In a recent paper, Using Phone Sensors and an Artificial Neural Network to Detect Gait Changes During Drinking Episodes in the Natural Environment, a cross-disciplinary group of researchers at the University of Pittsburgh, found that smartphones and AI can give surprisingly accurate estimations of your blood alcohol concentration (BAC) - with very little data. The researchers needed young adults who drink too much to train the AI. Being on a college campus, they didn't have to look very far. The local emergency department (I'm guessing college infirmary) proved to be a happy hunting ground. Surprisingly - to me - only 10 of severity screeners met the study enrollment requirements.
Automation has been relieving the strain on human hands, backs and knees for generations. But until recently, those whose jobs required high-level cognitive skills have been able to rest assured that no machine or program could possibly replace their ability to make nuanced decisions based on the evaluation of complicated, sometimes conflicting, data. That was before artificial intelligence (AI) rose to the fore. It appears possible--if not probable--that advanced algorithms will one day replace "mid-level" brainpower as well. It begs the question many have already asked: could robots someday replace highly deductive roles such as doctors and nurses?
Healthcare and Artificial Intelligence (AI) are each very much in the news right now. The United States Senate has released draft legislation for the repeal the Affordable Care Act (aka "Obamacare"), leaving some Americans with trepidation about their coverage. Meanwhile, the phrases "machine learning" (ML) and "artificial intelligence" can inspire concerns of their own. What if there were a way to combine healthcare coverage with machine learning to try and make delivery of services not just more efficient (which many worry can be code for "less generous") but more proactive as well? Could this cut costs and enhance care?
Singapore will introduce a new bill mandating all healthcare providers in the country to contribute to the national electronic health record system (NEHR). Launched in 2011, the system was developed to create a central database from which clinical summary records from different providers could be stored and shared to facilitate the delivery of healthcare. Government unveils a new scheme, investing up to S$150 million over five years, to use artificial intelligence to resolve challenges affecting society and sets up data science consortium to drive the sector. Touting the maxim "one patient, one health record", the database is owned by the Ministry of Health and managed by its agency Integrated Health Information Systems (IHIS). Data contribution currently is voluntary for private healthcare licensees and the ministry, over the years, has been encouraging all providers to participate.
The medical billing process is the backbone of healthcare revenue cycle management, but many healthcare providers face challenges in accurately and efficiently billing patients for their services, with an estimated 30 to 40 percent of medical bills containing errors. And those mistakes can be painful--one mistake in medical billing can result in thousands of dollars in mishandled costs for both physicians and patients. The medical billing process requires outstanding communication across departments and payers, as well as ensuring that vital information is correctly captured in each step of the procedure. Efficient medical billing is critical for optimizing healthcare revenue cycle management and driving value-based patient care, but effectively streamlining the process is currently a pain point for the healthcare industry. The Medicare Access and CHIP Reauthorization Act of 2015 (MACRA) is also intensifying the importance of resource effectiveness and quality improvements, and artificial intelligence (AI) can support it in doing so.
Healthcare analytics is evolving from analyzing what has happened (descriptive) to anticipating what will happen given past data (predictive) and, in its most powerful iteration to date, expecting what will happen plus providing proactive solutions based on those predictions (prescriptive). The next step in this evolutionary process is the application of artificial intelligence to healthcare data to help providers make the most effective decisions possible, both financially and clinically. While AI is still in its early stages and has yet to be fully embraced by healthcare leaders, many believe that AI offers tremendous potential for analyzing the vast amount of data generated by the industry. Only 14% of respondents say that their organizations use a software platform that provides an artificial intelligence capability, according to respondents in the 2017 HealthLeaders Media Analytics in Healthcare Survey. However, 35% of respondents say they don't currently have this capability but plan to within the next three years, indicating that there is potential for growth.
Akin to other industries, the healthcare sector is also undergoing the process of embracing artificial intelligence (AI) and machine learning, which provides a potential revolution in operations, patient care, and security. Creators of AI tools focus on AI and machine learning to leverage these technologies to improve the healthcare and other realms. The datasets of the healthcare sector are relatively smaller when compared to other consumer and business applications. Unlike AI tools of other sectors, healthcare AI tools depend on data sets having orders of magnitude much smaller and therefore demands AI developers to possess a deeper understanding of the data and industry knowledge since data interpretation and coding mistakes are amplified in smaller data sets. Additionally, the real world applicability should be a priority.
"For health care practitioners to remain relevant, it really means understanding data," said Dr. Mark Michalski, executive director of the Center for Clinical Data Science at Massachusetts General Hospital and Brigham and Women's Hospital. In fields like medical imaging, he says, "machine learning is going to be central to a lot of what we do." New technologies could improve the ability to detect and diagnose lung tumors or nodules, for instance. The challenge, he says, is incorporating emerging technology into health practice.
Google has made no secret of its overarching ambition to organise the world's information and make it accessible to anyone. And the healthcare industry has no shortage of such information, in any number of repositories and diverse formats, from MRI images to patient notes and data gathered from wearable devices. Google's DeepMind and the NHS: A glimpse of what AI means for the future of healthcare The Google subsidiary has struck a series of deals with organisations in the UK health service -- so what's really happening? Google has long sought to diversify its revenues streams away from search and advertising, the business it was founded on and which continues to make up the bulk of its revenue nearly 20 years later. So could health be the industry that helps the company to achieve that aim?
Modern health systems can treat and cure more diseases than ever before. New technology is bringing innovation to old treatments. Yet significant quality, access and cost issues remain and our health systems are becoming increasingly unsustainable. The emergence and increasing use of artificial intelligence (AI) and robotics will have a significant impact on healthcare systems around the world. How will AI and robotics define New Health?