Clinical laboratories and pathology groups should be on the alert to this new digital threat; telehealth sessions and video conferencing calls particularly vulnerable to acoustic AI attacks
Banks may be the first to get hit by a new form of hacking because of all the money they hold in deposit accounts, but experts say healthcare providers—including medical laboratories—are comparably lucrative targets because of the value of patient data. The point of this hacking spear is artificial intelligence (AI) with increased capabilities to penetrate digital defenses.
AI is developing rapidly. Are healthcare organizations keeping up? The hackers sure are. An article from GoBankingRates titled, “How Hackers Are Using AI to Steal Your Bank Account Password,” reveals startling new AI capabilities that could enable bad actors to compromise information technology (IT) security and steal from customers’ accounts.
Though the article covers how the AI could conduct cyberattacks on bank information, similar techniques can be employed to gain access to patients’ protected health information (PHI) and clinical laboratory databases as well, putting all healthcare consumers at risk.
The new AI cyberattack employs an acoustic Side Channel Attack (SCA). An SCA is an attack enabled by leakage of information from a physical computer system. The “acoustic” SCA listens to keystrokes through a computer’s microphone to guess a password with 95% accuracy.
“With recent developments in deep learning, the ubiquity of microphones and the rise in online services via personal devices, acoustic side channel attacks present a greater threat to keyboards than ever,” wrote UK study authors Joshua Harrison, MEng, Durham University; Ehsan Toreini, University of Surrey; and Maryam Mehrnezhad, PhD, University of London.
Hackers could be recording keystrokes during video conferencing calls as well, where an accuracy of 93% is achievable, the authors added.
This nefarious technological advance could spell trouble for healthcare security. Using acoustic SCA attacks, busy healthcare facilities, clinical laboratories, and telehealth appointments could all be potentially compromised.
“The ubiquity of keyboard acoustic emanations makes them not only a readily available attack vector, but also prompts victims to underestimate (and therefore not try to hide) their output,” wrote Joshua Harrison, MEng (above), and his team in their IEEE Xplore paper. “For example, when typing a password, people will regularly hide their screen but will do little to obfuscate their keyboard’s sound.” Since computer keyboards and microphones in healthcare settings like hospitals and clinical laboratories are completely ubiquitous, the risk that this AI technology will be used to invade and steal patients’ protected health information is high. (Photo copyright: CNBC.)
Why Do Hackers Target Healthcare?
Ransomware attacks in healthcare are costly and dangerous. According to InstaMed, a healthcare payments and billing company owned by J.P. Morgan, healthcare data breaches increased to 29.5% in 2021 costing over $9 million. And beyond the financial implications, these attacks put sensitive patient data at risk.
Healthcare can be seen as one of the most desirable markets for hackers seeking sensitive information. As InstaMed points out, credit card hacks are usually quickly figured out and stopped. However, “medical records can contain multiple pieces of personally identifiable information. Additionally, breaches that expose this type of data typically take longer to uncover and are harder for an organization to determine in magnitude.”
With AI advancing at such a high rate, healthcare organizations may be unable to adapt older network systems quickly—leaving them vulnerable.
“Legacy devices have been an issue for a while now,” Alexandra Murdoch, medical data analyst at GlobalData PLC, told Medical Device Network, “Usually big medical devices, such as imaging equipment or MRI machines are really expensive and so hospitals do not replace them often. So as a result, we have in the network these old devices that can’t really be updated, and because they can’t be updated, they can’t be protected.”
But telehealth, according to the UK researchers, may also be one way hackers get past safeguards and into critical hospital systems.
“When trained on keystrokes recorded using the video-conferencing software Zoom, an accuracy of 93% was achieved, a new best for the medium. Our results prove the practicality of these side channel attacks via off-the-shelf equipment and algorithms,” the UK researchers wrote in IEEE Xplore.
“[AI] has worrying implications for the medical industry, as more and more appointments go virtual, the implications of deepfakes is a bit concerning if you only interact with a doctor over a Teams or a Zoom call,” David Higgins, Senior Director at information security company CyberArk, told Medical Device Network.
Higgins elaborated on why healthcare is a highly targeted industry for hackers.
“For a credit card record, you are looking at a cost of one to two dollars, but for a medical record, you are talking much more information because the gain for the purposes of social engineering becomes very lucrative. It’s so much easier to launch a ransomware attack, you don’t even need to be a coder, you can just buy ransomware off of the dark web and use it.”
Steps Healthcare Organizations Should Take to Prevent Cyberattacks
Hackers will do whatever they can to get their hands on medical records because stealing them is so lucrative. And this may only be the beginning, Higgins noted.
“I don’t think we are going to see a slowdown in attacks. What we are starting to see is that techniques to make that initial intrusion are becoming more sophisticated and more targeted,” he told Medical Device Network. “Now with things like AI coming into the mix, it’s going to become much harder for the day-to-day individual to spot a malicious email. Generative AI is going to fuel more of that ransomware and sadly it’s going to make it easier for more people to get past that first intrusion stage.”
To combat these attacks patient data needs to be encrypted, devices updated, and medical staff well-trained to spot cyberattacks before they get out of hand. These SCA attacks on bank accounts could be easily transferable to attacks on healthcare organizations’ patient records.
Clinical laboratories, anatomic pathology groups, and other healthcare facilities would be wise to invest in cybersecurity, training for workers, and updated technology. The hackers are going to stay on top of the technology, healthcare leaders need to be one step ahead of them.
Device is latest example that wearable healthcare devices are moving past simple biomarker monitoring and into the area of assisting in rehab
Companies unrelated to traditional clinical laboratory medicine continue to develop wearable devices that enable individuals to monitor their health while also alerting physicians and caregivers in real time when certain biomarkers are out of range.
One recent example is US biotechnology company STAT Health Informatics in Boston, which has developed a wearable device that monitors blood flow to the ear and face “to better understand symptoms such as dizziness, brain fog, headaches, fainting, and fatigue that occur upon standing,” according to a press release. The tiny device is worn in the ear and connects wirelessly to a smartphone app.
Johns Hopkins University clinically tested the STAT device, and according to Medical Device Network, “It can predict a person fainting minutes before it happens and can be worn with more than 90% of devices that go in or around the ear. It can also be left in while sleeping and showering, meaning less likelihood of removing the device and forgetting to replace it.”
Another notable aspect of this invention is that it’s an example of how the ongoing miniaturization of various technologies makes it possible to invent smaller devices but with greater capabilities. In the case of the STAT device, it combines tiny sensors, Bluetooth, and an equally tiny battery to produce a device that fits in the ear and can function for up to three days before needing a recharge.
It’s easy to imagine these technologies being used for other types of diagnostic testing devices that could be managed by clinical laboratories.
“It’s well understood that the ear is a biometric gold mine because of its close proximity to the brain and major arteries. This allows for new biometrics … to be possible,” said Daniel Lee (above), co-founder and CEO of STAT Health, in a press release. “In addition, the ear is largely isolated from data corruption caused by arm motion—a problem that plagues current wearables and prevents them from monitoring heart metrics during many daily tasks. The ear is really the ideal window into the brain and heart.” Clinical laboratory managers may want to watch how this technology is further developed to incorporate other biomarkers for diseases and health conditions. (Photo copyright: STAT Health.)
How STAT Works
Every time the wearer stands, the STAT device tracks the change in response of blood pressure, heart rate, and blood flow to the head. “The device distills all this information into an ‘Up Score’ to track time spent upright. Its ‘Flow Score’ helps users pace their recovery by watching for blood flow abnormalities,” MassDevice reported.
According to the company’s website, STAT is intended for use in individuals who have been diagnosed with conditions known to suffer from drops in blood flow to the head, such as:
As an individual continues to use the device, STAT “learns about each user’s unique body to provide personalized coaching for healthy lifestyle choices,” MassDevice reported.
Another key factor is the technology built into the device. An optical sensor was chosen over ultrasound because STAT Health felt it was both easy to use and provided precise measurements accessing the shallow ear artery, MassDevice reported.
“Despite its small scale, the device incorporates advanced optical sensors, an accelerometer, a pressure sensor, temperature sensors, artificial intelligence (AI)-edge computing, three-day battery life (or more), and a micro solar panel,” Medical Device Network noted.
STAT’s image above demonstrates how truly minute the company’s wearable device is, even though it monitors blood flow to the face and ear looking for signs that the wearer is about to suffer bouts of dizziness or lightheadedness due to a drop in blood flow. (Photo copyright: STAT Health Informatics Inc.)
STAT’s Impact on Users’ Health
STAT’s developers intend the device to help individuals stay on track with their health. “The target population can navigate their condition better. If they’re not standing when they can, they will become deconditioned. This product encourages standing and being upright where possible, as part of rehab,” Lee told Medical Device Network.
Lee has been developing wearable in-ear devices for many years.
“Nobody has realized the ear’s true potential due to the miniaturization and complex systems design needed to make a practical and user-friendly ear wearable,” he told MassDevice. “After multiple engineering breakthroughs, we’ve succeeded in unlocking the ear to combine the convenience and long-term nature of wearables with the high fidelity nature of obtrusive clinical monitors. No other device comes close along the axis of wearability and cardiac signal quality, which is why we believe STAT is truly the world’s most advanced wearable.”
For clinical laboratories, though STAT is not a diagnostic test, it is the latest example of how companies are developing wearable monitoring devices intended to allow individuals to monitor their health. It moves beyond the simple monitoring of Apple Watch and Fitbit. This device can aid individuals during rehab.
Wearable healthcare devices will continue to be introduced that are smaller, allow more precise measurements of target biomarkers, and alert wearers in real time when those markers are out of range. Keeping in tune with the newest developments will help clinical laboratories and pathologists find new ways to support healthcare providers who recommend these devices for monitoring their patients conditions.
As 3D printing technology gains acceptance with pharmaceutical companies, clinical laboratories could see increased demand for pharmacogenomic testing
Will physicians someday “print” prescription drugs for patients in-office? It sounds like science fiction, but research being conducted at the University College London (UCL) indicates the capability may be closer than we think, and it could bring about a new type of collaboration between clinical laboratories, ordering physicians, and pharmacies.
UCL’s new 3D technique, which it calls “volumetric 3D printing,” is intended to enable the pharmaceutical industry to tailor drug dosage, shape/size, and release to an individual patient’s needs and preference. A key element of precision medicine.
According to GlobalData Healthcare, 3D printing also can “significantly reduce cost, wastes, and economic burden as printers only deposit the exact amount of raw materials required.”
3D printing may enable pharmaceutical companies to address gender and racial disparities in prescription drug manufacturing through a developing technology that could have implications for clinical laboratory testing. Fred Parietti, PhD (above), co-founder and CEO of Multiply Labs, a technology company that develops robotics for precision medicine pharmaceuticals, told 3D Natives, “Currently, medications are developed especially for white adult men, which means that all women and children have an excessive prescription for their bodies. This fact underlines the importance of the advent of personalized medicines, as well as highlighting the individuality of each patient, since the error in the dosage of certain active ingredients can even lead to the malfunctioning of some treatments.” (Photo copyright: Multiply Labs.)
.
Increased Demand for Pharmacogenomic Testing
Though 3D printing of prescription drugs is not directly in the clinical laboratory/pathology space, it is noteworthy because it shows how technological advancements are progressing that actualize the ability to deliver precision medicine care to individual patients.
In turn, this could increase physician/patient demand for pharmacogenomic tests performed by clinical laboratories. The test results would be used by treating physicians to determine proper dosages for their individual patients prior to ordering 3D-printed drugs.
Being able to provide medication tailored to patients’ specific needs could bring about a revolution in pharmaceutical manufacturing. If 3D printed prescription drugs become mainstream, the demands could affect the clinical laboratory and pathology industries as well.
How Far Are We from Mass Production of 3D Printed Drugs?
The first and only 3D printed pharmaceutical drug on the American market is Spritam (levetiracetam) an anti-epileptic drug developed by Aprecia Pharmaceuticals, according to Medical Device Network. It received FDA clearance under the name Keppra in 1999.
Headquartered in Blue Ash, Ohio, Aprecia’s patented ZipDose manufacturing process allows 3D-printed pills to hold a larger dosage and dissolve rapidly. They currently have the only FDA process-validated 3D printing platform for commercial-scale drug production. They are leading the way on this new 3D technology and others are following suit.
FabRx, a start-up 3D printing company developed by academic researchers in 2014 at the University College London, released its first pharmaceutical 3D printer for personalized medicine called M3DIMAKER according to LabioTech.eu. The system is “controlled by specialized software, allowing the selection of the required dose by the pharmacist according to the prescription given by the clinician,” the company’s website notes.
The technology also allows for additional customization of pills, including the application of Braille for visually impaired patients, and printing of Polypills, which combine more than one drug into a single pill.
Other company’s developing 3D printing of pharmaceuticals, according to LabioTech.eu, include:
Germany’s Merck: currently in clinical trials of 3D printing medication with the goal of reaching large scale production.
China’s Triastek: which holds “41 patents that account for more than 20% of global 3D printing pharmaceuticals applications.”
We are still far away from large scale production of drugs using 3D printing, but that doesn’t mean it should not be on clinical laboratory leaders’ radar.
The rise of 3D printing technology for precision medicine could lead to big changes in the pharmaceutical world and alter how patients, providers, and clinical laboratories interact. It also could increase demand for pharmacogenomic testing to determine the best dosage for individual patients. This breakthrough shows how one line of technology research and development may, as it reaches clinical use, engage clinical laboratories.
Should the test prove clinically viable, it could lead to new biomarkers for eye disease diagnostics and a new assay for clinical laboratories
Scientists at Flinders University in Australia have developed a genetic blood or saliva test that, they say, is 15 times more effective at identifying individuals at high risk of glaucoma than current medical laboratory tests.
If so, this discovery could lead to new biomarkers for diagnostic blood tests that help medical professionals identify and treat various diseases of the eye. Their test also can be performed on saliva samples. The researchers plan to launch a company later in 2022 to generate an accredited test that can be used in clinical trials.
“Early diagnosis of glaucoma can lead to vision-saving treatment, and genetic information can potentially give us an edge in making early diagnoses, and better treatment decisions,” said lead researcher Owen Siggs, PhD, Associate Professor, College of Medicine and Public Health at Flinders University, in a university press release.
Flinders University researchers have been collaborating with scientists at the QIMR Berghofer Medical Research Institute and other research institutes worldwide for some time to identify genetic risk factors for glaucoma, the press release noted.
“In the cross-sectional study of monogenic and polygenic variants related to the disease, the new genetic test was evaluated in 2,507 glaucoma patients in Australia and 411,337 people with or without glaucoma in the UK. The test, conducted using a blood or saliva sample, could potentially detect individuals at increased risk before irreversible vision loss happens,” Medical Device Network reported.
“Genetic testing is not currently a routine part of glaucoma diagnosis and care, but this test has the potential to change that,” said Jamie Craig, PhD, (above), Distinguished Professor, College of Medicine and Health at Flinders University in Australia and senior author of the study, in a press release. “We’re now in a strong position to start testing this in clinical trials,” he added. This is yet another example of how new research is identifying a novel biomarker that could be incorporated into a clinical laboratory test. (Photo copyright: Flinders University.)
Who Is at Risk for Glaucoma?
Glaucoma is a group of eye diseases that are typically caused by a buildup of pressure within the eye. The eyeball contains and produces a fluid called aqueous humour which provides nutrition to the eye and keeps the eye in a proper pressurized state. Any excess of this fluid should be automatically released via a drainage canal called the trabecular meshwork.
But that’s not always the case. When the fluid cannot drain properly, intraocular pressure is created. Most forms of glaucoma are characterized by this pressure, which can damage the optic nerve and eventually cause vision loss and even blindness. Treatments for the disease include medications, laser treatments, and surgery.
Anyone can develop glaucoma, but according to the Mayo Clinic, individuals at higher risk of the disease include:
Individuals over the age of 60.
Those with a family history of glaucoma.
People of African, Asian, or Hispanic descent.
Patients with certain medical conditions, such as diabetes, heart disease, high blood pressure, and sickle cell anemia.
Those with corneas that are thin in the center.
Individuals who have had a past eye injury or certain types of eye surgery.
People who have taken corticosteroid medications, especially eyedrops, for an extended period of time.
Glaucoma is the second leading cause of blindness worldwide, particularly among the elderly. When diagnosed early, the condition is manageable, but even with treatment, about 15% of glaucoma patients become blind in at least one eye within 20 years.
According to the federal Centers for Disease Control and Prevention (CDC), approximately three million Americans are living with glaucoma. The disease often has no early symptoms, which is why it is estimated that about 50% of individuals who have glaucoma do not realize they have the illness.
Thus, a clinically-viable genetic test that is 15 times more likely to identify people at risk for developing glaucoma in its early stages would be a boon for ophthalmology practices worldwide and could save thousands from going blind.
More research and clinical trials are needed before the Flinders University genetic test for glaucoma becomes available. But the discovery alone demonstrates the importance of continuing research into identifying novel biomarkers that could be incorporated into useful clinical laboratory diagnostic tests.
