AI learns Hindi: How a health website achieved 86% accuracy in medical diagnosis

The mobile healthcare market in India is booming. It’s set to expand at a compound annual growth rate of 31%, reaching INR 13,800 crore by the end of 2024, according to the report “Healthcare Apps Market in India 2019” from Research and Markets. The COVID-19 outbreak has only catalysed the sector’s rapid growth.

Urban India is no stranger to online heath consultation thanks to the likes of Practo and WebMD. Now, though, online healthcare companies are seeing increased traction in tier-2 and tier-3 cities too.

In fact, it’s smaller cities, and not metros, that are now the biggest growth drivers in the health insurance domain.

Two Stanford graduates, Rajat and Manuj Garg, identified the business opportunity these cities represented in 2016, and created myUpchar to meet the need for reliable healthcare consultation.

More recently, with the increase in demand for online health consultation, myUpchar turned to AI to improve the efficiency of registered doctors in their network by examining patients’ inputs, combining them with their existing data, and suggesting a diagnoses to the doctors.

rajat garg co founder ceo myupchar myUpchar

Rajat Garg, co-founder and CEO of myUpchar

Rajat Garg, CEO and co-founder of myUpchar, said that the company has done over 10 lakh free consultations and this turned out to be a source for quality data.

“This data, along with our research, is used to provide the right diagnosis and medications for the queries. Our system then analyses user inputs which are combined with our data to generate a diagnosis and prescription,” he explained.

He added that the technology helped achieve a high accuracy level which decreased the time per consultation to 1–2 minutes.

The linguistic challenge

Garg said that the foremost concern was the scarcity of research in the Hindi AI space. Choosing the right kind of AI technology was a crucial task and

Accuracy of England and Wales convictions on police computer questioned after ‘slip’

The accuracy of convictions stored on the Police National Computer (PNC) has been questioned after the courts service apologised when two offences were wrongly recorded against a defendant.

Photograph: Jonathan Brady/PA

© Provided by The Guardian
Photograph: Jonathan Brady/PA

The error led to a woman who had not at that stage been tried gaining a criminal record for offences relating to a violent crime she denied, and took three months for her lawyers to correct. It was dismissed by HM Courts and Tribunal Service as a “slip”.

a clock tower in the background: The mistakes are understood to have been due to human error when information that updated the PNC was wrongly entered by court staff.

© Photograph: Jonathan Brady/PA
The mistakes are understood to have been due to human error when information that updated the PNC was wrongly entered by court staff.

The case, which recently came to trial, highlights the fact that mistakes can occur in the system that is supposed to be the ultimate authority on criminal records in England and Wales.

A lawyer involved in the case reported hearing of other mistakes on the same day. Checks are supposed to be in place to ensure criminal convictions are correctly recorded.

Three months after the convictions were entered on to the PNC, the courts service, HMCTS, sent the woman a letter apologising for the error.The Guardian is not identifying the individual affected.

It stated: “Very occasionally, there can be a slip in the digital system. Our records suggest that this must unfortunately have applied on … in your case.”

The letter said a detective inspector “has been notified to take corrective action of the Police National Computer Records”.

On the day on which her guilty pleas were entered on to the PNC, the defendant had not even been to court. The letter added: “I apologise on behalf of HMCTS for the error made and any anxiety caused.”

When the case eventually came to trial the defendant contested the allegations.