Two children playing with chalk

An autism diagnostic tool that you can use on your phone is headed toward FDA approval. How does it work? Parents answer several basic questions about their child and then upload a video of their child performing basic tasks at home. Then a machine learning algorithm sifts through the information to predict the likelihood of autism.

What are the implications? It can take a long time for parents to figure out if their children have autism and get them help early enough to make a difference. This tool will help the first problem. The second problem, the shortage of care, is still a concern.

Photo by Tina Floersch on Unsplash

Brown eye

It’s been hot news for the last 24 hours: Google’s developed a machine learning algorithm that can scan images of your eyes and predict your risk of heart disease. While this tech is not ready for clinical use yet (it needs more testing), it holds a lot of promise—it predicts heart disease to about the same level of accuracy as other current medical methods, and it’s fast because testing doesn’t require analyzing blood results.

What are the implications? Once this tool goes live in a medical setting, it’ll save doctors and patients time, time that doctors can use to better treat patients.

Photo by Liam Welch on Unsplash

Piglets romping around

Chinese farmers aim to use machine learning to manage their large swine farms. The tech is similar to, if not the same as, tech we’ve previously mentioned here, like the pig belt that saves piglets’ lives, the AI that detects chicken sicknesses, and the cow-identifying computer vision tool. But beyond using sound-triggered shocking belts to keep mommas from crushing their distressed piglets, identifying when animals are vocalizing their sicknesses, and tracking individual animals with computer vision, these swine farms will also assign some sort of health score to each pig by using data on a pig’s individual daily physical activity and temperature readings from infrared sensors.

What are the implications? Farmers, who have too many pigs to realistically keep track of, will have the help of computer vision to count new piglets on a daily basis and identify each pig’s physical activity. Machine learning algorithms will help save the lives of piglets being crushed and indicate the health of each individual pig.

Photo Found Here:

Old pictures

Maybe you have a photo with a substantial hole in it that you want to fill in, but the section mission is a complex background. This deep learning tool offers an impressive, albeit not perfect, cleanup patch.

What are the implications? People can more easily restore pictures, and photo manipulation becomes easier.

Photo by Mr Cup / Fabien Barral on Unsplash

Burmese temple affected by earthquake

It’s hard to detect smaller earthquakes in areas that have few seismic stations. And the less data you have, the harder it can be. Now, with a convolutional neural network developed by Harvard and MIT researchers, seismologists can better sift through the data to find earthquakes. By feeding the network training sets from seismically inactive regions, the network can identify and disregard regular activity while parsing the data, allowing it to clearly identify tremors.

What are the implications? We can better identify earthquakes and tremors with less data.

Photo Found Here:

Fashionable men standing around

There’s a fashion game that crowdsources fashion sense from its community and then gives it to you: After community members rate which specific items (shoes with pants, pants with shirt, necklace with shirt) go with which other specific items, the app uses that information to create various outfit pairings. Then the community rates which of these outfits are the hottest, allowing everyone to see which styles work and which ones don’t. Machine learning also steps in to offer you ways to complete your outfit, basing its suggestions on data generated by your user community.

It’s not only helpful for you, it’s also helpful for retailers. They can see what trends are hot while the season is moving, instead of gathering outdated data in an industry that moves rapidly. Retailers don’t have to wait for actual inventory to move before they see what people like, and this can save them from buying a product that their customers won’t buy.

Photo by Mariya Georgieva on Unsplash

Person on cell phone

Gmail’s Smart Reply function is coming to Google Hangouts, Facebook Messenger, and WhatsApp. It learns your response style and mimics your linguistic preferences to offer you short, applicable one-tap responses to people you chat with. Some new features of this functionality include silencing your phone when it knows you’re driving and letting people who are messaging you know that you can’t respond right at that moment.

What are the implications? This saves you time, that precious limited resource. It allows you to properly respond to those you chat with while also allowing you to quickly move on to your next task.

Photo Found Here:

Doctor with stethoscope slung over his neck

When dealing with a long-term ailment, like asthma, it means a lot of trips to the doctor. But what if you could reduce those trips by enabling yourself to monitor your symptoms or your child’s symptoms from home? That’s what this wireless stethoscope, StethoMe, aims to do. It monitors heartbeat, body temperature, and lung sounds. If it finds something unusual as it compares those numbers against its repository of information, then it will ping your family doctor. The creators are currently looking for funding to commercialize the tool.

What are the implications? It reports respiratory issues to your doctor faster and saves you time and potentially money by reducing the number of your visits to the doctor.

Photo Found Here:

Lung xray

It’s easy for lung doctors to find larger nodules that are developing into cancer, but often when discovered, those cancerous nodules have advanced too far and the doctors can’t save the patients’ lives. Now there’s an AI that can help doctors identify smaller cancerous nodules earlier. The earlier the detection, the higher the likelihood of patient survival.

What are the implications? Not only does this identify the cancerous nodules earlier and increase life expectancy, but it also saves doctors up to four and a half hours a day in analyzing scans—time that can be used to research cancer treatments and to better treat and communicate with patients.

Photo Found Here:

Girl with Green Hair

Want to try a new hair color but don’t want to spend your money and time only to find out it doesn’t work for you? Take the guesswork out of it by trying this user-friendly app. It realistically shows you what you’d look like with a new hair color.

What are the implications? This app takes the risk out of coloring your hair by giving you a better idea of what that color would look like on you before you take the plunge.

Photo Found Here: