Tag: artificial intelligence

Categories : Hospitals Medical Research & TechnologyTags :

Would it be Ethical to Entrust Human Patients to Robotic Nurses?

On By ModernMedia
Photo by Alex Knight on Unsplash

Advancements in AI have resulted in typically human characteristics like creativity, communication, critical thinking, and learning being replicated by machines for complex tasks like driving vehicles and creating art. With further development, these human-like attributes may develop enough to one day make it possible for robots and AI to be entrusted with nursing, a very ‘human’ practice. But… would it be ethical to entrust the care of humans to machines?

In a step toward answering this question, Japanese researchers recently explored the ethics of such a situation in the journal Nursing Ethics.

The study was conducted by Associate Professor Tomohide Ibuki from Tokyo University of Science, in collaboration with medical ethics researcher Dr Eisuke Nakazawa from The University of Tokyo and nursing researcher Dr Ai Ibuki from Kyoritsu Women’s University.

“This study in applied ethics examines whether robotics, human engineering, and human intelligence technologies can and should replace humans in nursing tasks,” says Dr Ibuki.

Nurses show empathy and establish meaningful connections with their patients, a human touch which is essential in fostering a sense of understanding, trust, and emotional support. The researchers examined whether the current advancements in robotics and AI can implement these human qualities by replicating the ethical concepts attributed to human nurses, including advocacy, accountability, cooperation, and caring.

Advocacy in nursing involves speaking on behalf of patients to ensure that they receive the best possible medical care. This encompasses safeguarding patients from medical errors, providing treatment information, acknowledging the preferences of a patient, and acting as mediators between the hospital and the patient. In this regard, the researchers noted that while AI can inform patients about medical errors and present treatment options, they questioned its ability to truly understand and empathise with patients’ values and to effectively navigate human relationships as mediators.

The researchers also expressed concerns about holding robots accountable for their actions. They suggested the development of explainable AI, which would provide insights into the decision-making process of AI systems, improving accountability.

The study further highlights that nurses are required to collaborate effectively with their colleagues and other healthcare professionals to ensure the best possible care for patients. As humans rely on visual cues to build trust and establish relationships, unfamiliarity with robots might lead to suboptimal interactions. Recognising this issue, the researchers emphasised the importance of conducting further investigations to determine the appropriate appearance of robots for facilitating efficient cooperation with human medical staff.

Lastly, while robots and AI have the potential to understand a patient’s emotions and provide appropriate care, the patient must also be willing to accept robots as care providers.

Having considered the above four ethical concepts in nursing, the researchers acknowledge that while robots may not fully replace human nurses anytime soon, they do not dismiss the possibility. While robots and AI can potentially reduce the shortage of nurses and improve treatment outcomes for patients, their deployment requires careful weighing of the ethical implications and impact on nursing practice.

“While the present analysis does not preclude the possibility of implementing the ethical concepts of nursing in robots and AI in the future, it points out that there are several ethical questions. Further research could not only help solve them but also lead to new discoveries in ethics,” concludes Dr Ibuki.

Source: Tokyo University of Science

Categories : Medical Research & TechnologyTags :

Dr Robot Will See You Now: Medical Chatbots Need to be Regulated

On By ModernMedia
Photo by Alex Knight on Unsplash

The Large Language Models (LLM) used in chatbots may appear to offer reliable, persuasive advice in a format which mimics conversation but in they can offer potentially harmful information when prompted with medical questions. Therefore, any LLM-chatbot in a medical setting would require approval as a medical device, argue experts in a paper published in Nature Medicine.

The mistake often made with LLM-chatbots is that they are a true “artificial intelligence” when in fact they are more closely related to the predictive text in a smartphone. They mostly use conversations and text scraped from the internet, and use algorithms to associate words and sentences in a manner that appears meaningful.

“Large Language Models are neural network language models with remarkable conversational skills. They generate human-like responses and engage in interactive conversations. However, they often generate highly convincing statements that are verifiably wrong or provide inappropriate responses. Today there is no way to be certain about the quality, evidence level, or consistency of clinical information or supporting evidence for any response. These chatbots are unsafe tools when it comes to medical advice and it is necessary to develop new frameworks that ensure patient safety,” said Prof Stephen Gilbert at TU Dresden.

Challenges in the regulatory approval of LLMs

Most people research their symptoms online before seeking medical advice. Search engines play a role in decision-making process. The forthcoming integration of LLM-chatbots into search engines may increase users’ confidence in the answers given by a chatbot that mimics conversation. It has been demonstrated that LLMs can provide profoundly dangerous information when prompted with medical questions.

The basis of LLMs do not have any medical “ground truth,” which is inherently dangerous. Chat-interfaced LLMs have already provided harmful medical responses and have already been used unethically in ‘experiments’ on patients without consent. Almost every medical LLM use case requires regulatory control in the EU and US. In the US their lack of explainability disqualifies them from being ‘non devices’. LLMs with explainability, low bias, predictability, correctness, and verifiable outputs do not currently exist and they are not exempted from current (or future) governance approaches.

The authors describe in their paper the limited scenarios in which LLMs could find application under current frameworks. They also describe how developers can seek to create LLM-based tools that could be approved as medical devices, and they explore the development of new frameworks that preserve patient safety. “Current LLM-chatbots do not meet key principles for AI in healthcare, like bias control, explainability, systems of oversight, validation and transparency. To earn their place in medical armamentarium, chatbots must be designed for better accuracy, with safety and clinical efficacy demonstrated and approved by regulators,” concludes Prof Gilbert.

Source: Technische Universität Dresden

Categories : Medical Research & TechnologyTags :

In the ICU, Artificial Intelligence Beats Humans

On By ModernMedia
Image created using an AI art program, Craiyon, with the prompt “An AI monitoring a patient in an ICU ward”.

In the future, artificial intelligence will play an important role in medicine. In diagnostics, successful tests have already been performed with AI, such as accurately categorising images according to whether they show pathological changes or not. But training an AI run in real time to examine the time-varying conditions of patients in an ICU and to calculate treatment suggestions has remained a challenge. Now, University of Vienna Researchers report in the Journal of Clinical Medicine that they have accomplished such a feat.

With the help of extensive data from ICUs of various hospitals, an AI was developed that provides suggestions for the treatment of people who require intensive care due to sepsis. Analyses show that AI already surpasses the quality of human decisions making it important to also discuss the legal aspects of such methods.

Making optimal use of existing data

“In an intensive care unit, a lot of different data is collected around the clock. The patients are constantly monitored medically. We wanted to investigate whether these data could be used even better than before,” says Prof Clemens Heitzinger from the Institute for Analysis and Scientific Computing at TU Wien (Vienna).

Medical staff make their decisions on the basis of well-founded rules. Most of the time, they know very well which parameters they have to take into account in order to provide the best care. But now, a computer can easily take many more parameters than a human into account – sometimes leading to even better decisions.

The computer as planning agent

“In our project, we used a form of machine learning called reinforcement learning,” says Clemens Heitzinger. “This is not just about simple categorisation – for example, separating a large number of images into those that show a tumour and those that do not – but about a temporally changing progression, about the development that a certain patient is likely to go through. Mathematically, this is something quite different. There has been little research in this regard in the medical field.”

The computer becomes an agent that makes its own decisions: if the patient is well, the computer is “rewarded”. If the condition deteriorates or death occurs, the computer is “punished”. The computer programme has the task of maximising its virtual “reward” by taking actions. In this way, extensive medical data can be used to automatically determine a strategy which achieves a particularly high probability of success.

Already better than a human

“Sepsis is one of the most common causes of death in intensive care medicine and poses an enormous challenge for doctors and hospitals, as early detection and treatment is crucial for patient survival,” says Prof Oliver Kimberger from the Medical University of Vienna. “So far, there have been few medical breakthroughs in this field, which makes the search for new treatments and approaches all the more urgent. For this reason, it is particularly interesting to investigate the extent to which artificial intelligence can contribute to improve medical care here. Using machine learning models and other AI technologies are an opportunity to improve the diagnosis and treatment of sepsis, ultimately increasing the chances of patient survival.”

Analysis shows that AI capabilities are already outperforming humans: “Cure rates are now higher with an AI strategy than with purely human decisions. In one of our studies, the cure rate in terms of 90-day mortality was increased by about 3% to about 88%,” says Clemens Heitzinger.

Of course, this does not mean that one should leave medical decisions in an ICU to the computer alone. But the artificial intelligence may run along as an additional device at the bedside – and the medical staff can consult it and compare their own assessment with the AI’s suggestions. Such AIs can also be highly useful in education.

Discussion about legal issues is necessary

“However, this raises important questions, especially legal ones,” says Clemens Heitzinger. “One probably thinks of the question who will be held liable for any mistakes made by the artificial intelligence first. But there is also the converse problem: what if the artificial intelligence had made the right decision, but the human chose a different treatment option and the patient suffered harm as a result?” Does the doctor then face the accusation that it would have been better to trust the artificial intelligence because it comes with a huge wealth of experience? Or should it be the human’s right to ignore the computer’s advice at all times?

“The research project shows: artificial intelligence can already be used successfully in clinical practice with today’s technology – but a discussion about the social framework and clear legal rules are still urgently needed,” Clemens Heitzinger is convinced.

Source: EurekAlert!

Categories : NeurologyTags :

Building a Future ‘Biocomputer’ Using Human Brain Cells

On By ModernMedia
Depiction of a human brain
Image by Fakurian Design on Unsplash

A “biocomputer” powered by human brain cells could be developed within our lifetime, according to an article in the journal Frontiers in Science. The Johns Hopkins University researchers expect such “organoid intelligence” technology to exponentially expand the capabilities of modern computing and create novel fields of study, as well as yielding insights into neurodegenerative diseases.

“Computing and artificial intelligence have been driving the technology revolution but they are reaching a ceiling,” said Thomas Hartung, a professor of environmental health sciences at the Johns Hopkins Bloomberg School of Public Health and Whiting School of Engineering who is spearheading the work. “Biocomputing is an enormous effort of compacting computational power and increasing its efficiency to push past our current technological limits.”

For nearly two decades scientists have used tiny organoids, lab-grown tissue resembling fully grown organs, to experiment on kidneys, lungs, and other organs without resorting to human or animal testing. More recently Hartung and colleagues at Johns Hopkins have been working with brain organoids, orbs the size of a pen dot with neurons and other features that promise to sustain basic functions like learning and remembering.

“This opens up research on how the human brain works,” Hartung said. “Because you can start manipulating the system, doing things you cannot ethically do with human brains.”

Hartung began to grow and assemble brain cells into functional organoids in 2012 using cells from human skin samples reprogrammed into an embryonic stem cell-like state. Each organoid contains about 50 000 cells, about the size of a fruit fly’s nervous system. He now envisions building a futuristic computer with such brain organoids.

Computers that run on this “biological hardware” could in the next decade begin to alleviate energy-consumption demands of supercomputing that are becoming increasingly unsustainable, Hartung said. Even though computers process calculations involving numbers and data faster than humans, brains are much smarter in making complex logical decisions, like telling a dog from a cat.

“The brain is still unmatched by modern computers,” Hartung said. “Frontier, the latest supercomputer in Kentucky, is a $600 million, 6,800-square-feet installation. Only in June of last year, it exceeded for the first time the computational capacity of a single human brain – but using a million times more energy.”

It might take decades before organoid intelligence can power a system as smart as a mouse, Hartung said. But by scaling up production of brain organoids and training them with artificial intelligence, he foresees a future where biocomputers support superior computing speed, processing power, data efficiency, and storage capabilities.

“It will take decades before we achieve the goal of something comparable to any type of computer,” Hartung said. “But if we don’t start creating funding programs for this, it will be much more difficult.”

Medical applications

Organoid intelligence could also revolutionise drug testing research for neurodevelopmental disorders and neurodegeneration, said Lena Smirnova, a Johns Hopkins assistant professor of environmental health and engineering who co-leads the investigations.

“We want to compare brain organoids from typically developed donors versus brain organoids from donors with autism,” Smirnova said. “The tools we are developing towards biological computing are the same tools that will allow us to understand changes in neuronal networks specific for autism, without having to use animals or to access patients, so we can understand the underlying mechanisms of why patients have these cognition issues and impairments.”

To assess the ethical implications of working with organoid intelligence, a diverse consortium of scientists, bioethicists, and members of the public have been embedded within the team.

Source: John Hopkins University

Categories : Medical Research & TechnologyTags :

ChatGPT can Now (Almost) Pass the US Medical Licensing Exam

On By ModernMedia
Photo by Maximalfocus on Unsplash

ChatGPT can score at or around the approximately 60% pass mark for the United States Medical Licensing Exam (USMLE), with responses that make coherent, internal sense and contain frequent insights, according to a study published in PLOS Digital Health by Tiffany Kung, Victor Tseng, and colleagues at AnsibleHealth.

ChatGPT is a new artificial intelligence (AI) system, known as a large language model (LLM), designed to generate human-like writing by predicting upcoming word sequences. Unlike most chatbots, ChatGPT cannot search the internet. Instead, it generates text using word relationships predicted by its internal processes.

Kung and colleagues tested ChatGPT’s performance on the USMLE, a highly standardised and regulated series of three exams (Steps 1, 2CK, and 3) required for medical licensure in the United States. Taken by medical students and physicians-in-training, the USMLE assesses knowledge spanning most medical disciplines, ranging from biochemistry, to diagnostic reasoning, to bioethics.

After screening to remove image-based questions, the authors tested the software on 350 of the 376 public questions available from the June 2022 USMLE release. 

After indeterminate responses were removed, ChatGPT scored between 52.4% and 75.0% across the three USMLE exams. The passing threshold each year is approximately 60%. ChatGPT also demonstrated 94.6% concordance across all its responses and produced at least one significant insight (something that was new, non-obvious, and clinically valid) for 88.9% of its responses. Notably, ChatGPT exceeded the performance of PubMedGPT, a counterpart model trained exclusively on biomedical domain literature, which scored 50.8% on an older dataset of USMLE-style questions.

While the relatively small input size restricted the depth and range of analyses, the authors note their findings provide a glimpse of ChatGPT’s potential to enhance medical education, and eventually, clinical practice. For example, they add, clinicians at AnsibleHealth already use ChatGPT to rewrite jargon-heavy reports for easier patient comprehension.

“Reaching the passing score for this notoriously difficult expert exam, and doing so without any human reinforcement, marks a notable milestone in clinical AI maturation,” say the authors.

Author Dr Tiffany Kung added that ChatGPT’s role in this research went beyond being the study subject: “ChatGPT contributed substantially to the writing of [our] manuscript… We interacted with ChatGPT much like a colleague, asking it to synthesise, simplify, and offer counterpoints to drafts in progress…All of the co-authors valued ChatGPT’s input.”

Source: EurekAlert!

Categories : Cardiovascular Disease Lab Tests and ImagingTags :

AI Picks up Incidental Pulmonary Embolism on Chest CT

On By ModernMedia
Photo by Kanasi on Unsplash

According to a study published in the American Journal of Roentgenology, an AI tool for detection of incidental pulmonary embolus (iPE) on conventional contrast-enhanced chest CT examinations had high false negative and moderate false positive rates for detection, and was even able to pick up some iPEs missed by radiologists.

“Potential applications of the AI tool include serving as a second reader to help detect additional iPEs or as a worklist triage tool to allow earlier iPE detection and intervention,” wrote lead investigator Kiran Batra from the University of Texas Southwestern Medical Center in Dallas. “Various explanations of misclassifications by the AI tool (both false positives and false negatives) were identified, to provide targets for model improvement.”

Batra and colleagues’ retrospective study included 2,555 patients (1,340 women, 1,215 men; mean age, 53.6 years) who underwent 3,003 conventional contrast-enhanced chest CT examinations between September 2019 and February 2020 at Parkland Health in Dallas, TX. Using an FDA-approved, commercially available AI tool (Aidoc) to detect acute iPE on the images, a vendor-supplied natural language processing algorithm was then applied to the clinical reports to identify examinations interpreted as positive for iPE.

Ultimately, the commercial AI tool had NPV of 99.8% and PPV of 86.7% for detection of iPE on conventional contrast-enhanced chest CT examinations (ie, not using CT pulmonary angiography protocols). Of 40 iPEs present in the team’s study sample, 7 were detected only by the clinical reports, and 4 were detected only by AI.

Noting that both the AI tool and clinical reports detected iPEs missed by the other method, “the diagnostic performance of the AI tool did not show significant variation across study subgroups,” the authors added.

Source: American Roentgen Ray Society

Categories : Neurodegenerative DiseasesTags :

An AI ‘Storytelling’ Companion to Assist Dementia Patients

On By ModernMedia

Researchers at the National Robotarium in the UK, are developing an artificial intelligence (AI) ‘storytelling’ companion that will aid memory recollection, boost confidence and combat depression in patients suffering from Alzheimer’s disease and other types of dementia.

The idea for the ground-breaking ‘Agent-based Memory Prosthesis to Encourage Reminiscing’ (AMPER) project came from Dr Mei Yii Lim, a co-investigator of the project and an experienced memory modelling researcher.

In Alzheimer’s patients, memory loss occurs in reverse chronological order, with pockets of long-term memory remaining accessible even as the disease progresses. Rehabilitative care methods currently focus on physical aids and repetitive reminding techniques, but AMPER’s AI-driven user-centred approach will instead focus on personalised storytelling to help bring a patient’s memories back to the surface.

Dr Lim explained the project: “AMPER will explore the potential for AI to help access an individual’s personal memories residing in the still viable regions of the brain by creating natural, relatable stories. These will be tailored to their unique life experiences, age, social context and changing needs to encourage reminiscing.”

Having communication difficulties and decreased confidence are commonly experienced by people living with dementia and can often lead to individuals becoming withdrawn or depressed. By using AI to aid memory recollection, researchers at the National Robotarium hope that an individual’s sense of value, importance and belonging can be restored and quality of life improved.

The project’s long-term vision is to show that AI companions can become more widely used and integrated into domestic, educational, health and assistive-needs settings.

Professor Ruth Aylett from the National Robotarium is leading the research. She said: “One of the most difficult aspects of living with dementia can be changes in behavior caused by confusion or distress. We know that people can experience very different symptoms that require a range of support responses. Current intervention platforms used to aid memory recollection often take a one-size-fits-all approach that isn’t always suitable to an individual’s unique needs.”

“AI technology has the potential to play a pivotal role in improving the lives of people living with cognitive diseases. Our ambition is to develop an AI-driven companion that offers patients and their caregivers a flexible solution to help give an individual a sustained sense of self-worth, social acceptance and independence.

“Through projects like AMPER, we’re able to highlight the many ways AI and robotics can both help and improve life for people now and in the future. At the National Robotarium, we’re working on research that will benefit people in adult care settings as well as across a wide range of other sectors that will make life easier, safer and more supported for people.”

Once developed, the AI technology will be accessed through a tablet-based interface to make it more widely accessible and low-cost. The National Robotarium team will also investigate a using the AI in a desktop robot to see if a physical presence has any benefit.

Source: Heriot Watt University

Categories : Cancer Expert OpinionTags :

To Properly Use AI to Analyse Breast Cancers, Look to Past Mistakes

On By ModernMedia
Source: National Cancer Institute

Doctors writing in an editorial in JAMA Health Forum caution that while using AI to analyse breast cancer tumours has the potential to improve healthcare efficiency and outcomes, similar technological leaps have previously led to higher rates of false-positive tests and over-treatment.

The editorial wasco-written by Joann G. Elmore, MD, MPH, professor of medicine at the David Geffen School of Medicine at UCLA, and Christoph I. Lee, MD, MS, MBA, a professor of radiology at the University of Washington School of Medicine.

“Without a more robust approach to the evaluation and implementation of AI, given the unabated adoption of emergent technology in clinical practice, we are failing to learn from our past mistakes in mammography,” the authors wrote.

One of those “past mistakes in mammography,” the authors said, was adjunct computer-aided detection (CAD) tools, which grew rapidly in popularity in the field of breast cancer screening starting more than two decades ago. CAD was approved by the FDA in 1998, and by 2016 more than 92% of U.S. imaging facilities were using the technology to interpret mammograms and hunt for tumours. However, CAD did not improve mammography accuracy., according to the evidence. “CAD tools are associated with increased false positive rates, leading to overdiagnosis of ductal carcinoma in situ and unnecessary diagnostic testing,” the authors wrote. The US Medicare system stopped paying for CAD in 2018, but by then the tools had run up more than $400 million a year in wasted health costs.

“The premature adoption of CAD is a premonitory symptom of the wholehearted embrace of emergent technologies prior to fully understanding their impact on patient outcomes,” Drs Elmore and Lee wrote. “As AI algorithms are increasingly receiving FDA clearance and becoming commercially available with ROC curves similar to what we observed prior to CAD clearance and adoption, how can we prevent history from repeating itself?”

The doctors suggest a number of safeguards to avoid “repeating past mistakes” such as tying reimbursement to proven efficacy.

Source: UCLA Health

Categories : AgeingTags :

AI Model Identifies Compounds That Could Extend Life

On By ModernMedia
Photo by Tara Winstead from Pexels
Photo by Tara Winstead from Pexels

The University of Surrey has developed an artificial intelligence (AI) model that identifies chemical compounds that promote healthy ageing, which could help the development of pharmaceuticals for human lifespan extension.

In a paper published in Scientific Reports, a team of chemists from Surrey built a machine learning model based on the information from the DrugAge database to predict whether a compound can extend the life of Caenorhabditis elegans, a translucent worm whose metabolism is similar to humans. Because the worm has such a short lifespan, the researchers were able to test the effectiveness of the compounds.

The AI model identified three compounds that have an 80 percent chance of increasing the lifespan of elegans:

  • flavonoids (anti-oxidant pigments found in plants that promote cardiovascular health, examples include certain spices and herbs),
  • fatty acids (such as omega 3), and
  • organooxygens (compounds that contain carbon to oxygen bonds, such as alcohol).

Co-author Sofia Kapsiani, final year undergraduate student at the University of Surrey, said: “Ageing is increasingly being recognized as a set of diseases in modern medicine, and we can apply the tools of the digital world, such as AI, to help slow down or protect against ageing and age-related diseases. Our study demonstrates the revolutionary ability of AI to aid the identification of compounds with anti-aging properties.”

Commenting on the research, lead author Dr Brendan Howlin, Senior Lecturer in Computational Chemistry at the University of Surrey, said: “This research shows the power and potential of AI, which is a specialty of the University of Surrey, to drive significant benefits in human health.”

Source: SciTech Daily

Journal information: “Random forest classification for predicting lifespan-extending chemical compounds” by Sofia Kapsiani and Brendan J. Howlin, 5 July 2021, Scientific Reports.
DOI: 10.1038/s41598-021-93070-6