Mobile Technology and Healthcare

Stephen DeAngelis

January 22, 2014

Dr. Bonnie Feldman, Ellen M. Martin, and Tobi Skotnes report, “In healthcare, the data generated by mobile phones and sensors can give us new information about ourselves, extend the reach of our healers and help to accelerate a societal shift towards greater personal engagement in healthcare.” [“The Role of Big Data in Personalizing the Healthcare Experience: Mobile,” Strata, 6 September 2013] Many of the sensors to which the authors refer are helping generate data for the so-called quantified self. Concerning that subject, Serena Westra writes, “There are appearing more applications and tools that help you understand your own behavior in an easy way. This self-monitoring and personal data collecting is often referred to as the quantified self. Never heard of it? Do not worry, co-founder of the quantifiedself.com Kevin Kelly himself has a hard time defining the new concept: ‘I still do not know what the quantified self is, but we are using this whole thing [organizing meet ups and the website] to define it’.” [“The Quantified Self & Big Data: causing a new turn in science?Masters of Media, 8 March 2013] She writes about apps that can monitor what’s happening to your body while your sleep or while you are exercising. To learn more about wearable devices and the quantified self, read my post entitled Wearable Devices and the Quantified Self.

Feldman and her colleagues believe that three trends are coming together to make the quantified self a reality for millions of people. Those trends are mobile technologies, gamification, and sensors. They write:

Mobile is increasingly ubiquitous. With 6.8 billion mobile subscriptions worldwide, access anytime, anywhere through smart gadgets is now putting cheap and connected, mobile computing power in the hands of millions of consumers and healthcare practitioners. Gaming is popular too: 121.3 million Americans play mobile games at least occasionally. Now health apps are using games to improve health and wellness. Gaming elements are bringing deeper engagement, to improve compliance and make managing chronic conditions and complicated regimens easier. Sensors – accelerometers, location detection, wireless connectivity and cameras – offer another big step towards closing the feedback loop in personalized medicine. There is no more personal data than on-the-body or in-the-body sensors. … Sensors used to be exclusive to the laboratory (polysomnography) or hospital (EEG, EKG). Now, body area network applications can be used not only for fitness/wellness, but also to identify, diagnose and manage acute and chronic disease.”

One of the challenges surrounding the quantified self for medical purposes is that most of the collected data is siloed. Only when data is integrated and collected for some period of time does it become truly useful (and then only if someone is capable of analyzing it). Westra continues:

“This all sounds very promising, but there are some questions about this notion. For example, can data be valuable if only one individual is studied and no comparison is made? Are users able to study themselves and can they make sense of the data in an objective way? And can general claims be made out of data about the quantified self? One of the problems that I want to highlight is the massive amount of data that needs to be processed, since each user has its unique dataset. With all the new tools available, researchers are coping with enormous quantities of data produced by and about people, things and their interaction. … In other words, there are a lot of developments going on in the field of data. Quantified self methods provide new insights and perhaps even a new turn in the field of science. However, there are some problems that come along with these new ways of collecting data. Data is not always objective, datasets are often too big, and can have a very social and personal stance. There are of course many more problems and questions to address when talking about the field of the quantified self, big data and personalized search. Nevertheless, it is clear that these topics have a lot in store for the future of research.”

Right now the quantified self movement is really driven by individuals; however, Feldman and her colleagues believe that we are on the cusp of a new mobile health frontier. They note that Big Data generated by new technologies are “contributing new streams of data such as behavioral, biometric, and environmental in real time.” They believe that if healthcare providers can find a way of “combining these new data streams with EMR/EHR data,” and if “patients/consumers [are given] access” to the data, it “may enable us to make better-informed decisions and lead healthier lifestyles.” They continue:

“Mobile is extending the reach of our healers: healthcare providers, fitness coaches, and other supporters. Providers are in desperate need of better educational tools to improve efficiency and lower costs. Physical therapists, fitness coaches, home aides, occupational therapists, discharge planners, doctors, nurses, public health and other health educators are all interested in employing new ways to help patients understand their diseases and take better care of themselves. … Today there are over 96,000 health apps for mobile phones that use sensors, social networking, and gaming to improve health. This explosion includes mobile fitness tracking, support networks, and brain games. … In chronic disease, according to a Misfit graphic, mobile health apps could help over 124 million people with hypertension, 105 million obese adults, 21 million people with sleep apnea, 79 million pre-diabetics, and 81 million adults with cardiovascular disease. The data generated by body sensors and mobile phones can provide a rich new source of insights for patients, providers, and researchers. With their online social communities, companies such as Patients Like Me are using their data to support not only their members, but also new research initiatives in multiple sclerosis and other diseases.”

Feldman and her colleagues are excited about the potential of these technologies because they will permit patients “to be engaged and involved in their own care. Furthermore, an increasing number of healthy people are taking proactive personal responsibility for their own fitness and preventive care. Mobile health tools are enabling us to take better care of ourselves to accelerate a wider adoption of healthier lifestyles and preventive care.” Ben Comer reports that all of these new data streams may one day make better use of predictive analytics in healthcare. He reports, “At Duke University’s Fifth Annual Technology and Healthcare Conference, Eric Siegel, founder of Predictive Analytics World and executive editor of the Predictive Analytics Times called new predictive analytical tools ‘inevitable’ disruptions to the way physicians make treatment decisions and patients receive care.” [“,” PharmExecBlog, 25 September 2013] For some people, it may sound a bit scary (if not deterministic) that personal data could be used to predict future health challenges. Siegel admitted, however, that there are simply too many variables involved for predictive analytics to be used for individual outcomes. He told conference participants that their use is really “more about segmenting risk levels.” Comer notes, “The easiest and most basic form of predictive analysis begins with a decision tree.” He continues:

“In healthcare, the idea is that a … decision tree, based on extensive patient data and clinical drug information might help bring personalized medicine a lot closer to home for many patients. And it might also upend traditional treatment pathways and protocols, since no two people are exactly alike. Siegel said predictive analytics at the patient bedside is ‘inevitable,’ although it could start happening in five years or 20. Not because the technology and methodology isn’t ready for prime time, and not because predictive analysis is too complicated, but because ‘cultural change is hard…we have to learn to trust the machine.’ The three most promising applications for predictive analytics in the healthcare space, according to Siegel, are in the areas of clinical (diagnosis, outcome prediction, and treatment decision-making); marketing; and insurance coverage.”

Clearly, new technologies are having (and are going to have) a large impact in the healthcare field. Big Data analytics, in all its forms, will likely play a role. For consumers, privacy issues are likely to be raised and some consumers may find the collection of extensive personal data too invasive. I suspect such concerns will become secondary after someone becomes sick and all that data can be used to make better diagnoses and result in more personal treatments with fewer side effects.