Beukenlaan 137
5616 VD Eindhoven
The Netherlands
+31 85064 55 82
info@interhospi.com
PanGlobal Media IS not responsible for any error or omission that might occur in the electronic display of product or company data.
Just like pediatric emergency units were developed to serve children, healthcare experts are recognizing that older adults require specialized forms of emergency care, which differ from the general population. Indeed, emergency rooms can be unforgiving for the elderly, many of who are often traumatized by the experience.
New geriatric emergency departments have recently begun to emerge, led by the US. They not only provide more appropriate care for older people, but can bring cost savings to a hospital, too.
A major and growing challenge
In the US, up to 25% of ED patients are aged 65 years or older. Indeed, geriatric ED patients represent 43 percent of all admissions, including 48 percent admitted to the intensive care unit (ICU). Geriatric patients in the ED also have an average length of stay that is 20 percent longer than younger populations.
There are no consolidated figures for Europe. However, there are both similarities and differences vis-a-vis the US. In the UK, a Nuffield Trust report in 2009 found nearly 40 percent of all ED admissions being for the over-65s and 10 percent for people aged 85 and above. However, it also observed that “at most, 40 percent of the increased number of emergency admissions” over a four-year period could be explained by the effects of population ageing.
The numbers of elderly are not insignificant.
In the US, the 2010 Census found 13 percent of the population, corresponding to over 40 million people, were over 65 years in age. Their numbers too showed a sharper increase than other population groups, with people in the 85+ age group growing at almost three times the rate of the general population.
The situation in Europe is even more demanding, with 19.2 percent of the population in the 65+ age group in 2016, up from 16.8 percent a decade previously.
Benefits for both elderly and hospitals
There are several benefits which the elderly can derive from a geriatric ED. The most important is optimization of care. This is achieved by focusing resources, attention and capability to their most common risks and needs; the latter differ in several respects from other age groups.
Conversely, a geriatric ED can also provide benefits to a hospital. Improved standards of care for a large patient population are a useful marketing or public relations tool. In the US, hospitals have been marketing the geriatric ED to attract older patients who utilize higher reimbursing programmes. Finally, the case for special geriatric attention has become compelling due to the Affordable Care Act. This reduces reimbursement, should a patient return to the hospital due to iatrogenic complications such as infections and wounds.
Paradigm change for both emergency and geriatric care
Traditionally, ED teams were not provided with training for the care of older people. The ED environment was instead organized according to single organ management. For elderly ED admissions, a more holistic approach was considered as best practice, especially in terms of frailty and geriatric syndromes. Several such attitudes continue to this day.
In parallel, geriatric medicine (GM) has historically avoided paying attention to emergency care contexts, and competencies specifically associated with the elderly (e.g. management of falls, confusion, dementia, delirium, the risk of adverse drug-drug or drug-food interactions); these are as important in an acute care setting as in a geriatric ward. Indeed, various studies have pointed out that underlying vulnerabilities which led to an ER visit may go undetected and unaddressed by emergency room staff.
Compelling evidence
However, it has also become clear that dedicated geriatric EDs can make a major difference in delivering quality care to the elderly. One study used Medicare data from 2012 and 2013 to study falls by the elderly, a significant cause of morbidity – leading to hip fractures and nursing home admissions. The researchers found that less than 4 percent received a physical therapy (PT) consult. On the other hand, they also discovered that readmission rates for another fall within 60 and 180 days dropped significantly in patients who had a PT consult.
A brief history of the geriatric ED
The concept of a geriatric ED took root in the US in 2008. Since then, such facilities have become increasingly common in the country. Figures from the non-profit ECRI institute state there were 50 geriatric EDs in operation in the US in early 2014, with another 150 in development.
The first American hospital to develop a geriatric ED model was Holy Cross Hospital in Silver Spring, Maryland, part of the St. Joseph Mercy Health Systems. The geriatric practice was inspired by the fact that nearly one of five of its ED patients was 65 or older. Moreover, its CEO made a more prosaic observation – that the hospital’s ED was not well suited to take care of his mother.
The Holy Cross Hospital was used to pilot the concept of a geriatric ED. Since then, other St. Joseph Mercy’s hospitals have developed geriatric EDs, as have other hospital groups.
In 2012, the Icahn School of Medicine at Mount Sinai received an award from the US government’s Department of Health and Human Services to implement a geriatric ED model at three major urban hospitals, namely Mount Sinai Medical Center in New York City, Northwestern Memorial Hospital in Chicago and St. Joseph’s Regional Medical Center at Paterson, New Jersey.
Common sense innovations
The practices prescribed by Holy Cross for its pioneering geriatric ED involved simple environmental standards such as natural glare-free lighting, soothing colours, beds rather than gurneys equipped with better mattresses and non-skid flooring. Posters and scales were equipped with larger print, and reading glasses made available. The designers also ensured that rooms/units were large enough to accommodate family members, whose role in care delivery of the elderly is now widely acknowledged.
Staff training
However, the most important developments at the Holy Cross ED concerned staff training and responsibilities. ED staff were given special training in geriatrics, while pharmacists were charged with reviewing medications of every elderly patient, to monitor and analyse them as causative factors for a medical emergency. Lessons from Holy Cross, including the maxim that geriatrics care is the ‘ultimate team environment’, have been transferred to other US healthcare facilities and to hospitals in Europe and elsewhere too.
The expertise a well-trained ED team bring to interactions with a geriatric patient directly impact the latter’s condition. Studies have shown that trained ED staff also lead to the use of relatively less expensive outpatient treatments.
The advantage of training nurses for an ED role was highlighted by the ‘Journal of the American Geriatrics Society’ in January 2018. The article, which studied 57,287 patients over 65, reported that an ED-based transitional care nurse (TCN) programme focused on geriatric care was able to reduce the number of unnecessary hospitalizations by 33 percent. Its co-author, Scott Dresden, MD, an Assistant Professor of Emergency Medicine at Northwestern University wrote that the programme “created an otherwise non-existent safety net for this vulnerable population.”
Holy Cross’ first ED also ushered in a full-time, trained geriatric social worker, dedicated to emergency rooms. According to some estimates, geriatric ED patients are 400% more likely to require social services than the general population. Indeed, social workers play a key role in advising and assisting elderly patients to get post-ED care, after discharge. They also seek to know the patients and discover underlying reasons for their coming to the ED.
Reducing re-admissions and penalties
Overall, US hospitals are being compelled by the Affordable Care Act to reduce iatrogenic complications in the elderly. One study showed that 40 percent of emergency room patients older than 65, who had been denied admission, returned to EDs with conditions which had worsened. An article in ‘Modern Physician’ found that 27 percent of elderly patients either returned to the ED for admission or died, in the first three months after a hospital visit.
The ‘Modern Physician’ article, however, observed that 30-day readmission rates for the elderly at Holy Cross Hospital halved after it set up a geriatric ED, from 10.9 percent to 5.2 percent. Results at another geriatric ED, at St. Joseph Regional Medical Center in Paterson, New Jersey, were even more dramatic: returns of elderly ED patients dropped from 20 percent to just over 1 percent.
Guidelines
Geriatric ED practices are the target of new guidelines in the US, developed by The American College of Emergency Physicians (ACEP), the American Geriatrics Society (AGS) and the Society for Academic Emergency Medicine (SAEM). These call for education and training of medical staff, making specific risk-assessments of senior patients and screening those considered to be vulnerable for co-morbidities such as cognitive problems, falls, etc., performing a comprehensive review of medication, and providing a comprehensive discharge plan.
As part of their geriatric risk management, some hospitals are emphasizing the screening and triaging of elderly patients beyond their primary complaint. One popular tool here is the Identification of Seniors at Risk (ISAR), a simple patient checklist to be completed at the point of entry.
Another innovation is the use of telemedicine as part of ED discharge plans, with a typical 72 hours of coverage at home via video monitoring, and then transitioning care to a primary care physician.
Accreditation
On its part, ACEP has recently launched an accreditation programme for emergency rooms, with three levels of accreditation — basic, intermediate and advanced.
All ACEP accredited facilities must provide elderly patients with walkers, canes and reading glasses. Intermediate accreditation requires provision of suitable lighting and non-slip floors, along with hearing aids, thicker mattresses and warm blankets. Advanced accreditation targets physician-supervised improvement initiatives, such as limiting the use of urinary catheters in older patients.
Europe launches GEM curriculum
In Europe, too, efforts are being made by professional societies to develop a validated curriculum on geriatric emergency medicine (GEM). The curriculum is thorough and covers a full spectrum of activity: pre-hospital care, primary clinical assessment and stabilization, secondary clinical assessment, medication, pain management, palliative care and transitional care, along with continuous attention to typical co-morbidities in the elderly and to differences in care paradigms and challenges vis-a-vis younger age groups.
Geriatric friendly – a new standard?
In the long run, we may well witness some major re-thinking about the impact of geriatric ED. Mark Rosenberg, who heads geriatric emergency medicine at St. Joseph’s – one of the three hospitals that received US government funding in 2012 for implementing a geriatric emergency practice – suggests that if an ED is designed for the most vulnerable patients, it will work for the strongest patients as well. In other words, he argues that all EDs should be designed to be geriatric-friendly, as a baseline standard.
At the European Society for Breast Imaging (EUSOBI) meeting last September in Berlin, Hologic officially launched the 3Dimensions™ mammography system which offers a variety of groundbreaking features designed to provide higher quality 3D™ images for radiologists, enhanced workflow for technologists, and a more comfortable mammography experience, with low-dose options, for patients (see featured item).
On this occasion, International Hospital talked to Lori Fontaine, Vice President of Clinical Affairs for Hologic.
Is the launch at EUSOBI only for Europe or is it global?
The 3Dimensions™ mammography system received CE Mark in July 2017 making it commercially available in EMEA, followed shortly thereafter by the U.S. launch in August 2017.
Can you give some details and figures on dose reduction for the new system?
We know that dose is a common concern across Europe, and the 3Dimensions system helps address this by providing low-dose options for patients, among many other benefits. The 3Dimensions system results in a 45 percent dose reduction with a generated 2D image compared to 2D FFDM alone.
Is the improvement in image clarity regardless of breast density likely to reduce the need for a secondary ultrasound in the screening of high density breasts?
We already know the 3Dimensions system’s Clarity HD high-resolution 3D™ imaging reduces recalls by up to 40 percent compared to 2D alone, and given Clarity HD works to deliver exceptional 3D™ images, regardless of breast size or density, it makes sense that the 3Dimensions system would be an ideal option for women with dense breasts. This is especially true since the 3Dimensions system operates in tandem with Hologic’s 3D Mammography™ exam, the only mammogram approved by the U.S. Food and Drug Administration as superior for women with dense breasts compared to 2D alone, which further demonstrates that tomosynthesis should be the standard of care for women across the globe when it comes to breast cancer screening.
Do you have any information and figures on the adoption rate of DBT by radiologists in the various European countries, are there significant country variations (or regional between US, Europe and Asia)?
Digital Breast Tomosynthesis (DBT) adoption rates vary by country. While DBT has been approved in EMEA since 2009, the majority of EMEA countries limit the use of DBT to diagnostic imaging as they have concerns regarding dose and reading time. Hologic remains at the forefront of technology innovation and is working to overcome these barriers, so that all women can be screening with DBT.
Hologic was the first company to receive FDA approval for DBT use in both the screening and diagnostic setting in the U.S. in 2011. Today, DBT is used in approximately 40 percent of all U.S. screening mammography exams and is covered by the majority of insurance companies. The evidence of the benefit of Hologic’s 3D Mammography exam as a better mammogram continues to expand and resulted in the addition of DBT to the National Comprehensive Cancer Network (NCCN) Guidelines in 2016. NCCN is recognized globally as an alliance of 27 U.S. cancer centers that develop recommendations designed to help healthcare professionals diagnose, treat and manage cancer care.
Cancer remains the second leading cause of death in Europe after cardiovascular diseases with approximately 3.5 million new cases diagnosed every year and an annual death toll of 1.5 million. However, the good news is that the trend of total cancer mortality levels is downwards for both men and women and also children for which the progress of 5-year leukemia survival has been spectacular.
Breast cancer provides a good example of this trend, being not just the most common female cancer globally but also the number one diagnosed cancer in Europe (13%). Its 5-year survival rate has more than doubled in 40 years, from 40% of patients in 1970 to 90% in 2013. Looking into the future there are also some encouraging signs for certain types of cancer, particularly cervical cancer as the full impact of the HPV vaccination programmes becomes measurable.
In Europe, some of the credit for these positive developments should go to the European Organization for Research and Treatment of Cancer (EORTC), founded in 1962. Over the years, EORTC’s clinical research has helped make significant progress in the treatment and management of cancer, evaluating new molecules, refining existing treatment regimens, identifying biomarkers and assessing patients’ qualify of life. In 2016, the EORTC research network counted more than 4850 physicians from about 870 institutions while patient accrual from 2000 to 2016 totalled over 89,000 patients in clinical studies.
The bad news is that the overall burden of cancer continues to increase not just because of progress in early detection but largely because of the ageing of the population (65% of new cancer cases are diagnosed in patients who are 65 or older). Also, smoking, particularly in women, is linked to a rising incidence of lung cancer.
There are still a number of challenges to be met if the promises of translational research and personalized medicine for cancer therapy are to be fulfilled. Effective coordination in Europe of advances in basic research and quality clinical research programmes is essential. New models of partnerships between academia and the pharma industry are also required as well as public funding for research on rare cancers. Prevention is paramount, though, as no cancer research will have a bigger and quicker impact than smoking cessation. Tobacco kills over one third of its users and studies have shown that smokers lose at least 10 years of life expectancy compared to non-smokers and that quitting smoking before the age of 40 reduces the risk of tobacco-related death by 90%.
Magnetom Vida, the new high-end 3-Tesla MRI scanner with BioMatrix
technology from Siemens Healthineers, was launched to the public at University Hospital Tübingen, where the first system is installed. It has been undergoing clinical tests in the hospital’s Department for Diagnostic and Interventional Radiology since December 2016.
Magnetom Vida is the first scanner equipped with BioMatrix, a brand-new, innovative scanner technology that addresses inherent anatomical and physiological differences among individual patients, as well as variability among users. Magnetom Vida and BioMatrix allow users to meet the growing demand for MR imaging, perform the full range of routine as well as complex examinations, and deliver robust results for every patient. Furthermore, the scanner also makes MRI more cost-effective by reducing rescans and increasing productivity. High-precision imaging means that radiologists can deliver essential and robust information to choose the right treatment for each patient every time. Siemens Healthineers, in collaboration with its customers, is playing an important role in taking healthcare forward in the development of precision medicine.
Siemens Healthineers has been developing this disruptive and innovative BioMatrix technology for over five years. Its introduction represents a further advance in MRI imaging as well as the next level of automation and patient centricity.
High image quality and efficient workflows – regardless of user or patient
Due to high levels of exam variability, MRI is often considered to be one of the most complex medical imaging modalities. Physiological and anatomical differences between patients as well as different experiences levels in users contribute to this unwanted variability. This frequently is a source of errors, rescans, and inefficient workflows in MR imaging, making it all the more important that MRI scanners deliver reliable and reproducible image data irrespective of the patient being examined or the person operating the system. This issue is precisely addressed with the new BioMatrix technology.
BioMatrix sensors in the table automatically track a patient’s respiratory pattern, giving users insights into a patient’s individual ability to hold his or her breath during the scan. This allows the user to select the optimal exam strategy, while also saving time during the examination. BioMatrix tuners can help avoid rescans, which represent a major burden on productivity as well as a driver of additional costs in radiology. In cervical spine examinations, for example, this feature uses intelligent coil technology to automatically set the optimal scan parameters based on the individual patient anatomy, all without any additional user interaction. BioMatrix tuners also improve the quality and reproducibility of whole-body diffusion. Precise control of scan parameters in real-time to match the individual patient anatomy makes it possible to avoid distortions, which can render diffusion imaging non-diagnostic, especially in 3 Tesla MRI. Innovative interfaces also help ensure a consistently high examination quality, accelerating workflows, and improving quality of care. BioMatrix Interfaces accelerate the scanning process by up to 30 percent. Automated patient positioning based on intelligent body models automatically moves the patient table to the correct scan position. An intuitive touchscreen user interface integrated onto the scanner allows for one-touch positioning. A new, easy-to-move motorized patient table further simplifies examinations, especially for adipose, immobile, and trauma patients.
Magnetom Vida is the first system to be equipped with the new BioMatrix technology, designed to tackle the challenges of variability and thereby, reduce unwanted variability in MRI examinations. It will help users achieve fewer rescans, predictable scheduling, and consistent, high-quality personalized examination results.
The ability to provide consistent and reproducible quality regardless of the individual patient and user will help reduce rescans, which can be a great financial burden for healthcare institutions. As publications have shown, rescans can account for up to €100,000 per year and system in additional costs.
Professor Konstantin Nikolaou, Medical Director of the Department of Diagnostic and Interventional Radiology at University Hospital Tübingen considers Magnetom Vida to be part of the general trend toward precision medicine: “To provide our patients with individual therapies, we need every piece of information available. When it comes to imaging, this means that we need robust, standardized, and reproducible image data that are always of the same quality regardless of the patient or user. Only then we can compare results and link them with additional information, such as data from laboratory medicine or genetics,” says Nikolaou, referring to the clinical validation of the new MRI scanner in his department. “Magnetom Vida gives us this data quality and comprehensive image information so that we can choose the right kind of personalized therapy and evaluate it – to see, for instance, how a patient responds to chemotherapy before tumour removal. This MRI scanner along with BioMatrix technology is the perfect fit for our current medical approaches, and is helping us on our way to quantitative radiology,” says Nikolaou.
Faster scans with very high patient comfort
Magnetom Vida has another major advantage: “We can examine sick patients faster with Magnetom Vida,” says Professor Mike Notohamiprodjo who, as head of MRI at University Hospital Tübingen, works intensively with the new scanner. “The scanner offers the highest degree of patient comfort with the performance of a research system, which speeds up our workflows,” he says. As examinations in Tübingen show, the new scanner decreases measurement times for musculoskeletal and prostate imaging compared to previous MRI systems. What is more, it does so with significantly improved image quality: “The signal-to-noise ratio in the clinical images is up to 30 percent higher than with systems from the previous generation,” says Notohamiprodjo.
While this is partly due to BioMatrix technology, it is also a result of the diverse insights that developers at Siemens Healthineers gathered from intense fundamental research and close customer collaborations. Key learnings from the development of a 7-Tesla research MRI system translated into a new 3-Tesla magnet design. Magnetom Vida’s all-new system architecture offers extremely high performance and unmet long-term stability – without requiring any more space than previous clinical systems. The new scanner’s 60/200 XT gradient system provides over 2.7 megawatts of power, making it the most powerful commercially available gradients in a 70-centimeter bore scanner. And, thanks to a very large field of view (55x55x50 cm), Magnetom Vida can also cover larger body regions in one step, such as full coverage abdominal exams.
The result is a great increase in productivity for routine examinations of the brain, spine, and joints – from correct patient positioning at the touch of a button to transferring the clinical images to the PACS archiving system. This is made possible by the GO technologies, which automate and simplify workflows from the start of the scan right through to the quality control of the image data. A new user interface allows not only for automated acquisition and processing, but also for more advanced post-processing applications to run at the scanner. With spine examinations, for instance, GO technologies reduce the time needed by about a fifth. This means that a department could carry out four additional spine examinations per day and per system. Given the decline in reimbursement rates, this is of great value to many radiological institutes.
Broader patient groups and new clinical growth areas
The system also allows customers to access additional clinical growth fields – for instance, by serving patient groups that were previously deemed unsuitable for MRI due to issues such as cardiac arrhythmias, excess weight, or health problems that prevent them from actively supporting the scan. With the introduction of Magnetom Vida, Siemens Healthineers expands its Compressed Sensing applications – which can make MRI scans up to ten times faster – to cover more body regions. It features Compressed Sensing Cardiac Cine, which allows free-breathing cardiology examinations (even when using contrast medium for comprehensive tissue characterization). Now, Compressed Sensing Grasp-Vibe, which enables dynamic, free-breathing liver examinations in one comprehensive scan by the push of button and for every patient, is also available. Until today, in contrast, dynamic liver imaging required four steps with exhausting breath-holds and complex timing. Grasp-Vibe technology also makes the post-processing of liver images significantly faster. During the studies he carried out in Tübingen, Professor Notohamiprodjo found that post-processing times fell from 20 to just four minutes.
Magnetom Vida even simplifies whole-body scans, which are currently particularly challenging, because they have to cover multiple scan sections and demand highly trained users. A new special technology, the Whole-Body Dot Engine, allows these difficult scans to be carried out in predictable time slots, as short as 25 minutes, with very high quality. This is accomplished through intelligent automation. The planning and execution of the scan requires only a few simple clicks. Providing high-quality diffusion weighted imaging is important for whole body exams; Magnetom Vida, with its BioMatrix Tuner technology, can deliver this distortion-free. Combined also with its strong 60/200 gradients and a large homogeneous field of view, Magnetom Vida makes whole-body examinations simple to perform, reproducibly, and with very high-quality. This is a major advantage, particularly when treating oncology patients, such as those with multiple myeloma, where guidelines have recently been moving toward whole-body MRI scans for therapy control.
Magnetom Vida offers not only numerous clinical advances, but also a number of improvements in energy consumption. These help to lower the total cost of ownership of the system over its entire life-cycle. Technologies such as Eco-Power provide an intelligent control of power-hungry components by switching them off when they are not needed for longer periods of time. The result is a MR scanner that consumes 30 percent less energy than the industry average for 3-Tesla scanners, as reported by the European Coordination Committee of the radiological, electromedical and healthcare IT industry (COCIR).
A fluid, game-changing combination of mathematical tools and Big Data seems ready to disrupt the field of radiology. However, it also promises to pave the way for what may turn out to be potentially-dramatic advances in healthcare.
There is some irony here. Data was once seen as a liability, to maintain and pay for. It is now being considered a potentially major asset. The key to this turnaround in perspectives lies in increasingly sophisticated, deep learning algorithms, advanced analytics and artificial intelligence which interpret the Big Data and make it usable.
Explosion in image numbers and volume
There is no hyperbole in the use of the term Big Data, as far as radiology is concerned. In recent years, there has been a veritable explosion in the stock of medical images. Emergency room radiologists often examine up to 200 cases a day, and each patient’s imaging studies can be around 250 GB of data. At the upper end, a ‘pan scan’ CT of a trauma patient can render 4,000 images. Currently, about 450-500 petabytes of medical imaging data are generated per year, but this is accelerating. Decisions are made on the basis of small parts of imaging data, the proverbial tip of the iceberg. Much of the information in this data has still to be deciphered and used.
Medical imaging and disease
Medical imaging provides important information on anatomy and organ function as well as detecting diseases states. Its analysis covers a gamut of areas from image acquisition and compression, to transmission, enhancement, segmentation, de-noising and reconstruction.
Technology has enabled often-dramatic leaps in image resolution, size and availability. Sophisticated picture archiving and communications systems (PACS) have allowed for the merger of patient images from different modalities and their integration with other patient data for analysis and use in a clinical setting.
Limits to vision – from digital to analogue
So far, radiology information to identify disease or other clinical conditions is presented in the form of images. Although scanners digitize data into pixels, this is reconstructed into shapes and shades or colours for display in a form that can be understood by the human brain.
This is where the ‘tip of the iceberg’ statement above comes into play. Medical scanners encode an image pixel in 56 bits, equivalent to 72,000 trillion ‘shades’. However, the scanner reduces the data amount to 16 bits, just 65,536 shades, for the human eye. As a result, 40 bits of information is lost, in just one pixel.
At some point in the future, it seems likely that radiologists use numbers rather than images to numerically define and detect patterns of diseases. The process may in fact have already begun.
Imaging analytics and deep learning
Such trends are being fuelled by rapid advances in imaging analytics. Smart, deep learning (DL) algorithms, which analyse pixels and other digital data bytes within an image, have the capacity to detect specific patterns associated with a pathology and provide conclusions in terms of a numerical metric.
One example of the use of numbers as a diagnostic definition concerns the use of algorithms in CT images to calculate bone density. The result is compared to a reference number, which au tomatically trigger alerts on low bone density. Avoiding the need for another dedicated examination, a physician can determine if a patient needs calcium supplements or another preventative measure.
Such algorithms also learn over time, and become better at what they do, resulting in even greater speed and more confidence in the future. Such a process has been driven by the steady acceleration, over the years, in computer processing speed. Indeed, while training an algorithm at the turn of the century took 2-3 months, the same results can now be achieved and iterated within minutes.
Neural systems and algorithms
Technically, deep learning produces a direct mapping from raw inputs to outputs such as image classes. Many DL algorithms are inspired by biologic neural systems. They are different from traditional machine learning, which requires manual feature extraction from inputs, and face limitations to use in the face of the large volumes of information associated with Big Data.
Big Data’s virtuous circle
Many DL algorithms directly seek to harness Big Data in radiology. Gigantic (and fast-growing) image libraries are being accessed for investigation to develop, test, validate and continuously refine algorithms, with the aim of covering a whole range of pathologies.
For radiologists, analytic results from an examination can be comprehensively evaluated against similar data obtained over a long period of time and evaluated to suggest appropriate diagnosis in current scenarios.
Such a virtuous cycle of algorithms and Big Data have become the focus for a host of major medical technology vendors as well as start-ups. However, the key enabling players are radiology departments, who own the data repositories and are uniquely placed to curate the data, in other words, organize it from fragments and make it available for running analytical algorithms.
The above process has, in some senses, been jump-started by previous efforts to data mine reports from radiology departments as they transitioned from PACS to enterprise imaging. The next step in this Big Data-driven opportunity will consist of linking information in radiology reports to the pixels of medical images.
The pixel goldmine
Few doubt any more that pixels are a goldmine, holding wholly new insights into a medical image and how best they could be utilized, not just by radiologists but other clinicians offering patient care. Alongside data mined from electronic medical records, quantitative pixel-based analysis algorithms are increasingly likely to be used to find patterns in images.
Big Data-based screening algorithms, for example, can be used to highlight subtle, multi-dimensional changes in a nodule or a lesion. This can be followed by applications such as curved planar or 3D multi-planar reconstructions, or dynamic contrast enhancement (DCE) texture analysis on highly targeted data subsets, instead of making the time-consuming effort of querying a complete imaging dataset.
Specific examples of such an approach might include diagnosis of lesions in the liver and identification of disease-free liver parenchyma. Another would be volume analysis of lung tumours and solitary pulmonary nodules to decide temporal evolution of lesion. Big data based pattern analysis modules can detect areas of opacities, honeycombing, reticular densities and fibrosis, and thereby provide a list of differentials, using computer aided diagnostic tools.
For tumours, in general, radiologists can run algorithms to check contrast enhancement characteristics, and such metrics can be compared to prior results as well as other pathology data to provide a specific differential list.
Decision support systems
One decision support system based on Big Data assists physicians in providing treatment planning for patients suffering from traumatic brain injury (TBI). The algorithm couples demographic data and medical records of the patient to specific features extracted from CT scans in order to predict intracranial pressure (ICP) levels.
Google’s entry into this field seeks to address real world limitations – not just in terms of human capacities but also trained medical personnel. Its first deep learning imaging algorithm sought to recognize diabetic retinopathy, the fastest growing cause of blindness in poor countries, where a shortage of specialists meant many patients lost their sight before diagnosis.
The promise of AI
Google’s algorithm is based on artificial intelligence (AI), seen as an especially promising catalyst for advances in such areas.
AI-based algorithms, for example, can calculate the volume of bleed on the basis of multiple brain CT slices in stroke patients, with the size of bleed volume indicating urgency as well as care pathway. Another recent algorithm assesses recent infarcts on CT, which can be missed if they are hyper-acute (less than 8-12 hours old), and is therefore relevant to all patients with sudden onset weakness. The University of California in San Francisco has been testing an algorithm to identify pneumothorax in chest radiographs of surgery patients, before they exit the OR (operating room). The aim is to not only avoid the huge costs of a collapsed lung but also ensure that the OR is freed from being used for an otherwise-avoidable procedure.
AI is also being considered for workflow management and triaging. In the near future, it is almost certain that images are screened as data is acquired by a scanner, to distinguish between ‘normal’ and ‘abnormal’ images, prioritize cases according to the likelihood of disease and alerting radiologists to conditions that require urgent attention. The results are tangible and impressive. One algorithm has helped physicians to shrink the time for cardiac diagnoses from 30 minutes to 15 seconds.
Certain vendors are leveraging AI to correlate findings on properties like morphology, cell density or physiological characteristics to expert radiologist’s reports, while taking additional clinical data such as biopsy results into account. Others use reasoning protocols as well as visual technologies such as virtual rendering to analyse medical images. This is then combined with data from a patient’s medical record to offer radiologists and clinicians decision-making support.
AI and the radiologist
So far, algorithms and emerging metrics are expected to be largely used as a complement to decisions made by radiologists.
However, at some point in the future, it seems plausible that radiologists no longer need to look at images at all. Instead, they would simply analyse outcomes of the algorithms.
Once again, AI is at play here. Apart from deep learning algorithms, radiology can claim to be witness to the first successes with the emerging science of ‘swarm’ AI, which helps form a diagnostic consensus by turning groups of human experts into super experts. Swarm AI is directly based on nature, which sees species accomplishing more by participating in a flock, school or colony (a ‘swarm’) than they can individually. One report, published in ‘Public Library of Science (PLOS)’, stated that swarm intelligence could improve other types of medical decision-making, ”including many areas of diagnostic imaging.”
In December 2015, a study in ‘IET Systems Biology’ reported about a swarm intelligence algorithm which assisted “in the identification of metastasis in bone scans and micro-calcifications on mammographs.” The authors, from universities in the UK and India, also reported about the use of the algorithm in assessing CT images of the aorta and in chest X-ray. They proposed a hybrid swarm intelligence approach to detect tumour regions in an abnormal MR brain image.
The future: human-machine symbiosis
AI is unlikely to become a replacement for radiologists, but a tool to help them. According to Curt Langlotz, MD, PhD, professor of radiology and biomedical informatics at Stanford, the “human-machine system always performs better than either alone.”
April 2024
The medical devices information portal connecting healthcare professionals to global vendors
Beukenlaan 137
5616 VD Eindhoven
The Netherlands
+31 85064 55 82
info@interhospi.com
PanGlobal Media IS not responsible for any error or omission that might occur in the electronic display of product or company data.
This site uses cookies. By continuing to browse the site, you are agreeing to our use of cookies.
Accept settingsHide notification onlyCookie settingsWe may ask you to place cookies on your device. We use cookies to let us know when you visit our websites, how you interact with us, to enrich your user experience and to customise your relationship with our website.
Click on the different sections for more information. You can also change some of your preferences. Please note that blocking some types of cookies may affect your experience on our websites and the services we can provide.
These cookies are strictly necessary to provide you with services available through our website and to use some of its features.
Because these cookies are strictly necessary to provide the website, refusing them will affect the functioning of our site. You can always block or delete cookies by changing your browser settings and block all cookies on this website forcibly. But this will always ask you to accept/refuse cookies when you visit our site again.
We fully respect if you want to refuse cookies, but to avoid asking you each time again to kindly allow us to store a cookie for that purpose. You are always free to unsubscribe or other cookies to get a better experience. If you refuse cookies, we will delete all cookies set in our domain.
We provide you with a list of cookies stored on your computer in our domain, so that you can check what we have stored. For security reasons, we cannot display or modify cookies from other domains. You can check these in your browser's security settings.
.These cookies collect information that is used in aggregate form to help us understand how our website is used or how effective our marketing campaigns are, or to help us customise our website and application for you to improve your experience.
If you do not want us to track your visit to our site, you can disable this in your browser here:
.
We also use various external services such as Google Webfonts, Google Maps and external video providers. Since these providers may collect personal data such as your IP address, you can block them here. Please note that this may significantly reduce the functionality and appearance of our site. Changes will only be effective once you reload the page
Google Webfont Settings:
Google Maps Settings:
Google reCaptcha settings:
Vimeo and Youtube videos embedding:
.U kunt meer lezen over onze cookies en privacy-instellingen op onze Privacybeleid-pagina.
Privacy policy