healthcare technology

Google's AI-powered tool that will be available later this year helps anyone identify skin conditions using their phone’s camera.

Artificial intelligence (AI) has the potential to help clinicians care for patients and treat disease — from improving the screening process for breast cancer to helping detect tuberculosis more efficiently.

When we combine these advances in AI with other technologies, like smartphone cameras, we can unlock new ways for people to stay better informed about their health, too.  

Google's AI-powered dermatology assist tool is a web-based application that they hope to launch as a pilot later this year, to make it easier to figure out what might be going on with their skin.

Once the user launchs the tool, simply use their phone’s camera to take three images of the skin, hair or nail concern from different angles. They are  then  asked questions about their skin type, how long they’ve had the issue and other symptoms that help the tool narrow down the possibilities. The AI model analyzes this information and draws from its knowledge of 288 conditions to give the user a list of possible matching conditions that they can then research further.

For each matching condition, the tool will show dermatologist-reviewed information and answers to commonly asked questions, along with similar matching images from the web.

The tool is not intended to provide a diagnosis nor be a substitute for medical advice as many conditions require clinician review, in-person examination, or additional testing like a biopsy. Rather Google hopes it gives users access to authoritative information so they can make a more informed decision about their next step.

Developing an AI model that assesses issues for all skin types 

Google's tool is the culmination of over three years of machine learning research and product development. To date, Google has published several peer-reviewed papers that validate their AI model and they claim more are in the works. 

Recently, the AI model that powers the tool successfully passed clinical validation, and the tool has been CE marked as a Class I medical device in the EU.

more at https://blog.google/technology/health/ai-dermatology-preview-io-2021/

Scientists have fabricated a device that can mimic human brain cognitive actions and is more efficient than conventional techniques in emulating artificial intelligence, thus enhancing the computational speed and power consumption efficiency.

Artificial intelligence is now a part of our daily lives, starting from email filters and smart replies in communication to helping battle the Covid-19 pandemic. But AI can do much more such as facilitate self-driving autonomous vehicles, augmented reality for healthcare, drug discovery, big data handling, real-time pattern/image recognition, solving real-world problems, and so on.

These can be realised with the help of a neuromorphic device which can mimic the human brain synapse to bring about brain-inspired efficient computing ability. The human brain comprises of nearly a hundred billion neurons consisting of axons and dendrites. These neurons massively interconnect with each other via axons and dendrites, forming colossal junctions called synapse.

This complex bio-neural network is believed to give rise to superior cognitive abilities.

Software-based artificial neural networks (ANN) can be seen defeating humans in games or helping handle the Covid-19 situation. However, the power-hungry (in megawatts) von Neumann computer architecture slows down ANNs performance due to the available serial processing while the brain does the job via parallel processing consuming just 20 W. It is estimated that the brain consumes 20% of the total body energy. From the calory conversion, it amounts to 20 watts. While the conventional computing platforms consume megawatts, i.e., 1 million watts of energy, to mimic basic human cognition.

To overcome this bottleneck, a hardware-based solution involves an artificial synaptic device that, unlike transistors, could emulate the functions of human brain synapse. Scientists had long been trying to develop a synaptic device that can mimic complex psychological behaviors without the aid of external supporting (CMOS) circuits.

To address this challenge, Scientists from Jawaharlal Nehru Centre for Advanced Scientific Research, Bengaluru, an autonomous institute of the Department of Science & Technology, Government of India, devised a novel approach of fabricating an artificial synaptic network (ASN) resembling the biological neural network via a simple self-forming method (the device structure is formed by itself while heating). This work has been recently published in the journal ‘Materials Horizons’.

“Nature has had an incredible amount of time and diversity to engineer ever new forms and functions through evolution. Learning and emulating new processes, technologies, materials and devices from the nature and biology are the important pathways to the significant advances of the future which will increasingly integrate the worlds of the living with the man-made technologies,” said Prof Ashutosh Sharma, Secretary, DST.

read the original unedited post at https://www.indianext.co.in/2021/06/scientists-develop-efficient-artificial-synaptic-network-that-mimics-human-brain/

If there’s one dialogue that’s been growing louder across the healthcare landscape, it’s the consumerization of healthcare. Market trends are undeniably steering the healthcare experience into a new paradigm where patients are seizing control. Yet this new direction is not always beneficial for patients or providers.

Just as consumer-driven industries like Uber and Netflix offer quick and seamless digital transactions, many patients want greater convenience and speed from care delivery. Many are also seeking more cost-effective options, thanks to climbing medical debt and high-deductible insurance plans. They’re less willing to tolerate care delays and inefficiencies; many will leave a poor online review after a frustrating appointment.

These are all understandable goals and reactions. But as patients climb into the driver’s seat of healthcare, they’re not always given a roadmap to their intended destination. As they navigate their options, some are running up against four dynamics:

1. Dr. Google

In our fast-paced world, many patients don’t want to wait weeks for an appointment or take time off from work to bring their child to the pediatrician.

Instead they take out their smartphone and look up symptoms to get a quick and theoretical diagnosis. Patients can view photographs of lesions, read checklists of cancer symptoms and lurk on forums where people describe surgery experiences – and encourage each other to self-diagnose.

2. Retail Clinics

Retail clinics like CVS and Walgreens have exploded in popularity – and the market is expected to surpass $8 billion USD by 2028. Patients who feel they’re too busy or too peripatetic to maintain a consistent PCP relationship often prefer the extended hours and easy access of these clinics.

3. Cost Avoidance

Patients are paying higher and higher coinsurances, deductibles and copays – and they’re sick of it.

They’re annoyed by a hospital’s inability to give them an accurate procedure cost in advance; many are stuck with “surprise” invoices after checking into a network hospital and receiving care from an out-of-network doctor.

4. Application Chaos

As applications and portals take over the Internet, many healthcare systems have turned a great idea into patient confusion.

Even patients with moderate care needs may find themselves managing an overwhelming collection of healthcare apps for their OB/GYN practice, dentist, dermatologist, PCP, various hospital online payment portals, lab result repositories and data from their wearables.

A Recent Harris Poll Survey on behalf of NextGen Healthcare Confirms Patients Seek the Convenience of Self Service and Option to See Providers Virtually

The survey was conducted online and the results are based on the inputs gathered from 2,000 U.S. adults, including 1,733 who typically see a healthcare provider annually (“patients”).

The survey results generated insights into patient experiences and preferences related to online healthcare tools.

Telehealth is here to stay.

• 84 % of U.S. patients who received telehealth services since March 2020 plan to continue using telehealth appointments in the future citing reasons such as
  • convenience (43 %)
  • or to avoid being around people who are ill (39 %).

• More than half of U.S. patients (57 %) say they would be more likely to get follow-up medical care if telehealth appointments were an option.
• 48 % patients indicate they would switch to a different healthcare provider if their current provider did not offer telehealth appointments.WOW!
• 69 % patients have seen a healthcare provider via telehealth since the COVID-19 pandemic began,
  • 46 % -  primary care physician (PCP) 
  • 19 % - mental healthcare provider.
  • 15% - women’s health provider
  • 9% ophthalmologist
  • 7% orthopedist

Online access is a must.

58 percent patients would like to have more online access to their healthcare provider. Age plays a role in this: Patients from 18-54 are significantly more likely than patients 55 and older to say they would like to have more online access to their healthcare provider (68 percent vs. 43 percent). Topping the list of most important online services patients would look for if seeking a new provider are:

• online appointment scheduling (49 percent)
• ability to check-in or complete health forms/appointment paperwork online before an appointment (49 percent)
• online prescription management (48 percent)
• online medical records access (47 percent)

John Beck, chief solutions officer for NextGen Healthcare says in the release -  “These survey results confirmed that patients’ overall expectations for healthcare have shifted permanently. Integrated healthcare technology is good for the patient and good for the practice.”

read the original release at https://www.businesswire.com/news/home/20210520005327/en/National-Survey-Shows-Online-Access-and-Telehealth-are-Keys-to-Patient-Loyalty

Improving the management of unstructured content is crucial when it comes to creating successful healthcare platforms.

Clinicians can build better pictures of their patients when they use healthcare platforms which harness unstructured content, as well as structured content, to create a single source of clinical information.

Analysts estimate that as much as 80 per cent of patient information is currently unstructured and is not contained in Electronic Health Records (EHRs). This means that vital clinical information, such as paper records or medical imaging, which does not tick specific boxes, can be overlooked.

to read more, visit https://www.healthcareitnews.com/news/apac/improving-healthcare-better-managing-unstructured-content

In the United States, on April 5, a federal rule went into effect that requires health care providers to give patients electronic access to their health information without delay upon request, at no cost.

Many patients may now find their doctors’ clinical notes, test results and other medical data posted to their electronic portal as soon as they are available.

Advocates herald the rule as a long-awaited opportunity for patients to control their data and health.

But the rollout of the rule has hit bumps, as doctors learn that patients might see information before they do.

Patients have long had a legal right to their medical records but often have had to pay fees, wait weeks or sift through reams of paper to see them.

“This levels the playing field, A decade ago, the medical record belonged to the physician.” as per  Jan Walker, co-founder of OpenNotes“

Privacy rules under the Health Insurance Portability and Accountability Act, which limit sharing of personal health information outside a clinic, remain in place, although privacy advocates have warned that patients who choose to share their data with consumer apps will put their data at risk.

Studies have shown numerous benefits of note sharing. Patients who read their notes understand more about their health, better remember their treatment plan and are more likely to stick to their medication regimen. Non-white, older or less educated patients report even greater benefits than others.

read the original unedited story at https://www.kevinmd.com/blog/2021/05/doctors-now-must-provide-patients-their-health-data-online-and-on-demand.html

Antibiotic resistance is a significant public health challenge, caused by changes in bacterial cells that allow them to survive drugs that are designed to kill them. Resistance often occurs through new mutations in bacteria that arise during the treatment of an infection. Understanding how this resistance emerges and spreads through bacterial populations is important to preventing treatment failure.

Scientists have developed a mathematical model that predicts how the number and effects of bacterial mutations leading to drug resistance will influence the success of antibiotic treatments.

Their model, described in the journal eLife, provides new insights on the emergence of drug resistance in clinical settings and hints at how to design novel treatment strategies that help avoid this resistance occurring.

"Mathematical models are a crucial tool for exploring the outcome of drug treatment and assessing the risk of the evolution of antibiotic resistance," explains first author Claudia Igler, Postdoctoral Researcher at ETH Zurich, Switzerland. "These models usually consider a single mutation, which leads to full drug resistance, but multiple mutations that increase antibiotic resistance in bacteria can occur. So there are some mutations that lead to a high level of resistance individually, and some that provide a small level of resistance individually but can accumulate to provide high-level resistance."

"Our work provides a crucial step in understanding the emergence of antibiotic resistance in clinically relevant treatment settings," says senior author Roland Regoes, Group Leader at ETH Zurich. "Together, our findings highlight the importance of measuring the level of antibiotic resistance granted by single mutations to help inform effective antimicrobial treatment strategies."

read the study paper at https://elifesciences.org/articles/64116

read the original unedited article at https://phys.org/news/2021-05-mathematical-effect-bacterial-mutations-antibiotic.html

Data encoded on DNA could last 500 years! Check out a new DNA decoder that can read data at 330 gigabits per square centimeter

Years ago, the world marveled as it recognized that more human information was created on the internet than had been written in thousands of years of human history. But with the information age growing more complex by the day, we may have to look at new ways of storing information, and it turns out the DNA we're made of might hold the key to the ultimate organic hard drive.

A team of scientists has developed a new way of storing data, using pegs and pegboards composed of DNA, which can be retrieved via microscope, in a molecular variant of the traditional Lite-Brite, according to a recent study published in the journal Nature Communications.

The prototype can store information in DNA strands with a 10-nanometer space between them. This distance is less than one-thousandth of the diameter of a human hair, and roughly one-hundredth the size of a living bacterium.

The team tested a digital nucleic acid memory (dNAM) with the storage of a simple statement: "Data is in our DNA/n." Earlier attempts to retrieve data stored in DNA called for DNA sequencing, which involves reading the genetic code of DNA strands — which is a critical tool in biology and medicine, but not very efficient for DNA memory.

Data stored on DNA strands can last for 500 years

Using a microscope, the team imaged hundreds of thousands of DNA pegs in one recording, allowing for an error-correction algorithm to retrieve all data. Once all of the bits were organized via algorithms, the prototype DNA decoder could read data at 330 gigabits per square centimeter. While this technology likely won't show up in smartphones or laptops in the near future, DNA storage has incredible potential for archival use. In case you missed it, DNA evolved to store unconscionable amounts of data. If we knew how, our genes could store all of the emails, tweets, songs, photos, films, and books that ever existed in a DNA volume the size of a jewelry box.

read the original version of this interesting article at https://interestingengineering.com/dna-could-store-every-tweet-movie-book-and-more-in-a-jewelry-box-sized-device

What is photonics? In short, photonics is the scientific study and technological harnessing of light. 

However, it is important to note that the term "photonics" is something of a nebulous one. That being said, it is often used today to refer to a set of emerging technologies that deal with various aspects of light. These include technologies used to store, transfer, or manipulate information, but can also be used to include methods of harvesting energy from light and/or converting it to electricity. To put it another way, photonics, in the technological sense, refers to devices that use photons to send, receive, and process information similar to modern-day electronics. 

Today, one of the major applications of photonics, specifically integrated photonics, is in high-performance computing. Specific examples would be in the servers in large data server farms used by large tech companies like Google or Amazon.

Beyond computing, photonics has applications in many other fields from medical sciences to energy production. 

In medical sciences, for example, photonics is used in a variety of ways including in surgery (such as eye surgery), tattoo removal, and surgical endoscopy. In the future, optical integrated circuits may well lead to the development of smaller, more compact, biosensors and other implantable medical devices freed from the limitation of electronics. 

more at https://interestingengineering.com/photonics-a-story-of-our-quest-to-harness-the-power-of-light

Identifying new COVID-19 cases is challenging. Not every suspected case undergoes testing, because testing kits and other equipment are limited in many parts of the world. Yet populations increasingly use the internet to manage both home and work life during the pandemic, giving researchers mediated connections to millions of people sheltering in place.

Objective: The goal of this study was to assess the feasibility of using an online news platform to recruit volunteers willing to report COVID-19–like symptoms and behaviors.

Methods: An online epidemiologic survey captured COVID-19–related symptoms and behaviors from individuals recruited through banner ads offered through Microsoft News. Respondents indicated whether they were experiencing symptoms, whether they received COVID-19 testing, and whether they traveled outside of their local area.

Results: A total of 87,322 respondents completed the survey across a 3-week span at the end of April 2020, with 54.3% of the responses from the United States and 32.0% from Japan. Of the total respondents, 19,631 (22.3%) reported at least one symptom associated with COVID-19. Nearly two-fifths of these respondents (39.1%) reported more than one COVID-19–like symptom. Individuals who reported being tested for COVID-19 were significantly more likely to report symptoms (47.7% vs 21.5%; P<.001). Symptom reporting rates positively correlated with per capita COVID-19 testing rates (R2=0.26; P<.001). Respondents were geographically diverse, with all states and most ZIP Codes represented. More than half of the respondents from both countries were older than 50 years of age.

Conclusions: News platforms can be used to quickly recruit study participants, enabling collection of infectious disease symptoms at scale and with populations that are older than those found through social media platforms. Such platforms could enable epidemiologists and researchers to quickly assess trends in emerging infections potentially before at-risk populations present to clinics and hospitals for testing and/or treatment.

source: Credit to Regenstrief Institute

read the entire study here : https://www.jmir.org/2021/5/e24742

A team of researchers has developed the first human "mini-hearts" in the lab to have clearly beating chambers. The miniature organs, or organoids, are no bigger than sesame seeds and were generated by self-assembly using pluripotent stem cells, according to Science Magazine.

The organoids mimic the functioning heart of a 25-day-old human embryo, and they may help humans solve the heart's many mysteries.

Our capability to model the complexity of the human heart in vitro is still limited, consequently limiting our knowledge of how heart diseases develop.

Congenital heart defects, for example, are the most common birth condition in humans, affecting around 1 percent of all live births. This alone demonstrates the need to create more precise organ-like platforms, which is where the researchers come in, with their newly devised method which was described in a study published in the journal Cell.

The researchers engineered human pluripotent stem cells, which can divide into any kind of tissue, into multiple forms of cardiac cells to create heart organoids whose cells self-organize like those in an embryo. The aim was to create three tissue layers that make up a heart chamber's walls, which are one of the first parts of the heart to form.

The organoids, which are around 2 mm in diameter and have survived more than 3 months in the lab so far, become structurally equal to the heart of a 25-year-old embryo in a week. They only have one chamber and the main types of cells at this point of development. Moreover, the heart's clearly defined chamber beats 60 to 100 times a minute, much like the heart of an embryo at the same age.

read the entire story at https://interestingengineering.com/lab-grown-mini-heart-beats-like-a-25-day-old-human-embryos-heart

The linked interview gives us all in Healthcare Technology  a lot of food for thought. This below is a set of points extracted and massaged with my viewpoints

The biggest barrier to physicians having the most complete medical history for their patients at every point of patient care is the lack of interoperability among information systems.

State of Interoperability today:

The industry has made progress in developing open standards and application programming interfaces to facilitate data fluidity and sharing among multiple electronic health record systems and data repositories. As a result, commercial and open source interoperability services are coming online. While there is room for optimism, the industry is still grappling with data structure and management challenges

.

First, incomplete, disparate and disconnected data.

Most health and patient data is stored as unstructured medical format, and identifying information in the data is a manual and time-consuming process. There are significant variations in the way data is shared, read and understood across health systems, which can result in information being siloed and overlooked or misinterpreted

.

Further, most EHR systems do not follow patients on their care journey beyond the hospital or clinic walls. As a result, only a portion of healthcare data is available at any point of care, resulting in a fragmented view of a patient's health history.

Second, slow adoption and scaling of open interoperability standards.

Standards can streamline the structured data exchange needed to improve preventive and value-based care for people, predictions, diagnostics, post-marketing surveillance of medical products (for example drug, device), care quality, cost reduction and clinical research.

Industry guidelines and resources like the Fast Healthcare Interoperability Resources (FHIR) from Health Level Seven International (HL7) have helped to set a standard, though there is still more work to be done to support organizations to remove barriers toward adoption and make the electronic exchange of data more seamless, with the goal of providing a better provider and patient experience.

Third, risks due to siloed data:

When it comes to storing health information including clinical, genomic, device, financial, supply chain and claims, data security is the top priority. Storing patient data across different systems and platforms makes it difficult to deliver personalized care, draw data insights and streamline service.

This is a pivotal moment in time when healthcare can take what it's learned over the past year and fix the underlying problems.

Perhaps the most important learning is that achieving true healthcare interoperability requires understanding, evaluating and solving issues in the underlying syntactic and semantic characteristics of the data. 

Syntactic interoperability requires a common structure so that data can be exchanged and interpreted between health IT systems,

while semantic interoperability requires a common language so that the meaning of data is transferred along with the data itself. This combination supports data fluidity.

The industry has made meaningful progress on this front.

Unlocking Benefits of Interoperability

As technology creates more data across healthcare organizations, applying technologies like artificial intelligence and machine learning will be essential to help take that data and create the shared structure and meaning necessary to achieve interoperability.

Shared structure and meaning will enable interoperability solutions that transform data input from various media types and forms: voice, image, scan, PDF, etc., into a common text format which can be shared with and leveraged by every entity in the value chain.

Instead of moving static, electronic documents or faxes like care summaries between healthcare providers, clinical AI-service APIs can enable EHR vendors and health systems to communicate in a standardized way with apps and other EHRs.

With access to all available information, advanced analytics and machine learning can then enhance medical and scientific insights tied to patient outcomes in an accurate, scalable, secure and timely manner.

read more at https://www.healthcareitnews.com/news/amazon-web-services-exec-talks-interoperability-lessons-past-year