Incorporating-Ai-In Healthcare

Every year, around 50,000 individuals graduate to become certified doctors. In order to maintain the minimum doctor-patient ratio, as suggested by World Health Organization (WHO), India will need 2.3 million doctors by 2030. If there was ever a requirement to push healthcare in India into the future, it is now, says an Indian medical expert.

 “Today is the time when we can see a significant disruption in the Indian healthcare industry. Much of this is credited to the level of involvement of big data, cloud, machine learning and deep learning, wearables or fitness trackers, which connect the organisations with the individuals. To start with, Artificial Intelligence or AI as we call it, has the potential to transform the diagnosis and cure of multiple diseases which were considered incurable a decade ago. Artificial intelligence in the Indian medical industry relies on a paradigm shift in the way the machines read electronic data of patients, including their age, medical history, tests, medical images, DNA sequences, and other factors to fuel treatment,” Amit Sharma, Founder and CEO at eExpedise Healthcare said in a statement. 

AI does the hard work of compiling the complex identification trigger points and creating a pattern out of this data on an intensity level and speed beyond any human being’s capability. AI can take charge of rural areas with a mobile device without having the doctors travel from village to village.

In his book, Deep Medicine, Dr Eric Topol has sited organisations and their role in developing tools to analyse health conditions. One such tool that Google has developed can detect diabetes relatively accurate. The software has a sensitivity score of 87-90% and accuracy of 98% while detecting diabetic retinopathy, says Sharma. His company eExpedise is a healthcare company providing medical treatment services to patients travelling to India, he adds.

“A team of advanced doctors in London have come up with a treatment approach for more than 50 eye diseases having 94% accuracy. To understand the level of precision, their results were compared to that of international eye specialists. As per the reports of this experiment, the doctors missed a few reference points, but the machine didn’t.
In China, on the other hand, Artificial Intelligence is being used to diagnose the presence of polyps on the colon during a colonoscopy. When the diagnosis of a gastroenterologist was compared to that of a machine, the latter had 9% more chances of early detection. The beauty of this experiment was that the machine didn’t miss the tiny polyps, even the ones with a size less than 5mm, which were otherwise easier for the doctors to miss.”

Our mobile phones are performing functions they were designed for and collecting our digital footprints and analysing our behaviour on screen. Even our eye-tracking data collected while we freely watch TV can determine neurodegenerative eye diseases, as cited in an article by Artificial Intelligence in Medicine Journal. In India, young startups are coming together to help doctors diagnose chronic diseases at an early stage. With the help of predictive analytics and machine learning, these startups create diagnostic tools that could help specialists diagnose faster and more accurately. 

A medical wearable startup, ten3T, has developed medical-grade wearable devices attached with a Cicer (device embedded with multiple sensors) to help monitor patient’s health, even at home. mFine, Bengaluru based healthcare startup, has close to 1200 diseases in the system to give an 85% accurate diagnosis. 

Evidently, artificial intelligence and deep learning are the hope of new-age technology, which if correctly harnessed, can help doctors and scientists make better decisions, believes the medical expert. In this month’s Feature Story, we take a look at some of the biggest names currently on the market ranging from start-ups to tech giants applying AI to transform healthcare.

CellCarta

CellCarta, a global provider of precision medicine services, announced recently the acquisition of Reveal Biosciences (“Reveal”), a San Diego California based computational pathology company offering cutting-edge artificial intelligence (AI)-based quantitative pathology and immunohistochemistry services to the biopharmaceutical industry. This acquisition further strengthens CellCarta’s position as a leading provider of histopathology biomarker services and will enable the company to broaden its offering in AI-enabled multi-omic data analysis services and applications.

Reveal Biosciences has created a new generation of Pathology Intelligence™ to enhance research, clinical trials and improve patient outcomes globally. Reveal’s imageDx™ pathology platform combines cutting edge machine learning (ML)-AI with traditional histopathology to transform tissue biology into actionable data. Reveal’s unique proprietary pipeline architecture and biomarker-based training methods also enable the development of scalable custom AI models for specific pathology endpoints, companion diagnostics and predictive models integrating multi-omic data.

“Reveal’s exceptional AI and machine learning capabilities will support more objective tissue biomarker quantitation and will enable a broader and faster deployment of our histological services,” said Martin LeBlanc, CEO of CellCarta He further adds, “Acquiring this leading business is part of a game-changing strategy to expand our services to better support our global clients who are actively seeking more objective, reproducible and scalable methods for tissue biomarker assessment, deployed within a robust quality and regulatory platform.”

ARMMAN

ARMMAN, an India-based nonprofit, is leveraging Artificial Intelligence (AI) to enhance adherence in maternal and child health programs. Initiated in 2020, the project with Google Research India and IIT Madras uses AI to predict the risk of women dropping out of healthcare programs such as mMitra. Along with scientific collaboration, the project was supported with funding from Google Research and Google.org.

India accounts for 11% of global maternal mortality, and a woman in India dies in childbirth every fifteen minutes. However, almost 90% of maternal deaths are avoidable if women receive timely intervention. Access to timely, accurate health information is a significant challenge among women in rural areas and urban slums.

To address this issue, ARMMAN launched the mMitra program in 2013. mMitra is a free service sending voice calls with critical preventive care information directly to women’s mobile phones, covering the period from pregnancy till the child turns one. With Google’s support, a project was launched to increase adherence to mMitra, with an overall goal of improving maternal and child health outcomes. Researchers from Google Research and IIT Madras have been working with ARMMAN to design an AI technology solution that could indicate women at risk of dropping out from mMitra. The early targeted identification helps ARMMAN to personalise interventions for an improved engagement with mMitra. Test results indicate a reduction in the risk of drop-offs by up to 32% for women at high risk of dropping out. So far, mMitra has reached over 2.3 million women in India and is 1 of only 5 scaled mobile-based maternal messaging programs globally.

“We are very happy to execute this project across our mMitra program, supported by Google. We see an immense potential to replicate these learnings from AI across other technology-enabled at-scale programs implemented by ARMMAN,” shared Ramesh Padmanabhan, ARMMAN’s CEO.

Milind Tambe, Director - AI for Social Good at Google Research India, added, “ARMMAN has made tremendous strides on the project with IIT Madras and Google to apply AI to help improve preventive care for mothers and children. Together with Google.org, we’re excited to continue to support them as they continue to scale their work to even greater impact.”

Google Research and ARMMAN are currently working towards scaling this to 300,000+ mothers and children in mMitra, with a goal of eventually reaching 1 million mothers and children.

Ping An Good Doctor

The world’s first AI healthcare system in compliance with international standards was launched. In 2020, Ping An Good Doctor announced that it received the highest level of certification by WONCA, the world’s largest family physician organisation, for its AI healthcare system. The organisation’s first-time awarding the certification to a Chinese medical system symbolises the alignment of China’s intelligent AI health technology with international standards and that Ping An Good Doctor’s AI system meets the world’s highest standards for AI health technologies.

WONCA (The World Organization of Family Doctors) is the world’s largest academic organisation for family physicians and a senior consultant and partner of the World Health Organisation (WHO) in community healthcare. Up to now, WONCA has 118 members and a presence in 131 countries and regions, covers over 90% of the world’s population, and boasts approximately 500,000 family physician members. The WONCA standard accreditation means that Ping An Good Doctor’s AI system can meet the requirements of patients from different countries, offer useful assistance to family doctors around the globe, and serve patients of tens of thousands of families in both hospitals and communities.

For the accreditation, WONCA’s current president, Prof. Li Guodong, led an expert group of German and Danish general medicine experts to give a comprehensive and detailed certification and evaluation on Ping An Good Doctor’s AI system in Shanghai. Overall, it took WONCA’s panel of experts nine months in total to evaluate the AI system of Ping An Good Doctor by looking at 11 key indicators, such as service quality, technical standards, data protection, etc., through a combination of field trips, interviews and research.

Finally, the WONCA panel of experts unanimously agreed to certify Ping An Good Doctor’s AI system. An expert panellist commented that Ping An Good Doctor’s AI system could efficiently help family physicians collect users’ medical history, eliminate the differences in knowledge of general practitioners, and provide a professional reference for family physicians in the form of an initial diagnosis. The WONCA certification of Ping An Good Doctor’s AI system also proves that Ping An Good Doctor’s AI technology is a globally leading provider of timely and high-quality medical solutions for patients from different countries and different cultures, meeting their personalised healthcare needs and providing advanced technical support for family physicians around the world.

The AI system developed by Ping An Good Doctor is equipped with knowledge about 3,000 diseases. Continuously trained with accumulated 670 million consultation data, the system covers the entire consultation process, doubles the efficiency of doctor consultations, greatly reduces the possibility of misdiagnoses and missed diagnoses, and improves patients’ experience with remote medical consultations. During the pandemic, the system had accumulated 1.11 billion consultation records.

Bobble AI

Amid the confusion and a deluge of unverified data circulating on social media related to Covid help, Tech Company Bobble AI claims to provide real-time accurate nationwide information on ventilators, oxygen cylinders, ICU beds, among others, all through the phone keyboard.

The Artificial Intelligence-powered innovation startup, which offers highly engaging smartphone keyboard solutions and personalised content for users, has introduced a section on the keyboard called aceCovid 19 Resources.

It provides information with telephone numbers and addresses segregated into sections: oxygen cylinders, concentrators, ICU beds, ventilators, Remdesivir, plasma donors, among others, the company said in a statement.

The information is being collated on a real-time basis, picked up from government sources and tweets based on Covid related keywords, the company said.

The information can be accessed by all android users with default Bobble Indic keyboard across all over 120 Indic and international languages, along with IOS and users of Bobble’s regional keyboards (including Marathi, Malayalam, Bangla and Hindi keyboards). Users of the platform can also share the links with others.

“The last few weeks have been exceptionally hard, with the second wave of the virus outbreak in the country, and depleting resources. Social media platforms have been filled with people seeking help,” Ankit Prasad, CEO, and Founder, Bobble AI, said in the statement.

“Seeing the massive need to provide essential sources of information and resources inspired us to collate a simple and easy-to-share database of important links for Covid-19 related resources. It is time that each organisation steps up and contributes in their own way in this hour of grave crisis,” Prasad added.

Tech giants in India

Today, only one in 10 people with disabilities globally has access to assistive technologies and products. In May, Microsoft CEO Satya Nadella kicked off “AI for Accessibility” – a $25 million, five-year programme for developers globally, including in India.

The programme has put AI tools in the hands of developers to accelerate the development of accessible and intelligent AI solutions for nearly one billion people with disabilities.

Designed for the low-vision community, one such Microsoft app called “Seeing AI” is harnessing the power of AI to describe people, text and objects. It can tell visually-impaired persons what is around them.

Amazon’s Cloud arm Amazon Web Services (AWS), has an ML service called SageMaker that is helping developers create AI models for health care. GE Healthcare is training computer vision models with Amazon SageMaker that are then deployed in its MRI and X-Ray devices.

Amazon Comprehend Medical is a natural language processing (NLP) service for medical text which uses ML to extract disease conditions, medications and treatment outcomes from patient notes, clinical trial reports and other electronic health records.

Google is also using AI models on smartphones to help the blind. It is working on an app called “Lookout” that uses image recognition and AI to describe a scene through a phone’s camera.

Touted as the world’s “most human” AI assistant, Amelia – created by New York-headquartered AI company Ipsoft – combines automation, cognitive and emotional intelligence with ML capabilities to perform as a digital colleague.

Amelia allows patients to self-manage in scheduling doctors’ appointments, tests and medicines. She also offers condition-specific advice and well-curated health management tips.

As tech giants began training AI for health care, the “AI for Accessibility” dream also reached India in a big way.

In December, Google announced it has developed an AI model that can detect diabetic retinopathy with a level of accuracy on par with human retinal specialists.

Google is working on rolling out this diabetic retinopathy initiative in clinics in India with Verily – an Alphabet-owned company that works on life sciences research and development.

According to Google, the new assistive technology can help doctors and staff screen more patients in less time, sparing people from blindness through a more timely diagnosis.

NITI Aayog, last year entered into a partnership with Microsoft to deploy AI technologies in areas such as agriculture, health care, natural language computing and sustainable environment.

In a novel effort to predict the risk of cardiovascular disease (CVD) among the Indian population, Microsoft India and Apollo Hospitals in August launched the first-ever AI-powered heart disease risk score API (application programme interface).

Part of Microsoft’s “AI Network for Healthcare” initiative, it will help doctors across the Apollo network of hospitals leverage the AI-powered API to predict the risk of CVD and drive preventive cardiac care across the country.

The company also applied AI to devices for the early detection of diabetic retinopathy to prevent blindness. Microsoft India also announced a partnership with SRL Diagnostics to expand the “AI Network for Healthcare” to pathology to detect cancer.

The Telangana government also adopted Microsoft Intelligent Network for Eyecare (MINE), which was developed in partnership with Hyderabad-based LV Prasad Eye Institute. MINE uses ML and advanced analytics to predict regression rates for eye operations, enabling doctors to pinpoint the procedures needed to prevent and treat visual impairments.

The Telangana government is already using Microsoft’s Cloud-based advanced analytics solution to screen children from birth to 18 years of age for major conditions affecting their health.

In October last year, global health technology firm Philips selected 19 startup companies for its first global startup collaboration programme focused on applying artificial intelligence (AI) in healthcare.

The programme focuses on the application of AI-based clinical decision support tools, such as image interpretation, analysis and integration and workflow tools, such as intelligent treatment plans for radiology, ultrasound and oncology.

IBM, last year, joined hands with IIT-Delhi (IIT-D) to partake in a multi-year research collaboration on AI in India, with a focus on sectors such as healthcare and medicine.

According to Nadella, recent advances in AI have been “pretty stunning”, but what the humanity is going to see soon will be even more profound across the spectrum and health care is set to become an AI-first industry.

Health startups join the fight against Covid

Not just the tech giants, health-tech startups too joined the fight against Covid. Recently, health-tech startup Qure.ai collaborated with the international NGO PATH to accelerate and intensify Covid-19 screening by making advanced Artificial Intelligence-based diagnostic technology available to physicians across India through the Telegram App.

Qure’s CE-certified and World Health Organization-endorsed AI solution can read and interpret chest X-ray to detect findings indicative of Covid-19 as well as quantify the proportion of lungs affected due to the lesions.

The technology, which is being used by the Mumbai Municipal Corporation and super-speciality hospitals across the globe, is now available to physicians on the Telegram app.

Qure’s AI bot would enable clinicians to triage for Covid-19 instantaneously. Physicians would only have to download the Qure bot from the Telegram app, upload the patient’s chest X-rays either as DICOMs images or as images taken by the smartphone camera.

The result would be available in less than a minute and would serve as a second opinion or confirmation of diagnosis.

“What we’ve seen in the last few weeks is truly taking a toll on our frontline caregivers and straining our public and private healthcare infrastructure severely. We need to implement and leverage technology that’s been extensively trained and validated to tackle this ongoing tragedy fast and it needs to be now,” said Prashant Warier, CEO and co-founder of Qure.ai, in a statement.

Bengaluru-based Dozee also has launched the MillionICU initiative to address the massive shortage of ICU beds and staff in public hospitals. The initiative will raise funds to upgrade normal beds in government hospitals across India into Step-Down ICUs, using Dozee’s contactless sensor, in under five minutes and enable remote and central monitoring of patients at ward level.

The company aims to install 50,000 step-down ICU beds across India in the next six months and take it to one million in the next three years.The initiative has benefited 25 such hospitals across 15 districts, with more than 10,000 patients being monitored and having saved over 25,000 nursing hours.

“One of the major challenges the Indian health care system is facing a shortage of nurses, doctors and ICU beds. Technologies such as Remote Patient Monitoring and AI can help doctors and nurses save valuable hours by prioritising patients based on their needs,” said Mudit Dandwate, CEO and Co-founder, Dozee, in a statement.

“The MillionICU campaign is an effort to combat the current situation by providing much-needed support to government hospitals in the country. By converting ward beds into step-down ICUs, we aim at upgrading the healthcare infrastructure, thereby enabling improved patient outcomes while significantly reducing the load on nurses and doctors,” he added.

Dozee will also be setting up a 24x7 Central Monitoring Cell, which will enable healthcare staff to monitor multiple patients remotely who were previously monitored manually only every couple of hours.        --- Anisha