Modern artificial intelligence uses complex algorithms to perform all kinds of tasks in an instant, for example to determine the feeling of a client based on his or her examination or to identify specific features of an image . However, the brightest moments of artificial intelligence come from the creativity with which we use these algorithms. People used the AI for generate new sports, transform scribbles into realistic landscapesand now, MIT has found a way to detect breast cancer up to five years in advance using an in-depth image classification model.
The MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Massachusetts General Hospital (MGH) have used mammograms and known results from more than 60,000 patients to form their new model to the smallest visual detail from the human eye. Well-trained doctors do not miss these predictive patterns simply because they may seem too small to be noticed, but because more subtle patterns just do not attract enough attention. An image classification model that can categorize thousands of scans down to the smallest detail can quickly solve this daunting task.
Regina Barzilay, a professor at MIT (and breast cancer survivor), explains how this new model can improve treatment plans:
Rather than taking a single approach, we can customize the screening for cancer risk in women. For example, a doctor might recommend to a group of women to have a mammogram every two years, while another higher-risk group could undergo additional MRI screening.
When doctors can order mammograms according to the needs of the patient, they can avoid unnecessary exposure to radiation and the cost of potentially unnecessary examinations. Although existing models can accurately identify 18% of patients in the high-risk category, this new model increases this number by up to 31%. Its success is based on the team's approach to its development. For the first time, a model of breast cancer prevention targets women individually. It also takes into account racial diversity, where earlier models focused mainly on white populations. This not only contributes to increased accuracy, but significantly reduces the breast cancer mortality rate among African-American women.
As demonstrated by MIT and HGM, well-trained image classification models can help doctors save lives. Although no AI gives perfect results, image classification algorithms have matured and become reliable in many applications, especially in specific models such as this one. You need a little more than a good idea, relevant data and a little time to create a successful image recognition model. Services like Clarifai, Microsoft Azure, IBM Watson, Vize and others offer free, bespoke customized training platforms that require no programming skills. Thanks to these algorithms, accessible to all, we have all the necessary resources to train AI to solve problems and help others. It takes time and care to safely integrate a successful experience into the practice of diagnostic medicine; This approach will likely see many revisions as it develops outside of a single hospital. But the first results are promising.
Antibiotics were miracle drugs for most of the twentieth century, but they are no longer a magic bullet for treating any infection. The overuse of antibiotics has promoted the proliferation of life-threatening resistant organisms, particularly for those whose immune systems are already weakened. In the UK, a teenager was on the verge of death after a transplant, but a last effort using genetically modified viruses you saved his life. Doctors say that it is a decisive moment for the use of so-called bacteriophages in medicine.
Isabelle Carnell-Holdaway, 17, started having problems when she was small. The doctors diagnosed him with cystic fibrosis, a genetic disease that halves life expectancy. The only long-term treatment for cystic fibrosis is a lung transplant. Carnell-Holdaway was able to get a transplant at age 15, but a low-grade chronic infection flourished during convalescence and immunosuppressive medication. The body, a strain of Mycobacterium Abcessus, has been proven resistant to all antibiotic treatments.
After exhausting all conventional treatment options, doctors turned to bacteriophages. These microscopic viruses Do not infect human cells, but they are potentially deadly to bacteria. Doctors have used bacteriophages to treat infections in the past, but it is difficult and time-consuming to find phage strains that can effectively fight an infection. In this case, the doctors had access to a library of 15,000 phages gathered for a research project.
The team identified a phage called "Muddy" as the best candidate (see above). It was discovered in 2010 attacking bacteria in a decaying eggplant. The doctors discovered two other phages that could help and altered their tiny genomes, thus making them more similar to Muddy – virulent and deadly. Mycobacterium Abcessus.
As of June 2018, physicians administered the mixture of three bacteriophages to Carnell-Holdaway twice daily. In the following months, the infection decreased until it disappeared completely. It should be noted that Carnell-Holdaway's body has not been hit by billions of phage particles each day.
Doctors ensure that their patient is not "cured". It still carries the dangerous bacteria and the return of the treatment to the bacteria could be advanced if the treatment is interrupted too early. For the moment, Carnell-Holdaway continues to receive daily injections of the phage cocktail. However, she was able to resume her normal daily routine without the disabling effects of cystic fibrosis. The results of his treatment were published in the journal Nature.
There is no fountain of youth to go back in time, but it may be possible to remember the ravages of the age. An ESA experiment that has just arrived on the International Space Station (ISS) is going test nanoparticles as a way to eliminate the body from free radicals. This could prevent some of the cellular damage associated with aging, but it could also help astronauts on long-term space missions to stay healthy.
There is no single cause for aging, but free radicals are an essential piece of the puzzle. A free radical is just a molecule with an unpaired electron in its outer layer. They are very reactive, which means that they will steal electrons from other molecules, which may prevent them from working. Over time, this causes cellular damage known as oxidative stress associated with aging. It turns out that similar constraints affect astronauts in space.
Doctors advise people to make sure that their diet contains antioxidants such as vitamin A, vitamin C and beta-carotene to neutralize some of these molecules. These substances can not neutralize antioxidants forever, so you must continue to take them. The European Space Agency (ESA) Nano Antioxidants will test a type of ceramic nanoparticle called "nanoceria" (the green dots above) to see if it absorbs free radicals any longer in order to reduce the heart risk. Parkinson's disease and muscle loss.
The nanoceres have enzymatic activity inside the cells, allowing them to neutralize free radicals for weeks between doses. It's much longer than natural antioxidants. Short-term studies have shown that nanocerias protect living cells from oxidative stress. In 2017, researchers discovered that the particles remained stable and could protect the muscle cells aboard the ISS. The new study will track the effects of nanoceria longer.
The nanoceria and the host cells are housed in a device called the Kubik Incubator. It keeps the samples at a constant temperature of 30 degrees Celsius (86 degrees Fahrenheit). The experience lasts six days, twice as long as the last. After that, the ISS crew will freeze the samples for further analysis on Earth. Scientists will compare samples of space to controls that did not go into space. The comparison should help the team determine the effects of microgravity and cosmic radiation on nanoceria.
Someday, ESA may be able to use nanoceria as a supplement protecting astronauts from cellular damage associated with free radicals. Here on Earth, nanoceria could also contain oxidative stress and reduce the incidence of age-related diseases.
A laser tenth of solar power on Earth officially debuted in March when Romanian researchers conducted the first successful test at 10 petawatts (PW). The laser is one of three of an international project in Europe called Extreme Light Infrastructure. To date, it is the most powerful laser ever built and the most concentrated power on the planet.
It is hard to exaggerate the enormity of 10PW, which equates to 10 trillion watts. It's only a few years ago that this site was referring to a simple 1PW laser like a death star. The new is 10 times stronger. In comparison, laser pointers sold in the United States are limited to a maximum of 0.005 watts for security reasons.
The laser in question is part of the Extremely Light Infrastructure Project (ELI), an effort initiated by scientists in Europe in the mid-2000s and led by French scientist and Nobel laureate Gerard Mourou. The project aims to advance not only the research infrastructure for lasers, but also applied sciences.
The program was funded by the European Commission and in just a few years, three countries have been selected to host three new lasers: Romania, Hungary and the Czech Republic. At present, the project has received more than 850 million euros, mainly from the European Regional Development Fund.
The 10PW laser resides in a newly built lab called Extreme Light Infrastructure – Nuclear Physics installation (ELI-NP) in a town called Măgurele, not far from the capital Bucharest. ELI-NP is dedicated to the study of photonuclear physics and its applications. The other two laboratories are called ELI-Beamlines in the Czech Republic, focusing on secondary sources of radiation and short-pulse particles, and ELI-ALPS or Attosecond Light Pulse Source in Hungary.
With 10 PW of power, scientists can literally vaporize matter, opening up new perspectives on what happens during a supernova. This is only one example, albeit rather epic. This type of power in a laser also helps to study how heavy metals are formed.
In terms of more practical research, ELI-NP will work to advance medical research on proton cancer treatment as well as research into new methods of treating radioactive waste. This could also help to create new ways to find and characterize nuclear material, allowing security teams to analyze, for example, incoming shipping containers in search of dangerous and illegal content. The formal research phase of the project is scheduled to begin in early 2020.
The power of lasers has increased in recent decades. "The laws of light-matter interaction change fundamentally because of the predominance of relativistic effects in the dynamics of charged particles under the influence of laser light," according to ELI. From this fundamental change, scientists can develop new methods for generating X-rays, gamma rays, and high-energy particles. These new methods, in turn, open up new opportunities for use in different scientific fields, whether it is medical research or materials science.
As much as anyone would want to imagine a giant satellite antenna pulling from its center (ahem, Death Star), the reality of a 10PW laser is a little more mundane. The laser itself is inside a room and the scientists who operate it are of course behind a computer.
For the laser to have both power and precision, it relies on two systems working together. One is the high-powered laser system, which itself includes two laser arms. They are what the laser pulses deliver. The second piece is the laser beam transport system, which directs the pulses where they need to go with micrometric precision. This second component is not a laser at all, but rather "one-meter wide adjustable aperture mirrors installed in a vacuum system of pipes and housings", according to ELI-NP information. The entire system requires a highly controlled environment with respect to air quality and vibration, at least one image in a clean room, in the scientific sense of the term.
If we could take a look at the inside of the protective chamber while the laser was working, the beam would be visible to the human eye and reddish, although it is close of the infrared radiation limit, according to Dr. Nicolae Zamfir, project manager at ELI-NP. A high energy laser pump would be visible to the eye, too, appearing in green.
Mr. Zamfir also explained the size of the laser beam, about 60 cm or just under two feet in diameter, and the area that he can target: "The beam is focused on mm2 only in the Interaction (chamber), "he added.
If everything goes as planned, the ELI-NP 10PW laser will be even more powerful. According to optics.org (as well as a Job offer for an engineer at ELI-NP – a simple bachelor's degree required, two 10PW lasers will combine together "deliver focused laser intensities up to 1023 watts per square centimeter, at a wavelength of 820 nanometers and a pulse duration of 25 femtoseconds. "The intensity of the current is 1015.
In addition to the three sites in Romania, Hungary and the Czech Republic, ELI plans to create a fourth installation and a laser, with a location to be determined. This should be an order of magnitude stronger than that of Romania.
Top image credit: Getty Images
If you have read articles about fitness trainers, they have probably been written by compulsive drug addicts who compare them to find out if they can follow these bike rides or these marathon training races. Well, I am not one of them. But the technology in the follow-ups of sleep and fitness is quite amazing and deserves to be written. And yes, they can also offer health benefits to the rest of us who exercise if the weather permits.
Trackers, like many of the digital health movement, have come a long way in recent years. The simple and unclear step counters of a few years ago have evolved into devices that can monitor your heart rate, sleep and other vital signs. However, they are far from perfect, so they can also give an undeserved impression of accuracy.
The simplest form of counting steps is to use data from the accelerometer and the unit of inertial measurement (IMU) of the device to detect rhythmic movements consistent with the movement of the -and-comes usually associated with walking or running. Using the data from both sensors, the device tries to filter false positives.
Once the device has a number of steps, it multiplies it by an estimate of your stride to calculate the distance traveled. In the worst case, it uses a generic estimate of your stride, but you can usually enter your height to give it a more precise starting point, or even directly enter the length of your stride. Some devices go a step further and will calibrate your stride by comparing the GPS results with your estimates. Since consumer GPS has limited accuracy, this process typically requires several minutes of travel at a constant speed. Some also consider separate stride lengths for walking and running. Until recently, this involved reminding the tracker when you started a hike or a run. But many new devices do a good self-detection when you start a type of exercise and classify it appropriately.
Having owned various fitness trackers Over the years, it's clear that counting steps and stairs is an art as much as a science at this stage. Even if you use multiple advanced trackers at the same time, their number of steps may vary by 15%. AI-based analyzers for wrist tracking and typical watches to help clean the data.
Devices with altimeters also often allow you to count the number of stairs (or the equivalent) that you have mounted. Here too, the fusion of sensors is necessary, so that the altitude gained at the wheel or at the wheel is not taken into account by your form (a pity for the technical journalists who spend a lot of time in the planes).
Climbing tracking can be even more of a crapshoot. For example, my Fitbit Versa regularly reports dozens of floors on which I play tennis – even though each floor is supposed to represent 10 feet of altitude gained while walking or running. On the other hand, my Huawei Band 3 Pro is not fooled. However, the Versa does a better job keeping my climbs and descents in the day.
As in many technological areas, digital health has been significantly improved through the use of AI. For example, instead of writing long, complicated code sequences based on physical models to count steps, modern trackers rely on neural networks who use machine learning to determine progress. Similarly, instead of relying on human analysis of sleep data for each patient, monitoring systems have systems driven on huge amounts of human-labeled sample data. As a result, they can classify the sensor information of users not only in sleep or sleep, but even depending on the type of sleep.
If you have ever had a heart problem, you may have been connected to a machine with a variety of electrodes to monitor your heart (an ECG or ECG). These electrodes measure the small electrical currents emitted by the "pacemaker cells" of your heart. The best consumer heart monitors use a simplified version of the same technique. A chest strap with electrodes inside is used. With this approach, it is possible to obtain both a very accurate measurement of heart rate and also to calculate heart rate variability (VFC), an increasingly popular measure of fitness.
As you can imagine, it's a little tedious. Most trackers rely on a less accurate optical system, but less tedious. Optical heart rate monitors Use a process called photoplethysmography (PPG) to calculate your heart rate by projecting light into your skin and measuring reflectance. The light is emitted by LEDs (usually at least two) inside the tracking device. Multiple LEDs at different frequencies provide better results on the wide range of possible skin colors and thicknesses.
Unfortunately, readings from an optical drive placed on your wrist or in a ring are likely to fluctuate as you move. In particular, if you run or jog at a pace similar to your heart rate, then it's possible for a tracker to follow him and think that's your heartbeat. This is often called the "crossover problem". Since only about 1% of the light reflected by your skin is related to the heart rate signal, the possibilities for error are increasing.
To help with this, many trackers also incorporate an accelerometer to help them ignore the incorrect data. The amount of reflected light also varies with the ambient light level. Indeed, unless you are in a dark room or have your hand and wrist fully covered, this will cause some light pollution from the LEDs. High-end devices include ambient light monitoring to minimize this problem.
Because of these problems, optical heart rate devices seem to be the most accurate files and clips. Of course, neither one nor the other is easy to use as a wrist-based tracker or even a ring, so it took a lot of effort to create a more accurate heart rate tracking for popular devices that can be worn all day (and all night). Garmin, Fitbit and other brand-name manufacturers claim at least a 5% accuracy of a medical-grade device for their wrist trackers. It's quite reasonable if you just want a general measure of your health and an estimate of how much "cardio" time you get from exercise each day, but certainly not enough for the training of your body. 39, elite athletes.
On an experimental basis, I am equipped with five different tracking devices capable of measuring heart rate. For starters, we have a FullPower Sleeptracker under our mattress (which uses pressure and vibration to measure heart rate during sleep). I then tried to watch ZeTime, Fitbit Versa, Huawei Band 3 Pro and an inexpensive pulse oximeter. While the ZeTime data gave me almost a coronary (it showed massive peaks during sleep that certainly did not look healthy), the other four follow-ups were generally consistent and relatively close to current values. I am sure that some of the differences were caused by having to wear several at a time, or none of them was really in an ideal location. However, none of these devices are accurate enough to calculate the HRV. EliteHRV, the leading manufacturer of VRC applications, only supports chest strap for this purpose.
While the Apple Watch 4 is not the first laptop to provide users with an electrocardiogram (ECG), it is by far the most popular. Specifically, on demand, the latest Apple Watch watch can provide an ECG trace and detect if the user may be suffering from an irregular heartbeat – in this case, atrial fibrillation or a fib. To do this, it measures the electrical impulses emitted by the heart as they reach the watch. To get a reading, the user puts his finger next to the watch for 30 seconds to close the circuit. In itself, diagnosing an irregular heartbeat may not be important, but it is reason enough to consider further evaluation by a health professional. Apple facilitates the process by providing a PDF file of the ECG that the user can pass to his doctor.
To validate the effectiveness of this feature, Apple has funded an in-depth study showing that Watch 4 users using this feature enjoy similar benefits to those who use a medical device during a more typical assessment. from one week. Early detection of symptoms of possible heart disease clearly has advantages. However, the medical community is divided on the importance of diagnosing apathy in otherwise healthy people with no specific propensity for heart disease. In any case, this ability is certainly a foretaste of what could well be an additional development in the monitoring of heart health through popular portable devices.
If you suffer from a sleep disorder or have previously thought that you have a sleep apnea problem, you have probably been referred to a clinic that could charge you with electrodes and charge you for sleeping. One ton to tell you how and how good you sleep. . But if you just want to get an idea of your sleep quality and what you may be able to do to improve it, wearing a dozen electrodes every night is definitely not practical. Enter the sleep trackers. With the help of one or more sensors, they rely on science and machine learning to estimate the moment of your sleep and the phase of sleep in which they are, and to suggest various health tips and tricks.
My experience with five different trackers that signal sleep indicates that consumer products can do a reasonable job of sketching out your sleep and waking states, and maybe about the total time spent in each of the states of sleep. labeled sleep. These are commonly referred to as Light, Depth, and REM, although one dormant researcher who I spoke to stated that medically, EMT was important enough to start by classifying sleep into REM and non-REM sleep. REM. In any case, not two of the trackers matched on a consistent basis.
The sleep tracker I've been using for the longest is the Sleeptracker. The detection cell goes under your mattress, which avoids the hassle. Fullpower has also done a great job in building health statistics based on your demographic profile in relation to its user community. This allows them to provide interesting and potentially useful coaching tips. The placement of the sensor also helps them to measure the breathing rate – which the conventional fitness trackers that I used could not estimate. Unfortunately for the curious, Fullpower does not disclose any information about the sensors it uses, except that it is an internal design.
Most other sleep monitoring systems used are simply fitness monitoring systems that monitor the heart rate continuously. They analyze data, including your mobility and heart rate, to estimate whether you are asleep or awake, and at what stage of sleep you are. At present, none of the standard fitness tracking devices are certified as a medical device or to diagnose sleep apnea. However, Starter Bootdr has a device that can also be connected to your forehead, which also includes a pulse oximeter and can be used to detect apnea events. Fitbit proposes that its Charge 3 and Versa sensors be equipped with SpO2 sensors, but they are currently doing nothing.
While consumers' fitness and sleep followers clearly have a long way to go before they are on par with medical quality procedures, progress has been and is likely to continue to be rapid. The sensors are becoming smaller, less expensive and more accurate, along with the increase in processing power and improved analysis tools. What took a big watch a few years ago can now be done with a ring. As a next step, look for increased integration of personal tracking devices into the professional health system. This is already starting to happen on a limited basis, but is likely to become commonplace.
Read now from PCMag: