Evaluation of a Remote Diagnosis Imaging Model vs Dilated Eye Examination in Detecting Macular Degeneration | Diabetic Retinopathy |

ADVANCES IN MEDICINE

JUST WHAT THE DOCTOR ORDERED:
IMPROVING PATIENT CARE WITH AI

Artificial Intelligence is transforming the world of medicine. AI can help doctors make faster, more accurate diagnoses. It can predict the risk of a disease in time to prevent it. It can help researchers understand how genetic variations lead to disease.

Although AI has been around for decades, new advances have ignited a boom in deep learning. The AI technique powers self-driving cars, super-human image recognition, and life-changing—even life-saving—advances in medicine.

Deep learning helps researchers analyze medical data to treat diseases. It enhances doctors’ ability to analyze medical images. It’s advancing the future of personalized medicine. It even helps the blind “see.”

“Deep learning is revolutionizing a wide range of scientific fields,” said Jensen Huang, NVIDIA CEO and co-founder. “There could be no more important application of this new capability than improving patient care.”

Three trends drive the deep learning revolution: more powerful GPUs, sophisticated neural network algorithms modeled on the human brain, and access to the explosion of data from the internet (see “Accelerating AI with GPUs: A New Computing Model”)

Community Medicine is a term used to describe medical conditions in a large population setting. It often involves the screening of large groups to select those with disease and provide appropriate treatment to avoid further complications.  This involves an examination of large groups of patients. Often more than 100 persons will be examined with a positive finding of less than five in one hundred examinations.  This is a massive undertaking when screening perhaps as much as 1000 or more persons. It is often not cost effective. 

However, the development of image analysis, high-speed computing power, and deep learning machines can be trained to accomplish this task. Algorithms can be developed to digitize images (x-rays, CT scans, and photographs.




Artificial intelligence or machine learning is bringing a new powerful tool for rapid interpretation of medical images, such as chest x-rays, retinal fundus photography, and scans.  Images of the skin can be analyzed for suspicious moles to rule out malignant melanoma rapidly.   As the science matures there are sure to be significant cost savings as well as time. 

Machine learning is dependent upon large data stores, and accuracy improves as images are added and curated by human beings (physicians).  It is doubtful if AI will ever stand alone without human oversight.  

A study of retinal fundus evaluation (as reported JAMA) using machine learning showed
Remote diagnosis imaging and a standard examination by a retinal specialist appeared equivalent in identifying referable macular degeneration in patients with high disease prevalence; these results may assist in delivering timely treatment and seem to warrant future research into additional metrics.

The study has shown equivalency in diagnosing age-related macular degeneration using ocular coherence tomography. 

The use of deep learning has also been applied in dermatology to screen for malignant melanoma or other skin malignancy.

As radiology is inherently a data-driven specialty, it is especially conducive to utilizing data processing techniques. One such technique, deep learning (DL), has become a remarkably powerful tool for image processing in recent years. In this work, the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning provides an overview of DL for the radiologist. This article aims to present an overview of DL in a manner that is understandable to radiologists; to examine past, present, and future applications; as well as to evaluate how radiologists may benefit from this remarkable new tool. We describe several areas within radiology in which DL techniques are having the most significant impact: lesion or disease detection, classification, quantification, and segmentation. 





Some are concerned that AI, or deep learning may replace human radiologists, however, this is unlikely to occur.  But deep learning won’t be replacing radiologists anytime soon, Bratt explained, and one key reason for this is that deep neural networks (DNNs) are naturally limited by “the size and shape of the inputs they can accept.” But deep learning won’t be replacing radiologists anytime soon, Bratt explained, and one key reason for this is that deep neural networks (DNNs) are naturally limited by “the size and shape of the inputs they can accept.” A DNN can help with straightforward tasks reliant on a few images—bone age assessments, for instance, but they become less useful as the goal grows more and more complex. This limitation, Bratt explained, is related to the concept of long-term dependencies.  Another issue related to DNNs is how easily they can fall apart when introduced to small changes. A DNN can be working perfectly after being trained on one institution’s dataset, for instance, but its performance suffers when it is introduced to new data from a new institution.

“This again reflects the fact that ostensibly trivial, even imperceptible, changes in input can cause catastrophic failure of DNNs, which limits the viability of these models in real-world mission-critical settings such as clinical medicine,” Bratt wrote.

In addition to evaluating images, DNN can be applied to other tasks.

MINING MEDICAL DATA FOR BETTER, QUICKER TREATMENT

Medical records such as doctors' reports, test results and medical images are a gold mine of health information. Using GPU-accelerated deep learning to process and study a patient's condition over time and to compare one patient against a larger population could help doctors provide better treatments.

BETTER, FASTER DIAGNOSES


Medical images such as MRIs, CT scans, and X-rays are among the most important tools doctors use in diagnosing conditions ranging from spine injuries to heart disease to cancer. However, analyzing medical images can often be a difficult and time-consuming process.

Researchers and startups are using GPU-accelerated deep learning to automate analysis and increase the accuracy of diagnosticians:

Imperial College London researchers hope to provide automated, image-based assessments of traumatic brain injuries at speeds other systems can't match.
Behold.ai is a New York startup working to reduce the number of incorrect diagnoses by making it easier for healthcare practitioners to identify diseases from ordinary radiology image data.
Arterys, a San Francisco-based startup, provides technology to visualize and quantify heart flow in the body using an MRI machine. The goal is to help speed diagnosis.
San Francisco startup Enlitic analyzes medical images to identify tumors, nearly invisible fractures, and other medical conditions.

GENOMICS FOR PERSONALIZED MEDICINE

Genomics data is accumulating in unprecedented quantities, giving scientists the ability to study how genetic factors such as mutations lead to disease. Deep learning could one day lead to what’s known as personalized or “precision” medicine, with treatments tailored to a patient’s genomic makeup.

Although much of the research is still in its early stages, two promising projects are:

A University of Toronto team is advancing computational cancer research by developing a GPU-powered “genetic interpretation engine” that would more quickly identify cancer-causing mutations for individual patients.
Deep Genomics, a Toronto startup, is applying GPU-based deep learning to understand how genetic variations lead to disease, transforming personalized medicine and therapies.

DEEP LEARNING TO AID BLIND PEOPLE

Nearly 300 million people worldwide struggle to manage such tasks as crossing the road, reading a product label, or identifying a face because they’re blind or visually impaired. Deep learning is beginning to change that.

Horus Technology, the winner of NVIDIA’s first social innovation award at the 2016 Emerging Companies Summit, is developing a wearable device that uses deep learning, computer vision, and GPUs to understand the world and describe it to users.

One of the early testers wept after trying the headset-like device, recalled Saverio Murgia, Horus CEO, and co-founder. “When you see people get emotional about your product, you realize it’s going to change people’s lives.”

Further DNN utilizes optical diffractive circuits in lieu of electrons



The setup uses 3D-printed translucent sheets, each with thousands of raised pixels, which deflect light through each panel in order to perform set tasks. By the way, these tasks are performed without the use of any power, except for the input light beam.

The UCLA team's all-optical deep neural network – which looks like the guts of a solid gold car battery – literally operates at the speed of light and will find applications in image analysis, feature detection, and object classification. Researchers on the team also envisage possibilities for D2NN architectures performing specialized tasks in cameras. Perhaps your next DSLR might identify your subjects on the fly and post the tagged image to your Facebook timeline.  For now, though, this is a proof of concept, but it shines a light on some unique opportunities for the machine learning industry.










The winner of NVIDIA’s first social innovation award at the 2016 Emerging Companies Summit, is developing a wearable device that uses deep learning, computer vision, and GPUs to understand the world and describe it to users.

One of the early testers wept after trying the headset-like device, recalled Saverio Murgia, Horus CEO and co-founder. “When you see people get emotional about your product, you realize it’s going to change people’s lives.”


Evaluation of a Remote Diagnosis Imaging Model vs Dilated Eye Examination in Referable Macular Degeneration | Diabetic Retinopathy | JAMA Ophthalmology | JAMA Network: This study evaluates a retinal diagnostic device and compares its utility and outcomes with those of traditional eye examinations by retinal specialists for patients with potential retinal damage from diabetic retinopathy and age-related macular degeneration.

Helping Practices Thrive

Helping Practices Thrive

View Webinar . 

Join the leading experts in ACO policy for a discussion about the CMS Medicare Shared Savings Plan (MSSP) proposed rule.
We believe primary care doctors are the foundation of an efficient and effective health system.

In the Aledade model, primary care physicians are back where they should be: quarterbacking their patients’ health care – while maintaining the independence that makes their practices unique and trusted. The Aledade team strives every day to help doctors focus on what’s best for their patients- not paperwork and bureaucracy. Most importantly, we believe in a simple but radical idea that Aledade only succeeds when our partner practices succeed in delivering better care at a lower cost. Doctors are our true partners.

THE ALEDADE DIFFERENCE

ALEDADE INTRODUCTION

WHAT DOES VALUE BASED CARE MEAN TO YOU?

FOR HEALTH PLANS

Study: Most mental health apps give Facebook, Google access to personal info without users' knowledge

 Study: Most mental health apps give Facebook, Google access to personal info without users' knowledge

A new study published in JAMA Network Open found that a majority of mental health and wellness apps surveyed distribute users' personal data to commercial third parties like Facebook and Google without explicitly informing users.

Researchers from the University of New South Wales Sydney, the Sydney-based Black Dog Institute, and the Beth Israel Deaconess Medical Center's Department of Psychiatry in Boston examined 36 apps for depression and smoking cessation that was highest ranked in the iOS and Android app stores in early 2018. Results show that 33 of the programs transmitted user data to Facebook, Google or other entities for advertising or analytical purposes, but only 12 fully disclosed this practice to users.

Just 23 of the surveyed apps incorporated privacy policies mentioning that data would be transmitted to a third party, and many of those fail to explicitly describe how the data will be used, and by which third parties.

According to the study's authors, despite the mental health benefits of these and similar apps, the lack of disclosure "may limit their ability to offer effective guidance to consumers and health care professionals," who would likely prefer to know whether and how their personal health information is accessed by advertising and analytical firms.

Persons with mental health issues are extremely vulnerable to lack of privacy issues. While there are HIPAA protections as to de-identifying data the marketing of pharmaceutical information or devices to this group of vulnerable individuals deserves scrutiny. 

The non-disclosure of the use of data is highly irresponsible and deserves universal condemnation.

A quick Google search yields hundreds of apps for both iPhone and Android phones.

There are apps for depression, anxiety, meditation, and mindfulness, as well as cognitive behavioral therapy Virtual Reality applications, are being promoted and used by behavioral therapists. Most reviews are testimonials by persons using the smartphone app and not a professional evaluation.  Significant time has not elapsed for good peer-reviewed analysis.

Furthermore, self-diagnosis can be dangerous for some mental health disorders. A little knowledge can be a dangerous thing.  Prior to using any of the apps, one should consult with an experienced mental health provider who has experience using apps and/or virtual reality.

Several sources are referenced below:

The use of Virtual Reality for treatment of a mental disorder.  Much of these treatments could lead to worsening of some conditions such as hallucinations, and schizophrenia. The VR experience can be depersonalizing which could exacerbate other conditions. The outcome of a combination of psychotropics and VR is unknown.

Both practitioners and patients must be informed about these dangers. Manufacturers of the hardware devices and software should be required to provide this information to users.

The buyer should remember caveat emptor.

Study: Most mental health apps give Facebook, Google access to personal info without users' knowledge

FDA To End Program That Hid Millions Of Reports On Faulty Medical Devices |

Medical Device Fail

The entire video can be viewed on Netflix (subscription required)

All of us have read about safety and reliability issues of medical devices ranging from implantable mesh for pelvic support, pacemaker defects, and breast implants,

Silicone Breast Implant

Intravaginal Pelvic support Meshwork

In the wake of the KHN investigation, the agency will no longer let device makers file reports of harm outside a widely used public database.

Frequently these device failures do not become publicly known until a number of occurrences, which is brought to the attention of the FDA by users (surgeons, or medical professionals.) It often takes a number of providers to connect the dots.  In some cases such as academic institutions, or very large integrated health systems which have their own internal checks by surgical committees detects the device failure.

Investigation of metal deposition in organs after joint replacement

Some patients experienced serious neurologic problems, including memory loss, tremors, and even dementia. Patients with MOM hip replacements had Cobalt levels elevated in blood and urine. During replacement of the metal on a metal hip prosthesis, severe tissue damage was found, with Cobalt ions leached into the tissue causing necrosis and entering the circulatory system.  The question arises, is Cobalt poisoning be the next Mercury poisoning?

Failing metal hip implants could be releasing genotoxic material

In any case, the FDA has its own reporting mechanism FDA WATCH.  There is no online reporting form. Form FDA3500 (pdf)(form fill) can be downloaded by providers and consumers to report individual incidents

The KHN report exposes a redundant, confusing and largely unknown file of device incidents. The situation was so confusing that even a former FDA Commissioner was unaware of the database.

The FDA has built and expanded a vast and hidden repository of reports on device-related injuries and malfunctions, a Kaiser Health News investigation shows. Since 2016, at least 1.1 million incidents have flowed into the internal “alternative summary reporting” repository, instead of being described individually in the widely scrutinized public database known as MAUDE, which medical experts trust to identify problems that could put patients in jeopardy.

Deaths must still be reported in MAUDE. But the hidden database has included serious injury and malfunction reports for about 100 medical devices, according to the FDA, many implanted in patients or used in countless surgeries. They have included surgical staplers, balloon pumps snaked into vessels to improve circulation and mechanical breathing machines.

An FDA official said that the program is for issues that are “well-known and well-documented with the FDA” and that it was reformed in 2017 as a new voluntary summary reporting program was put in place for up to 5,600 devices.

Yet the program, in all its iterations, has been so obscure that it is unknown to many of the doctors and engineers dedicated to improving device safety. Even a former FDA commissioner said he knew nothing of the program.

Agency records provided to KHN show that more than 480,000 injuries or malfunctions were reported through the alternative summary reporting program in 2017 alone. The FDA alternative summary reporting program was established in 2000, perhaps as a method to reduce reporting administration by the overworked FDA. The devil in the details is described at the link above.

Alison Hunt, another FDA spokeswoman, said the majority of device makers’ “exemptions” were revoked that year as a program took shape that requires a summary report to be filed publicly.

More than a million reports of malfunctions or harm spanning about 15 years remain in a database accessible only to the FDA. But with the agency’s new transparency push, the public may find a public report and submit a Freedom of Information Act request to get information about incidents. A response can take up to two years.  The long-standing exemption program “has allowed the FDA to more efficiently review adverse events … and take action when warranted without sacrificing the quality of our review or the information we receive,” Hunt said in an email.

The KHN investigation had to perform a careful dissection of FDA databases, exceptions and who had access to the relatively unknown information.  There was certainly a lack of transparency even within the FDA.

To those outside the agency, though, the exceptions to the reporting rules are troubling. They strike Madris Tomes, a former FDA manager, as the agency surrendering some of the strongest oversight and transparency powers it wields.  “The FDA is basically giving away its authority over device manufacturers,” said Tomes, who now runs Device Events, a website that makes FDA device data user-friendly. “If they’ve given that up, they’ve handed over their ability to oversee the safety and effectiveness of these devices.”

The FDA issued the same kind of exemption to the makers of da Vinci surgical robots months after Johns Hopkins University School of Medicine researchers pointed out that the company was filing a notably small number of injury reports in the public database.

"The FDA is basically giving away its authority over device manufacturers. If they’ve given that up, they’ve handed over their ability to oversee the safety and effectiveness of these devices. " 

 Madris Tomes, former FDA manager

Doctors, like Kwazneski, who have turned to the public data to gauge the risks of surgical staplers have seen little. He wrote about the “unacknowledged” problem of stapler malfunctions in a 2013 article in the journal Surgical Endoscopy. In 2016, while reports of 84 stapler injuries or malfunctions were openly submitted, nearly 10,000 malfunction reports were included in the hidden database, according to the FDA.

Device maker Medtronic, which owns stapler maker Covidien, has been described as the market leader in surgical staplers. A company spokesman said that the firm has used reporting exemptions to file stapler-related reports through July 2017. Ethicon, the other major stapler maker, said it has not. The public database shows that Medtronic has reported more than 250 deaths related to staplers or staples since 2001.

"I don’t want to sound overdramatic here, but it seemed like a cover-up." 

Dr. Douglas Kwazneski, surgeon

FDA To End Program That Hid Millions Of Reports On Faulty Medical Devices | California Healthline: