Google is working on an AI and machine learning model that can read doctors’ handwritten prescriptions which are otherwise difficult to decipher.
(For insights on emerging themes at the intersection of technology, business and policy, subscribe to our tech newsletter Today’s Cache.)
The machine learning model can identify and even highlight medicines within handwritten prescriptions, Manish Gupta, research director, Google Research India, said in a blog post on Monday.
This will act as an assistive technology for digitising handwritten medical documents by augmenting the humans in the loop like pharmacists, according to the blog post.
However, no decision will be made based solely on the output provided by this technology.
The information in the prescription is important for both patients and their healthcare providers, for early diagnosis or self-management. However, they are often handwritten and hard to read.
Even computers find them hard to digitise as they are unstructured, in shorthand, and full of clues for pharmacists to decipher, Gupta said in the blog post.
Google is making substantial investments to develop Responsible AI. It has invested $1 million in grants for the Indian Institute of Technology, Madras, to establish the first of its kind multi-disciplinary centre for Responsible AI.
This centre aims to help researchers, domain experts, developers, community members, policy makers, and others in getting AI right, and localising it to the Indian context.
