Scientists have created an artificial intelligence system that could help treat patients with sepsis.
The technology, developed by researchers from Imperial College London, was found to predict the best treatment strategy for patients.
The system ‘learnt’ the best treatment strategy for a patient by analysing the records of about 100,000 hospital patients in intensive care units and every single doctor’s decisions affecting them.
The findings showed the AI system made more reliable treatment decisions than human doctors. The team behind the technology say the tool could be used alongside medical professionals, to help doctors decide the best treatment strategy for patients.
Sepsis, also known as blood poisoning, is a potentially fatal complication of an infection, and kills around 44,000 every year in the UK.
In the study, researchers looked back at US patient records from 130 intensive care units over a 15 year period to explore whether the AI system’s recommendations might have been able to improve patient outcomes, compared with standard care. The researchers now hope to trial the system, called AI Clinician, in intensive care units in the UK.
Dr Aldo Faisal, senior author from the Department of Bioengineering and the Department of Computing at Imperial, said: “Sepsis is one of the biggest killers in the UK – and claims six million lives worldwide – so we desperately need new tools at our disposal to help patients. At Imperial, we believe that AI for Healthcare is the solution. Our new AI system was able to analyse a patient’s data – such as blood pressure and heart rate – and decide the best treatment strategy. We found that when the doctor’s treatment decision matched what the AI system recommended, they had a better chance of survival.”
The team used the AI system to assess which particular treatment approach to sepsis was most successful.
Sepsis can cause a drastic drop in blood pressure which can leave organs deprived of blood flow and oxygen, and can ultimately lead to multiple organ failure and death.
To raise blood pressure and keep the heart pumping, doctors give extra fluids, usually in the form of a salt solution, as well as medication that tightens blood vessels and raises blood pressure, called vasopressors.
Professor Anthony Gordon, senior author from the Department of Surgery & Cancer at Imperial explained: “We know that most patients with sepsis need fluid drips and in more severe cases also need vasopressors to maintain blood pressure and blood flow. There is still much debate amongst clinicians about how much fluid to give and when to start vasopressors. There are clinical guidelines but they provide general advice. The AI Clinician is able to learn what is the best option for each individual patient at that moment in time.”
We’re already making steps to improve diagnosis with our new sepsis tool, but we must also embrace any new technology solutions that can improve patient care and save lives.”
To help doctors decide which approach would boost a patient’s chance of survival, the research team created an AI system that would assess a patient’s vital signs and recommend the best treatment approach.
The system analysed the medical records of 96,000 US patients with sepsis in intensive care units. Using a process called reinforcement learning – where robots learn how to make decisions and solve a problem – the AI Clinician went through each patient’s case and worked out the best strategy of keeping a patient alive. The system calculated 48 variables including age, vital signs and pre-existing conditions.
The system then predicted the best treatment strategy for each patient with sepsis. The results revealed that 98 per cent of the time, the AI system matched or was better than the human doctors’ decision.
The study also found that mortality was lowest in patients where the human doctor’s doses of fluids and vasopressor matched the AI system’s suggestion. However, when the doctor’s decision differed from the AI system, a patient had a reduced chance of survival.
The team say the findings show the AI Clinician could help doctors decide the best treatment strategy for patients.

Imperial College Londonhttps://tinyurl.com/y7bubfbc

Turning down the lights and reducing noise levels as part of a stimulation reduction initiative can decrease assaults and the amount of time patients must spend in restraint at psychiatric intensive care units, according to new research from the University of Alabama at Birmingham. Findings showed that simple techniques to reduce sensory overstimulation played a major role in creating a safer environment for both patients and staff.
“The time period roughly between 4-7 p.m. often sees an environment of commotion and disquietude on high acuity psychiatric units resulting in a higher incidence of assaults and/or need to place patients in restraints to control aggressive behaviour” said Rachel E. Fargason, M.D., professor in the UAB Department of Psychiatry and senior author of the study. “On many psychiatric units, this three-hour period between the end of structured activities and the dinner meal is the most problematic of the day.”
Fargason says the combination of bright lights, talkative staff, anxious evening visitors, clattering housekeeping carts and physician traffic can create a highly overstimulating environment.
“Sensory overstimulation is irritating to healthy individuals, but can be intolerable to individuals with neuro-psychiatric disorders,” said Badari Birur, M.D., assistant professor of psychiatry at UAB and a study co-author. “Healthy individuals regularly engage in centering activities such as stroking their hair or tapping a foot. However, neuro-psychiatrically challenged individuals are often unable to self-identify their sensory needs or execute these adaptive behaviours.”
Fargason and her team began a structured change in sensory stimulation on the 20-bed, locked psychiatric intensive care unit at UAB Hospital in October 2015 by dimming lights in the common spaces of the units at 4 p.m. This was followed by sound reduction and the introduction of music in November. Between December and February 2016, the team added tactile and visual art activities, movement, stretching, and aromatherapy.
“Both assaults and use of restraints dropped dramatically as we implemented these sensory adaptations,” Fargason said. “Rates for both fell to close to zero, well below industry benchmarks and regulatory requirements.”
The need for restraints fell by 72 percent, to just over half of 1 percent of total patient hours requiring restraint usage. Assault rates fell 83 percent to a rate of 0.06 percent.
Since the completion of the study, the psychiatric ICU has continued to utilize the stimulation reduction techniques and continues to see positive results on a regular basis.
“Once the project was fully implemented, the evident calming effects on the patients became reinforcing,” Birur said. “Altering the sensory milieu on a busy psychiatry unit requires multidisciplinary efforts by leaders and frontline team champions to influence this kind of beneficial culture change.”
The team, which included nurses, occupational and physical therapists, patient care technicians, and physicians, reports that the quieter auditory and low-light culture became the new normal on that unit.
“While initially implementing the process changes, assistant nurse manager Barbara Aguilar had to remind patients, visitors and even staff to leave overhead lights off and to speak in quiet voices,” said Melissa Bearden, OT/L, occupational therapy manager for the Center for Psychiatric Medicine. “Eventually the culture shifted, and patients and staff now remind each other or self-correct.”
Fargason says the findings could have impact on other hospital units, particularly where patients are behaviourally challenged due to dementia, delirium or medication.

University of Alabama at Birminghamhttps://tinyurl.com/ydd949rw

Researchers at the University of Louisville, Kentucky, have demonstrated that a new radiotracer, 2-18F-fluorodeoxysorbitol (18F-FDS), can identify and track bacterial infection in lungs better than current imaging methods and is able to differentiate bacterial infection from inflammation.
“Currently, bacterial infections can be diagnosed only after they have become systemic or have caused significant anatomical tissue damage, a stage at which they are challenging to treat owing to the high bacterial burden,” explains Chin K. Ng, PhD, at the University of Louisville School of Medicine, Louisville, Kentucky.
He points out, “18F-FDG PET, a widely commercially available imaging agent, is capable of imaging infection, but it cannot distinguish infections from other pathologies such as cancer and inflammation. Therefore, there is a great need to develop imaging agents with high specificity and sensitivity. There are still no specific imaging agents that can differentiate bacterial infection from sterile inflammation at an early stage.”
For this study, mice were inoculated with either live Klebsiella pneumoniae bacteria to induce lung infection, or the dead form of the bacteria to induce inflammation. Half of the mice with the live bacteria were imaged with PET/CT using either 18F-FDS or 18F-FDG on days 0, 1, 2 and 3 to monitor disease progression post infection. The other half were screened by bioluminescent imaging, and mice with visible infection were selected for follow-up PET/CT scans with 18F-FDS. For the inflammation group, half the mice were imaged with PET/CT using 18F-FDS and half using 18F-FDG from day 1 to day 4 post-inoculation.
While both 18F-FDS and 18F-FDG effectively tracked the degree of bacterial infection measured by bioluminescent optical imaging, only 18F-FDS was able to differentiate lung infection from lung inflammation.
Ng notes, “Bacterial infection represents a threat to human health, including hospital-acquired, implant-related, and multidrug-resistant infections. 18F-FDS whole-body PET/CT imaging in mice has shown to be a unique imaging technique that could differentiate infection from inflammation. This same technique could potentially be used in patients to identify infection sites and determine the bacterial infection class, so that patients could avoid taking antibiotics that are known to have no effect against specific bacteria.”
He adds, “The interpretation of CT appearances of lung disorders can be complex if a differential diagnosis needs to distinguish between inflammation and infection. Thus 18F-FDS PET/CT could be initially used as a follow up after an inconclusive CT diagnosis for suspected bacterial lung infection. As proven clinical data accumulate over time, 18F-FDS PET/CT could become a new clinical standard for confirming bacterial infection in the lungs or other sites.”
Looking ahead to making 18F-FDS clinically available, Ng states, “Since 18F-FDS can be made from 18F-FDG with one extra, simple conversion step, and sorbitol has already been approved for use in humans by the U.S. Food and Drug Administration, the approval pathway for 18F-FDS should be straightforward. 18F-FDS would be inexpensive and readily available once approved.”
He also observes, “This and other new PET imaging agents demonstrate that molecular imaging and nuclear medicine can offer unique technologies for patient care and will continue to play a key influential role in healthcare.”

Society of Nuclear Medicine and Molecular Imaginghttps://tinyurl.com/y9n45qso

Due to overwhelming demand, the abstract submission for paper presentations and posters for the 43rd World Hospital Congress of the International Hospital Federation has been extended to 1 March.

The World Hospital Congress is a unique global forum that brings together leaders of national and international hospital and healthcare organizations to share knowledge, expertise, experiences and best practices in leadership in hospital and healthcare management and delivery of services.

The 2019 World Hospital Congress is being hosted by the Ministry of Health of the Sultanate of Oman with the over-arching theme “People at the heart of health services in peace and crisis”.

Hospitals and health service providers that want to share their programs, projects, researches and experiences with health leaders and professionals from across the globe can still submit their abstracts for the following sub-themes:

Resilient health services:

• Best practices for preparedness and responses to disasters, outbreaks and cyberattacks
• Mitigating consequences of conflicts and terror attacks to continue serving all especially vulnerable groups
• Operating under severe resource constraints
• Leading practices reflecting systematic approaches to learning from crises and trauma
• Violence in the workplace

Health investment for prosperity

• Exploring governance practices driving better efficiency and relevance
• What management and leadership can do for increased efficiency and outcomes
• Inter-professional leadership for cost effectiveness and quality improvement
• What are the impacts of hospitals in the local and national economy
• Future of hospitals in an economically constrained world

Innovation for health impact

• Removing barriers to innovation with change management
• Hospital Technology Assessment to speed up innovation adoption
• Embedding collaboration with industries for health innovation
• Procurement to accelerate and develop innovation
• Enhancing digital health services in the virtual space

More information including the submission process, general criteria and terms and conditions for presenters are available at https://congress.ihf-fih.org/ihf_abstracts

Successful abstracts will also be considered for publication in the IHF Journal and presentation in the IHF Webinars. Poster abstracts will also be entered in the Best Poster Award.

For any questions please contact congress@ihf-fih.org or visit www.worldhospitalcongress.org.

For decades, clinicians treating multiple sclerosis (MS) have interpreted the appearance of new or expanding brain lesions on magnetic resonance imaging (MRI) scans as a sign that a patient’s disease is getting worse. Now, University at Buffalo researchers are finding that it may be the atrophy or disappearance of these lesions into cerebrospinal fluid (CSF) that is a better indicator of who will develop disability.
The five-year study, conducted by MS researchers in the Jacobs School of Medicine and Biomedical Sciences at UB, was published in the Journal of Neuroimaging. Similar findings also resulted from their 10-year study of 176 patients that they presented at the annual meeting of the American Academy of Neurology (AAN) in Los Angeles in April.
Robert Zivadinov, MD, PhD, first author on the 10-year study and senior author on the five-year study, said: “Using the appearance of new brain lesions and the enlargement of existing ones as the indicator of disease progression, there was no sign of who would develop disability during five or 10 years of follow-up, but when we used the amount of brain lesion volume that had atrophied, we could predict within the first six months who would develop disability progression over long-term follow-up.”
Zivadinov, a professor of neurology in the Jacobs School and director of the Buffalo Neuroimaging Analysis Center (BNAC) in the Jacobs School, also directs the Center for Biomedical Imaging at UB’s Clinical and Translational Science Institute.
Brain lesions in general are a sign of damage to the brain, such as physical trauma, a stroke, normal aging or chronic disease. Patients with MS receive MRI scans as part of their routine care so that doctors can track the appearance of new lesions and the enlargement of existing ones, typically seen as indicators of disease progression. Approval by the Food and Drug Administration for new MS drugs typically depends on the drug’s ability to reduce the number of brain lesions over 24 months.
Zivadinov noted that according to this premise, the loss of brain lesions could inadvertently be seen as a sign that the patient’s condition is improving. MS is characterized by the loss of myelin sheaths surrounding axons in the brain and disrupting the brain’s ability to send and receive neuronal messages. The growth of new myelin sheaths around axons may demonstrate that some brain tissue has been repaired spontaneously or as the result of medication.
In order to focus specifically on the disappearance of lesions that likely indicate pathological change like atrophy, not beneficial change, like resolution or remyelination, the researchers looked exclusively at lesions seen on previous scans that were later replaced by cerebrospinal fluid.
“How do we know the lesions have disappeared?” asked Zivadinov. “Because where there was brain lesion tissue before, there now is just fluid.”
“The big news here is that we did the opposite of what has been done in the last 40 years,” said Michael G. Dwyer, PhD, assistant professor of neurology and bioinformatics in the Jacobs School and first author on the five-year study in the Journal of Neuroimaging. “Instead of looking at new brain lesions, we looked at the phenomenon of brain lesions disappearing into the cerebrospinal fluid.”
The researchers looked specifically at the rate of brain lesion loss due to atrophy compared to accumulation of lesion volume seen both at baseline and follow-up. They found that the amount of lesion volume that atrophied was the only significant lesion parameter that correlated with clinical disability as measured by the Expanded Disability Status Scale (EDSS), the most widely used method of quantifying disability in MS. 
“We didn’t find a correlation between people who developed more or larger lesions and developed increased disability,” said Dwyer, “but we did find that atrophy of lesion volume predicted the development of more physical disability.”
While patients with relapsing remitting MS showed the highest amount of new lesions during the study, patients with progressive MS — the most severe subtype — had the most accelerated volume of brain lesion atrophy. The UB researchers said this indicates that this new imaging biomarker could be particularly important in transitional phases between relapsing and progressive MS subtypes.
“Paradoxically, we see that lesion volume goes up in the initial phases of the disease and then plateaus in the later stages,” said Zivadinov. “When the lesions decrease over time, it’s not because the patient lesions are healing but because many of these lesions are disappearing, turning into cerebrospinal fluid.”
Another important scientific finding of the studies, Zivadinov continued, is that atrophied brain lesions were a more robust predictor of disability progression than the development of whole brain atrophy itself, the most accepted biomarker of neurodegeneration in MS.
“Our data suggest that atrophied lesions are not a small, secondary phenomenon in MS, and instead indicate that they may play an increasingly important role in predicting who will develop a more severe and progressive disease,” he said.

University at Buffalo
www.buffalo.edu/news/releases/2018/05/025.html