Powered by increasing healthcare data and the progress of analytics technique, Artificial Intelligence (AI) is bringing a massive shift in the healthcare industry in early detection and diagnosis, treatment, and outcome prediction and prognosis evaluation. From detecting major diseases such as cancer and Alzheimer’s to designing antibiotics, AI tools are increasingly used. It’s more because a discovery process that would take scientists years, the AI system does it in a matter of days, and gives much more accurate results.
It won’t be long before data on patient visits to the clinic, medications prescribed, lab tests, and procedures performed are analysed with data such, Internet search activity logs that contain valuable health information to transform patient care and diagnoses.
AI adoption not only supports improvements in care outcomes, patient experience and access to healthcare services, but increases productivity and the efficiency of care delivery and allows healthcare systems to provide more and better care to more people.
While the use of AI and the Internet of Medical Things (IoMT) in consumer health applications is already helping people, IBM’s Watson is helping healthcare organisations apply cognitive technology to unlock vast amounts of health data and power diagnosis. Beyond scanning health records, AI is helping human medical experts take a more comprehensive approach for disease management, better coordinate care plans.
In India, a country where breast cancer claims over 87,000 lives each year, NIRAMAI Health Analytix, a Bangalore-based deep-tech startup, uses machine learning algorithms, big data analytics and thermal image processing to improve breast cancer diagnosis. The radiation-free, painless, contact-free device addresses most of the problems that conventional mammograms grapple with by reducing over-diagnosis and false positives. The company’s screening tool is said to be able to detect breast cancer based on subtle abnormalities that cells display as the disease begins to take hold.
In the US, using deep convolutional neural networks, researchers from MIT have devised a system that quickly analyses wide-field images of patients’ skin in order to more efficiently detect melanoma, cancer responsible for more than 70 per cent of all skin cancer-related deaths worldwide.
The researchers, using AI, trained the system using 20,388 wide-field images from 133 patients at the Hospital Greg orio Marañón in Madrid and publicly available images taken with a variety of ordinary cameras. Dermatologists working with the researchers visually classified the lesions in the images for comparison. They found that the system achieved more than 90 per cent sensitivity in distinguishing suspicious pigmented lesions (SPLs )from non-suspicious lesions, skin, and complex backgrounds, by avoiding the need for cumbersome and time-consuming individual lesion imaging. According to the researchers, this allows for more rapid and accurate assessments of SPLs and could lead to earlier treatment of melanoma.
There are numerous applications of AI on the market today that can improve patient care and potentially save lives, involving pattern recognition, robotics and natural language processing. For example, Bionik Laboratories use robotics and AI to assist patients in their stroke recovery. A robotic arm and hand use digital algorithms to detect motions that patients can’t execute during therapy and guide them through it.
Last year, a team from Stevens Institute of Technology developed an AI tool to diagnose Alzheimer’s disease that can impact a person’s use of language with more than 95 per cent accuracy, eliminating the need for expensive scans or in-person testing. The AI tool uses attention mechanisms and a convolutional neural network to accurately identify well-known as well as subtle linguistic patterns and signs of Alzheimer’s.
Recently, in a paper, published in Nature Biomedical Engineering, the IBM researchers have detailed how they are using an AI system to automatically generate the design of molecules for new antibiotics. They have already used it to quickly design two new antimicrobial peptides — small molecules that can kill bacteria — that are effective against a bunch of different pathogens in mice.
IBM’s AI system, called a generative model, starts with a huge database of known peptide molecules, from where the AI pulls information and analyses the patterns to figure out the relationship between molecules and their properties. It allows the system to understand the basic rules of molecule design, and eventually, researchers can tell the AI exactly what properties they want a new molecule to have.
In a blog post, the IBM researchers stated how the AI system can potentially accelerate antibiotic discovery and keep antibiotic-resistant bacteria at bay, as they envision it helping scientists “to discover and design better candidates for more effective drugs and therapies for diseases, materials to absorb and capture carbon to help fight climate change, materials for more intelligent energy production and storage, and much more.”
In 2020, DeepMind, the AI research lab, cracked the “protein folding problem” that challenged biologists for almost 50 years, which has implications for drug discovery.
In April, BrainChip Holdings, a leading provider of AI technology, entered into a research collaboration with precision immunology company Biotome in developing highly accurate antibody tests for infections. Cutting-edge neural processors are expected to improve the antibody-tests’ accuracy, identify the antibodies that can protect against Covid-19 infection — the so-called neutralising antibodies, by providing advanced AI capacity at the point of care.
The Healthcare system is struggling globally, more with the ongoing pandemic. It needs a larger workforce. According to the World Health Organization, although the global economy could create 40 million new health-sector jobs by 2030, there is still a projected shortfall of 9.9 million physicians, nurses and midwives globally over the same period. And so, building on automation, artificial intelligence (AI) has the potential to revolutionise healthcare.
The AI-based image analysis tools and cloud-based deployment is now expected to expand the global digital pathology market, estimated to hit $825.9 million by 2025 from $513.3 million in 2019 at a compound annual growth rate (CAGR) of 8.2 per cent, according to Frost & Sullivan’s recent analysis. According to a report by the Center for Internet and Society, investment in AI in the healthcare sector is estimated to add $957 billion to the economy by 2035.
Needless to say, AI advances for problem-solving are yielding exciting benefits, saving a lot of lives as well as improving the experience of healthcare practitioners, enabling them to spend more time in direct patient care.