Artificial Intelligence relates to the concept of machines simulating human intelligence processes such as learning, reasoning, and self-correction. While little debate exists over AI’s potential to revolutionize the modern world, leading tech experts are torn over whether or not an AI future will be gloomy or bright. Elon Musk is a leading skeptic, who once remarked that AI technologies will eventually “destroy humans.” Mark Zuckerberg, on the other hand, is more cheerful about the future of AI, calling Musk’s doomsday predictions “pretty irresponsible.”
While AI is an enigmatic and even frightening modern advancement, many optimistic consumers believe that this technology has the potential to relieve an overburdened workforce, elevate customer service, democratize costly services, and assist in medical breakthroughs. With a market projected to reach $70 billion by 2020, AI advancement is not slowing down. AI innovation in the healthcare industry is particularly rampant, with growth expected to reach a staggering $6.6 billion by 2021. In this article, we explore how revolutionary AI solutions in healthcare are helping to save both human lives and the industry billions of dollars.
Decoding the Complex Genome
Genomics is a branch of molecular biology focused on studying all aspects of the genome or the complete set of genes within a particular organism. Genomics is closely related to the field of “precision medicine,” which is an approach to patient care that encompasses genetics, behaviors, and environment with a goal of implementing a patient or population-specific treatment intervention rather than a one-size-fits-all approach.
Making sense of the enormous amount of data that encodes human life remains a formidable challenge. To help cut down on costs, many researchers are using AI tools to turn the information gleaned from genetic sequencing into life-saving therapies. Genome sequencing refers to identifying and translating patterns within high volume genetic data sets. Machine learning techniques translate these patterns to computer models which predict an individual’s probability of developing certain diseases and help inform the design of potential therapies. Companies are also using AI to achieve greater depth in the interpretation of genetic information such as how an individual’s genes may impact everything from their risk for fatal diseases to their weight, fertility, and so on.
The Toronto-based startup Deep Genomics is leveraging AI to help researchers interpret genetic variation by decoding the meaning of the genome. CEO Brendan Frey was inspired to use machine learning to trace potential genetic causes for disease back in 2002 when his wife was pregnant. While tests revealed that the baby had a genetic problem, doctors and genetic counselors couldn’t pinpoint what it was. “Living with that uncertainty was exhausting—diagnosticians couldn’t make sense of it,” Frey told Business Insider.
Using machine learning technology, Deep Genomic’s AI software recognizes patterns in massive datasets and infers computer models of how cells read the genome and generate biomolecules. In this way, a causal interpretation for genetic variation is provided rather than the simple correlative information given by industry standard techniques. So far, Deep Genomics has used their computational system to develop a database that provides predictions for how more than 300 million genetic variations could affect a genetic code.
Deep Genomics’ approach ultimately opens the door to a wide range of new techniques for classifying, prioritizing, interpreting and linking genetic variants, whether neutral or therapeutic. As Frey says: “The only technology we have for interpreting and acting on these vast amounts of data is AI. That’s going to completely change the future of medicine.”
Accurately Detecting Diseases
When treating life-threatening or debilitating illnesses, early detection is crucial to a successful recovery. A study by Frost & Sullivan reports that AI software has the potential to improve patient outcomes by 40% and save reduce the cost of treatment by as much as 50%.
Google DeepMind is a recent AI development that aims to fight blindness through the early detection of diabetic retinopathy. A common diabetes complication, this chronic disease damages the back of the eye and is the main source of vision loss when left untreated. DeepMind’s co-founder Mustafa Suleyman told The Guardian: “If you have diabetes, you’re 25 times more likely to go blind. If we can detect this, and get in there as early as possible, then 98% of the most severe visual loss might be prevented.” DeepMind’s eye-scanning AI algorithm uses the same machine learning technique that Google uses to categorize millions of web images. By searching retinal images and detecting signs of retinopathy with precision and accuracy, DeepMind might soon replace the most highly trained ophthalmologists.
Furthermore, Ultromics has already developed the world’s most accurate echocardiography AI diagnostics software. The technology extracts over 80,000 data points from a single echocardiogram image and analyzes the information using machine learning. These precise scans are forecasted to boost the detection of coronary heart disease to over 90%. Furthermore, by reducing the amount of misdiagnoses that cost the UK’s National Health Service (NHS) an approximate 600 million pounds per year in needless surgeries, this AI software is forecasted to save the NHS billions of pounds in just a few years.
In Canada, the Toronto-based company Analytics 4 Life focuses on using AI to detect and prevent coronary artery disease (CAD). As current diagnostic methods for CAD are costly, risky, and time-consuming, A4L’s state-of-the-art technology provides a novel method of cardiac imaging. CorVista, A4L’s initial product, non-invasively assesses the presence of significant CAD in a single office visit without radiation, exercise, or pharmacological stressors using physiologic signals naturally emitted by the body. After the signals are acquired, a machine-learned algorithm generates a unique image and a heart model indicating areas of potential heart disease associated with the presence of CAD.
Aiding the Discovery of Impactful Drugs
Drug discovery is arduous and expensive. The process typically entails chemists sifting through tens of thousands of candidate compounds in order to discover only a handful that will be approved for further research. AI’s deep learning algorithm thrives on big data and is therefore perfectly suited for this sort of challenge. Unearthing subtle, molecular patterns in huge databases, AI solutions are speeding up the tiring drug discovery process.
A San Francisco startup Atomwise is the creator of AtomNet, the first Deep Learning technology for novel small molecule discovery, characterized by its unprecedented speed, accuracy, and diversity. Neural networks examine 3D images depicting thousands of molecules that might serve as drug candidates in order to predict their suitability for blocking the mechanism of a pathogen. Screening more than 10 million compounds a day, Atomwise claims that its success rate at identifying potential therapeutic drugs is as much as 10,000 times higher than that of physical high-throughput screening.
In Toronto, Cyclica uses a patented, structure-based and AI-augmented platform, Ligand Express, to offer novel insight and analysis into a drug’s polypharmacology. As stated on the Cyclica website: “By focusing on a small molecule structure and its polypharmacological profile, we distinguish ourselves with virtual screening technologies that are specific for a target protein structure.” These pre-clinical insights and predictions improve current attrition rates of lead therapeutic compounds and improve patient outcomes.
Discovering new treatments for human diseases is an immensely complicated challenge. However, AI machine learning at scale has significant potential to accelerate drug discovery and improve human health.
Enhancing the Patient Experience
AI also has the potential to transform patient experience by vastly improving how patients feel about doctors, hospitals, and healthcare in general. With the emergence and acceptance of wearables and mobile health apps, AI-paired smart devices are expected to play a major role in alleviating some of the strain put on medical service providers.
Computer software technology company Nuance introduced a Computer-Assisted Physician Documentation (CAPD) that uses AI to provide real-time clinical documentation (CDI) guidance to patients throughout their day-to-day lives. The cloud-based solution ensures consistent recommendations and drives everything from appropriate reimbursement to compliance with regulatory requirements to improve quality outcomes.
Rather than tangling a patient in wires and devices or requiring nurses to make time-consuming routine checkups, Studio 1 Labs has created an intelligent bed sheet that produces, measures, and tracks a patient’s essential medical information. The Toronto-based company’s innovative solution to monitoring patient health is pleasantly unobtrusive, requiring no attachments to a patient’s body or in-person assessments. Fabric sensors in the sheet send data to computers that use AI and machine learning algorithms to give doctors real-time information about a patient’s health and wellbeing.
The typical doctor’s visit of the near future will likely start from a patient’s personal smart device, which will already be tracking diet, medications, glucose, and other daily health measurements.
To conclude, Artificial Intelligence has unimaginable potential, specifically in the healthcare sector. McKinsey recently estimated that big data could save medicine and pharma up to $100 billion annually across North American health systems by optimizing innovation, improving the efficiency of research and clinical trials, and building new tools for physicians, consumers, insurers, and regulators to meet the promise of more individualized approaches.
“Based on the extraordinary impact improvements to the healthcare system can have for so many people and its potential to save lives and money, healthcare has become a key industry for investment and efforts for AI and machine learning,” wrote best-selling author Bernard Marr in a Forbes article last year.