Precision Medicine

Working with AWS, researchers from UPMC, the University of Pittsburgh, and Carnegie Mellon are building new machine learning tools for breast cancer and depression screening.

The extent to which the world of digital health has changed during the COVID-19 pandemic has been widely recognised. Remote medicine has become part of the new normal for patients and clinicians, introducing innovative care delivery models that are likely to endure even if the pendulum swings back to some degree in a post-COVID age. With this change has come a fresh focus on the role of smartphones to measure disease progression, rather than just a means of raising alerts and triggers that require immediate clinical intervention. This growing emphasis on evaluating how a condition affects the individual, and how well that patient is performing or functioning over time, has led to great interest in how remote assessment can enable new evidence-based approaches to treating and managing disease. New measures Tools such as FLOODLIGHT MS, a smartphone-based digital assessment suite for multiple sclerosis (MS) in development by Roche and Genentech, are attracting attention for the way they can deliver novel measures to help detect if, and how, the different functional domains and symptoms of a disease are evolving. “From what we see, I think the medical community is ready for these types of approaches,” says Mike Baker, PHC product leader at Roche. “Developers of this kind of tool need to be able to provide evidence that shows that they work and give the medical community some confidence to move forwards.” Baker says that for assessment tools like FLOODLIGHT MS to be successful, they have to generate actionable data. FLOODLIGHT MS focuses on generating data from active and passive tests to measure functional status in key domains typically impacted by MS, providing insights to clinicians and people with the disease to help them to manage the condition. The value of rapid diagnosis and proactive management of the disease was emphasised in a 2016 paper, Brain health: time matters in multiple sclerosis. By complementing standardised care models, digital assessment tools can enhance the treatment and management of MS on a continuous basis. Time shift “What we hope is that FLOODLIGHT MS impacts clinical practice in a positive way,” says Baker. “That it empowers people with MS to have better conversations and brings them closer to their care team. It’s not about replacing anything – the six-monthly visits or the interactions they already have. Rather, we hope it can help people make the most of that limited amount of time.” Baker suggests that people who have MS hold the key to understanding their own data. “If you’re seeing changes in the data, what does that really mean? Only the person with the disease can tell you what it means to them, and that element of context is crucial,” he says. This is a major reason why Roche and Genentech are working towards a tool which focuses on underlying disease worsening rather than alerts and triggers. With changes in data being so dependent on context, it can be difficult to derive the severity of a condition solely through information gathered via smartphone. In any case, a patient suffering a rapid worsening of symptoms will probably already have a care team around them. “We want to look at the underlying concept of progression,” says Baker. “The fact that MS progresses independent of relapse makes it important to identify and manage the condition continuously in an appropriate way. We’re trying to offer something that the care team can’t do today – monitoring the steady decline rather than the more obvious acute activity.” Engagement and collaboration with existing health systems As far as the adoption of smartphone-based assessment and monitoring goes, the critical aspects are: engagement among patients and clinicians, industry collaboration and embedding digital tools into existing care pathways. Baker says co-creation of solutions is as important as the science of assessment. “It’s certainly important that you can measure MS, but equally as important is that people with MS are willing to use the tools to generate data, share the data and do it on an ongoing basis,” he says. “It’s    something that takes a lot of thought and close partnership with the community.” Post-COVID, Baker expects the appetite for digital assessment tools in neuroscience and medicine to continue its rapid growth. “COVID changed everything in terms of access to care,” he says. “Many people with MS don’t want to go to higher risk places such as hospitals unnecessarily. It’s changed the way care is delivered, and I think we’ll see much more access to remote medicine in the future.” But one developer cannot deliver change on their own. It requires industry-wide collaboration among the medical and pharma community, leading to a standardised approach to digital monitoring. “If we have better mechanisms to detect changes in people with MS, it improves our ability to develop medicines,” explains Baker. “We can see those changes sooner and in more detail, and that means we can be faster and more efficient in the way we run clinical trials. It’s all about the understanding of MS - and that translates into better care for the patient.” To learn more, visit the Roche booth at the HIMSS & Health 2.0 European Digital Conference (7-11 September). Click here for further information and to get your ticket. Keep up with the latest news and deveopments from the event here.

The ADT-based collaboration network will collaborate with the Hospital Industry Data Institute to support delivery of near real-time data to Missouri care teams.

Shifting the focus from acute to preventative health and care is the ultimate aim for the digital transformation of health systems globally. Precision health integrates health insights and social determinants to improve clinical and financial outcomes.

Dragon Medical One voice technology will be integrated with mCODE core data, enabling easier documentation within clinical workflows – and a new partnership with Mayo will explore automation opportunities.

Health and care have been inexorably moving toward a new paradigm – one where the nature of the interactions is more personalised and they require the person to be more active in their pursuit of reducing risks that have an adverse effect upon the development of non-communicable diseases, says Dr Charles Alessi, chief clinical officer at HIMSS.

The U.S. Department of Health and Human Services also announced it would give $450 million to the biotech company Regeneron to manufacture and supply the company's antibody treatment.  

The Chicago area health system has expanded its DNA-10K precision medicine program by integrating detailed pharmacogenomic information into its EHR workflows.

Researchers from New York-based Mount Sinai Health System have combined artificial intelligence, imaging and clinical data to rapidly detect COVID-19 in patients. In a study published this week in Nature Medicine, researchers used AI algorithms in conjunction with chest CT scans and patient history to quickly diagnose patients who were positive for COVID-19 and improve the detection of patients who presented with normal CT scans. "We were able to show that the AI model was as accurate as an experienced radiologist in diagnosing the disease, and even better in some cases where there was no clear sign of lung disease on CT," said Dr. Zahi Fayad, director of the BioMedical Engineering and Imaging Institute at the Icahn School of Medicine at Mount Sinai, in a statement. WHY IT MATTERS Because the symptoms of COVID-19 are non-specific, it can be difficult to diagnose. Meanwhile, the SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test commonly used to identify COVID-positive patients can take up to two days to complete – and clinicians face the possibility of false negatives. RT-PCR test kits are also in short supply throughout many parts of the country. This, researchers say, reiterates the need for other ways to quickly and accurately diagnose patients with COVID-19. Researchers relied on CT scans of more than 900 patients that had been admitted to 18 medical centers in 13 Chinese provinces. They included 419 confirmed COVID-19-positive cases and 486 COVID-19-negative scans. The team also had access to patients' clinical information, including blood test results, age, sex and symptoms.  Using patient data, Mount Sinai researchers developed an AI algorithm to produce separate probabilities of COVID-19 positivity based on CT images, clinical information and the two combined.  "In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist," researchers wrote. In addition, the algorithm correctly identified 17 of 25 patients whose RT-PCR results had tested positive for COVID-19 but who presented with normal CT scans; for comparison, radiologists had classified all the patients as COVID-negative.  Although clinicians in the United States do not frequently use CT scans to diagnose COVID-19, researchers say imaging can play a vital role in conserving hospital resources and treating patients quickly.  "The high sensitivity of our AI model can provide a 'second opinion' to physicians in cases where CT is either negative (in the early course of infection) or shows nonspecific findings, which can be common," said Fayad. "It's something that should be considered on a wider scale, especially in the United States, where currently we have more spare capacity for CT scanning than in labs for genetic tests," Fayad continued. THE LARGER TREND Researchers have increasingly relied on AI to diagnose and treat patients with the novel coronavirus. In March, cognitive computing platform vendor behold.ai announced it had developed an AI-based algorithm to flag chest X-rays from COVID-19. Calling its platform "instant triage," behold.ai predicted it could help speed COVID-19 diagnosis.  "As we evaluate further positive cases from across the world, our results will be further validated," said behold.ai Chief Medical Officer Dr. Tom Naunton Morgan.  "This will increase the utility of our instant triage and potentially help reduce the burden on healthcare systems as more and more cases of pneumonia present and require rapid diagnosis," Morgan said. Other technology vendors have adapted existing tuberculosis-detecting AI technology to help indicate COVID-affected lung tissue in chest X-rays. ON THE RECORD Mount Sinai researchers say their next steps will be to further develop the model to forecast patient outcomes and to share their results with other healthcare facilities. "This study is important because it shows that an artificial intelligence algorithm can be trained to help with early identification of COVID-19, and this can be used in the clinical setting to triage or prioritize the evaluation of sick patients early in their admission to the emergency room," said Dr. Matthew Levin, director of the Mount Sinai Health System's clinical data science team.  "This is an early proof [of] concept that we can apply to our own patient data to further develop algorithms that are more specific to our region and diverse populations," said Levin. "This toolkit can easily be deployed worldwide to other hospitals, either online or integrated into their own systems," said Fayad.   Kat Jercich is senior editor of Healthcare IT News. Twitter: @kjercich Healthcare IT News is a HIMSS Media publication.

Precision medicine’s equivalent for people who are not necessarily ill, precision health, is only now starting to be developed.