Antoaneta Roussi

home

authors

antoaneta-roussi

Digital health is rapidly changing our lives. Almost every day, new developments using data, artificial intelligence and smartphones to improve health, on individual and population levels, are entering the market. In 2015, there were more than 40,000 healthcare apps on Apple's U.S. App Store alone. And the number has kept growing.

But in the process of delivering the next revolutionary technology, health-tech innovators have often neglected to include usability in their apps so that they may also benefit people with disabilities, research suggests (

READ: Inadequate Health Records Are Failing Mothers and Providers

“People with disabilities have a particularly hard time, as they are often overlooked in the design of new technology, both regarding tools and content,” noted a report titled, “Health Inequalities in eHealth Context,” by the European Commission. “Due to their impairment, the notion of them being proficient (information and communications technology) users is often sidelined.”

So, what does this issue look like in the real world?

In August, the U.S. Food and Drug Administration 

 of the first mobile health (mHealth) app for contraception: Natural Cycles. The app allows women to avoid pregnancy by monitoring their resting body temperature — known as the basal body temperature &mdash; and recording their data so that an algorithm can determine their daily fertility.

With “perfect use,” the app’s creators say the failure rate is 1.8 percent, which means that 1.8 in 100 women annually will become pregnant despite using the technology.

But although the app meets the FDA’s guidelines governing mHealth apps, Natural Cycles poses problems for some nontraditional eHealth users, including women who have disabilities or irregular periods.

Natural Cycles told Healthcare Analytics News™ that while the algorithm had been “intricately designed” to account for a number of factors, including variation in cycle length, ovulation day and the length of the follicular and luteal phase, women with very irregular cycles could not benefit from it.

“They may find that Natural Cycles is not the most suitable method of contraception for them, but it may be helpful as a means to track and better understand their monthly cycles,” a Natural Cycles spokesperson said.

Similarly, for those with conditions that are not classified as disabilities but that could impair the menstrual cycle — such as polycystic ovary syndrome, thyroid disorders or eating disorders &mdash; Natural Cycles said the app “may be less suitable.”

Finally, for women with physical disabilities like cerebral palsy and multiple sclerosis or conditions such as down syndrome, the app doesn’t have the “data that investigates the effectiveness” in those patient groups, the company said.

Some industry observers expect that other birth control apps will be granted FDA approval soon by simply demonstrating that they work in a similar way to Natural Cycles. Critics say this could set a bad precedent for contraceptive mHealth apps, which may reach market without catering to women with disabilities.

“There is very little written about disability and menstruation generally, and what little there is (is) most often not written by disabled people,” writes Kim Sauder, a Ph.D. student in disability studies, in her blog, 

. “As a result, a lot of it is about control and often menstrual cessation in order to make the menstruating person more convenient for a care giver … Menstruation is still, unfortunately, a taboo subject.”

Therefore, in the process of eHealth development, companies might be smart to consider disability and the accessibility of alternative menstrual products. Otherwise, who will?

Get the best insights in healthcare analytics 

FDA Approves Marketing of First mHealth Solution for Contraception

Progenity Raises $125M in Series B Financing

AI Can Tailor Touchscreens for Those with Disabilities

Articles

Is it OK for digital health tools to exclude vulnerable populations?

Natural Cycles Is the First FDA-Approved Contraception App. But It's Not for All Women

Scientists will tell you that the single greatest hindrance to their research is time. And with the growing collection of data amassing globally, their schedules haven’t gotten any freer.

In fact, the National Institutes of Health said the growth of their biomedical databases had resulted in data scientists spending 80 percent of their time collecting and organizing data rather than analyzing it. By 2025, genomic information alone is expected to “equal or exceed” the quantity of data currently produced by data giants YouTube and Twitter, the agency said.

READ: 4 Ways Mobile Tech Is Driving Digital Health Research

That’s great news for advancing personal medicine, but it’s a mammoth task for researchers to sort.

For this reason, NIH recently announced its first “Strategic Plan for Data Science,” which will weave its existing data science efforts into a larger data ecosystem and shape how the agency manages its biomedical data. The agency hopes this will allow researchers to spend less time processing data and more time analyzing it.

“Accessible, well-organized, secure, and efficiently operated data resources are critical to modern scientific inquiry. By maximizing the value of data generated through NIH-funded efforts, the pace of biomedical discoveries and medical breakthroughs for better health outcomes can be substantially accelerated,” the agency said in a statement.

Most biomedical data is highly scattered and exists in a wide variety of formats that complicates researchers’ ability to use research data generated by their peers, creating the need for extensive data cleaning.

The new plan has a number of goals to address these issues, including: supporting an efficient biomedical research data infrastructure; promoting the modernization of the data ecosystem; promoting advanced data management, analytics, and visualization technologies; supporting workforce development; and creating policies that make these steps sustainable.

The plan will also ensure that all data-science activities and products supported by the agency continue to adhere to the FAIR principles, meaning that data is Findable, Accessible, Interoperable, and Reusable.

Following the announcement, Robert Alpern, MD, dean of the Yale School of Medicine, said this was an “important area” and that he was pleased that NIH was “dealing with this as a high priority.”

In its effort to modernize the way it stores, processes, and publishes biomedical data, the agency also said it would hire its first chief data strategist to oversee the plan.

The data chief will be involved with data intensive research initiatives such as 

—which aims to gather data from 1 million people in the US to accelerate research and improve health&mdash;the BRAIN Initiative, the Cancer Moonshot, and the Opioid Initiative. The data head will also serve as NIH’s advocate and representative in global data science efforts.  

The basics of the data strategy are already underway, but the NIH said it expects to begin implementation in the next 12 months, while continuing, “to seek community input” throughout the implementation. It also noted that the plan would likely require “frequent course corrections” as technology and data needs evolve.

NIH Announces Partnerships for All of Us Program Awareness

What to Know Before Hiring a Data Scientist

The mHealth App Cutting Through the Herbal Supplement Hype

The agency released a strategic plan and intends to hire a data chief. Why?

The NIH Makes a Big Push for Big Data

A mock-up of the 3D jet writer. Design has been cropped and resized. Courtesy of Purdue University/Luis Solorio.

Irrespective of the billions of dollars society spends on cancer research each year, scientists have yet to find a cure. In the United States alone, 1.7 million people are diagnosed with the disease, and about 600,000 die, each year.

The main reason that it is so hard to find effective treatments, researchers have said, is because the disease is so personal to an individual. Although many factors contribute to the development of cancer, there’s a lack of understanding about the underlying molecular mechanisms that drive it. Precision medicine, of course, has been gaining steam, but it has yet to take off across healthcare.

Researchers from Purdue University in Indiana hope to further the effort to make cancer treatment more personalized by identifying which drugs are particularly effective against a patient’s cancer type. The group, led by Luis Solorio, PhD, assistant professor of biomedical engineering, created a lifelike cancer environment out of polymer to better analyze drugs that might stop the disease in its tracks.

In the past, studies have used a 3D printer to re-create a controlled cancer environment, but the copies were not realistic enough for drug testing. The 3D jet writer developed at Purdue enables a cancer microenvironment by producing polymer tissues on an authentic scale with pore sizes large enough for cells to enter just as they would in a human body.

Right now, cancer treatment is not curative, so the long-term plan is for the technique to identify which drugs are particularly effective against a cancer, Solorio said.

“Clinicians have tons of different drugs at their disposal, but they don't really have the tools in place to be able to select which drugs might actually work, because a lot of those drugs are going to just make the patient feel better but not give them clinical benefit,” Solorio noted.

In the study, researchers used a patient’s fluids that already contained cancer cells—like those from water on the lungs, which are drained and usually discarded&mdash;to grow the cells. Solorio said the findings “are exciting,” as the cancer cells grew well and even outgrew some of the other cells in that space. When the researchers tried to take those same samples and grow them using standard tissue culture practices, they either died or stopped growing. “When we test them in this defined protein metrics, that never happened,” Solorio added.

In this case, the cells not only maintained the proliferative space but also the receptors that clinicians can use to determine which drugs a patient should receive.

Solorio hopes the finding will give clinicians a tool that will help guide their decision-making, which is particularly hard after a cancer has metastasized, and the cells are not as responsive to drugs as they were in the initial tumor.

“The clinician has only a limited amount of information to use when selecting the best drug or drug combination for the patient after the cancer has metastasized. So what we are hoping to do is provide a tool that can be used to inform the clinicians about which drugs may perform the best for a particular patient by screening thousands of compounds using the patients own cancer cells,” he said.

Researchers began working on the project at the Biointerfaces Institute at the University of Michigan and the continued it at Purdue.

Texas Team Becomes First in US to Perform AR Sinus Surgery

Stryker Reaches Deal to Distribute 3D Systems' Surgical Modeling Tech

Startup Looks for Its Own Lane With Hands-Free VR Therapy

What might this means of data generation teach medicine about drugs?

3D Model Could Provide Better Understanding of Cancer's Spread

Image has been resized. Courtesy of University of Copenhagen.

One of society’s greatest challenges is its growing dependence on prescription narcotics. In the last decade, soaring rates of drug abuse across the United States have led to a sharp increase in emergency room visits, and President Donald Trump’s administration is seeking some $13 billion in the next budget to combat the opioid epidemic.

But physicians and healthcare innovators hope that the onset of personalized medicine will empower people to better control their intake of drugs, as doses become specifically designed for the individual.

In January, a group of researchers at the University of Copenhagen in Denmark, 

 describing one such way of personalizing prescriptions in drug production.

The group printed drugs in QR-coded patterns onto a white edible material, allowing each dosage to be tailored to fit an individual patients’ needs. The thinking is that this high-tech type of drug production has the potential to protect against incorrect medications, overdoses, and even fake medicine.

Natalja Genina, PhD, assistant professor at the school’s department of pharmacy and a co-author of the paper, said she believes the method can reduce the current waste of mass-produced medicines that are left unconsumed.

“The idea of this personalized dose is that it won’t be produced en masse but in smaller amounts,” said Genina. “Sometimes patients split the pill incorrectly, or take too little or too much. That can have negative side effects.”

The QR code, which is printed in edible ink on the drug, will allow the patient to scan a barcode by a mobile phone app, revealing the patient, the dose, and how it should be administered. The app will also create an automatic alarm on a patient’s phone for when it should be taken.

The researchers hope that, going forward, a regular printer will be able to print the QR code on the medical drug.

"If we are successful with applying this production method to relatively simple printers, then it can enable the innovative production of personalized medicine and rethinking of the whole supply chain," said professor Jukka Rantanen, PhD, a member of the department of pharmacy and a study co-author.

Similar to apps that allow users to monitor their heart rate or the number of steps they’ve taken, the phone app will contain the patients’ medical data and track their treatment plan. For data protection, only the patient will be able to access the platform using a personal password.

But a drawback of this type of treatment is that patients will always need to carry their smartphones with them. Genina said some people might not feel comfortable tracking their progress.

“As it is personal medicine, there will be more responsibility on the patient to track their dose and continuously monitor their health,” she said. “Some people might not like to constantly log in to this platform to be reminded that they are sick, while for others, it will be a relief.”

The research into the QR-coded medicine is still in the trial phase, and Genina said once it passes a review, the group will start clinical based tests.

But the technology will then face another battle, with the pharmaceutical industry, which might not like to see a change to the status quo of mass drug production.

Genina believes that personalized medicine could bring back the esteem of pharmacists, who with the advent of online shopping have steadily lost their role in society.

“For 100 years, we were producing medicine in the tablet form. Now, we are much more flexible and can make it in any shape and way. This can be a way for pharmacists to produce on-demand medicine and stay relevant,” she said.

Investors Urge Apple to Address Childhood Smartphone Addiction

Smartphones Can Help Track the Progression of Multiple Sclerosis

When Digital Dieters Don't Track Their Data

The development helps patients monitor their drug intake through a smartphone app.

An Edible QR Code Might Advance Precision Medicine

Imagine facing this: You’ve been ill for months, and no doctor can determine the cause. Countless hospital visits and exams do not produce any tangible results. The very idea seems ludicrous to many, but for the few living with a rare disease, it’s all too real.

According to the Genetic and Rare Disease Information Center, there might be as many as 7000 rare diseases, with the total number of Americans living with a rare disease estimated to be as high as 30 million.

But a technique using computer-aided facial analysis could lend a hand in diagnosing at least 1 rare disease. A group of researchers at the University Hospital Bonn and the Charité Universitätsmedizin in Berlin, Germany, used artificial intelligence (AI) image analysis to identify patients with GPI anchor deficiencies and presented their findings in a paper 

Using data on genetic material of cells, surface texture, and typical facial features, researchers employed artificial intelligence methods to simulate disease models of Mabry syndrome, a condition featuring intellectual disability. The technology could serve for diagnosis in other diseases as well, researchers said.

“The artificial modeling of gene-typical faces that we achieved with these data sets clearly shows that the computer-aided evaluation of patients' portraits can facilitate and improve the diagnosis of GPI anchor deficiencies, which is significant progress,” wrote lead author Alexej Knaus, PhD, from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn.

GPI, or glycolipids, maintain the stability of a cell and aid in cell-to-cell communication. In GPI anchor deficiencies, the interaction is faulty because of gene mutation.

As those with Mabry syndrome have a range of distinctive facial features, including a narrow, tent-shaped upper lip, a broad nose bridge, and wide-set eyes, Peter Krawitz, MD, a co-author of the GPI study, said patients often suffer many years in uncertainty before receiving a correct diagnosis.

“Face2Gene Clinic will shorten the diagnostic odyssey for many families,” Krawitz said, referencing the name of the app that uses this technology.

In their research, the group photographed the faces of 91 patients with the condition. Krawitz said the main challenge in genomics is making sense out of the thousands of variants detected in a patient and that AI is particularly useful in interpreting that data. He believes the technology can be applicable to all conditions for which diagnoses can be done through a patient photo.

“We are quite optimistic that with AI it is possible to group patients of unknown cause that have a common mutation and the same gene,” he said.

The research group is conducting a large study on the performance that can be gained by using AI in exome analysis in collaboration with FDNA, an AI precision medicine company. 

“Until recently I was the greatest skeptic about this [AI] technology, but the systems have an astonishingly good performance,” Krawitz said. “The challenge now from a scientific point of view is to understand why they are better in certain tests than humans are. So there’s something we can learn, too.”

The tech can help identify Mabry syndrome. So what’s next?