Jump to content
  • articles
    9,852
  • comments
    83
  • views
    12,493,550

Contributors to this article

About this News

Articles in the news

Alarm after EHRC says long Covid should not be treated as disability

People suffering from long Covid have reacted with alarm to comments by government’s equalities watchdog that the condition should not be treated as a disability.

Under the Equalities Act, anyone with a physical or mental impairment that has lasted for longer than 12 months and substantially impacted their ability to carry out normal day-to-day activities qualifies as disabled and is entitled to protection to ensure that they aren’t discriminated against in the workplace. This includes requesting that their employer makes “reasonable adjustments”, such as flexible working hours or home working, to ensure that they can continue working.

In a tweet posted on Sunday night, the Equalities and Human Rights Commission (EHRC), which was set up to promote and enforce equality and non-discrimination laws said: “Discussions continue on whether ‘long Covid’ symptoms constitute a disability. Without case law or scientific consensus, EHRC does not recommend that ‘long Covid’ be treated as a disability.”

The statement prompted immediate concern and confusion from long Covid support groups and unions.

Dr Jenny Ceolta-Smith, an employment advocate for Long Covid Support and co-founder of Occupational Therapy for Long Covid, said: “There is already disbelief of workers’ long Covid symptoms within the workplace, and this harmful announcement by the EHRC may make it much harder for workers to gain the support that they need from colleagues and line managers. It may even mean more jobs are lost.”

Read full story

Source: The Guardian, 9 May 2022

Read more

Alabama doctor on treating unvaccinated, dying COVID patients

In this article, an Alabama doctor describes how her unvaccinated patients are dying from Covid-19. 

Dr Brytney Cobia, a hospitalist at Grandview Medical Center in Birmingham said in a Facebook post on Sunday, “I’m admitting young healthy people to the hospital with very serious COVID infections. One of the last things they do before they’re intubated is beg me for the vaccine. I hold their hand and tell them that I’m sorry, but it’s too late.”

Read full story.

Source: Advance Local, 21 July 2021

Read more
 

Aishwarya Aswath's parents say Perth Children's Hospital staff ignored their pleas for help as daughter was dying

The mother of a seven-year-old girl who died at Perth Children's Hospital says she pleaded with staff to help her daughter but was not taken seriously.

Aishwarya Aswath died in April last year after attending the Perth Children's Hospital (PCH) with a high temperature and cold hands.

The Perth Coroner's Court on Wednesday heard a statement from Aishwarya's mother Prasitha Sasidharan, who described how she grew increasingly worried about her daughter while in the hospital waiting room. She approached staff five times while they were in the waiting room for almost two hours. "I feel like I was ignored and not taken seriously," she said. The court heard from both parents on Wednesday, the start of an eight-day inquest. After Aishwarya died her father wanted to hold her but was only allowed to do so for a brief time. In his statement, read to the court, he said there were "many missed opportunities to save her."

Former PCH chief executive Aresh Anwar said the hospital was grappling with a rise in mental health presentations and a shortage of staff when Aishwarya died.

Read full story

Source: ABC News (24 August 2022)

Read more

Airedale NHS FT delay EPR go-live for further safety testing

Airedale NHS Foundation Trust told Digital Health News that it has pushed back the go-live date for its Oracle Health electronic patient record (EPR) system to allow further testing to ensure it is safe and efficient.

The Oracle Health Millennium EPR is able to store more in-depth clinical information on patients in one place, referred to as a ‘single source of truth’.

In a statement published on its website, the trust said: “Our aim was to introduce our new EPR in September 2024. This date has now been changed to November 2024.

“This date has been reviewed to ensure that when the EPR goes live it is safe and efficient. We would never introduce a new system unless we are confident that it will be safe.”

David Crampsey, deputy chief executive at Airedale NHS FT and chair of the Electronic Patient Record Transformation Assurance Group, said: “We have been working alongside our technical supplier, Oracle Health, as well as a wide range of stakeholders to ensure the EPR system meets our functionality requirements and that we have a robust system in place.

“We have moved the go-live date for the new system to enable our technical teams to incorporate the developments based on stakeholder feedback and allow for further testing.

“The comprehensive testing element of the programme ensures that the system is as safe as possible and will mean a smoother transition for both patients and staff”.

Read full story

Source: Digital Health News, 9 September 2024

Related reading on the hub:

Read more

Air pollution is the largest environmental health risk we face today - call for a Fossil Fuel Non-Proliferation Treaty

Every year, air pollution causes up to 36,000 deaths in the UK.  The World Health Organization and the UK Government recognise that air pollution is the largest environmental health risk we face today. 

Millions of people around the world breathe polluted air that puts their respiratory and cardiovascular health, and in some cases even their lives, at risk. Phasing out fossil fuels would be a major step in protecting health for current and future generations.

More than a thousand health professionals have already endorsed the call for a treaty. 

Add your name to endorse the call for a treaty.

Next week, the Global Climate and Health Alliance are planning a major press launch of the health community's letter calling for a Fossil Fuel Non-Proliferation Treaty and want to secure as many signatures as possible. They are encouraging healthcare professionals to help to build momentum by inviting two—or more—of your health colleagues to sign the health letter before the launch on 14 September.

Invite your colleagues to sign the health letter

By clicking the link above, you'll be taken to a form where you can send a short note of invitation to a colleague to sign the letter. They will be sent your note, as well as a link to some additional information about the Fossil Fuel Non-Proliferation Treaty. The form can only send one email at a time, but you use the form as many times as you wish.

Read more

Aid cuts forcing people in 70 countries to miss out on much-needed medical care, WHO warns

People in at least 70 countries are missing out on much-needed medical treatment thanks to aid cuts by the US and other nations, the World Health Organization (WHO) director has said – in a stark warning about the colossal impact of these moves.

The Donald Trump-sanctioned slashing of US-funded programmes under the United States Agency for International Development (USAID) is the most prominent example. But Germany, France and the Netherlands have also taken an axe to aid spending, while the UK is set to cut foreign assistance spending by billions of pounds.

"Patients are missing out on treatments, health facilities have closed, health workers have lost their jobs, and people face increased out-of-pocket health spending," WHO Director-General Tedros Adhanom Ghebreyesus said in an address to the World Health Assembly.

“Many ministers have told me that sudden and steep cuts to bilateral aid are causing severe disruption in their countries and imperilling the health of millions of people,” Dr Tedros added.

Read full story

Source: The Independent, 19 May 2025

Read more

Aid cuts could have ‘pandemic-like effects’ on maternal deaths, WHO warns

More women risk dying in pregnancy and childbirth because of aid cuts by wealthy countries, which could have “pandemic-like effects”, UN agencies have warned.

Pregnant women in conflict zones are the most vulnerable, and face an “alarmingly high” risk that is already five times greater than elsewhere, according to a new UN report on trends in maternal mortality.

Deaths due to complications in pregnancy and childbirth declined 40% globally between 2000 and 2023, but progress is “fragile” and has slowed since 2016, the authors said. An estimated 260,000 women died in 2023 from pregnancy-related causes.

There is a “threat of major backsliding” amid “increasing headwinds”, the authors said. US funding cuts this year have meant clinics closing and health workers losing their jobs, and disrupted the supply chains that deliver life-saving medicines to treat leading causes of maternal death such as haemorrhage, pre-eclampsia and malaria, World Health Organization experts warned.

The report – itself part-funded by the US – revealed that maternal deaths rose by 40,000 in 2021 due to the Covid pandemic, probably driven by complications from the virus itself and by the disruptions to healthcare.

Dr Bruce Aylward, an assistant director general at the WHO, said that rise could offer insights into the possible impact of current aid cuts.

“With Covid, we saw an acute shock to the system, and what’s happening with financing is an acute shock,” he said.

“Countries have not had time to put in place and plan for what other financing they’re going to use, what other workers they’re going to use, [and] what are the trade-offs they’re going to make in their systems to try to make sure the most essential services can continue.”

The shock to services, he said, would lead to “pandemic-like effects”, adding that funding cuts risked not only progress, “but you could have a shift backwards”.

Read full story

Source: The Guardian, 6 April 2025

Read more

AI will soon be everywhere in the NHS. It’s a risk for women and ethnic minorities, experts say

Artificial intelligence (AI) could lead to UK health services that disadvantage women and ethnic minorities, scientists are warning.

They are calling for biases in the systems to be rooted out before their use becomes commonplace in the NHS.

They fear that without that preparation AI could dramatically deepen existing health inequalities in our society.

A new study has found that AI models built to identify people at high risk of liver disease from blood tests are twice as likely to miss disease in women as in men.

The researchers examined the state of the art approach to AI used by hospitals worldwide and found it had a 70% success rate in predicting liver disease from blood tests.

But they uncovered a wide gender gap underneath – with 44% of cases in women missed, compared with 23% of cases among men.

“AI algorithms are increasingly used in hospitals to assist doctors diagnosing patients. Our study shows that, unless they are investigated for bias, they may only help a subset of patients, leaving other groups with worse care,” said Isabel Straw, of University College London, who led the study.

“We need to be really careful that medical AI doesn’t worsen existing inequalities.”

Read full story

Source: iNews, 9 July 2022

Read more

AI use in breast cancer screening cuts rate of later diagnosis by 12%, study finds

The use of artificial intelligence in breast cancer screening reduces the rate of a cancer diagnosis by 12% in subsequent years and leads to a higher rate of early detection, according to the first trial of its kind.

Researchers said the study was the largest to date looking at AI use in cancer screening. It involved 100,000 women in Sweden who were part of mammography screening and were randomly assigned to either AI-supported screening or to a standard reading by two radiologists between April 2021 and December 2022.

The AI system worked by analysing the mammograms and assigning low-risk cases to a single reading and high-risk cases to a double one by radiologists, as well as highlighting suspicious findings to support radiologists.

Mammography screening supported by AI reduced cancer diagnoses in the years after a breast screening appointment by 12%, according to the research, published in The Lancet. There were 1.55 cancers per 1,000 women in the AI-supported group compared with 1.76 cancers per 1,000 women in the control group.

More than four in five cancer cases (81%) in the AI-supported mammography group were detected at the screening stage, compared with just under three quarters (74%) in the control group, and there were also almost a third (27%) fewer aggressive sub-type cancers in the AI group compared with the control.

Dr Kristina Lång, from Lund University in Sweden and the lead author of the study, said that AI-supported mammography could help detect cancers at an early stage, but that there were caveats.

“Widely rolling out AI-supported mammography in breast cancer screening programmes could help reduce workload pressures among radiologists, as well as helping to detect more cancers at an early stage, including those with aggressive subtypes,” Lång said.

“However, introducing AI in healthcare must be done cautiously, using tested AI tools and with continuous monitoring in place to ensure we have good data on how AI influences different regional and national screening programmes and how that might vary over time.”

Read full story

Source: The Guardian, 29 January 2026

Read more
 

AI use in breast cancer screening as good as two radiologists, study finds

The use of artificial intelligence in breast cancer screening is safe and can almost halve the workload of radiologists, according to the world’s most comprehensive trial of its kind.

Breast cancer is the most prevalent cancer globally, according to the World Health Organization, with more than 2.3 million women developing the disease every year.

Screening can improve prognosis and reduce mortality by spotting breast cancer at an earlier, more treatable stage. Preliminary results from a large study suggest AI screening is as good as two radiologists working together, does not increase false positives and almost halves the workload.

The interim safety analysis results of the first randomised controlled trial of its kind involving more than 80,000 women were published in the Lancet Oncology journal.

Read full story

Source: Guardian 2 August 2023

Read more
 

AI tutor outperforms human experts in training medical students to remove brain tumours

Medical students aided by an AI tutor outperformed peers taught remotely by human experts in a complicated surgical training procedure, new research reports.

The Neurosurgical Simulation and Artificial Intelligence Learning Centre in Montreal, Canada, randomly assigned 70 students feedback and assistance from either a sophisticated AI system, a remote expert human instructor, or neither, while they removed virtual brain tumours using a neurosurgical simulator.

The AI system, called the Virtual Operative Assistant (VOA), delivered personalised feedback to its students via a machine learning algorithm to teach them safe surgical techniques.

Human instructors observed the students over a live feed and gave instructions based on their performance.

The students tutored by the AI system learned surgical skills 2.6 times faster and performed 36 per cent better than those advised by human experts, without experiencing the heightened stress the researchers had anticipated.

Using AI training models to tutor students could be an effective way to improve their skills and patient safety while reducing the burdens placed on human instructors, the study, published in the Journal of the American Medical Association, found.

“Artificially intelligent tutors like the VOA may become a valuable tool in the training of the next generation of neurosurgeons,” said Dr Rolando Del Maestro, the study’s senior author.

Read full story

Source: iNews, 22 February 2022

Read more

AI tools used by English councils downplay women’s health issues, study finds

Artificial intelligence tools used by more than half of England’s councils are downplaying women’s physical and mental health issues and risk creating gender bias in care decisions, research has found.

The study found that when using Google’s AI tool “Gemma” to generate and summarise the same case notes, language such as “disabled”, “unable” and “complex” appeared significantly more often in descriptions of men than women.

The study, by the London School of Economics and Political Science (LSE), also found that similar care needs in women were more likely to be omitted or described in less serious terms.

Dr Sam Rickman, the lead author of the report and a researcher in LSE’s Care Policy and Evaluation Centre, said AI could result in “unequal care provision for women”.

“We know these models are being used very widely and what’s concerning is that we found very meaningful differences between measures of bias in different models,” he said. “Google’s model, in particular, downplays women’s physical and mental health needs in comparison to men’s.

“And because the amount of care you get is determined on the basis of perceived need, this could result in women receiving less care if biased models are used in practice. But we don’t actually know which models are being used at the moment.”

AI tools are increasingly being used by local authorities to ease the workload of overstretched social workers, although there is little information about which specific AI models are being used, how frequently and what impact this has on decision-making.

Read full story

Source: The Guardian, 11 August 2025

Read more

AI to help doctors spot broken bones on X-rays

Artificial intelligence (AI) has the potential to reduce the number of broken bones missed when doctors analyse X-rays, according to the National Institute for Health and Care Excellence (NICE).

The health assessment body says research suggests the technology is safe and could speed up diagnosis, relieving pressure on clinicians and reducing the need for some follow-up appointments.

AI will not be working alone - each image will be reviewed by a healthcare professional.

NICE says broken bones are missed in 3-10% of cases - it is the most common diagnostic error in emergency departments.

And the trained experts who perform and analyse thousands of X-ray images every day in the NHS are in short supply, with a huge workload.

Vacancy rates are 12.5% for radiologists and 15% for radiographers, according to the long-term plan for the NHS in England, external.

The solution, according to NICE, is to harness the power of AI to work alongside clinicians.

Mark Chapman, director of health technology at NICE, said it would make their job easier.

“These AI technologies are safe to use and could spot fractures which humans might miss, given the pressure and demands these professional groups work under," he said.

Read full story

Source: BBC News, 22 October 2024

Read more

AI to be deployed more widely across the NHS as new funding announced

Artificial intelligence (AI) is set to be rolled out more widely across the NHS in a bid to diagnose diseases and treat patients faster.

The Government has announced a £21 million funding pot that NHS trusts can apply for to implement AI tools for the likes of medical imaging and decision support.

This includes tools that analyse chest X-rays in suspected cases of lung cancer.

AI technology that can diagnose strokes will also be available to all stroke networks by the end of 2023 – up from 86% – and could help patients get treated faster and lead to better health outcomes.

The Department of Health and Social Care (DHSC) said the technology could help cut NHS waiting lists ahead of winter.

Read full story

Source: The Independent, 23 June 2023

 

Read more

AI stethoscope could detect major heart conditions in seconds

Stethoscopes powered by artificial intelligence (AI) could help detect three different heart conditions in seconds, researchers say.

The original stethoscope, invented in 1816, allows doctors to listen to the internal sounds of a patient's body.

A British team conducted a study using a modern version and say they found it can spot heart failure, heart valve disease and abnormal heart rhythms almost instantly.

The tool could be a "real game-changer" resulting in patients being treated sooner, the researchers say - with plans to roll the device out across the UK following a study involving 205 GP surgeries in west and north-west London.

The device replaces the traditional chest piece with a device around the size of a playing card. It uses a microphone to analyse subtle differences in heartbeat and blood flow that the human ear cannot detect.

It takes an ECG (electrocardiogram), recording electrical signals from the heart, and sends the information to the cloud to be analysed by AI trained on data from tens of thousands of patients.

The study by Imperial College London and Imperial College Healthcare NHS Trust saw more than 12,000 patients from 96 surgeries examined with AI stethoscopes manufactured by US firm Eko Health. They were then compared to patients from 109 GP surgeries where the technology was not used.

Those with heart failure were 2.33 times more likely to have it detected within 12 months when examined with the AI stethoscope, researchers said.

Dr Sonya Babu-Narayan, clinical director at the British Heart Foundation (BHF) and consultant cardiologist, said such innovations are vital "because so often this condition is only diagnosed at an advanced stage when patients attend hospital as an emergency".

"Given an earlier diagnosis, people can access the treatment they need to help them live well for longer."

Read full story

Source: BBC News, 30 August 2025

Read more

AI stethoscope can help spot life-threatening heart disease years earlier, study finds

A stethoscope that uses artificial intelligence could help doctors detect serious heart valve disease years earlier, potentially saving thousands of lives, a new study suggests.

It is estimated that 41 million people worldwide, including 1.5 million people in the UK, live with a type of heart valve disease, which can lead to heart failure, hospital admissions and death.

Early diagnosis is vital for successful treatment, but the condition can be symptom-free in its early stages before causing dizziness, shortness of breath and heart palpitations, which can be confused with other conditions, meaning some patients do not get a diagnosis until the disease is advanced.

Currently, diagnosis of valve disease relies on echocardiography, a type of ultrasound scan that is expensive and time-consuming. While doctors do listen to the heart using a stethoscope, this is not routinely done in short GP appointments, and is known to miss many cases.

But the new technology that works with digital stethoscopes was found to outperform GPs at detecting valve disease, and could be used as a rapid screening tool.

“Valve disease is a silent epidemic,” said Professor Anurag Agarwal from Cambridge’s department of engineering, who led the research. “An estimated 300,000 people in the UK have severe aortic stenosis alone, and around a third don’t know it. By the time symptoms appear, outcomes can be worse than for many cancers.”

For the study published in the journal npj Cardiovascular Health, researchers analysed heart sounds from nearly 1,800 patients using an AI algorithm trained to recognise valve disease.

The AI was found to correctly identify 98% cent of patients with severe aortic stenosis, the most common form of valve disease requiring surgery, and 94% cent of those with severe mitral regurgitation, where the heart valve does not fully close and blood leaks backwards across the valve.

Read full story

Source: The Independent, 10 February 2026

Read more
 

AI standards need to be created to protect patient safety, experts warn

Appropriate methods and standards around artificial intelligence (AI) need to be created to protect patient safety, experts have said. Responding to the Government’s pledge of £250 million for a National Artificial Intelligence (AI) Lab, Matthew Honeyman, researcher at The Kings Fund, said the NHS workforce needs to be equipped with digital skills for the benefits of new technologies to be realised.

“AI applications are in development for many different use cases – from screening, to treatment, to admin work – there needs to be appropriate methods and standards developed for safe deployment and evaluation of these solutions as they enter the health system,” he told Digital Health.

Adam Steventon, Director of Data Analytics at the Health Foundation, said the commitment was a “positive step” but that technology needs to be driven by patient need and “not just for technology’s sake”. “Robust evaluation therefore needs to be at the heart of any drive towards greater use of technology in the NHS, so that technologies that are shown to be effective can be spread further, and patients protected from any potential harm,” he said.

Read full story

Source: Digital Health, 9 August 2019

 

Read more

AI software predicting daily A&E admissions rolled out in 100 NHS hospitals

New artificial intelligence software being rolled-out in NHS hospitals will be able to predict daily A&E admissions weeks in advance.

The software, which launched in 100 hospitals across England on Monday, analyses data, including Covid infections rates, 111 calls and traffic to predict the number of patients that will seek emergency care.

It also takes into consideration public holidays, such as New Year’s Eve, when A&E is more likely to be busy.

The AI software is being rolled after trials showed an “impressive” ability to forecast admissions up to three weeks in advance.

The NHS believes it will help tackle the record waiting list and allow hospitals to more easily manage their patient and bed capacity, prepare for busier days and staff up when needed.

Nine trusts were given the software to use during the pandemic which notified them of expected spikes in cases, staff levels and numbers of beds and equipment necessary.

However, hospitals receiving the new equipment have also been warned uncertainties within the data mean the system should be used as a “starting point to consider an operational response, not as a definite signal for action.”

Read full story

Source: The Independent, 28 March 2022

Read more

AI skin cancer diagnoses risk being less accurate for dark skin – study

Artificial intelligence (AI) systems being developed to diagnose skin cancer run the risk of being less accurate for people with dark skin, research suggests.

The potential of AI has led to developments in healthcare, with some studies suggesting image recognition technology based on machine learning algorithms can classify skin cancers as successfully as human experts.

NHS trusts have begun exploring AI to help dermatologists triage patients with skin lesions. But researchers say more needs to be done to ensure the technology benefits all patients, after finding that few freely available image databases that could be used to develop or “train” AI systems for skin cancer diagnosis contain information on ethnicity or skin type. Those that do have very few images of people with dark skin.

Dr David Wen, first author of the study from the University of Oxford, said: “You could have a situation where the regulatory authorities say that because this algorithm has only been trained on images in fair-skinned people, you’re only allowed to use it for fair-skinned individuals, and therefore that could lead to certain populations being excluded from algorithms that are approved for clinical use."

“Alternatively, if the regulators are a bit more relaxed and say: ‘OK, you can use it [on all patients]’, the algorithms may not perform as accurately on populations who don’t have that many images involved in training.”

That could bring other problems including risking avoidable surgery, missing treatable cancers and causing unnecessary anxiety, the team said.

Read full story

Source: The Guardian, 9 November 2021

Read more

AI pregnancy scans twice as fast and just as accurate as traditional sonograms, study finds

Artificial intelligence is being hailed as a potential game-changer in prenatal care, cutting down the time it takes to identify fetal abnormalities by almost half, according to a groundbreaking new study.

Researchers at King’s College London and Guy’s and St Thomas’ NHS Foundation Trust found as well as being faster, AI is just as accurate as traditional methods, offering the potential to revolutionise the 20-week scan.

The technology, tested in the first trial of its kind, could significantly reduce scan times, easing anxiety for expectant parents and freeing up sonographers to focus on potential problem areas.

The AI also proved more reliable than human sonographers in taking crucial measurements.

This improved accuracy offers the potential for earlier detection of potential issues, allowing medical professionals to intervene sooner if required.

The AI tool was also found to alter the way in which the scan is performed, as sonographers no longer needed to pause, save images or measure during the scan.

Read full story

Source: The Independent, 27 March 2025

Read more

AI poses existential threat and risk to health of millions, experts warn

AI could harm the health of millions and pose an existential threat to humanity, doctors and public health experts have said as they called for a halt to the development of artificial general intelligence until it is regulated.

Artificial intelligence has the potential to revolutionise healthcare by improving diagnosis of diseases, finding better ways to treat patients and extending care to more people.

But the development of artificial intelligence also has the potential to produce negative health impacts, according to health professionals from the UK, US, Australia, Costa Rica and Malaysia writing in the journal BMJ Global Health.

The risks associated with medicine and healthcare “include the potential for AI errors to cause patient harm, issues with data privacy and security and the use of AI in ways that will worsen social and health inequalities”, they said.

One example of harm, they said, was the use of an AI-driven pulse oximeter that overestimated blood oxygen levels in patients with darker skin, resulting in the undertreatment of their hypoxia.

Read full story

Source: The Guardian, 10 May 2023

Read more

AI outperforms surgeons in writing post-op reports

A study has demonstrated that AI can create more accurate operative reports than surgeons.

Published in the Journal of the American College of Surgeons, it is the first report on fully automated, video-based AI surgical documentation.

The research highlights the potential of AI-driven solutions to reduce administrative burdens and improve surgical documentation.

Surgeons frequently regard the creation of operative reports as essential yet time-consuming. These reports are inevitably subjective and may contain inaccuracies or incomplete information.

The administrative task of documentation has also been recognised as a potential factor in physician burnout.

Recent advancements in AI, especially in computer vision, have allowed automated systems to accurately detect surgical steps from video footage.

Researchers aimed to create a platform that automates the generation of video-based AI surgical operative reports for robotic-assisted radical prostatectomy (RARP).

Using an AI-powered algorithm, surgical steps were automatically identified in video recordings and mapped to pre-specified text to generate narrative AI operative reports.

The accuracy of these AI-generated reports was then compared to traditional surgeon-written reports using an expert review of raw surgical video footage as the gold standard.

The findings suggest that AI-driven operative reporting can enhance accuracy, reduce the documentation burden, and improve transparency in surgical procedures.

Read full story

Source: Surgery News, 24 March 2025

Read more

AI outperforms doctors in Harvard trial of emergency triage diagnoses

A groundbreaking Harvard study has found that AI systems outperformed human doctors in high-pressure emergency medicine triage, diagnosing more accurately in the potentially life and death moments when people are first rushed to hospital.

The results were described by independent experts as showing “a genuine step forward” in the clinical reasoning of AIs and came as part of trials that tested the responses of hundreds of doctors against an AI.

The authors said the results, published in the journal Science, showed large language models (LLMs) “have eclipsed most benchmarks of clinical reasoning”.

One experiment focused on 76 patients who arrived at the emergency room of a Boston hospital. An AI and a pair of human doctors were each given the same standard electronic health record to read – typically including vital sign data, demographic information and a few sentences from a nurse about why the patient was there. The AI identified the exact or very close diagnosis in 67% of cases, beating the human doctors, who were right only 50%-55% of the time.

It showed the AIs’ advantage was particularly pronounced in triage circumstances requiring rapid decisions with minimal information. The diagnosis accuracy of the AI – OpenAI’s o1 reasoning model – rose to 82% when more detail was available, compared with the 70-79% accuracy achieved by the expert humans, though this difference was not statistically significant.

But it is not curtains for emergency doctors yet, the researchers said. The study only tested humans against AIs looking at patient data that can be communicated via text. The AI’s reading of signals, such as the patient’s level of distress and their visual appearance, were not tested. That means the AI was performing more like a clinician producing a second opinion based on paperwork.

“I don’t think our findings mean that AI replaces doctors,” said Arjun Manrai, one of the lead authors of the study who heads an AI lab at Harvard Medical School. “I think it does mean that we’re witnessing a really profound change in technology that will reshape medicine.”

Read full story

Source: The Guardian, 30 April 2026

Read more

AI model predicts patients at most risk of complication during treatment for advanced kidney failure

Artificial intelligence experts and healthcare professionals in Portsmouth have come together to help prevent a common and painful complication in advanced kidney failure treatment.

A study led by the University of Portsmouth and Portsmouth Hospitals University NHS Trust (PHUT) has developed an AI model to predict which patients are most at risk of their blood pressure dropping during dialysis; a condition known as intradialytic hypotension (IDH).

3 million people have Chronic Kidney Disease in the UK and 31,000 of these are on haemodialysis (Kidney Care UK), where their blood is circulated through a machine to clean it of toxins.

One of the most common complications for patients undergoing this treatment at home or in centres is IDH, which occurs when their blood pressure drops suddenly. It is associated with increased mortality and hospitalisations, and until now there has been no reliable way to predict if it will occur.

Pre-dialysis and real-time data were collected from 10 treatment centres over two decades (2000-2020), involving 3,944 patients. The team used data comprising a total of 73,323 sessions with 36,662 IDH events.

Using this information, they identified 33 variables to determine the most at-risk individuals. These were all observations that are routinely collected during clinical care, such as weight, temperature, age, blood pressure, medication and treatment details.

Project lead, Dr Shamsul Masum from the University’s School of Electrical and Mechanical Engineering, said: “This research highlights the value of using machine learning in healthcare, particularly in complex situations like haemodialysis. Predicting hypotension not only helps clinicians intervene early but also opens the door to personalised care.

"As we continue to develop and refine these models, the goal is to create a practical decision-support system that could enhance dialysis management, patient safety and quality of care.”

Read full story

Source: University of Portsmouth, 23 October 2024

Read more

AI medical advice on drugs could lead to death in one in five cases

Dr AI could be providing 'potentially harmful' medication advice, a concerning study has suggested. 

German researchers found more than a fifth of AI powered chatbot answers to common prescription drug questions could 'lead to death or severe harm'. 

Experts urged patients not to rely on such search engines to give them accurate and safe information. 

Medics were also warned against recommending the tools until more 'precise and reliable' alternatives are made available. 

In the study, the scientists from the University of Erlangen-Nuremberg, pinpointed the 10 most frequently asked patient questions for the 50 most prescribed drugs in the US.

These included adverse drug reactions, instructions for use and contraindications — reasons why the medication should not be taken. 

Using Bing copilot — a search engine with AI-powered chatbot features developed by Microsoft — researchers assessed all 500 responses, against answers given by clinical pharmacists and doctors with expertise in pharmacology. 

Responses were also compared against a peer-reviewed up-to-date drugs information website. 

They found chatbot statements didn’t match the reference data in over a quarter (26%) of all cases and were fully inconsistent in just over 3%. 

But further analysis of 20 answers also revealed four in ten (42%) were considered to lead to moderate or mild harm and 22%, death or severe harm. 

Read full story

Source: Mail Online, 11 October 2024

Read more

© 2026 Patient Safety Learning. All rights reserved.

Patient Safety Learning is registered as a charity with the Charity Commission Registration number 1180689.

×
  • Create New...

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.