How is your experience at your doctor’s office likely to change? The Human Diagnosis Project (also referred to as “Human Dx”) could be a big factor. Human Dx is a worldwide effort led by the global medical community to build an online system that maps the best steps to help any patient. By combining collective intelligence with machine learning, Human Dx constructs an online map designed to help physicians diagnose illnesses quicker and connect patients to the appropriate specialists. Ultimately, Human Dx intends to enable more accurate, affordable and accessible care for all.
The project is structured as a partnership between the social, public and private sectors. Its partners include the American Medical Association, the American Board of Internal Medicine, the American Board of Medical Specialties, the Association of American Medical Colleges, the Association of Clinicians for the Underserved, the National Association of Community Health Centers and the Dartmouth Institute for Health Policy and Clinical Practice.
Currently, Human Dx includes more than 6,000 doctors across 70 countries. An alliance with some of the country’s largest medical groups offers more weight to the initiative and provides an influx of new users. The project plans to focus its efforts on making specialty care more accessible for patients at safety net hospitals. These patients often delay care because of the high out-of-pocket costs associated with seeing a medical specialist.
Human Dx’s development was inspired by other scientific projects (e.g., the International Space Station, the Large Hadron Collider at CERN and the Human Genome Project) and open technology efforts (e.g., Wikipedia, Linux and the Internet Protocol Suite). The global medical community submits clinical case contributions to Human Dx similar to the way people around the world contribute encyclopedia articles to Wikipedia or engineers contribute code to open source software projects like Linux. This can be done from any connected device. As medical practitioners, residents and students give and receive input on clinical cases within Human Dx, the open system automatically puts their clinical insights into context.
A recent Wired article provides a good example of how it works from a physician’s perspective. When a primary care doctor gets a patient with a perplexing issue, the doctor describes the patient’s background, medical history and presenting symptoms via Human Dx. The doctor may add an image of an X-ray, a photo of a rash or an audio recording of lung sounds. Human Dx’s natural language processing algorithms will mine each case entry for keywords to funnel it to specialists who can create a list of likely diagnoses and recommend treatment.
Since getting back 10 or 20 different doctors’ viewpoints on a single patient can be cumbersome, Human Dx’s machine learning algorithms comb through the responses to check them against all the project’s previously stored case reports. The network uses them to validate each specialist’s finding, weight each one according to confidence level and combine it with others into a single suggested diagnosis. With every solved case, Human Dx gets a little smarter.
Some physicians are skeptical about the quality of information generated by Human Dx. Because of this skepticism, researchers at Johns Hopkins, Harvard and UCSF have been assessing the platform for accuracy and recently submitted results for peer review.
The next big hurdle for Human Dx is money. The project is currently one of eight organizations in contention for a $100 million John D. and Catherine T. MacArthur Foundation grant. If Human Dx wins, the project will spend the money on a nationwide roll out. Human Dx is not dependent upon the $100 million award, but it would certainly be a nice way to kick-start the process.
If all goes well, it is possible your experience will be different the next time you have a medical issue that stumps your regular physician. Instead of seeing a specialist across town, you will see five or 10 specialists from around the country.
(Photo: Doctor with Tablet, Public Domain Pictures)