Drones for Health Care

Gadfin, or “wings” in Aramaic—

Its flagship aircraft hovers like a UAV and folds out wings to fly like a plane—is hoping to connect Israeli hospitals with drone supply networks and has its sights set on providing essential services in remote Third World locations.

Israel’s Gadfin UAVs (Unmanned Aerial Vehicle) and drone producer was the first company in the world to receive the Israeli Civil Aviation Authority permit for urban airspace deliveries this year. That permit means that Gadfin can compete for tenders that provide a glimpse into the near future. Under this vision, hospitals, laboratories, and a range of organizations will send and receive supplies via drone transport networks, skipping over-congested roads and reducing risk to sensitive, refrigerated packages.

Gadfin holds several breakthrough patents, including for a first of its kind drone called “Spirit One” that folds out its wings in-flight. It can take packages weighing up to 15 kilograms across more than 250 kilometers. The aircraft are operated autonomously with almost no human intervention.

The company is also designing a larger version of “Spirit One,” called “Spirit X,” which can take 100-kilogram packages across 500 kilometers.

Spirit One

The use of drones requires electrification of it's engine(s) and the use of GPS, possibly 5G and integration of air traffic control systems for optimization and safety concerns.  Modern air control systems will have to adapt to new flight modes.

Gadfin CEO Eyal Regev states,

“When we look at the world, we see that most areas are in the periphery. Most peripheral areas are very much lacking the services that city centers enjoy. It’s true for Southeast Asia, it’s true for Africa, it’s true for South America, but also for the West. This applies to many services. Medical tests, for example, have short lifespans and need to reach destinations quickly,” he explained.

“We hope that within two years, we can connect Israeli hospitals. This could speed up deliveries of sensitive medical supplies like bone marrow transplants. These are highly complex and expensive deliveries on land,” said Regev. “Instead of having doctors or nurses accompany the delivery to make sure the taxi doesn’t stop in the sun, our aircraft whisks them to the lab or hospital in minutes.”

Numerous health applications have become available. The Coronavirus pandemic has stimulated 'no contact' means of delivery of supplies.

UCSD hospital gets a drone delivery program powered by Matternet and UPS

UC San Diego Health. The California health system this month is launching a drug transport program in a collaboration with United Parcel Service to speed delivery of medical samples, supplies, and documents between its hospitals.

Several hospitals and health systems have created partnerships to use the flying robots to deliver medical supplies, samples and even organs between their facilities. Here are six that have launched programs or plan to: 

Rady Children's Hospital (San Diego). The Rady Children's Institute for Genomic Medicine has partnered with Deloitte to create a program that uses drones to deliver genomic testing specimens from the hospital to the lab.

WakeMed Health & Hospitals (Raleigh, N.C.) WakeMed partnered with Matternet, a California-based drone technology company, to carry blood and urine samples between its labs and clinics.

University of Utah Health (Salt Lake City). The hospital partnered with UPS to transfer medical samples and devices between facilities in its health system.

Kaiser Permanente (Oakland, Calif.) The health system said it will work with UPS to test how well drones can move medical supplies between its 39 hospitals. 

 University of Maryland Medical Center (Baltimore). The hospital was the first to use a drone to transport a donor kidney for transplantation surgery. 

Zipline’s drones are delivering medical supplies and PPE in North Carolina

The drones will fly on 20- to 30-mile round trips

TRANSPORTING ALMOST FOUR 

POUNDS OF CARGO AT UP TO 80 MPH

Although this is the US first for Zipline, this is not the first time the company’s drones have been used to deliver medical supplies globally. In 2016, the drone logistics company started delivering blood in Rwanda in what was, at the time, the first national drone delivery system. In 2019, it expanded operations to Ghana. In total, the company says its drones have flown over 1.8 million autonomous miles, and now, it’s using its drones to help respond to the COVID-19 pandemic in both countries.

The service has begun by delivering supplies to Novant Health’s Huntersville medical center from a depot next to its facility in Kannapolis, North Carolina. Once the drones reach their destination, they drop the supplies via parachute, meaning the center doesn’t need any additional infrastructure to receive deliveries. Zipline says its drones can carry almost four pounds of cargo and travel at speeds of up to 80 mph.

For now, Zipline has been given Federal Aviation Administration (FAA) approval for flights over two routes, with round trips of between 20 and 30 miles. However, the company’s drones have a total range of over 100 miles, meaning they’re capable of reaching 30 more Novant Health facilities, pending FAA approval. In the next two years, Novant and Zipline hope to get the FAA’s go-ahead to serve health facilities and even patients’ homes as part of a full commercial service.

Zipline Drone to Go

Delivery by parachute enables no contact delivery to a hospital landing zone.

The marketplace is expanding for drones in health care.  It is also apparent that the new niche will have many competitors looking for a business.

‘This is a revolution’: Israeli drone company plans for worldwide aerial-supply networks | JNS.org: 

Should Artificial Intelligence and Machine Learning be taught to medical students and physicians in CME as a requirement for licensure?

Credits:  Stan Benjamens, Pranavsingh Dhunnoo & Bertalan Meskó

Introduction

The 2010s have brought a rise in the number of studies and papers discussing the role of artificial intelligence (AI) and machine learning (ML) in medicine and healthcare (AI/ML). The number of life science papers describing AI/ML rose from 596 in 2010 to 12,422 in 2019. While we are at the beginning of the AI/ML era, the expectations are high and experts foresee that AI/ML shows potential for diagnosing, managing, and treating a wide variety of medical conditions1.

Indeed, AI/ML-based technologies have been shown to support several medical specialties from radiology2 and oncology3 to ophthalmology4 and general medical decision-making5. ML models have been shown to reduce waiting times6; improve medication adherence7; customize insulin dosages8; or help interpret magnetic resonance images9, among others. AI/ML- based technologies are coming to electronic health record systems and AI-based notifications and messaging systems.

We classify technology like AI/ML-based if official FDA announcements, communications by the company or other publicly available information resources used the expressions ‘deep learning,’ ‘machine learning,’ ‘deep neural networks,’ ‘artificial intelligence,’ and/or ‘AI’ to describe the technology11. For simplicity, we use the term “AI/ML-based” to denote these technologies in this paper. With the increasing expertise and attention on AI/ML in the medical field, the opportunities and possible implications of its use are the topics of an ongoing debate12. A crucial element in this implementation debate is regulating such technologies. Because of the high-risk nature of these medical devices and the unknown consequences of using AI/ML for medical decision-making and data analysis, the FDA has stringent regulatory requirements for medical device licensing. Developers of AI/ML-based medical devices and algorithms have to go through rigorous processes that are time and resource consuming. This can be considered pivotal as a barrier to the introduction of AI/ML in medicine. 

Some artificial intelligence platforms are 'locked'. They cannot be modified, once approved by the FDA. Those such as the Apple Smartwatch which essentially has it's AI built-in as firmware.  If any of the firmware is updated Apple would be required to file an exemption or file for a new 501K

Before medical hardware or software is legally made available in the US market, the parent company has to submit it to the FDA for evaluation. For medically oriented AI/ML-based algorithms, the regulatory body has three levels of clearance, namely, 510(k)14, premarket approval15, and the de novo pathway16, each of which needs specific criteria to be fulfilled in order to be granted (Table 1). This process is similar to drug approvals.  

Table 1 Descriptions of the types of FDA approvals for AI/ML-based medical technologies.

From: The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database

Level of FDA clearance Description

510(k) clearance A 510(k) clearance for an algorithm is granted when it has been shown to be at least as safe and effective as another similar, legally marketed algorithm. The submitter seeking this clearance must provide substantial proof of equivalence in their application. Without approval of being substantially equivalent to the other algorithm, the one pending approval cannot be legally marketed.

Premarket approval Premarket approval is issued to algorithms for Class III medical devices. The latter are those that can have a large impact on human health and as such, their evaluation undergoes more thorough scientific and regulatory processes to determine their safety and effectiveness. In order to approve an application, the FDA determines that the device’s safety and effectiveness are supported by satisfactory scientific evidence. Upon approval, the applicant can proceed with marketing the product. de novo pathway Regarding the de novo classification, it is used to classify those novel medical devices for which there are no legally marketed counterparts, but which offer adequate safety and effectiveness with general controls. The FDA performs a risk-based assessment of the device in question before approval and allowing the device to be marketed.

TABLE  Descriptions of the types of FDA approvals for AI/ML-based medical technologies. 

An infographic about the 29 FDA-approved, AI/ML-based medical technologies.

The two main medical specialties with AI/ML-based medical innovations are Radiology and Cardiology, with 21 (72.4%) and 4 (13.8%) FDA approved medical devices and algorithms respectively. 

The remaining medical devices and algorithms can be grouped as focusing on internal medicine/endocrinology, neurology, ophthalmology, emergency medicine, and oncology.

The medical field of radiology is the trendsetter regarding FDA-approved medical devices and algorithms, with the introduction of AI/ML-based solutions for worldwide applied image reading software. 

Examples are the three algorithms for Arterys Inc., Arterys Cardio DL, Arterys Oncology DL, and Arterys MICA, which are connected to the workflow Picture Archiving and Communication Systems from main vendors as Siemens Healthineers AG (Germany) and GE Healthcare (USA)20. 

Six out of these 21 algorithms can be applied in the field of oncology, with three focusing on mammography analyses (ProFound™ AI Software V2.1, cmTriage, and TransparaTM) and three others on CT-based lesion detection (Arterys Oncology DL, Arterys MICA, and QuantX). 

This is followed by two algorithms focusing on brain image analyses, with innovations for stroke and hemorrhage detection (ContaCT, Accipiolx, and Echobrain), and six algorithms to improve image processing, with noise and radiation dosage reduction (SubtlePET, Deep Learning Image Reconstruction, Advanced Intelligent Clear-IQ Engine, SubtleMR, AI-Rad Companion (Pulmonary) and AI-Rad Companion (Cardiovascular)). Another four algorithms focusing on acute care, with two algorithms for the assessment of pneumothorax (HealthPNX and Critical Care Suite), 

One focusing on wrist fracture diagnosis (OsteoDetect) and the Aidoc Medical BriefCase system for triage of head, spine, and chest injuries. The final two algorithms in this specialty can be applied for cardiovascular assessments, focusing on the assessment of the heart ejection fraction (EchoMD AEF Software and EchoGo Core).

During the past decade, the use of AI/ML-based medical innovations has become ubiquitous driven by specialty needs in the clinical process from diagnosis to remote monitoring and treatment.  Despite FDA approvals, end-users such as physicians, nurse practitioners must have the final word. Algorithms are continuously updated, and the FDA uses a "locked" or "adaptive" classification in order to monitor algorithms that 'learn' and change with time and use.

The authors clearly state the limitations for the FDA to accomplish this process, explaining that other organizations assess the accuracy of AI/ML-based devices.

eMurmer ID, CSD Labs GmbH), Apple Inc, being the ECG App and Apple Irregular Rhythm Notification Feature, Excel Medical Electronics, Spry Health, and Current Health, Stratoscientific, Inc. introduced the Steth IO device to analyze heart and lung sounds. BrainScope Company Inc. has introduced AI/ML for the evaluation of brain injuries. MindMotion GO (MindMaze SA), (Cantab Mobile, Cambridge Cognition Ltd), and seizure monitoring (Embrace, Empatica Srl.). 

QbCheck (QbTech AB) and ReSET-O (Pear Therapeutics Inc.). With QbCheck, healthcare workers can substantiate their diagnosis or rule out attention deficit hyperactivity disorder (ADHD), enhancing objective medical decisions in psychiatry29, whereas ReSET-O can be applied for patients with Opioid Use Disorder, providing cognitive behavioral therapy as a mobile medical application for prescription use only. As a next step, the ReSET-O algorithm will be used in a randomized controlled trial, which is scheduled to start this year (April 2020)30.

The FDA has a clinical trial protocol for drugs, which may also be applied to devices and AI/ML-based devices and software.

A challenge has developed for the FDAs search algorithm, which itself will require an AI/ML-based search-based method beyond its current version.

Users of AI/ML-based software need (CME) Continuing Medical Education in each specialty.

The ACMGE as the accrediting body for medical education should supervise this as a requirement for the training of physicians

Reference source:

The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database | npj Digital Medicine

Preparing AI-Powered Virtual Assistants to Improve EHR Usability

Natural Language Processing  (NLP) has been around for many years. It began with dictation, using speech to text applications for transcription in a well known 'Dragon Naturally Speaking'  for attorneys, and physicians dictating letters.  The engines for this application were much simpler than today's versions now on the market. 

It has taken many years to mature from developers to the market place.  NLP is now in the consumer marketplace, offered by Google and Amazon.  Their speech engine an AI and machine learning algorithm support many other devices licensed by the patent holders to add functionality to their own products.  The demand for this application has stimulated demand for smart speakers, and distributed voice commands for security systems, control devices, and also the (IoT),  Internet of all Things. It is a self-sustaining and economic return on investment.

It may be the saving grace for the shortcoming of data entry into electronic health records. If properly designed it could alter the physician's perception of electronic health records.  EHR is listed as a major cause of physician burnout and early retirement.  It eliminates many keystrokes, and point and click operations that slow down data entry.

It has taken a long time to gain entry into the medical system.  Vendors have been distracted by federal regulations regarding meaningful use and data collection. They were required to obtain certification regarding meaningful use to be able to bill Medicare for services. While it may have improved the 'back end", invisible to users it distracted from the User Interface (UX).

In our opinion, HHS, and CMS should require this in EHR to become a certified vendor. What is my reasoning?


Vanderbilt University Medical Center is exploring the potential for Epic EHR-integrated virtual assistants to boost EHR usability.

Problems with EHR usability continue to counter the potential benefits of EHR systems and leave physicians, nurses, administrators, and patients by and large feeling dissatisfied and frustrated with the technology.

While patient EHRs contain a wealth of potentially actionable clinical information providers and researchers can use to improve clinical decision-making, care delivery, and patient health outcomes, the administrative burden associated with documenting and retrieving health data still weighs heavily on providers.

EHR-integrated, voice-activated virtual assistants powered by artificial intelligence (AI) may help to resolve some of the industry’s longstanding problems with EHR usability. Virtual assistants enable providers to dictate physician notes, request specific data, order prescriptions and view lab results without touching their keyboards.

But is the technology effective, or will it only cause more frustration for providers? That’s the question providers at Vanderbilt University Medical Center (VUMC) hope to answer.

VUMC Assistant Professor of Biomedical Informatics Yaa Kumah-Crystal, MD, is currently working with Nuance to develop an EHR-integrated virtual assistant capable of summarizing patient health information and dictating that information to providers in response to verbal queries.  Kumah-Crystal uses a prototype of the Nuance virtual assistant integrated into VUMC’s Epic EHR system.

“I've been testing it, and I actually use it on a regular basis to review some of the content in the patient's chart before I walk into the room to see them,” Kumah-Crystal told EHRIntelligence.com. “We have another provider who's testing it as well, and in the next month, we're going to be doing some studies with the rest of our clinicians.”

While new and emerging virtual assistants will be used to complete a variety of tasks within provider EHR systems, VUMC is testing a product primarily designed to ease patient management and health data access for providers.

“The main purpose of the voice assistant is to help summarize the information that's hard to get out of the EHR,” Kumah-Crystal explained. “We’re going to have providers there with the scheduled patients that they're going to see within the next week. We’re going to review the patient's information in the chart.”

VUMC providers who participate in upcoming studies exploring the efficiency of voice recognition software and virtual assistants will use Nuance technology to find information about patient’s vital signs, medication lists, problem lists, and general health status. Kumah-Crystal and her team will then compare the individual provider’s experience using virtual assistants with each provider’s experience retrieving information manually. The VUMC team will do a timed task analysis to determine whether providers are able to access and review health data more quickly using either method. 

A new report from AMA, Pew Charitable Trusts, and MedStar Health outline recommendations on how stakeholders can improve EHR usability and safety throughout the entire EHR life cycle, as well as criteria for rigorous safety tests.

How Front-End Speech Recognition Adoption Impacts EHR Usability

Epic Clinical Documentation Module Utilizes AI Solution

Will Specializing EHR Interfaces Solve the  

Preparing AI-Powered Virtual Voice recognition software and virtual assistants may help to boost EHR usability. 

Nothing is foolproof. Adding another interface can increase errors.   A 2018 JAMA study found clinical documentation generated through voice recognition software is often error-prone, with physician notes generated through Dragon Medical and Nuance’s eScription showing a 7.4 percent error rate. Clinician review can help to reduce dictation errors and boost the accuracy of voice recognition-generated notes.

VUMC is currently in the process of building a use case for utilizing virtual assistants to prep providers for patient visits.

“You're gathering information to build a picture in your mind about who the patient is and what the next steps and their care will be,” said Kumah-Crystal.

The tool could be especially effective for prepping providers during their morning commutes. Kumah-Crystal hopes to further develop commute summaries through virtual assistants after getting more active participation with the existing workflow.

“The concept of a commute summary where you know that you have a schedule of 10 patients for the day, you have a 30-minute commute to work, and you can say, ‘Tell me about my patients,’ or, ‘What's today look like?’” said Kumah-Crystal. “And then it summarized for you just patients on your list while you're on your commute.”

“It saves me time as a physician, and I'm oriented by the time I walk in,” she added.

While concepts like the commute summary hold potential, Kumah-Crystal recognizes that some providers will be hesitant to integrate virtual assistants and voice recognition software into their workflows.

“They're right to be reluctant to completely adopt something that's not tried and true and tested,” she said. “And that's exactly what we're doing.”

Physicians, like engineers, solve challenges 'one step at a time' Each step depends upon the accuracy and reliability of the preceding steps

University of Utah pays $457,000 to ransomware gang | ZDNet

ARE YOU PREPARED?

9 A.M Monday, and you have reported to work. At your desk you enter your password expecting to start the week's work. You may be an appointment clerk or a back offfice nurse.

The physician is not at the office as yet.  He is unaware of the pending disaster and interruption to patient care.

You enter your password and 'enter'. The screen hesitates a bit longer and a screen pops up. You are a bit disoriented since it is Monday morning and you have never seen this screen before.

It may be any one of these screenshots, taken from real victims of this nefarious scheme of cybercriminals. They have a variety of names, and all are known as Ransomware.

Different Types of Ransomware

CryptoLocker

CryptoLocker botnet is one of the oldest forms of cyberattacks that have been around for the past two decades. The CryptoLocker ransomware came into existence in 2013 when hackers used the original CryptoLocker botnet approach in ransomware.  CryptoLocker is the most destructive form of ransomware since it uses strong encryption algorithms. It is often impossible to decrypt (restore) the Crypto ransomware-infected computer and files without paying the ransom.



WannaCry

WannaCry is the most widely known ransomware variant across the globe. The WannaCry has infected nearly 125,000 organizations in over 150 countries. Some of the alternative names given to the WannaCry ransomware are WCry or WanaCrypt0r.

Bad Rabbit

Bad Rabbit is another strain of Ransomware which has infected organizations across Russia and Eastern Europe. It usually spreads through a fake Adobe Flash update on compromised websites.

Cerber

Cerber is another ransomware variant that targets cloud-based Office 365 users. Millions of Office 365 users have fallen prey to an elaborate phishing campaign carried out by the Cerber ransomware.

Crysis

Crysis is a special type of ransomware that encrypts files on fixed drives, removable drives, and network drives. It spreads through malicious email attachments with double-file extension. It uses strong encryption algorithms making it difficult to decrypt within a fair amount of time.

CryptoWall

CryptoWall is an advanced form of CryptoLocker ransomware. It came into existence since early 2014 after the downfall of the original CryptoLocker variant. Today, there are multiple variants of CryptoWall in existence. It includes CryptoDefense, CryptoBit, CryptoWall 2.0, and CryptoWall 3.0.

GoldenEye

GoldenEye is similar to the infamous Petya ransomware. It spreads through a massive social engineering campaign that targets human resources departments. When a user downloads a GoldenEye-infected file, it silently launches a macro which encrypts files on the victim's computer.



Jigsaw

Jigsaw is one of the most destructive types of ransomware which encrypts and progressively deletes the encrypted files until a ransom is paid. It starts deleting the files one after the other on an hourly basis until the 72-hour mark- when all the remaining files are deleted.

Locky

Locky is another ransomware variant that is designed to lock the victim's computer and prevent them from using it until a ransom is paid. It usually spread through a seemingly benign email message disguised as an invoice.

When a user opens the email attachment, the invoice gets deleted automatically, and the victim is directed to enable macros to read the document. When the victim enables macros, Locky begins encrypting multiple file types using AES encryption.

Apart from the list of attacks mentioned above, Petya, NotPetya, TeslaCrypt, TorrentLocker, ZCryptor, etc., are some of the other ransomware variants that are well-known for their malicious activities. Some of these ransomware malware are focused on gaming sites, not on healthcare centers.  TeslaCrypt is now defunct

Fortunately, a whole new industry devoted to recovering encrypted data from ransomware has evolved. The Federal Bureau of Investigation now has a cybersecurity division led by ex-hackers, and who cooperate for a plea bargain. 

 The effect is that.you computer has been encrypted and the demand for payment includes a deadline after which your data will be permanently deleted.  This allows you time to make a.decision to comply and pay.  The amount demanded is considerable and depends upon the organization that has been attacked.

Now that we have introduced you to the worst day of your work life you will need a process ready in place. That at least will give focus on the next steps.

1. You should already have a crypto-insurance policy.  They are available and worth the expense.  Attacks are not rare anymore.  In fact, ransomware has evolved. Many of the original ransomware (WannaCry) is passe, having been used enough that cybersecurity experts have decoded them.  Payments are usually demanded in some form of cryptocurrency which cannot be traced.

The 10 Best Cyber Insurance Providers for 2020

No need to list them here, just go to the link

We have all read about ransomware intrusions into large enterprise systems: The financial reward is much greater since enterprise systems will more likely pay the ransom, in lieu of decrypting their databases which can be very large. 











The University of Utah pays $457,000 to ransomware gang | ZDNet