A unit of Hitachi Ltd. will launch a business using artificial intelligence to analyze hospital food left uneaten by inpatients to help supply them with nutrients they are failing to take and facilitate their recovery, company officials said Monday.

While AI is already being used in calculating calories and nutrients in meals from images taken before people eat, using AI to analyze leftovers from images is rare, according to officials at Hitachi Solutions Create Ltd., which is set to start the business by the end of March 2019.

Hospitals prepare meals to accommodate each inpatient's medical needs, but if inpatients fail to eat them completely they may not recover from their illnesses or injuries as expected.

To avoid such stalls in recovery, the Tokyo-based company plans to have AI learn what kinds of dish or ingredient each patient tends to avoid and enable hospitals to serve alternative food to make up for missing nutrition.

The company has already begun testing the system at a major hospital in Japan by taking images of leftovers on trays with cameras installed on trolleys for collecting the trays and having AI analyze the images and learn on its own through a method known as deep learning.

[File photo]

Analyzing a complete meal is relatively easy but learning about different patterns of leftovers is technologically difficult. The company will cope with this issue with its own technology, the officials said.

In Japan, nurses usually visually check leftovers for inpatients, but the practice has increased their workload. They also could not conduct thorough analyses of how the foods have been eaten as they are not trained as nutritional experts.

The Japanese government considers AI as a pillar of its growth strategy and has been promoting its development and use in the medical field among others.

Hitachi Solutions Create is also planning to provide a food analysis service in which patients staying at home would take images of their meals by smartphones for AI analysis and receive feedback.

==Kyodo