All posts by Brian Horowitz

Can AI Lead to Pregnancy?

Post Syndicated from Brian Horowitz original

Artificial intelligence in healthcare is often a story of percentages. One 2017 study predicted AI could broadly improve patient outcomes by 30 to 40 percent. Which makes a manifold improvement in results particularly noteworthy. 

In this case, according to one Israeli machine learning startup, AI has the potential to boost the success rate of in vitro fertilization (IVF) by as much as 3x compared to traditional methods. In other words, at least according to these results, couples struggling to conceive that use the right AI system could be multiple times more likely to get pregnant.

The Centers for Disease Control and Prevention defines assisted reproductive technology (ART) as the process of removing eggs from a woman’s ovaries, fertilizing it with sperm and then implanting it back in the body.

The overall success rate of traditional ART is less than 30%, according to a recent study in the journal Acta Informatica Medica

But, says Daniella Gilboa, CEO of Tel Aviv, Israel-based AiVF—which provides an automated framework for fertility and IVF treatment—help may be on the way. (However, she also cautions against simply multiplying 3x with the 30% traditional ART success rate quoted above. “Since pregnancy is very much dependent on age and other factors, simple multiplication is not the way to compare the two methods,” Gilboa says.)

In the U.S. alone, 7.3 million women are battling infertility, according to a 2020 report from the American Society for Reproductive Medicine. In the U.S., 2.7 million IVF cycles are performed each year. 

AiVF is using ML and computer vision technology to allow embryologists to discover which embryos have the most potential for success during intrauterine implantation. AiVF is working with eight facilities in clinical trials around the world, including in Israel, Europe and the United States. It plans to launch commercially in 2021.

Ron Maor, head of algorithm research at AiVF, says that AiVF has built its own “bespoke” layer on top of various off-the-shelf AI, ML and deep learning applications. These tools “handle the specific and often unusual aspects of embryo images, which are very different from most AI tasks,” Maor says. 

AiVF’s ML technique involves creating time-lapse videos of developing embryos in an incubator. Over five days, the video shows the milestones of embryo development. Gilboa explains that previous methods yielded just one microscope image per day of the embryo compared with computer vision’s greater image-capturing success.

“By analyzing the video, you could dig out so many milestones and so many features the human eye cannot even detect,” Gilboa says. “Basically you train an algorithm on successful embryos, and you teach the algorithm what are successful embryos.”  

Likely only one embryo out of 10 can be implanted in the uterus. Once a physician implants the embryo, the embryologist will know within 14 days whether the patient is pregnant, Gilboa says. 

“As an embryologist I look at embryos, and I understand what happens to them,” Gilboa says. “If I learn on maybe thousands of embryos, the algorithm would learn on millions of embryos.”

As AiVF’s initial results suggest, computer vision and ML could potentially drive IVF’s prices down—in turn making it less expensive and burdensome for a woman to become pregnant. 

“Once you have a digital embryologist, then you could set up clinics much easier,” Gilboa says. “Or each clinic could be much more scalable. So many more people could enjoy IVF and achieve their dream of having a child.”

IoT Makes Fire Detection Systems Smarter

Post Syndicated from Brian Horowitz original

For years, first responders relied on paper maps to reach a fire in an apartment building or office. Incomplete information would delay firefighters from arriving at an emergency, and false alarms would set them on the wrong path altogether. Dispatchers in 911 centers would receive erroneous information on a problem with a smoke detector rather than a sprinkler switch.

“It gets to the point where you don’t even trust the data,” said Dick Bauer, fire chief for the Killingworth Volunteer Fire Company in Killingworth, Connecticut.

Now cloud computing, mobile apps, edge computing and IoT gateways will enable fire safety personnel to gain visibility into how to reach an emergency.

Remote monitoring and diagnostic capabilities of an IoT system help firefighters know where to position personnel and trucks in advance, according to Bauer. An IoT system tells fire personnel the locations of a smoke detector going off, a heat detector sending signals or a water flow switch being activated.

“You can see a map of the building with the actual location identified where the fire really is, and you can actually watch it spread if you have enough sensors,” said Bill Curtis, analyst in residence, IoT, at Moor Insights & Strategy.

IoT will make systems in commercial buildings work together like Amazon’s Alexa controls lights, thermostats and audio/video (AV) equipment in a home, Curtis said. An IoT system could shut down an HVAC system or put elevators in fire mode if smoke is blowing around a building, he suggested. A mobile app populated with sensor data can provide visibility into emergency systems and how to control specific locations in a building. It provides a holistic view of sensors, controls and fire panels.

Firefighters speeding to the scene will know what floor the fire is on and which sensors the emergency triggered. They’ll also learn how many people are in the building, and which entrance to use when they get there, Curtis explained.

“The more sensors and different types of sensors means earlier detection and greater resolution as well as greater precision on exactly where the fire is and how it is moving,” he said.

How IoT Fire Detection Works

Companies such as such as BehrTech and Honeywell offer IoT connectivity systems that provide situational awareness when fighting fires. BehrTech’s MyThings wireless IoT platform provides disaster warnings to guard against forest fires. It lets emergency personnel monitor the weather as well as atmospheric and seismic data.

On 20 Oct., Honeywell introduced a cloud platform for its Connected Life Safety Services (CLSS) that allows first responders to access data on a fire system before they get to an emergency. It’s now possible to evaluate the condition of devices and get essential data about an emergency in real time using a mobile app.

The CLSS cloud platform connects to an IoT gateway at a central station, which collects data from sensors around a building. CLSS transmits data on the building location that generated the alarm to fire departments. It also provides a history of detector signals over the previous 24 hours and indicates whether the smoke detector had previously triggered a false alarm, says Sameer Agrawal, general manager of software and services at Honeywell.

Agrawal said smart fire IoT platforms like CLSS indicate precisely where an emergency is occurring and will enable firefighters to take the right equipment to the correct location.

“When the dispatch sends a fire truck, the Computer Aided Dispatch (CAD) system will provide an access code that the officer in the truck can punch into an application; that will bring up a 2D model of the building and place the exact location of the alarm,” Agrawal said. “You’re able to track your crews that way, so this really is the kind of information that’s going to make their jobs so much safer and more efficient and take all the guesswork out of it.”

IoT Fire Safety Systems in the Future

Curtis suggests that, as more emergency systems to become interconnected in the future, building managers and workers should get access to these dashboards in addition to firefighters.

“Why not show the building occupants where the fire is so they can avoid it?” Curtis says.

In addition, smart fire detection systems will use artificial intelligence (AI) to detect false alarms and provide contextual information on how to prevent them—and prevent people from being thrown out of their hotel beds unnecessarily at 3 a.m., Agrawal said.

“When next-generation AI comes into play,” Agrawal says, “we start understanding more information about, you know, why was it a false alarm or what could have been done differently.”

An AI-equipped detection system will present a score to a facility manager indicating whether there’s a need to call the fire department. Information on the cause of an event and how first responders responded to past emergencies will help the software come up with the score.

What’s more, the algorithms will help detect anomalies in the data from multiple sensors. These anomalies can include a sensor malfunction, a security breach, or a reading that’s “unreasonable,” says Curtis.