Neetu Chandra Sharma

• Biotechnology companies have accelerated their use of cloud computing, machine learning (ML), and analytics for advancing research and development.
• More than 100,000 customers use AWS for ML today, right from creating a more personalized customer experience to developing personalized pharmaceuticals.

Covid-19 pandemic has majorly accelerated healthcare digitization in India. Rahul Sharma, president, public sector–Amazon Internet Services Private Ltd (AISPL), Amazon Web Services (AWS)-India and South Asia talked about patterns that have emerged in healthcare digitization, data, adoption of machine learning and artificial intelligence in India’s healthcare ecosystem. Edited excerpts from an interview:

How covid-19 pandemic brought digitization of healthcare to the fore?

There are broadly two patterns that have emerged in healthcare digitization since the start of the pandemic. The first is the adoption of digital technologies by the central and state governments to monitor and track the spread of the pandemic, connect with various authorities for decision-making, and provide healthcare services that can help citizens. The pandemic created the need for collaboration among various stakeholders at an unprecedented scale – multiple departments and decision-makers in governance at the ward, city, district, state and national level; administration and medical staff at hospitals; drug manufacturers and distributors; care-givers and health counselors; volunteers; and police and security personnel.

This meant a large volume of data flow, data storage, analytics, and visualization, necessitated the need for a robust, scalable, and secure cloud platform to deliver it. The second trend is how technology has been adopted by healthcare organizations and companies developing products and services for the healthcare sector. Biotechnology companies have accelerated their use of cloud computing, machine learning (ML), and analytics for advancing research and development. Startups and independent software vendors (ISVs) that are focusing on the healthcare sector are applying these technologies to develop telemedicine and remote patient monitoring solutions, as well as analyse lab and radiology tests at scale in minutes.

How does AWS empower healthcare service providers with data?

The largest healthcare providers, payers and IT vendors to the smallest ISVs and newest startups, across the globe are applying AWS ML services to store, transform, and analyse health data. For example, we’re seeing ML being used to derive important insights and trends from healthcare and patient data to help medical specialists make better and quicker decisions – be it precision diagnosis using genomic sequencing, early-stage cancer detection or advanced cardiac visualization. At the same time, healthcare and life science customers are using ML to uncover new insights from scientific research and data by enabling researchers to quickly and easily search thousands of research papers and documents using natural language questions.

Data has also played a critical role in government decision-making. As part of the NASSCOM task force, AWS helped enable a covid-19 data platform for the government of Telangana. The solution was deployed within five days to help the state tackle the pandemic. The solution deploys more than 100 dashboards using anonymized government and public datasets, with hundreds of thousands of covid-19 related data points. This platform features the covid-19 India Vulnerability Map, which provides anonymized mobility data at a district-level, to enable a holistic view of the pandemic within the Telangana state. It also offers more than 10 ML models for covid-19 response, which enables decision-making to manage the lockdown and sustainable recovery scenarios in the industry zones across the state, including disease transmission predictions, citizen mobility analytics, situational awareness of disease spread, and hospital care readiness.

There is a lot of interest in ML. More than 100,000 customers use AWS for ML today, right from creating a more personalized customer experience to developing personalized pharmaceuticals. ML went from being an aspirational technology to mainstream extremely fast. For a long time, the technology was limited to a few major tech companies and hardcore academic researchers. Things began to change when cloud computing became widely used. Compute power and data became more available, and now, ML is now making an impact across every industry, moving from the peripheral to a core part of every business and industry.

India is a growing economy and the scope of ML applications and AI is broad, and our customers are using these technologies to reinvent entire areas of their business. The scope of ML is vast even in application areas such as drones. AWS is working with the Drone Federation of India (DFI) to support the adoption of ML and AI-driven drone solutions among startups. The Adopt Drones Program from DFI will recognize ML-based solutions by drone application developers to generate deep insights from the data collected using drones, with a focus on 20 sectors, including agriculture, infrastructure, healthcare, and rural development.

The post Machine learning, data is helping medical fraternity: Rahul Sharma appeared first on Artificial Intelligence.

Today it was announced that Andreas Weber has been appointed CEO of EvidentIQ, the newly formed life science group from the merger of clinical software vendors XClinical and Fortress Medical with social platform Carenity.

The company said Weber brings more than 20 years of industry experience after management positions at ERT, Bioclinica and Oracle Health Sciences.

The EvidentIQ offering brings an end-to-end eClinical solution that meets increasing customer demand across clinical operations and clinical data management needs with its suite of applications, including EDC, coding, remote monitoring, RBM ePRO, eTMF, CTMS, RTMS, Payments and eFeasibility within a single integrated cloud platform. By combining the platform with a broad data science service portfolio such as patient recruitment, patient engagement media and a host of RWE late phase solutions EvidentIQ significantly helps customers optimize HTA submissions, pricing and reimbursement needs.

In a statement on the new company name and future positioning of the group, Weber said: “By evolving into a next generation technology-amplified data science group, EvidentIQ is paving the way for a new standard in value creation and innovation driven relevance for its customers. Our customers across XClinical, Carenity and Fortress Medical are at the heart of everything we do. As such, I wanted to assure our current loyal and valued customers, that not only will we continue the existing solutions and support offerings, we will in fact be expanding them technologically as well as increasing their interoperability.”

Seconding Mr. Weber, Lewis Baird will manage sales as chief commercial officer. Before joining EvidentIQ, Lewis established and led the European commercial team at Medrio after holding commercial leadership roles at DataTrial, Biorasi and Quintiles.

Together with Manuel Neukum (Chief Operations Officer), Michael Chekroun (Chief Strategy and Transformation Officer) and Roland Hiltmann (Chief Financial Officer), Lewis is part of Andreas Weber’s Executive Management Team.

Today EvidentIQ supports 7 of the top 10 pharma companies through novel RWE solutions and 150+ SMB customers in over 20 countries, including US, Germany, France, UK, Italy, Japan and China.

The post EvidentIQ: Data Science Group Created from XClinical, Carenity and Fortress Medical appeared first on Artificial Intelligence.

Can better design of deep learning studies lead to the faster transformation of medical practices? According to the authors of “Designing deep learning studies in cancer diagnostics,” published in Nature Reviews Cancer‘s latest issue, the answer is yes.

“We propose several protocol items that should be defined before evaluating the external cohort” says first author Andreas Kleppe at the Institute for Cancer Diagnostics and Informatics at Oslo University Hospital.”

“In this way, the evaluation becomes rigorous and more reliable. Such evaluations would make it much clearer which systems are likely to work well in clinical practice, and these systems should be further assessed in phase III randomized clinical trials.”

Slow implementation is partly a natural consequence of the time needed to evaluate and adapt systems affecting patient treatment. However, many studies assessing well-functioning systems are at high risk of bias.

According to Kleppe, even among the seemingly best studies that evaluate external cohorts, few predefine the primary analysis. Adaptations of the deep learning system, patient selection or analysis methodology can make the results presented over-optimistic.

The frequent lack of stringent evaluation of external data is of particular concern. Some systems are developed or evaluated on too narrow or inappropriate data for the intended medical setting. The lack of a well-established sequence of evaluation steps for converting promising prototypes into properly evaluated medical systems limits deep learning systems’ medical utilization.

Millions of adjustable parameters

Deep learning facilitates utilization of large data sets through direct learning of correlations between raw input data and target output, providing systems that may use intricate structures in high-dimensional input data to model the association with the target output accurately. Whereas supervised machine learning techniques traditionally utilized carefully selected representations of the input data to predict the target output, modern deep learning techniques use highly flexible artificial neural networks to correlate input data directly to the target outputs.

The relations learnt by such direct correlation will often be true but may sometimes be spurious phenomena exclusive to the data utilized for learning. The millions of adjustable parameters make deep neural networks capable of performing correctly in training sets even when the target outputs are randomly generated and, therefore, utterly meaningless.

Design and evaluation challenges

The high capacity of neural networks induces severe challenges for designing and developing deep learning systems and validating their performance in the intended medical setting. An adequate clinical performance will only be possible if the system has good generalisability to subjects not included in the training data.

The design challenges involve selecting appropriate training data, such as representativeness of the target population. It also includes modeling questions such as how the variation of training data may be artificially increased without jeopardizing the relationship between input data and target outputs in the training data.

The validation challenge includes verifying that the system generalizes well. For example, does it perform satisfactorily when evaluated on relevant patient populations at new locations and when input data are obtained using differing laboratory procedures or alternative equipment? Moreover, deep learning systems are typically developed iteratively, with repeated testing and various selection processes that may bias results. Similar selection issues have been recognized as a general concern for the medical literature for many years.

Thus, when selecting design and validation processes for diagnostic deep learning systems, one should focus on the generalization challenges and prevent more classical pitfalls in data analysis.

“To achieve good performance for new patients, it is crucial to use various training data. Natural variation is always essential, but so is introducing artificial variation. These types of variation complement each other and facilitate good generalisability,” says Kleppe.

The post Designing and evaluating medical deep learning systems appeared first on Artificial Intelligence.

The use of robotics in medtech continues to grow. Whether it’s a cobot working alongside humans to automate manufacturing or a surgical robot in the OR, a single point of failure can cause serious harm. The incorporated software systems must take safety into account.

IEC 61508-3 offers several techniques for developing software for safety-related systems, which the medical device software development community can draw on when designing and implementing risk-control measures as required by ISO 14971.

Developing “safe” software begins with establishing a software coding standard. IEC 61508-3 promotes using well-known techniques, including:

• Using modular code.
• Using preferred design patterns.
• Avoiding reentrance and recursion.
• Avoiding dynamic memory allocations and global data objects.
• Minimizing the use of interrupt service routines and locking mechanisms.
• Avoiding dead wait loops.
• Using deterministic timing patterns.

Keep it simple

There are other suggestions under the “keep it simple” principle around limiting the use of pointers, unions and type casting, and not using automatic type conversions while encouraging the use of parentheses and brackets to clarify intended syntax.

A hazard analysis might identify that your code or data spaces can get corrupted. There are well-known risk-control measures around maintaining code and memory integrity which can be easily adopted. Running code from read-only memory, protected with a cyclic redundancy check (CRC-32) that can be checked at boot time and periodically during runtime, prevents errant changes to the code space and provides a mechanism to detect these failures.

Segregating data into different memory regions that can be protected through virtual memory space and using CRC-32 over blocks of memory regions or even adding a checksum to each item stored in memory allows these CRC/checksums to be checked periodically.

CRC/checksums can be verified on each read access to a stored item and updated atomically on every write access to these protected items. Building tests into the software is an important tool as well. It’s a good idea to perform a power-on self-test (POST) at power-up to make sure the hardware is working and to check that your code and data spaces are consistent and not corrupt.

What else can happen?

Another hazardous situation arises when controlling and monitoring are performed on the same processor or in the same process. What happens to your safety system if your process gets hung up in a loop? Techniques that separate the monitor from the controlling function introduce some complexity to the software system, but this complexity can be offset by ensuring the controlling function implements the minimum safety requirements while the monitor handles the fault and error recovery.

Fault detection systems and error recovery mechanisms are much easier to implement when designed from the start. Poorly designed software can experience unexpected, inconsistent timing, which results in unexpected failures. It’s possible to avoid these failures by controlling latency in the software. State machines, software watchdogs and timer-driven events are common design elements to control this.

Keep an eye on communications

Inter-device and inter-process communications are another area of concern for safety-related systems. The integrity of these communications must be monitored to ensure they are robust. Using CRC-32 on any protocol between two entities is recommended. Separate CRC-32 on the headers and the payload helps to detect corruption of these messages. Protocols should be written and designed with the idea that at any time, your system could reboot due to some fault. Thus, building in retry attempts and stateless protocols is recommended.

Safe operational software verifies the ranges of all inputs at the interface where it is encountered; checks internal variables for consistency; and defines default settings to help recover from an inconsistent setting or to support a factory reset. Software watchdog processes can be put in place to watch the watcher and ensure that processes are running as they should.

By taking these techniques into account, software developers working on medical robotic devices can better address the concerns of safety-related systems.

The post Developing software for safety in medical robotics appeared first on Artificial Intelligence.

When Merdis Wells visited the diabetes clinic at the University Medical Center in New Orleans about a year ago, a nurse practitioner checked her eyes to look for signs of diabetic retinopathy, the most common cause of blindness.

At her next visit, in February of this year, artificial intelligence software made the call.

The clinic had just installed a system that’s designed to identify patients who need follow-up attention.

The Food and Drug Administration cleared the system — called IDx-DR — for use in 2018. The agency said it was the first time it had authorized the marketing of a device that makes a screening decision without a clinician having to get involved in the interpretation.

It’s a harbinger of things to come. Companies are rapidly developing software to supplement or even replace doctors for certain tasks. And the FDA, accustomed to approving drugs and clearing medical devices, is now figuring out how to make sure computer algorithms are safe and effective.

Wells was one of the first patients at the clinic in early February to be tested with the new device, which can be run by someone without medical training. The system produces a simple report that identifies whether there are signs that a patient’s vision is starting to erode.

Wells had no problem with the computer making the call. “I think that’s lovely!” she says.

“Do I still get to see the pictures?” Wells asks nurse practitioner Debra Brown. Yes, Brown replies.

“I like seeing me because I want to take care of me, so I want to know as much as possible about me,” Wells says.

The 60-year-old resident of nearby Algiers, La., leans into the camera, which has an eyepiece for each eye.

“It’s just going to be like a regular picture,” Brown explains. “But when we flash, the light will be a little bright.”

Once Wells is in position, Brown adjusts the camera.

“Don’t blink!” she says. “3-2-1-0!” The camera flashes and captures the image. Three more flashes and the exam is done.

She says still planning to examine the images and backstop the computer’s conclusion. That reassures Wells.

The test is quick and easy, which is by design. People with diabetes are supposed to get this screening test every year, but many don’t. Brown says the new system could allow the clinic to screen a lot more patients for diabetic retinopathy.

That’s the hope of the system’s inventor, Michael Abramoff, an ophthalmologist at the University of Iowa and company founder.

“The problem is many people with diabetes only go to an eye-care provider like me when they have symptoms,” he says. “And we need to find [retinopathy] before then. So that’s why early detection is really important.”

Abramoff spent years developing a computer algorithm that could scan retina images and automatically pick up early signs of diabetic retinopathy. And he wanted it to work in clinics, like the one in New Orleans, rather than in ophthalmologists’ offices.

Developing the computer algorithm wasn’t the hard part.

“It turns out the biggest hurdle, if you care about patient safety, is the FDA,” he says.

That hurdle is essential for public safety, but not an easy one for a brand-new technology — especially one that makes a medical call without an expert on hand.

Often medical software gets an easy road to market, compared with drugs. Software is handled through the generally less rigorous pathway for medical devices. For most devices, the evaluation involves a comparison with something already on the market.

But this technology for detecting diabetic retinopathy was unique, and a patient’s vision is potentially on the line.

When Abramoff approached the FDA, “of course they were uncomfortable at first,” he says, “and so we started working together on how can we prove that this can be safe.”

Abramoff needed to show that the technology was not just safe and effective but that it would work on a very diverse population since all sorts of people get diabetes. That ultimately meant testing the machine on 900 people at 10 different sites.

“We went into inner cities, we went into southern New Mexico to make sure we captured all those people that needed to be represented,” he says.

All the sites were primary care clinics, because the company wanted to demonstrate that the technology would well without having an ophthalmologist on hand.

That extensive test satisfied the FDA that the test would be broadly useable, and reasonably accurate. IDx-DR surpassed the FDA’s requirement. Test results that indicated eye disease needed to be correct at least 85 percent of the time, while those finding no significant eye damage needed to be correct at least 82.5 percent of the time.

“It’s better than me, and I’m a very experienced retinal specialist,” Abramoff says.

The FDA helped guide the company’s software through its regulatory process, which is evolving to accommodate inventions flowing out of artificial intelligence labs.

Bakul Patel, associate director for digital health at the FDA, says that in general, the FDA expects more evidence and assurances for technologies that have a greater potential to cause harm if they fail.

Some software is completely exempt from the FDA process. A simple tweak in a routine piece of software may not require any FDA review at all. The rules get tighter for a change that could substantially alter the performance of an artificial intelligence algorithm.

The agency has years of experience approving software that is part of medical devices, but new algorithms are creating new challenges.

For one thing, the agency needs to be wary of approving an algorithm that’s based on a particular set of patients, if it’s not clear that it will be effective in different groups. An algorithm to identify skin cancer may be developed primarily on white patients and may not work on patients with darker skin.

And many algorithms, once on the market, will continue to gather data that can be used to improve their performance. Some programs outside of health science continually update themselves to accomplish that. That raises questions about how and when updated software needs another round of review.

“We realize that we have to re-imagine how we look at these things, and allow for the changes that go on, especially in this space,” Patel says.

To do that, the FDA is testing out a whole new approach to clearing algorithms. The agency is experimenting with a system called precertification that puts more emphasis on examining the process that companies use to develop their products, and less emphasis on examining each new tweak. Continued monitoring is another element of this strategy.

“We’re going to take this concept and take it on a test run,” Patel says.

Because many algorithms will likely be in a state of continual evolution, “it’s really important when a system is deployed in the real world that we monitor those systems to make sure that they’re performing the way we expect,” says Christina Silcox, a researcher at the Duke-Margolis Center for Health Policy.

She’s enthusiastic about the prospects of AI in medicine, while alert to some of the challenges the FDA will face.

“Right now we might see an update to a medical deviceevery 18 months,” she says. “In software you might expect to see one every two weeks or every month.”

Seemingly minor software glitches can occasionally have serious unintended consequences. One of the worst cases involved a radiation therapy machine that, in the 1980s, gave huge overdoses of radiation to some patients because of a software bug.

Researchers looking at more recent incidents identified 627 software recalls by the FDA from 2011 through 2015. Those included 12 “high risk” devices such as ventilators and a defibrillator.

Patel certainly doesn’t want to see a high-profile failure, because that could set back a promising and rapidly growing industry.

One challenge that’s beyond the FDA’s scope is figuring out how to resolve conflicting conclusions from rival devices. Genetic tests that are used to guide cancer treatment, for example, already provide conflicting treatment recommendations, says Isaac Kohane, a pediatrician who heads the biomedical informatics department at Harvard Medical School. “Guess what,” he says, “The same thing is going to happen with these AI programs.”

“We’re going to have built-in disagreements and no doctor and no patient will know what is right,” he says.

Indeed, IDx isn’t the only company that interested in using an algorithm to identify early signs of diabetic retinopathy. Among its competitors is Verily, one of Google’s sister companies, which is currently deploying its technology in India. (Google is among NPR’s financial supporters).

“Actually I’m quite bullish in the long term,” Kohane says, as he looks out on the burgeoning field of AI. “In the short term, it’s a wild land grab.”

He says we need the equivalent of Consumer Reports in this area to help resolve these disagreements and identify superior technologies. He would also like reviews to examine not simply whether a technology performs as expected, but if it’s an improvement for patients. “What you really want is to get healthy,” he says.

The cost of the camera and set-up for the IDx-DR systems is around $20,000, a company spokesperson said in an email. There are options to rent or lease-to-own the camera that can reduce the upfront costs.

The list price for each exam is $34, the spokesperson said. But it varies depending on factors including patient volume.

A technically accurate piece of software doesn’t automatically lead to better health.

At the diabetes clinic in New Orleans, for example, the system replaced a service that also checked for another cause of blindness, glaucoma.

Nurse practitioner Brown visually scans Wells’ images for signs of glaucoma, but that wouldn’t happen when the work is handed off to someone who lacks her expertise. Instead, the diabetes clinic staff will refer patients to get another appointment for that test.

Wells also got something that future patients might not – a review of her retina images, so she could see for herself any suspected issues. That interaction with a health care professional was also an important moment to talk about her diet and what she can do to stay healthy.

Chevelle Parker, another nurse practitioner, points to some silvery lines inside the eye’s blood vessels.

“That happens when your sugar levels are high,” Parker explains. “It can also be an indication of diabetic retinopathy. So we’re going to do a referral and send you on for complete testing.”

The software did its intended job. While Wells seemed a bit upset by the news, at least she has found out about this concern early, while there’s still time to protect her vision.

The post How Can We Be Sure Artificial Intelligence Is Safe For Medical Use? appeared first on Artificial Intelligence.

Artificial intelligence is coming to healthcare. In fact, in areas such as radiology and cancer detection, it’s already here in places, and is poised to become ever more prevalent in the industry. Which naturally raises a question for nurses and physicians: Is AI coming for my job?

Well, probably not. At least according to experts we interviewed for our Focus on Artificial Intelligence.

That said, both AI and machine learning are in a prime position to alter clinical workflows and physician training. And with the market growing the way it is, implementation is inevitable. A recent Accenture report estimated that the AI health market will hit $6.6 billion by 2021. That’s up from $600 million in 2014.

Artificial intelligence and machine learning algorithms tend to rely on large quantities of data to be effective, and that data needs human hands to collect it and human eyes to analyze it. And since AI in healthcare is currently utilized mainly to aggregate and organize data — looking for trends and patterns and making recommendations — a human component is very much needed.

So physicians and nurses don’t have to worry. Probably. At least for now.

WHAT THE EXPERTS THINK

PeriGen CEO Matthew Sappern puts no stock in the theory that clinicians’ jobs are in jeopardy. Instead, he looks at AI more as an empowerment tool.

“I think it does things that are really imperative that are not necessarily what nurses can do,” he said. “These tools are not so great where reasoning and empathy are required. You teach them to do something, and they will do it over and over and over again, period. They’re good tools to provide perspective, but it’s all about the provider or nurse who’s making sense of that information.”

In many ways, said Sappern, AI can help nurses focus more on the actual job of nursing, and focus more on the abstract things that can truly impact patient care. And it has the potential to increase their confidence, as they can report back to the doctor with hard stats instead of vagaries. Used wisely and it can be a boon to fact-based clinical observation.

Jvion Chief Product Officer Dr. John Showalter was equally dismissive of claims that jobs are in jeopardy. The hype is scary, he said. The reality is not.

“There are great benefits that do amazing things for patients,” said Showalter. “When you come in and improve the scoring for falls, for example, and you understand what needs to be done to prevent falls, that’s ready for prime time today.

“There absolutely places where AI is ready to go today, and then there’s a whole bunch of AI hype that’s really scary, so sorting out the AI that’s ready to help patients and the hype can be really difficult for leadership.

Sappern and Showalter’s opinions mirror the conclusions of an article appearing this year in The Conversation analyzing the potential effect of AI, or lack thereof, on high-skilled jobs.

USING AI AS A TOOL

In the analysis the author notes that innovations in various industrial revolutions have always created new jobs even as they’ve taken old jobs away; what makes the AI revolution different is that it has the potential to affect white-collar jobs.

No need for alarms to go off, though, at least not initially, since AI in healthcare would primarily affect lower-skilled office work, like data processing. Though highly trained professionals could also be affected, the switch so far seems to be happening in a way that shows AI to be a tool more so than a threat, as professionals can now learn how to benefit from its powerful predictive powers.

In some cases, the technology could be used to help fill the physician shortage that is even now gripping many parts of the country, and is expected to get worse.

Eldon Richards, chief technology officer at Recondo Technologies, said AI is now addressing a lot of repetitive tasks that a human might do today.

“If reviewing the ethics of a decision, or complex data or one-off decision, AI is not good at those today,” said Richards. “Ai is very far off when it comes to those capabilities. The mundane, routine things we do, like typing in a word processor, AI us simplifying those things for us, so now we’re shifting our focus from these simple tasks to things that require a little more training. I certainly do not see unemployment going up.”

That sentiment is echoed by Mary Sun, AI researcher at First Derm and medical student at Mount Sinai Medical Center.

“People see it as a job replacement thing and I think that’s a pretty flawed way to look at it,” she said. “In many other industries, like when I was in commercial tech, it’s viewed much more as an augmentation, and piece of mind, and double checking and making sure that you’re involving patterns that one doctor cannot possibly see.

“As one doctor, you can’t possibly see a million patients across your lifetime. But medicine, at least diagnosis, is all in the pattern recognition. So I think it’s going to be very exciting when we find ways to augment our diagnoses and make them a lot more robust.”

Carlo Perez, CEO of Swift Medical, feels similarly, viewing AI as augmentative tool. While it may alter the role of a doctor somewhat, it won’t replace them entirely.

“What we feel is the doctor will transition into someone who understands how to wield data science, who understands how to use these tools,” said Perez. “Hopefully someone will not need to truly understand AI, but will understand their relationship to it. Which is, ‘I can utilize these tools, I understand these tools, and I understand how to utilize them in partnership to make better decisions.'”

The post Why artificial intelligence won’t replace doctors appeared first on Artificial Intelligence.