Artificial Intelligence has to and will redesign healthcare
No one doubts that artificial intelligence has unimaginable potential. Within the next couple of years, it will revolutionize every area of our life, including medicine. Although many have their fears and doubts about AI taking over the world, Stephen Hawking even said that the development of full artificial intelligence could spell the end of the human race. However, I am fully convinced if humanity prepares appropriately for the AI-age, artificial intelligence will prove to be the next successful area of cooperation between humans and machines.
Concerning healthcare, artificial intelligence will redesign it completely – and for the better. AI could help medical professionals in designing treatment plans and finding the best suited methods for every patient. It might assist repetitive, monotonous jobs, so physicians and nurses can concentrate on their actual jobs instead of e.g. fighting with the tread-wheel of bureaucracy.
Mining medical records is the most obvious application of AI in medicine. Collecting, storing, normalizing, tracing its lineage – it is the first step in revolutionizing existing healthcare systems.
Just look at this picture taken in a Hungarian hospital in the capital city, Budapest. The personnel manages patients’ appointments MANUALLY on a huge black board, and I do not even want to comment on the index-card holder. The whole scene is rather from an early 20th century hospital than a healthcare institution way in the second decade of the 21st century.
State of Affairs in a Hungarian Hospital – Photo Credit: Tamas Meszaros/Index
It is obvious that such systems are unsustainable, and artificial intelligence could offer help. And some entrepreneurs already realized the huge transformative as well as financial potential in medical AI. Researcher Frost & Sullivan said artificial intelligence systems will generate $6.7 billion in global revenue from healthcare by 2021, compared with $811 million in 2015. The market is truly booming, hence start-ups grow out of nowhere like mushrooms. So, let me introduce you to companies which are on the best way to democratize healthcare through artificial intelligence. It is truly worth keeping an eye on them, since they are great partners in building a more transparent and effective healthcare.
Mining Medical Records within Minutes
In the age of Big Data, it is no question how valuable patient data is. When such tech giants as Google or IBM appear in the field of patient data mining, everyone knows, it is something worth doing.
1. Google DeepMind Health
Recently, the AI research branch of the company launched its Google Deepmind Health project, which is used to mine medical records in order to provide better and faster health services. These words are not just empty phrases; Google Deepmind is able to process hundreds of thousands of medical information within minutes. Although research into such data-harvesting and machine learning is in its early phase, at the moment Google is cooperating with the Moorfields Eye Hospital NHS Foundation Trust to improve eye treatment.
Also, Verily, the life sciences arm of Google’s umbrella corporation, Alphabet is working on its genetic data-collecting initiative, the Baseline Study. It aims to use some of the same algorithms that power Google’s famous search button in order to analyse what makes people healthy. This also includes experimenting with disease monitoring technologies, including a digital contact lens that could detect blood sugar levels.
2. IBM WatsonPaths
IBM Watson launched a project called WatsonPaths in collaboration with the Cleveland Clinic Lerner College of Medicine of Case Western Reserve University. WatsonPaths consists of two cognitive computing technologies that can be used by the AI algorithm, Watson, which are expected to help physicians make more informed and accurate decisions faster and to cull new insights from electronic medical records (EMR).
However, the market of AI is full of promising newcomers eager to change healthcare for the better.
A cloud-based predictive analytics platform for health systems and physician organizations: this is the offer of the start-up from Chicago. It is so promising that in August 2016, it secured 4.3 million dollars for financing its operation. Careskore basically predicts through its Zeus algorithm in real time, based on combination of clinical, labs, demographic and behavioural data, how likely a patient will be readmitted to a hospital. Through such data, hospitals are able to improve the quality of care, while patients could also get a clearer picture about their health. Especially if they sign up for Careskore’s personalized, AI-based communication service platform with notifications about their risks and issues.
4. Zephyr Health
After 5 years of mining Johnson & Johnson’s diverse data sets to help physicians identify better therapies, William King launched Zephyr Health in 2011 to help life science companies improve research and reduce the time it takes to bring their therapies to market. The start-up tapped into a rich field with such talent and vision that King was selected as one of 2016’s 100 Most Inspiring People in the life-sciences industry by PharmaVOICE magazine readers. The start-up combines databases, machine-learning algorithms and as its biggest plus, great data visualization to help healthcare companies gain insight into a diverse set of data more quickly.
5. Oncora Medical
The Philadelphia-based start-up aims to help cancer research and treatment, especially in radiation therapy. One of its co-founders, David Lindsay was doing clinical work as an M.D./Ph.D student at the University of Pennsylvania, when he recognized that radiation oncologists had no integrated digital database that collected and organized electronic medical records. So he decided to build exactly that: a data analytics platform that can help doctors design sound radiation treatment plans for patients. And Oncora Medical is thriving! In 2016, the start-up closed a seed round of $1.2 million from investors. In 2017, it plans to roll out their Precision Radiation Oncology platform to three major medical centers to help 10,000 patients receive personalized treatments.
“The remote patient intelligence company”, tells the slogan of the start-up. It actually aims to bring the medical community closer to the future, where smart algorithms tell people they are going to be sick even before they experience symptoms. Sentrian, which was launched two years ago with 12 million dollars, focuses on chronic diseases. Its outspoken goal is to eliminate all preventable hospital admissions through remote patient monitoring. It does this in a two-step process. First of all, it harvests patients’ data from the more and more widely available biosensors, and then to deal with this sea of data, it teaches machines to do the work of a dedicated clinical team, monitoring each patient’s data continually to detect subtle signs that warn of an impending problem.
7. CloudMedx Health
The start-up deep in the heart of the Silicon Valley focuses on optimizing patient and financial outcomes through predictive analytics. CloudMedX utilizes evidence based algorithms, machine learning and natural language processing to generate real-time clinical insights at all points of care to improve patient outcomes. “We are putting physicians back in the seat as physicians as opposed to data entry personnel,” said Co-Founder & CEO, Tashfeen Suleman to Bloomberg in a recent interview. I hope that many others will follow their lead in exempting medical professionals from administrative and data-related burdens.
Disrupting Medical Imaging
Medical imaging encompasses every technique and method with which it becomes possible to represent the inner secrets of the body. X-ray, ECG, MRI, ultrasound, tomography – to name a few of the most commonly known ones. And what comes to your mind when you think about these procedures? Usually a huge, unfriendly room in a hospital with an even bigger, expensive-looking and complicated machine. And if you think that you are awfully right. Also, 60% of the world lacks access to medical imaging exactly because current technologies are unwieldy, expensive, and require extensive training. This is exactly what the following, innovative AI-start-ups want to change.
1. Butterfly Network
Jonathan Rothberg established his start-up, Butterfly Network in 2011 with the goal to create a new handheld medical-imaging device that can make both MRI and ultrasounds significantly cheaper and more efficient. His ultimate aim is even to automate much of the medical imaging process. The bold entrepreneur already sold two DNA-sequencing company. Furthermore, he secured 100 million dollars in 2014 for developing his iPhone-sized scanner that you could hold up to a person’s chest and see a vivid, moving, 3-D image of what’s inside. It will work with a Deep Learning Algorithm trained by ultrasound experts. Although 3 years ago Rothberg promised it will be out in 18 months, we are still waiting for the butterfly to come out of its cocoon. I hope it will happen soon!
The San Francisco-based start-up aims to help laboratories and researchers with its robotic microscopes and machine vision to generate better view about tissues. According to the company’s co-founder and COO Megan Klimen, 3Scan can eliminate some drudgery for drug researchers who have been stuck using manual processes for tissue analysis. And 3Scan’s machine is so efficient that it can do a year’s worth of tissue sample analysis in one day that it would take a pathologist to do in one year using traditional methods, Klimen said.
Enlitic uses the power of deep learning technologies, specifically its prowess at certain forms of image recognition to harvest the data stemming from radiology images and applying it in unique medical cases. Deep learning means actually the process by which a computer takes in data and then, based on its extensive knowledge drawn from analyzing other data, interprets that information.
The start-up’s technology can interpret a medical image in milliseconds —up to 10,000 times faster than the average radiologist. In addition, in June 2016, The Economist reported that in a test against three expert human radiologists working together, Enlitic’s system was 50% better at classifying malignant tumours and had a false-negative rate (where a cancer is missed) of zero, compared with 7% for the humans. Impressive, isn’t it?
Where the cloud, artificial intelligence and medical imaging meets, that is the point of work for Arterys. The pioneering start-up promises to “open medical imaging to the power of the cloud”. Thus, they partnered with GE Healthcare to reform cardiac MRI through their project called ViosWorks. With the new method, the scanning process takes 6-to-10 minutes instead of an hour, and patients do not need to hold breath during the examination. From the records, Arterys’s platform is designed to acquire seven dimensions of data, which include 3D heart anatomy, blood flow rate, and blood flow direction.
5. Bay Labs
Bay Labs Inc., whose launch was communicated last year, uses deep learning to help medical professionals in developing countries interpret ultrasounds so they can better treat heart disease.
In September 2016, Bay Labs and some collaborators took the technology to Africa to help identify symptoms of Rheumatic Heart Disease (RHD) in Kenyan school children. The Bay Labs software analysed data derived from an ultrasound to take a good educated guess as to whether it’s seeing something consistent with RHD. During the trip, medical professionals scanned 1200 children in four days and were able to spot 48 children with RHD or congenital heart disease. Moreover, Johan Mathe from Bay Labs’ said the algorithm performed what usually takes a sonographer few years of training in a few minutes!
Speeding up biological and drug development from years to weeks
Developing pharmaceuticals through clinical trials take sometimes more than a decade and costs billions of dollars. Speeding up the process of drug development and making it more cost-effective through AI technologies would have an enormous effect on today’s healthcare.
It aims to reduce the costs of medicine development by using supercomputers to predict from a database of molecular structures, in advance, which potential medicines will work, and which won’t. In 2015, Atomwise launched a virtual search for safe, existing medicines that could be redesigned to treat the Ebola virus. They found two drugs predicted by the company’s AI technology which may significantly reduce Ebola infectivity. This analysis, which typically would have taken months or years, was completed in less than one day! Imagine how efficient drug creation would become, if such clinical trials could be run at the “ground zero” level of healthcare, namely in pharmacies. I hope it will happen sooner than we think!
2. Recursion Pharmaceuticals
The drug discovery company was founded in 2013 with the purpose to build a proprietary drug discovery platform that combines the best elements of high-throughput biology and automation with the newest advances in AI. The company has already identified novel uses for known drugs, bioactive compounds, and shelved pharma assets in the space of rare genetic disease. They promise to fulfill their ambitious goal of curing 100 diseases in just 10 years; and I whole-heartedly wish them a huge success in doing so.
The company’s mission statement says it aims to become the trusted brand in bringing the public improved health solutions through microbiome interventions. So, you have no idea what microbiomes are? Let me give you an idea about these teeny-tiny organisms! They are defined as all of the microbes that reside on the inside and outside of each individual. A person’s body contains 10-times more microbial cells than human cells. Humans have co-evolved with microbiomes and house many microbes that are beneficial for health. For decades, researchers have known that the microbiome represents a wealth of opportunity in shaping health. But only recently were these genomic and analytical tools made available to make it happen. As a result, Mayo Clinic teamed up with Whole Biome to help women avoid preterm labour through microbiome diagnostic testing.
The only Chinese start-up on our list, iCarbonX has the intent of “digitalizing everyone’s life information”; and it has taken in nearly 600 million in funding. In fact, even the biggest Chinese social media app, WeChat lined up among its supporter, which means the company must be pretty promising.
It basically wants to construct a “digital you” containing biological samples such as saliva, proteins and DNA; bolstered by environmental measurements such as air quality; and lifestyle factors such as workout regimes and diet. The barely more than a year-old company is developing algorithms to analyse the data, with the intention of recommending tailored wellness programs, food choices and possibly prescription medicines.
5. Deep Genomics
Brendan Frey’s company promises to solve the biggest puzzle in genetics. To get to know exactly what information most of the genome could provide. For doing so, Deep Genomics is leveraging artificial intelligence, specifically deep learning to help decode the meaning of the genome. Their learning software is developing the ability to try and predict the effects of a particular mutation based on its analyses of hundreds of thousands of examples of other mutations; even if there’s not already a record of what those mutations do. 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. For this reason, their findings are used for genome based therapeutic development, molecular diagnostics, targeting biomarker discovery and assessing risks for genetic disorders.
A dedicated team of AI developers, medical professionals and bioinformaticians has spent 6 years researching and building an artificial intelligence solution to design personalized treatments for any cancer type or patient faster than any traditional healthcare service. The technology models cell biology on the molecular level; it can identify the best drug to target a specific tumor with, moreover it identifies complex biomarkers and design combination therapies by performing millions of simulated experiments each day.
The key to Turbine’s uniqueness is its molecular model of cancer biology, which it uses to run scores of simulated experiments, guided by an AI to identify the biomarkers that signal sensitivity to treatment. As a result, the technology is already used in collaborations with Bayer, the University of Cambridge and top Hungarian research groups to find new cancer cures, speed up time to market, and save the lives of patients suffering from currently incurable forms of the lethal disease.