“Unorthodox” AI Helps Identify Best Cancer Treatments

The self-learning model identifies drug regimens that shrink tumors while minimizing side effects AlphaGo became the first household AI name by teaching itself to play the ancient Chinese game Go and then beating the world’s best human player. Self-driving cars use AI systems to learn to park or merge into traffic by practicing the maneuvers over and over until they get it right. It’s clear that AI programs are good at training themselves to win, maximize, or perfect. But what if success means striking a balance? In cancer treatments, doctors endeavor to dose patients with enough drugs to kill as many tumor cells as possible but as few patient cells as possible. In other words, they balance shrinking a tumor with minimizing side effects. “We said, ‘Wait. This sounds like a machine-learning search problem and optimization issue,’ ” says Pratik Shah, an MIT Media Lab principal investigator. “We thought we could do Continue reading “Unorthodox” AI Helps Identify Best Cancer Treatments

Therapy Robot Teaches Social Skills to Children With Autism

The QTrobot from LuxAI was designed to help children with autism learn to interact with humans For some children with autism, interacting with other people can be an uncomfortable, mystifying experience. Feeling overwhelmed with face-to-face interaction, such children may find it difficult to focus their attention and learn social skills from their teachers and therapists—the very people charged with helping them learn to socially adapt.  What these children need, say some researchers, is a robot: a cute, tech-based intermediary, with a body, that can teach them how to more comfortably interact with their fellow humans. On the face of it, learning human interaction from a robot might sound counter-intuitive. Or just backward. But a handful of groups are studying the technology in an effort to find out just how effective these robots are at helping children with autism spectrum disorder (ASD).  One of those groups is LuxAI, a young company spun out of the University of Luxembourg. The Continue reading Therapy Robot Teaches Social Skills to Children With Autism

Medical Imaging AI Software Is Vulnerable to Covert Attacks

An attacker could manipulate medical software to rig a clinical trial or justify unnecessary procedures Illustration: iStockphoto Artificial intelligence systems meant to analyze medical images are vulnerable to attacks designed to fool them in ways that are imperceptible to humans, a new study warns. There may be enormous incentives to carry out such attacks for healthcare fraud and other nefarious ends, the researchers say. “The most striking thing to me as a researcher crafting these attacks was probably how easy they were to carry out,” says study lead author Samuel Finlayson, a computer scientist and biomedical informatician at Harvard Medical School in Boston. “This was in practice a relatively simple process that could easily be automated.” “In addition to how easy they are to carry out, I was also surprised by how relatively unknown these weaknesses are to the medical community,” says study co-author Andrew Beam, a computer scientist and Continue reading Medical Imaging AI Software Is Vulnerable to Covert Attacks

Drone Delivery Becomes a Reality in Remote Pacific Islands

In Vanuatu, delivery drones will fly vaccines to isolated villages beginning in September Photo: UNICEFCurrently, health workers in Vanuatu often hike over mountains to deliver vaccines–but drones can fly over them. This September, delivery drones will begin to fly the friendly skies of Vanuatu. And this isn’t a one-shot demonstration, like many of the stunts we’ve seen from the likes of Amazon and Google. This is an attempt to make drones part of the medical infrastructure.   The South Pacific island nation of Vanuatu, a string of 83 volcanic islands spread over 1600 kilometers (995 miles), has just issued a “request for tender” to drone companies around the world. The companies are invited to submit bids for bringing vaccines to scattered hospitals and health clinics on three islands. With a government contract available for each of the islands, up to three companies will then begin a two-month trial in September.  Companies Continue reading Drone Delivery Becomes a Reality in Remote Pacific Islands

Tiny Robots in Disguise Combat Bacteria in the Blood

Miniature robots cloaked in platelets and red blood cells can clear bacterial infections in the blood Image: Esteban-Fernández de Ávila/ Science RoboticsNanorobots nab bacteria, spherical in shape, that cause a hard-to-treat infection known as MRSA. Researchers have come up with all sorts of ways to propel tiny robots deep into the human body to perform tasks, such as delivering drugs and taking biopsies. Now, there’s a nanorobot that can clean up infections in blood.  Directed by ultrasound, the tiny robots, made of gold nanowires with a biological coating, dart around blood,  attach to bacteria, and neutralize toxins produced by the bacteria. It’s like injecting millions of miniature decoys into blood to distract an infection from attacking the real human cells.   The invention, developed in the labs of Joseph Wang and Liangfang Zhang at the University of California San Diego (UCSD), was described today in Science Robotics. The researchers hope the robotic detoxification system could provide an alternative to the multiple, broad-spectrum antibiotics currently used to treat life-threatening infections—one Continue reading Tiny Robots in Disguise Combat Bacteria in the Blood

Synthetic Bacteria Drive New Ingestible Gut Sensor

An ingestible capsule pairs bacteria with electronics to monitor blood in the GI tract Photo: Lillie Paquette/MIT School of Engineering In the latest edition of “What would you be willing to swallow?”, researchers at MIT today unveiled an ingestible sensor that combines engineered bacteria with ultra-low-power microelectronics to sense changes in the gut. The sensor, roughly the size of a large pen cap, needs to undergo miniaturization and further study before it can be used in humans, but the team hopes to begin a clinical trial within a year or two, said senior author and MIT bioengineer Timothy Lu at a press conference this week. The prototype, described in the journal Science , successfully detected signs of excessive bleeding in the gut of pigs. Bleeding in the gut can be indicative of a serious health condition, including a gastric ulcer or colorectal cancer. Lu emphasized that the modular system can Continue reading Synthetic Bacteria Drive New Ingestible Gut Sensor

AI Cardiologist Aces Its First Medical Exam

A neural network outperforms human cardiologists in a task involving heart scans Photo-illustration: Rima Arnaout Rima Arnaout wants to be clear: The AI she created to analyze heart scans, which easily outperformed human experts on its task, is not ready to replace cardiologists.  It was a limited task, she notes, just the first step in what a cardiologist does when evaluating an echocardiogram (the image produced by bouncing sound waves off the heart). “The best technique is still inside the head of the trained echocardiographer,” she says. But with experimental artificial intelligence systems making such rapid progress in the medical realm, particularly on tasks involving medical images, Arnaout does see the potential for big changes in her profession. And when her 10-year-old cousin expressed the desire to be a radiologist when she grows up, Arnaout had some clear advice: “I told her that she should learn to code,” she says Continue reading AI Cardiologist Aces Its First Medical Exam

Cracking Open the Black Box of AI with Cell Biology

A deep neural network that’s mapped to the innards of a yeast cell reveals its inner workings Image: iStock Phot The deep neural networks that power today’s artificial intelligence systems work in mysterious ways. They’re black boxes: A question goes in (“Is this a photo of a cat?” “What’s the best next move in this game of Go?” “Should this self-driving car accelerate at this yellow light?”), and an answer comes out the other side. We may not know exactly how a black box AI system works, but we know that it does work. But a new study that mapped a neural network to the components within a simple yeast cell allowed researchers to watch the AI system at work. And it gave them insights into cell biology in the process. The resulting tech could help in the quest for new cancer drugs and personalized treatments.  First, let’s cover the basics Continue reading Cracking Open the Black Box of AI with Cell Biology

In Super Bowl of Startups, NFL Looks to Tackle Football Safety

The National Football League’s pitch competition features new technologies to promote athlete safety and performance Photo: Tim Bradbury/Getty Images In the world of tech startups, some say it’s best to “fail fast, fail often”—and it’s a mantra that WWE founder Vince McMahon might have had on his mind when he announced last week that he was bringing back the XFL. The gimmicky football league failed spectacularly when it first launched, flaming out in 2001 after only one season, and many are already predicting that McMahon’s 2020 reboot will fail again. There are, however, nine other innovate startups on display this week, any number of which could have far more lasting impacts on the game of football. And in Minneapolis tomorrow, the day before the New England Patriots and Philadelphia Eagles square off in Super Bowl LII, these nine companies will compete across three categories in the National Football League’s third Continue reading In Super Bowl of Startups, NFL Looks to Tackle Football Safety

Stanford’s AI Predicts Death for Better End-of-Life Care

Deep learning AI is helping screen for ill patients who could benefit from having end-of-life conversations earlier Illustration: iStockphoto Using artificial intelligence to predict when patients may die sounds like an episode from the dystopian science fiction TV series “Black Mirror.” But Stanford University researchers see this use of AI as a benign opportunity to help prompt physicians and patients to have necessary end-of-life conversations earlier. Many physicians often provide overly rosy estimates about when their patients will die and delay having the difficult conversations about end-of-life options. That understandable human tendency can lead to patients receiving unwanted, expensive and aggressive treatments in a hospital at their time of death instead of being allowed to die more peacefully in relative comfort. The alternative being tested by a Stanford University team would use AI to help physicians screen for newly-admitted patients who could benefit from talking about palliative care choices. Past studies have shown that about 80 percent of Americans would prefer Continue reading Stanford’s AI Predicts Death for Better End-of-Life Care