What’s for dinner, Watson?

​Who could possible be able to memorize more than 10,000 recipes, considering tastes and textures of 2,000 ingredients, within different cuisines and special diets and, based on all this, be able to propose instantly more than 16 billions of different combinations? Chef Watson from IBM can. I discovered it recently and I'm already using it to create recipes.  I have so much fun with Watson, I’m now more open to new ingredient combinations and I can expand (not replace) my creativity.

This technology is very intuitive and easy to use: select the ingredients you want to use, the type of dish or occasion (drink, dessert, main, breakfast, etc) and if you want, special diets (such as vegetarian, paleo, gluten free). Then, the proposed recipe can be personalized and of course it has to be tested. Artificial intelligence (AI) does not replace human thinking because these recipes have to be tested and with our feedback Watson keeps learning from us.
Chef Watson works using algorithms which calculate the level of pairing of flavors and based on the psychology of what pleases or not human taste buds. You may find combinations that a priori sound awful, (like combining champagne with milk). But why don’t we try Chef Watson suggestions? Chef Watson helps culinary professionals when investigating new recipes. For those food and nutrition expert who work developing recipes or designing menus in schools or hospitals, Chef Watson can help to do it more efficiently.

Chef Watson is just a sample of the multiple applications that may have systems of AI (such as IBM Watson). AI aims to help people make more successful decisions, based on the analysis of big data. Health care is the main sector where IBM Watson is having greater interest. Centers like New York Genome Institute or Mayo Clinic, are working with IBM Watson to deliver personalized treatments to their patients. "In an area like cancer — where time is of the essence — the speed and accuracy that Watson offers will allow us to develop an individualized treatment plan more efficiently, so we can deliver exactly the care that the patient needs," says Steven R. Alberts, M.D., chair of Medical Oncology at the Mayo Clinic Cancer Center.

Another example, Food Print™ by Nutrino, an app that uses this type of technology, demonstrated a significant reduction of hypoglycemia episodes in patients with type 1 diabetes (presented at the last meeting of the American Diabetes Association). We will increasingly see more AI in nutrition and health. I was a little reluctant at first, but as food and nutrition experts we have to be prepared to use this technology that will help us to do our work better and to empower people to make healthier food choices.  See the following videos for more info.