The AI protein-structure-prediction system may ‘revolutionize life sciences by enabling researchers to better understand disease,’ researchers say
Genomics leaders watched with enthusiasm as artificial intelligence (AI) accelerated discoveries that led to new clinical laboratory diagnostic tests and advanced the evolution of personalized medicine. Now Google’s London-based DeepMind has taken that a quantum step further by demonstrating its AI can predict the shape of proteins to within the width of one atom and model three-dimensional (3D) structures of proteins that scientist have been trying to map accurately for 50 years.
Pathologists and clinical laboratory professionals know that it is estimated that there are around 30,000 human genes. But the human proteome has a much larger number of unique proteins. The total number is still uncertain because scientists continue to identify new human proteins. For this reason, more knowledge of the human protein is expected to trigger an expanding number of new assays that can be used by medical laboratories for diagnostic, therapeutic, and patient-monitoring purposes.
DeepMind’s AI tool is called AlphaFold and the protein-structure-prediction system will enable scientists to quickly move from knowing a protein’s DNA sequence to determining its 3D shape without time-consuming experimentation. It “is expected to accelerate research into a host of illnesses, including COVID-19,” BBC News reported.
This protein-folding breakthrough not only answers one of biology’s biggest mysteries, but also has the potential to revolutionize life sciences by enabling researchers to better understand disease processes and design personalized therapies that target specific proteins.
In November, DeepMind’s AlphaFold won the 14th Community Wide Experiment on Critical Assessment of Techniques for Protein Structure Prediction (CASP14), a biennial competition in which entrants receive amino acid sequences for about 100 proteins whose 3D structures are unknown. By comparing the computational predictions with the lab results, each CASP14 competitor received a global distance test (GDT) score. Scores above 90 out of 100 are considered equal to experimental methods. AlphaFold produced models for about two-thirds of the CASP14 target proteins with GDT scores above 90, a CASP14 press release states.
According to MIT Technology Review, DeepMind’s discovery is significant. That’s because its speed at predicting the structure of proteins is unprecedented and it matched the accuracy of several techniques used in clinical laboratories, including:
Unlike the laboratory techniques, which, MIT noted, are “expensive and slow” and “can take hundreds of thousands of dollars and years of trial and error for each protein,” AlphaFold can predict a protein’s shape in a few days.
“AlphaFold is a once in a generation advance, predicting protein structures with incredible speed and precision,” Arthur D. Levinson, PhD, Founder and CEO of Calico Life Sciences, said in a DeepMind blogpost. “This leap forward demonstrates how computational methods are poised to transform research in biology and hold much promise for accelerating the drug discovery process.”
Science reported that AlphaFold, which scored a median of 87—25 points above the next best predictions—did so well that CASP14 organizers worried DeepMind may have been somehow cheated. To validate the results, they asked AlphaFold to complete a “special challenge”—modeling a membrane protein from an ancient species of microbes called archaea, which they had been unable to model satisfactorily using X-ray crystallography. AlphaFold returned a detailed image of a three-part protein with two long helical arms in the middle. “It’s almost perfect,” Andrei Lupas, PhD, Director at the Max Planck Institute for Developmental Biology, told Science. “They could not possibly have cheated on this. I don’t know how they do it.” (Graphic copyright: DeepMind/Nature.)
“Even tiny rearrangements of these vital molecules can have catastrophic effects on our health, so one of the most efficient ways to understand disease and find new treatments is to study the proteins involved,” Moult said in the CASP14 press release. “There are tens of thousands of human proteins and many billions in other species, including bacteria and viruses, but working out the shape of just one requires expensive equipment and can take years.”
Science reported that the 3D structures of only 170,000 proteins have been solved, leaving roughly 200 million proteins that have yet to be modeled. Therefore, AlphaFold will help researchers in the fields of genomics, microbiomics, proteomics, and other omics understand the structure of protein complexes.
“Being able to investigate the shape of proteins quickly and accurately has the potential to revolutionize life sciences,” Andriy Kryshtafovych, PhD, Project Scientist at University of California, Davis, Genome Center, said in the press release. “Now that the problem has been largely solved for single proteins, the way is open for development of new methods for determining the shape of protein complexes—collections of proteins that work together to form much of the machinery of life, and for other applications.”
Clinical laboratories play a major role in the study of human biology. This breakthrough in genomics research and new insights into proteomics may provide opportunities for medical labs to develop new diagnostic tools and assays that better identify proteins of interest for diagnostic and therapeutic purposes.
The clinics are part of a growing trend among large retailers to open full-service healthcare clinics where consumers seek out other goods and services
Major retail chains continue to partner with local health systems and other healthcare companies to expand the range of primary care services delivered in their stores. The latest such collaboration is a partnership between Walmart (NYSE:WMT) and Oak Street Health (NYSE:OSH) at three locations in Texas.
Why is this trend important for clinical laboratories to follow? Because after 15 years, retail chains are moving past the simple walk-in clinic model of using a nurse practitioner to provide limited diagnoses that produce prescriptions at chain store pharmacies and other retail locations. They are now partnering with local health systems to provide full healthcare services that are delivered by physicians. These medical services include many common clinical laboratory tests.
The new OSH clinics, located in Walmart Supercenters, are open and accepting patients via walk-in, same day, and scheduled appointments. The clinics are located in the Dallas-Fort Worth area at:
Arlington Walmart, 4801 S Cooper St, Arlington, TX, 76017
Carrollton Walmart, 1213 E Trinity Mills Rd, Carrollton, TX, 75006
The clinics offer comprehensive, preventative, and urgent care services to consumers, including:
Primary care
Optometry
X-rays
Dental
Behavioral counseling
Hearing services
Nutrition and fitness
As well as clinical laboratory testing, including:
A1C
Lipid
Pregnancy
Strep
Mono
Flu
Drug screenings, and more.
“While all members of the community—from toddlers to seniors—are welcome at these clinics, Oak Street Health’s focus in its growing network of more than 60 primary care centers remains adults on Medicare,” states an OSH press release.
This partnership between Walmart and Oak Street Health means clinical labs in that area will need to follow their patients to be able to collect the specimens and perform the lab tests for patients seen in Walmart Health clinics.
In, “Walmart Opens Second Health Center Offering Clinical Laboratory Tests and Primary Care Services,” Dark Daily reported in May on similar Walmart Health Center openings like that shown above in partnership with WellStar Health System in Georgia. These full-service primary care centers offer many common clinical laboratory tests. “By offering clinical laboratory testing in support of primary care and urgent care, Walmart may be able to lower prices for lab tests in any market that it enters,” said Robert Michel, Editor-in-Chief of Dark Daily and its sister publication The Dark Report. (Photo copyright: Walmart.)
Oak Street Health Brings Value-based Medicine to 11 States
“It is our mission at Oak Street Health to rebuild healthcare as it should be, and that aligns directly with Walmart’s history of providing accessible and equitable healthcare in communities across the country,” said Mike Pykosz, CEO of Oak Street Health, in the press release. “We look forward to becoming a positive addition to the neighborhood in these new markets and providing an unmatched healthcare experience in a convenient location.”
Both companies are planning to extend their relationship beyond these three locations and open additional clinics in other regions.
“We’ve proudly served customers at these three former Walmart Care Clinic locations for the last five years, and we are excited to bring this evolved approach to healthcare to our customers at these locations with Oak Street Health,” said Marcus Osborne, Senior Vice President, Walmart Health, in the press release. “As we grow Walmart Health locations in other markets, we think Oak Street Health’s innovative value-based healthcare model will help us continue to deliver on our live better promise at these locations.”
The majority of Oak Street Health consumers are Medicare Advantage patients, but OSH does accept most major and commonly-accepted insurance plans, Healthcare Dive reported.
There is evidence that savvy investors believe moving primary care into retail stores and other non-traditional locations can be a big winner. In its third quarter report, Oak Street Health released very strong numbers for their third quarter, which ended September 30. Their total reported revenue for the quarter was $217.9 million, which accounted for a 57% increase over last year’s third quarter earnings, Yahoo Finance reported.
OSH’s capitation revenue totaled $211.8 million, according to the report, which was a 59% increase year over year. Law Insider defines capitation revenues as “all payments from managed care organizations, where payment is made periodically on a per member basis for the partial or total medical care needs of a patient, co-payments, and all HMO incentive bonuses.”
In its third quarter statement, Oak Street Health also reported caring for approximately 59,500 at-risk patients, which represented 66% of its total patients.
“Our strong third quarter results were highlighted by 38% growth in at-risk patients, 57% revenue growth, and the resumption of new center openings, as we opened 13 centers during the quarter amidst continued uncertainty related to the COVID-19 pandemic,” said Pykosz in a statement, Yahoo Finance reported. “Looking ahead, we continue to be excited by the ample opportunity to drive continued de novo expansion across both new and existing markets, as well as the complementary growth opportunities presented by our Walmart collaboration and CMS’ Direct Contracting program.”
As we wrote in the May Dark Daily e-briefing, “Clinical laboratory leaders may want to explore partnerships with Walmart and other retailers that are developing healthcare centers to deliver primary care services in places where masses of people shop for everyday items. Especially given that these big-box retailers remain open during healthcare crises like the COVID-19 pandemic.”
This is even more critical now, as more retailers partner with health systems to provide expanded primary care and clinical laboratory services.
Clinical laboratories have been significantly stressed by the ongoing coronavirus pandemic. When COVID-19 treatments appropriated slots previously reserved for elective surgeries, procedures, and routine tests, labs lost revenue and turnaround times were lengthened.
Additionally, labs found the technology for running COVID-19 tests as well as administering the necessary documentation was lacking efficiency. Pressures have been compounded by demand from federal and state authorities for compliance with new COVID-related data reporting requirements— a process for which automation has been underused. In fact, most technology currently in place was not built for this new type of workflow, with the predominance of lab systems based on a patient encounter. COVID-19 testing frequently falls outside of these parameters.
Fortunately, since the pandemic began, lessons have been learned. Clinical laboratories have pivoted and adapted— and yet the question remains as to how far into the future labs will need to offer COVID-19 tests on a large scale, with some predictions stretching deep into 2021 and beyond.
As a result, because of urgent needs related to the pandemic, clinical labs are presented with a unique opportunity to strengthen their resilience, redefine their role and offerings, and further extend their value by enhancing patient safety and quality of care.
However, to accurately report on infection patterns and to track and predict infectious diseases—actionable data is a must, along with data structuring to support infection and treatment protocols. Progress in these areas depends on clean, reliable data. Clinical laboratory data that is originated efficiently and accurately using automation to collect, process, and report adds value, reduces costs, and improves patient outcomes.
To address labs’ dire need for clean and reliable data, Dark Daily is pleased to offer this new FREE white paper for laboratory professionals that explains the key steps—and positive results—of strengthening the data service infrastructure of your clinical lab.
This FREE White Paper will provide insights on:
Why the pandemic disruption carries an unprecedented opportunity, and underscores the imperative to strengthen the healthcare data service infrastructure
Understand how manual processing of data negatively impacts your lab and not only results in data incongruity, but also affects your practitioner relationships, patient care, and getting reimbursed in a timely manner
Learn the 3 crucial steps for improving the flow of your clinical laboratory’s data collection, capture, and reporting
How to ensure your lab’s data management can keep pace with innovation and ongoing new standards for infectious disease and public health reporting, and much more
White Paper Table of Contents
Introduction
Part 1: Strengthening the Clinical Laboratory Data Service Infrastructure
Part 2: Key Steps for Realizing Accuracy, Expanded Capacity, and Reporting of Clinical Laboratory Data
Improve the Data Collection Process of Clinical Laboratories by Reducing Manual Inputs: Three Primary Tasks
Ensure Clinical Laboratory Clean Order Entry: Best Practices
Implement Automation to Strengthen Clinical Laboratory Data Quality, Data Veracity, and Resilience: What to Expect on an Enterprise Level
Organize and Filter Clinical Laboratory Data for Internal, Vertical, and External Integration: Three Truths That Become Evident
Conclusion
Although the healthcare system and clinical laboratories remain significantly stressed by the COVID-19 pandemic, flexibilities and solutions continue to develop. 2021 indicates a sea change in healthcare data collection, integration, and interoperability.
Indeed, healthcare providers are in a unique position, with clinical laboratories the developers, custodians, and distributors of volumes of data that offer opportunities for improving healthcare outcomes, making it incumbent upon lab leaders and their hospital and health system stakeholders to think more strategically.
Learn what you need to know to develop a unified data organization, interoperability, and reporting plan for your lab that leverages accurate, actionable data. Download your FREE copy of “Clinical Laboratories Use Automation to Expand Their Data Capabilities And StrengthenTheir Resilience to Respond Faster During a Pandemic and Beyond” below!
Produced in partnership with:
Download the White Paper now by completing the form below.
Access to some white papers may require registration. In exchange for providing this free content, we may share your information with the companies whose content you choose to view. By accessing the white paper, you’re agreeing to our Terms of Service and Privacy Policy.
Clinical laboratory professionals should note that one case study describes a COVID-positive cancer patient shedding infectious particles for five months, which is much longer than expected
Just when researchers start believing they understand COVID-19 infections, something happens that reveals there is still more to learn. These additional findings are relevant for clinical laboratory managers and pathologists because the new insights often may play a role in how SARS-CoV-2 results should be interpreted for individual patients.
Researchers recently described a case where, in February, a 71-year-old woman underwent surgery related to her 10-year battle with cancer. While she was in the hospital, she was found to be positive for the SARS-CoV-2 coronavirus, though she showed no respiratory or systemic symptoms. Nevertheless, the hospital isolated her and monitored the infection.
To everyone’s surprise, the patient remained positive for five months. She underwent 15 COVID-19 tests from various diagnostics companies, as well as receiving two doses of convalescent plasma therapy, but she remained positive for the coronavirus into June.
In their published study, they wrote, “Although it is difficult to extrapolate from a single individual, our data suggest that long-term shedding of infectious virus may be a concern in certain immunocompromised people. Given that immunocompromised individuals could have prolonged shedding and may not have typical symptoms of COVID-19, symptom-based strategies for testing and discontinuing transmission-based precautions, as recommended by the Centers for Disease Control and Prevention (CDC), may fail to detect whether certain individuals are shedding infectious virus.”
Clinical laboratory professionals and pathologists will find it significant that patients with major health conditions may be shedding viral material for weeks longer than originally thought. This is relevant because it may be prudent to COVID test patients who present with compromised immune systems, and who are asymptomatic, and then repeat that testing at appropriate intervals.
The graphic above taken from the NIAID study shows how long it took for the SARS-CoV-2 coronavirus to clear the 71-year-old immunocompromised cancer patient’s system, and at which points the convalescent plasma doses were administered. (Graphic copyright: National Institute of Allergy and Infectious Diseases.)
Immunocompromised Patients May Handle COVID-19 Differently
The NIAID researchers believe the reason the patient continued to shed infectious virus for so long was because she was immunocompromised. They wrote, “Many current infection control guidelines assume that persistently PCR-positive individuals are shedding residual RNA and not infectious virus, with immunocompromised people thought to remain infectious for no longer than 20 days after symptom onset. Here we show that certain individuals may shed infectious, replication-competent virus for much longer than previously recognized. Although infectious virus could be detected up to day 70, sgRNA, a molecular marker for active SARS-CoV-2 replication, could be detected up until day 105.”
In the United States, some three million people have compromised or weakened immune systems. This is a significant population, Science Alert reported.
“As the virus continues to spread, more people with a range of immunosuppressing disorders will become infected, and it’s more important to understand how SARS-CoV-2 behaves in those populations,” Vincent Munster, PhD, Chief, Virus Ecology Unit at the National Institute of Allergy and Infectious Diseases and co-author of the NIAID study, told Science Alert.
The NIAID study findings match knowledge about other coronaviruses. For example, Science Alert reported that immunocompromised people with Middle East Respiratory Syndrome (MERS) have been shown to shed common seasonal coronaviruses for up to a month following infection.
That study included 303 patients, of which 193 were symptomatic. During the course of the study, 21 of the asymptomatic patients developed symptoms, however, the viral load was similar in all of the patients, regardless of symptoms.
“Isolation of asymptomatic patients may be necessary to control the spread of SARS-CoV-2,” concluded the JAMA researchers. But how long should asymptomatic patients remain isolated?
Official Guidance Is Based on Symptoms
The CDC updated its guidelines for who should isolate and for how long in October. The guidelines cover:
People who have or had COVID-19 and had symptoms;
People who tested positive for COVID-19 but did not have symptoms;
People who either had severe symptoms of COVID-19 or who have a compromised immune system;
People who were exposed to COVID-19, and
People who have been reinfected.
Regarding those who are immunocompromised and had COVID-19, the CDC says they “may require testing to determine when they can be around others.”
In addition to noting that people who are immunocompromised may require additional testing, the CDC is also continuously updating its published list of people who are at risk for complications and severe illness if they contract COVID-19. However, as the NIAID study showed, even those with underlying medical conditions can be asymptomatic.
And as the NIAID researchers note, there is more to learn. “Understanding the mechanism of virus persistence and eventual clearance will be essential for providing appropriate treatment and preventing transmission of SARS-CoV-2 because persistent infection and prolonged shedding of infectious SARS-CoV-2 might occur more frequently. Because immunocompromised individuals are often cohorted in hospital settings, a more nuanced approach to testing these individuals is warranted, and the presence of persistently positive people by performing SARS-CoV-2 gRNA and sgRNA analyses on clinical samples should be investigated.”
SARS-CoV-2 Science Is Young
An additional takeaway for pathology lab professionals is the reminder that the scientific research surrounding the novel coronavirus that causes COVID-19 is very young. New insights and understanding will continue to emerge, probably for many years.
One reason why the development of vaccines for COVID-19 has been so quick is that it built on scientific knowledge of the first SARS outbreak and MERS. It’s interesting to note that both SARS and MERS are relatively new as well: SARS emerged in 2002 and MERS in 2012. Compared to a disease like HIV, which was first identified in 1959, scientists have only been working on these particular coronaviruses for a short period of time.
The NIAID study is yet another example of new knowledge and insights emerging about how SARS-CoV-2 infects individuals. Collectively, these findings make it challenging for medical laboratory professionals to stay current with everything relevant and associated with the proper interpretation of COVID-19 test results.
Patients in health systems that use the Cerner EHR can now track and share specific health metrics with their healthcare providers
In what may be first steps toward becoming a full-service digital healthcare platform, Health information technology (HIT) developer Cerner (NASDAQ:CERN) is partnering with Amazon (NASDAQ:AMZN) to bring cloud-based health tracking services to its EHR customers. People who use Amazon’s Halo service—which includes a wristband device and smartphone app to monitor specific health metrics—can now import that data directly into Cerner electronic health record (EHR) systems for sharing with healthcare providers.
This may turn out to be a pioneering effort by one of the nation’s major providers of EHR systems to pull in useful health data from a variety of non-traditional sources and incorporate them into a patient’s electronic health record. Cerner has a major market share of EHR systems (exceeded only by Epic) and has a laboratory information system (LIS) that is used by many clinical laboratories.
For this fact alone, strategic planners at medical laboratories and anatomic pathology groups should follow this development. That is particularly true of those labs operated by hospitals and health systems that decide to add this new feature to their existing Cerner EHR. If data is flowing into the EHR from patients’ Amazon Halo service, for example, it is not a big leap to imagine that clinical lab test data from the patients’ EHRs might later flow back to the Halo service where it would be instantly accessible to those patients.
This collaboration, according to a Cerner press release, “allows consumers to easily connect vital health and well-being information with their broader healthcare teams. … Historically this type of data has been siloed or difficult to obtain. Wearable technology, such as the Amazon Halo, can help achieve greater interoperability across healthcare when integrated directly into a patient’s electronic health record (EHR).”
Cerner’s integration of the Amazon Halo Band and smartphone app (above) into its electronic health record (EHR) system allows users to share collected healthcare metrics with doctors in health systems that use the Cerner EHR. How long will it be before clinical laboratories that use Cerner’s laboratory information systems (LIS) will be able to incorporate similar metrics into their LIS as well? (Photo copyright: Amazon.)
Using Artificial Intelligence to Empower Healthcare Consumers
The Halo wristband, along with its accompanying smartphone app, “combines a suite of AI-powered health features that provide actionable insights into overall wellness … [and] uses multiple advanced sensors to provide the highly accurate information necessary to power Halo,” an Amazon press release states.
Data collected by Amazon Halo that are now importable into Cerner EHRs, according to the press release, include:
Activity: Informed by American Heart Association physical activity guidelines and the latest medical research, Amazon Halo awards points based on the intensity and duration of movement, not just the number of steps taken.
Sleep: Amazon Halo uses motion, heart rate, and temperature to measure time asleep and time awake; time spent in the various phases of sleep including deep, light, and REM; and skin temperature while sleeping.
Body: Amazon Halo lets customers measure their body fat percentage from the comfort and privacy of their own home, making this important information easily accessible.
Tone: This feature uses machine learning to analyze energy and positivity in a customer’s voice so they can better understand how they may sound to others, helping improve their communication and relationships.
Labs: Amazon Halo Labs are science-backed challenges, experiments, and workouts that allow customers to discover what works best for them specifically, so they can build healthier habits.
Leveraging Patient Generated Health Data
In the Cerner press release, David Bradshaw, Senior Vice President of Consumer and Employer Solutions at Cerner, said, “The healthcare industry is undergoing a digital revolution, where physicians are increasingly looking to leverage patient-generated health data to help keep them healthier and out of the doctor’s office.
“Our work with Amazon Halo,” he continued, “highlights the importance of using artificial intelligence and other leading-edge technologies to accelerate healthcare innovation and improve health outcomes. Cerner is focused on continuing to lead a wave of breakthrough innovation, and this integration with Amazon Halo is a step toward this goal.”
The first healthcare provider to offer the Amazon Halo service to its Cerner EHR users is Sharp HealthCare of San Diego. Some Sharp Health Plan members will participate in wellness programs and eventually have the option to link their Sharp and Halo data directly into the healthcare system’s Cerner EHR.
Sharp HealthCare includes 2,600 physicians, four acute care facilities, and three specialty hospitals.
“Technology is revolutionizing the way we care for patients and how consumers care for themselves, and at Sharp we strive to embrace innovative ways to leverage leading technology to engage consumers in managing their health,” said Michael Reagin, SVP and Chief Information and Innovation Officer at Sharp HealthCare, in the Cerner press release.
“With more relevant information at their fingertips, our populations will be empowered to make more informed decisions about the health and well-being of themselves and the communities they serve,” he added. “We are pleased to work with Cerner and Amazon Halo to offer our members, patients, and clinicians an opportunity to have a more connected health record.”
Cerner Expanding to Include Population Health and Precision Medicine
Cerner may be evolving toward a cloud-based platform that pulls in data from hospital and doctors’ office EHRs—as well as data gather by wearable devices—and uses that information for population health and precision medicine analysis to guide healthcare providers.
Last year, Cerner announced a collaboration with the Amazon Web Services (AWS) cloud platform, reportedly in an effort to pivot beyond its traditional health records business.
“Moving forward, I think Cerner will look more like a health platform company and less like an EHR company,” Dan Devers, SVP, Cloud Strategy, and Chief IP Officer at Cerner, told Fierce Healthcare. “As you play out the trend in healthcare, I see Cerner very much operating at the health network level—so beyond the enterprise of a single health system. Given the power of the cloud and the work we’re doing, I see Cerner having much more relevance into broader networks and providing nationwide capabilities.”
Cerner is aiming to provide consumers with more power regarding their own healthcare by equipping them with easy, fast, and efficient methods to access their personal information and provide healthcare professionals with useful data about individual patients.
Given the value and importance of clinical laboratory data, innovative lab managers should strive to be aware of collaborations like the one between Cerner and Amazon Halo. Remaining alert for opportunities to participate in these types of arrangements could provide labs with added revenue streams and inventive ways to offer customers value-added services.
