient still has pain in the right knee?”

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

“The data is not leaving the system,” says Mr. Malo. Informing the patient is good practice, he says.

“If the patient contests it, the doctor can’t record. We see a few instances of that because the patient can see better documentation.

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

Meanwhile, currently, 1,400 GP practices across England are using C the Signs, a platform that uses AI to analyze patients’ medical records and identify various signs, symptoms and risk factors of cancer. Checks, and recommends what action should be taken.

“It can capture symptoms like cough, cold, bloating and basically in a minute see if there’s any relevant information from their medical history,” says CSigns chief executive and co-founder Dr Biya Bakshi. are,” a GP

AI is trained on published medical research papers.

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

She says they have performed more than 400,000 cancer risk assessments in a real-world setting, detecting more than 30,000 cancer patients in more than 50 different cancer types.

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

In a statement, Dr Katie Brammel Steiner, head of the General Practice Committee UK at the BMA, said: “We recognize that AI has the potential to completely transform NHS care – but if it is not implemented safely AI is subject to bias and error, can potentially compromise patient privacy, and is still a work in progress.

“While AI can be used to improve and complement what a GP can offer as another tool in their arsenal, it is not a silver bullet. We cannot wait for the promise of tomorrow’s AI.” , to provide the much-needed productivity, consistency and safety improvements needed today.”

Alison Dennis, co-head and co-head of law firm Taylor Wessing’s international life sciences team, warns that GPs need to tread carefully when using AI.

“There is a high risk of production AI tools not being thorough and complete, or not providing accurate diagnoses or treatment options, and even providing incorrect diagnoses or treatment options, ie creating delusions or medical misdiagnoses,” says Ms. Dennis. but generating output on the wrong training data,” says Ms. Dennis.

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

She says specialist medical products should be regulated and have some form of government approval.

“The NHS will also want to ensure that all data entered into the tool is maintained securely within the infrastructure of the NHS system, and further used by the tool provider as training data without the appropriate GDPR. Not to be absorbed. [General Data Protection Regulation] Security measures in place.”

For now, for GPs like Misra-Sharp, it has changed their work. “It has made me enjoy my counseling again instead of feeling time pressure.”