Technology researchers expect to deliver breakthroughs in the area of cognitive systems within five years, effectively enabling computers to mimic the way humans see, smell, touch, taste and hear. Several of the projected developments will be applicable to healthcare, according to descriptions released Dec. 17 by IBM in its annual "5 in 5" list of innovations that have the potential to change the way people work, live and interact during the next five years.
The predicted sensing capabilities will help us become more aware, productive and help us think – but not think for us, IBM reported. Cognitive computing systems will help humans make more informed decisions and break down multiple barriers — including geographic, distance, language, cost and inaccessibility.
"Just as the human brain relies on interacting with the world using multiple senses, by bringing combinations of these breakthroughs together, cognitive systems will bring even greater value and insights, helping us solve some of the most complicated challenges," said Bernie Meyerson, IBM Fellow and vice president of innovation.
Here are the areas noted as having healthcare implications:
IBM scientists are developing applications for the retail, healthcare and other sectors using haptic, infrared and pressure-sensitive technologies to simulate touch. Utilizing the vibration capabilities of a smartphone, every object will have a unique set of vibration patterns that represents the touch experience: short, fast patterns, or longer and stronger strings of vibrations. The vibration pattern will help simulate the physical sensation of actually touching an object.
Computers today only understand pictures by the text we use to tag or title them; the majority of the information -- the actual content of the image -- is a mystery.
In the next five years, according to IBM, systems will not only be able to look at and recognize the contents of images and visual data, they will turn the pixels into meaning, beginning to make sense out of it similar to the way a human views and interprets a photograph. In the future, "brain-like" capabilities will let computers analyze features such as color, texture patterns or edge information and extract insights from visual media.
Within five years, these capabilities will be put to work in healthcare by making sense out of massive volumes of medical information such as MRIs, CT scans, X-rays and ultrasound images to capture information tailored to particular anatomy or pathologies. By being trained to discriminate what to look for in images -- such as differentiating healthy from diseased tissue -- and correlating that with patient records and scientific literature, systems that can "see" will help doctors detect medical problems with far greater speed and accuracy.
Within five years, a distributed system of sensors will be able to detect elements of sound such as sound pressure, vibrations and sound waves at different frequencies.
Raw sounds will be detected by sensors, much like the human brain. A system that receives this data will take into account other "modalities," such as visual or tactile information, and classify and interpret the sounds based on what it has learned. When new sounds are detected, the system will form conclusions based on previous knowledge and the ability to recognize patterns, IBM reported.
For example, "baby talk" will be understood as a language, telling parents or doctors what infants are trying to communicate. Sounds can be a trigger for interpreting a baby's behavior or needs. By being taught what baby sounds mean – whether fussing indicates a baby is hungry, hot, tired or in pain – a sophisticated speech recognition system would correlate sounds and babbles with other sensory or physiological information such as heart rate, pulse and temperature, IBM explained.
IBM researchers are developing a computing system that will break down ingredients to their molecular level and blend the chemistry of food compounds with the psychology behind what flavors and smells humans prefer. By comparing this with millions of recipes, the system will be able to create new flavor combinations. A system like this could be used to help humans eat healthier, creating novel flavor combinations that will make us crave a vegetable casserole instead of potato chips.
The computer will be able to use algorithms to determine the precise chemical structure of food and why people like certain tastes. These algorithms will examine how chemicals interact with each other, the molecular complexity of flavor compounds and their bonding structure, and use that information, together with models of perception to predict the taste appeal of flavors, IBM reported.
Not only will it make healthy foods more palatable -- it will also surprise us with unusual pairings of foods actually designed to maximize our experience of taste and flavor. In the case of people with special dietary needs such as individuals with diabetes, it would develop flavors and recipes to keep their blood sugar regulated, but satisfy their sweet tooth, IBM noted.
During the next five years, tiny sensors embedded in your computer or cell phone will detect if you're coming down with a cold or other illness. By analyzing odors, biomarkers and thousands of molecules in someone's breath, doctors will have help diagnosing and monitoring the onset of ailments such as liver and kidney disorders, asthma, diabetes and epilepsy by detecting which odors are normal and which are not, according to IBM.
This innovation is beginning to be applied to tackle clinical hygiene, one of the biggest challenges in healthcare today, IBM said. For example, antibiotic-resistant bacteria such as Methicillin-resistant Staphylococcus aureus (MRSA), which in 2005 was associated with almost 19,000 hospital stay-related deaths in the United States, is commonly found on the skin and can be easily transmitted wherever people are in close contact. One way of fighting MRSA exposure in healthcare institutions is by ensuring medical staff follow clinical hygiene guidelines. In the next five years, IBM technology will "smell" surfaces for disinfectants to determine whether rooms have been sanitized.