Where are artificial intelligence and deep learning going to be applied next? Beth Israel Deaconess Medical Center and Harvard Medical School believe it is breast cancer pathology. According to FierceBiotech, researchers at Beth Israel Deaconess Medical Center and Harvard Medical School have worked together to create an analysis of breast cancer pathology that incorporates artificial intelligence. They found that their system–and the evaluation by pathologists themselves–worked better when used in conjunction than either did alone.

In an evaluation of slides of lymph node cells, the automated diagnostic method was accurate about 92 percent of the time. This was almost as accurate as human pathologists–who are about 96 percent correct. When combined, the results were even better.

“The truly exciting thing was when we combined the pathologist’s analysis with our automated computational diagnostic method, the result improved to 99.5 percent accuracy,” said pathologist Dr. Andrew Beck, director of bioinformatics at the Cancer Research Institute at Beth Israel Deaconess Medical Center and associate professor at Harvard Medical School. “Combining these two methods yielded a major reduction in errors.”

“Our AI method is based on deep learning, a machine-learning algorithm used for a range of applications including speech recognition and image recognition,” said Beck. “This approach teaches machines to interpret the complex patterns and structure observed in real-life data by building multi-layer artificial neural networks, in a process which is thought to show similarities with the learning process that occurs in layers of neurons in the brain’s neocortex.”

Increasingly, the industry expectation is that deep learning can be useful to aid human analysis. This is a first step to pre-analyze and learn from massive quantities of data to offer insights that are subsequently reviewed by people.

Breast cancer is not the only new area where artificial intelligence and deep learning are being applied. MedyMatch Technology Ltd. and Capital Health are focusing on strokes. MedyMatch Technology, the data analytics healthcare company focused on providing physicians with artificial intelligence and real-time decision support tools, recently announced a partnership with Capital Health. This is the first of several partnerships with hospitals in the United States intended to improve stroke patient outcomes. As part of the agreement, Capital Health will provide anonymized data from its two-hospital health system to MedyMatch for use in the development of its first decision support tool directed towards stroke patients.

“MedyMatch is excited to be working with a leading institution like Capital Health which offers advanced radiology services that help support the critical diagnostics needed for its comprehensive stroke center. True innovation in healthcare only comes from the close collaboration between industry and world-class clinicians,” said Gene Saragnese, Chairman and CEO of MedyMatch Technology. “Our partnership with Capital Health brings together breakthrough technology in deep learning and clinical expertise that will accelerate the transformation we all desire in healthcare–better care at lower cost…The data Capital Health will provide will allow us to move closer to providing this decision support tool which can help ensure appropriate diagnosis critical for treatment.”

“MedyMatch is going to make clinical decision support in radiology faster and more accurate,” said Dr. Ajay Choudhri, Director, Vascular and Interventional Radiology and Assistant Director, Radiology, Capital Health, “MedyMatch’s AI capability augments physicians’ reading ability and provides a second set of eyes on the patient’s imaging study. In the area of stroke where time equals brain, it is critical to get a fast, spot on diagnosis.”

Additionally, MedyMatch will leverage medical imaging libraries across multiple imaging modalities including CT, X-ray, MRI, Ultrasound and PET, which will be utilized as part of its research and development efforts to train its next set of applications and deep learning algorithms. “The right data is at the core of application innovation,” said Robert Mehler, co-Founder and Chief Operating Officer.

Artificial intelligence and deep learning have a lot of potential especially with the wealth of data that is now available to researchers and clinicians. Diagnosing strokes and breast cancer is a great starting point to turn this potential into practical value.

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

(Photo: Harvard Medical School, Flickr)

Whether it is kicking off the summer or squeezing in a vacation as it ends. Along with it comes backyard barbecues, sunbathing, and a variety of other activities that involve extended sun exposure. Although many people seek this time in the sun and don’t mind the occasional sunburn that can come with it, they sometimes forget that it can be harmful. Sun exposure has become a major health issue, with 90 percent of nonmelanoma skin cancers being associated with exposure to ultraviolet (UV) radiation from the sun according to the Skin Cancer Foundation. Because the time it takes to get burned depends on many factors, it is not easy to tell when to seek shade. To help people stay safe, researchers report in ACS Sensors the development of a paper-based sunburn sensor for monitoring sun exposure given different skin tones and sunscreen levels.

Most current UV sensors require high-tech gadgets to operate, such as smartphones or wearable devices. Recently, single-use, disposable sunburn sensors have come onto the market. However, some of these sensors use substances that are potentially harmful to people or the environment. Others are only good for specific skin tones. Consequently, J. Justin Gooding and colleagues saw this as an opportunity to create a disposable, inexpensive sunburn sensor. This sensor is composed entirely of safe and benign materials, and it can be easily calibrated to take into account different skin tones and SPFs of sunscreens that are applied on the skin.

Gooding and his colleagues created a sun-exposure sensor by inkjet printing titanium dioxide, a nontoxic and inexpensive compound, and a food dye on paper. When enough UV radiation hits the sensor, titanium dioxide causes the dye to change color, warning people to get out of the sun or apply more sunscreen. To adjust the sensor for various skin tones and sunscreen use, the group added UV neutral density filters that can speed up or slow down the discoloration time of the sensor.

If you would prefer a stretchable sunburn sensor that you can wear, then look to L’Oréal. Its leading dermatological skincare brand, La Roche-Posay, has introduced a first-of-its kind stretchable electronic sensor, My UV Patch. The patch is a transparent adhesive that, unlike the rigid wearables currently on the market, stretches and adheres directly to any area of skin that consumers want to monitor. Measuring approximately one square inch in area and 50 micrometers thick – half the thickness of an average strand of hair – the patch contains photosensitive dyes that factor in the baseline skin tone and change colors when exposed to UV rays to indicate varying levels of sun exposure.

Consumers will be able to take a photo of the patch and upload it to the La Roche-Posay My UV Patch mobile app, which analyzes the varying photosensitive dye squares to determine the amount of UV exposure the wearer has received. The My UV Patch mobile app will be available on both iOS and Android, incorporating Near Field Communications (NFC)-enabled technology into the patch-scanning process for Android. My UV Patch is expected to be made available to consumers later this year.

“Connected technologies have the potential to completely disrupt how we monitor the skin’s exposure to various external factors, including UV,” says Guive Balooch, Global Vice President of L’Oréal’s Technology Incubator. “Previous technologies could only tell users the amount of potential sun exposure they were receiving per hour while wearing a rigid, non-stretchable device. The key was to design a sensor that was thin, comfortable and virtually weightless so people would actually want to wear it. We’re excited to be the first beauty company entering the stretchable electronics field and to explore the many potential applications for this technology within our industry and beyond.”

Alysa Herman, MD explained, “La Roche-Posay recently commissioned a global study in 23 countries, which surveyed 19,000 women and men and found a huge gap in consumer behavior: even though 92 percent were aware that unprotected sun exposure can cause health problems, only 26 percent of Americans protect themselves all year round, whatever the season. With the new My UV Patch, for the first time, we are leveraging technology to help incite a true behavioral change through real-time knowledge.”

My UV Patch was developed by L’Oréal’s U.S.-based Technology Incubator, a business division dedicated entirely to technological innovation, alongside MC10, Inc., a leading stretchable electronics company using cutting-edge innovation to create the most intelligent, stretchable systems for biometric healthcare analytics.

Whether you’re planning to work on your tan at the beach, attend a barbecue at a friend’s house, or relax on the patio, you will have some new medical technology to help you be safe in the sun. You just need to decide whether you want it to be stretchable or disposable.

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

(Photo: Beach Chairs, Cancun, Flickr)

While Google and Apple may have taken earlier steps into the healthcare arena, IBM has recently made its presence known. If you are curious, take a look at how IBM is helping Novo Nordisk, Medtronic and radiologists.

Novo Nordisk and IBM Watson Health announced in December that the two companies will work together to create diabetes solutions built on the Watson Health Cloud. The agreement combines Novo Nordisk’s deep understanding of diabetes with IBM’s leadership in cognitive computing. By harnessing the potential of the Watson Health Cloud, Novo Nordisk aims to further advance its offerings to people living with diabetes and their healthcare professionals.

IBM Watson is the first commercially available cognitive computing platform and represents a new era of computing. The platform, delivered through the cloud, processes vast amounts of big data to uncover patterns and insights, understands complex questions posed in natural language, proposes evidence-based answers, and learns from each interaction. The Watson Health Cloud is a development platform for health and wellness solutions.

At last month’s International Consumer Electronics Show, IBM and Medtronic unveiled a prototype for a diabetes-management app that tests have shown may be capable of predicting hypoglycemic events as early as three hours in advance. IBM Chief Executive Officer Ginni Rometty said, “Up to three hours in advance is what prevents dangerous health events from happening.” She considers this ability to predict hypoglycemic events to be a “breakthrough.”

The app gathers a patient’s readings from Medtronic insulin pumps and glucose monitors then combines them with information taken from the individual’s activity trackers and diet. The system uses pattern recognition gleaned through IBM’s Watson to provide feedback on how a patient can manage their diabetes. The app still needs to go through regulatory review, but Rometty said it will roll out this summer.

In addition to its work with Novo Nordisk and Medtronic, IBM is developing smart software that can serve as a radiologist’s assistant. The software, code-named Avicenna, identifies anatomical features and abnormalities in medical images such as CT scans and also draws on text and other data in a patient’s medical record to suggest possible diagnoses and treatments.

Avicenna is intended to be used by cardiologists and radiologists to speed up their work and reduce errors, and is currently specialized to cardiology and breast radiology. It is currently being tested and tuned up using anonymized medical images and records.

Avicenna “looks” at medical images using a suite of different image-processing algorithms with different specialties. Some determine where a CT scan slice is taken from on a patient’s chest. Others can identify organs or label abnormalities such as blood clots.

Avicenna has a “reasoning” system that draws on the output from all those different signals to suggest possible diagnoses for a patient. It shows a summary of that reasoning to the person working with the software.

In a demo of the system at IBM’s research lab near San Jose, Avicenna took on the case of a 28-year-old woman complaining of shortness of breath. The patient’s medical record included pulmonary angiogram images of the blood vessels around her lungs, some blood tests, and text noting that her mother had experienced multiple miscarriages.

Avicenna knew that family history can be associated with a tendency to form blood clots, which can lead to miscarriages, knowledge that changed how it analyzed the angiogram images. The software suggested pulmonary embolism as the most likely diagnosis and highlighted several possible embolisms in the patient’s left and right pulmonary arteries. When a radiologist independently reviewed the same case, this expert made the same diagnosis and highlighted the same embolisms.

With all of this in the works by IBM, this bodes well for diagnosing health issues. It looks like Google and Apple have some more competition in the life science sector.

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

(Photo: A Computer Called Watson, Flickr)

With the launch of their Head Health Initiative in 2013, the NFL and GE have helped to make positive strides to improve the health and safety of athletes at all levels. The initiative is a four-year, $60 million collaboration to aid in the prevention, detection and management of traumatic brain injuries (TBIs) as well as concussions. According to Forbes, the initiative is at least partly due to the increasing number of lawsuits filed against the NFL by former players who have suffered concussions. A CDC study is likely to be a factor, because it revealed that emergency departments in the U.S. treated 173,000 TBIs in 2010, including concussions as a result of sports and recreation among those 19 years of age or younger.

To date, there have been some promising advances by organizations that have received funding from the initiative. Quanterix, a Massachusetts-based diagnostic company, has been using its blood biomarker analyzer to detect and quantify tau protein biomarkers. According to Quanterix CEO Kevin Hrusovsky, “when the brain experiences any kind of trauma, whether caused by a hit on the sidelines at a sporting event or someone impacted during combat while serving in the military, minuscule quantities of protein enter the blood stream. Our technology is the only one sensitive enough to measure these proteins in a way that no one thought possible.” This technology can be used to understand and quantify the long-term effects of TBIs.

In addition to Quanterix, BrainScope, a diagnostics company out of Maryland, recently received FDA clearance for a smartphone-based EEG device to detect TBIs. Furthermore, the NFL and GE are interested in a UC Santa Barbara lab using MRI scans to identify damage to individual brain connections and determine which brain areas become disconnected following an injury. The goal is to develop software to help with TBIs.

In the next phase of the initiative, Under Armour and the U.S. Department of Commerce’s National Institute of Standards and Technology (NIST) have joined GE and the NFL to find preventative measures that can be used during sports activities. This phase will focus on next-generation materials that can better absorb or dissipate energy in protective gear.

For more information, see NFL and GE.

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

(Photo: Football Lineup, Flickr)

According to the Alzheimer’s Association, Alzheimer’s disease accounts for up to 80 percent of all dementia cases. Although a way to change the underlying Alzheimer’s process has not been discovered yet, diagnosing the disease early provides a number of opportunities including:

• Start treatment sooner which can preserve function for a longer period of time
• Allow Alzheimer’s patients and their families to make living arrangements, establish support networks and plan for the future

Scientists continue to look for ways to enable physicians to diagnose Alzheimer’s at an early stage in a more accurate manner. Besides memory and recall tests, the National Institute on Aging points out that there are a number of areas that show some promise. For example, advanced imaging systems may help measure the initial changes in brain function or structure to identify individuals who are in the very first stages of Alzheimer’s (long before they develop symptoms). Other tests look for the presence of certain proteins that are typically found in people with Alzheimer’s. The analysis of body fluids such as blood and cerebrospinal fluid can determine the presence of tau and beta-amyloid proteins.

A recent study at Mexico’s University of San Luis Potosi found a possible link to the skin of a patient. More specifically, researchers discovered that a skin sample taken from behind a patient’s ear showed tau protein levels seven times higher in Alzheimer’s and Parkinson’s patients. The study’s author, Dr. Ildefonso Rodriguez-Leyva, explained that pathological confirmation was not possible without a brain biopsy until now. Consequently, diseases like Alzheimer’s often go unrecognized until after the disease has progressed. His team hypothesized that skin might show the same abnormal proteins as brain tissue, because skin and brain tissue have the same origin while in the embryo. This new test provides a possible biomarker that could allow physicians to identify diseases such as Alzheimer’s at an earlier point.

Dr. Rodriguez-Leyva is optimistic about the work. “More research is needed to confirm these results, but the findings are exciting because we could potentially begin to use skin biopsies from living patients to study and learn more about these diseases…This also means tissue will be much more readily available for scientists to study.”

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

(Photo: Labomed CxL, Flickr)

With cancer detection moving this direction, Myriad Genetics just introduced its myRisk Hereditary Cancer multi-gene test which provides the ability to detect eight major forms of cancer. By analyzing results related to 25 genes, the test provides an increased sensitivity to breast, ovarian, colorectal, prostate, melanoma, gastric, pancreatic and endometrial cancers. Mark Capone (the president of Myriad Genetics Laboratories) explained, “myRisk Hereditary Cancer will improve the quality of patient care by empowering healthcare providers with knowledge about their patients’ risk of hereditary cancer and the appropriate medical management options available based on that risk.”

Since cancer is so prevalent and some of the treatments for those diagnosed with cancer seeming almost as bad as the disease itself, the ability to determine the potential risks for inheriting different forms is welcome. Therefore, it is crucial that multi-gene tests like the myRisk Hereditary Cancer test actually provide what they claim to provide. Based on Myriad Genetics’ press release, it looks like the company is taking steps to ensure this is the case. Myriad is using a phased approach for its myRisk Hereditary Cancer launch, and it will present its clinical validity data at the Collaborative Group of the Americas on Inherited Colorectal Cancer annual meeting in October and the San Antonio Breast Cancer Symposium in December. For more information, see Genetics in Medicine, Dana-Farber and World Cancer Research Fund International and Myriad Genetics.

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti

According the U.K. research, epigenetic switches are subtle shifts in gene activity that happen during early development and impact how genes express themselves from a physiological standpoint. The scientists’ work showed that more switching predicted a greater likelihood of obesity. By using the blood test with children, the research provides additional evidence that being overweight as children is not solely due to lifestyle–the processes that control their genes may also be involved.

This research looks promising. If the children who are at risk can be identified, then assistance can be provided to them before they start to put on weight.

For more details, here is the link to the UPI source: Blood Test for Obesity

———–

Ryan Lahti is the founder and managing principal of OrgLeader, LLC. Stay up to date on Ryan’s STEM-based organization tweets here: @ryanlahti