Image via shutterstock
Imagine a future where a doctor knows exactly which of one their patients might get sick and when. They would know exactly how sick and be able to prescribe a treatment before any problems occurred quickly. This vision of healthcare may not be too far off thanks to recent advancements in applying artificial intelligence within the space.
A recent report from CBinsights outlined more than 90 companies that are using machine learning algorithms and predictive analytics to reduce drug discovery times, provide virtual assistance to patients, and diagnose ailments by processing medical images, among other things.
Misdiagnosis by physicians is a grave and common occurrence in the health industry. Every year an estimated 10 percent to 20 percent of cases are misdiagnosed. These misdiagnoses exceed those of drug and surgery errors on the wrong patient or body part, both of which receive considerably more attention. The repercussions of a misdiagnosis can damage a patient's health, and cost healthcare provides significant amounts of money or even the life of a patient.
A recent study on the Veterans Administration hospital system in Texas estimated that there are at least 500,000 missed diagnostic opportunities that occur out of the 500 million primary care visits that occur annually in the United States.
A new Washington-based startup, KenSci thinks it can solve the problem of missed diagnosis by applying machine learning and artificial intelligence to it. The company, founded by a group of researchers from the University of Washington as well as ex-Microsoft employees. They believe they have found a better, more efficient way to predict health risks by identifying patterns and surfacing high-risk markers. Using a unique blend of modern machine learning and data analysis they can model disease progression and detect potential morbidity as well as predict chronic and critical illness within a group of patients.
The company has developed a kind of "App Store" for medical care complete with 40+ predictive and prescriptive apps targeting Physicians, Care Managers, Hospital Ops and Finance teams. Their claim is what used to take months to build and deploy, can now happen in a matter of weeks at a significant cost reduction regarding both deployment and ongoing platform operation.
The market opportunity is huge. The United States has the biggest healthcare industry in the world, spending approximately $3 trillion a year. By 2018, healthcare will comprise close to 18% US gross domestic product. So even small improvement to this market can have a dramatic effect not only on the lives of real people but on the bottom line for the many healthcare providers who are looking for more efficient ways to manage ever-growing healthcare costs.
One example the company gave was around the question of preventing Sepsis, a potentially life-threatening complication of an infection. Sepsis occurs when chemicals released into the bloodstream to fight the infection trigger inflammatory responses throughout the body. There are more than 750,000 cases of Sepsis every year in resulting in more than 250,000 deaths or 50% of hospital deaths in the US. More than HIV, prostate and breast cancer combined! The most alarming figure is 1 in 3 of these sepsis deaths are entirely preventable.
When it comes to Sepsis as well as other preventable diseases, the answer isn't just prevention, it's prediction. The less time it takes to get antibiotics to patients means more patients that can survive. A platform like KenSci can significantly improve the odds that these types of preventable diseases will be found more quickly and result in more lives saved, which ultimately help all those involved.
Of course, KenSci isn't alone in the emerging Healthcare AI space. Leading the charge is IBM with its Watson platform which they claim can significantly reduce the amount of work healthcare professional need to perform with the help of a kind of virtual assistant there to solve any problems that pop up.
"By 2025, AI systems could be involved in everything from population health management to digital avatars capable of answering specific patient queries." -- Harpreet Singh Buttar, an analyst at Frost & Sullivan.
Microsoft has also announced a collection of new initiatives focusing on using artificial intelligence in health care. The company says its researchers are effectively working to "solve" cancer, deploying machine learning techniques for tasks like analysing tumors and designing new medication regimes. Other Microsoft projects want to construct detailed simulations of how cancer develops in different patients' bodies, while another project -- which Microsoft is calling its "moonshot" effort -- aims to create biological cells that are programmable like computers. Another AI project from Microsoft wants to apply AI to radiology, using machine vision tools to analyse CT scans of tumors.
The opportunity for AI in Healthcare isn't just about making doctors and healthcare providers more efficient in their work; it's about making the lives of the patients better and saving lives is the ultimate business model you can have.