Jan 252018

 This week’s current CHIDS research highlight is Understanding Development Methods from Other Industries to Improve the Design of Consumer Health IT

Despite the potential power of consumer health IT to allow consumers to become more engaged with and assume greater control over their health management activities, health care consumers have not consistently been eager to adopt the technology. By contrast, consumer products in other industries are very widely used. By identifying design principles and methods that led to the success of other consumer products, and evaluating them so that they may be extended to the design and development of consumer health IT, we may facilitate improved consumer health IT application development and ergo improved consumer health management.

Image result for healthit

Research in cooperation with Westat. Support provided by AHRQ. Designing Consumer Health IT: A Guide for Developers and Systems Designers. (Prepared by Westat under Contract No. HHSA290200900023I.) AHRQ Publication No. 12-0066-EF. Rockville, MD: Agency for Healthcare Research and Quality. September 2012. (PDF, 3 MB). Agarwal R, Anderson C, Crowley K, et al. Improving Consumer Health IT Application Development: Lessons From Other Industries, Background Report. (Prepared by Westat, under Contract No. HHSA290200900023I.) Rockville, MD: Agency for Healthcare Research and Quality. May 2011. AHRQ Publication No. 11-0065-EF. (PDF, 1.47 MB)

Image courtesy of https://www.thenationalcouncil.org/wp-content/uploads/2012/10/HealthIT-270×197.jpg


Dec 112017

 This week’s current CHIDS research highlight is Promoting Better Pain Management Outcomes: Precision Decision Support for Opioid Prescription

Chronic opioid therapy (COT) has been associated with serious adverse outcomes and the social and economic impact of continuing opioid treatment is sizeable. The net effect of COT on a given patient’s health – beneficial, adverse, or neutral – may be difficult to determine ex ante, and affected by many unobservable factors. Given the risks and adverse outcomes associated with COT, many consider COT a care choice of last resort. Thus, to the extent that clinicians need to make decisions regarding whether opioid use will begin or continue, decision support on the individual-patient probability of COT appears critical. Personalized guidelines, built on decision support systems (DSSs), have the potential to influence care at the point of service. Building models that can serve as the foundation of such systems can therefore contribute to changes in physician prescribing. As a result, CHIDS aims to study personalized pain management-related decision support for opioid prescribing. Specifically, CHIDS will apply state of the art machine learning algorithms, as well as more traditional models, to study the feasibility and potential impact of a COT DSS, using a large data set from the U.S. Army. CHIDS will further investigate the economic impact of such decision support. The National Institute for Health Care Management (NIHCM) is helping support this work through its Research Grants program.

Image result for \Opioid Prescription

For more about ongoing research at CHIDS, check out our website here:


Published by Margret Bjarnadottir, Ritu Agarwal, Kenyon Crowley, Al Nelson, Kislaya Prasad

Dec 022017

This week’s current CHIDS research highlight is Digital Therapeutic Assessment and Development.

Mobile personal devices, health engagement technologies and analytics have the potential to play a transformative role in improving healthcare delivery and health outcomes by facilitating greater patient engagement and involvement in their own health, with personalization having effects. Vheda Health has developed a digital solutions portfolio targeted at chronic diseases like diabetes and congestive heart failure. CHIDS is working with Vheda to evaluate its product in field trials and help create a prescriptive analytics capability, which generates automated care plan recommendations for patients based on data collected from interactions, biometrics, and outcomes database of patients who previously completed the intervention.

For more about ongoing research at CHIDS, check out our website here:



Published by Gordon Gao, Kenyon Crowley, Michelle Dugas, Ritu Agarwal, Margret Bjarnadottir

Sep 272017

This week’s current CHIDS research highlight is Vocal Minority and Silent Majority: How Do Online Ratings Reflect Population Perceptions of Quality?

Consumer-generated ratings typically share an objective of illuminating the quality of a product or service for other buyers. While ratings have become ubiquitous and influential on the Internet, surprisingly little empirical research has investigated how these online assessments reflect the opinion of the population at large, especially in the domain of professional services where quality is often opaque to consumers. Building on the word-of-mouth literature, we examine the relationship between online ratings and population perceptions of physician quality. Our study builds on prior work by leveraging a unique dataset which includes direct measures of both the offline population’s perception of physician quality and consumer-generated online reviews. As a result, we are able to examine how online ratings reflect patients’ opinions about physician quality. In sharp contrast to the widely voiced concerns by medical practitioners, we find that physicians who are rated lower in quality by the patient population are less likely to be rated online. Although ratings provided online are positively correlated with patient population opinions, the online ratings tend to be exaggerated at the upper end of the quality spectrum. This study is the first to provide empirical evidence of the relationship between online ratings and the underlying consumer-perceived quality, and extends prior research on online word-of-mouth to the domain of professional services.


Image result for quality online rating

For more about ongoing research at CHIDS, check out our website here:



Published by Gordon Gao, Brad Greenwood, Ritu Agarwal

Sep 212017

Social influence in the form of social norms has been widely used to transform behaviors, and is argued to be especially efficacious in the context of health related activities. However, can such externally induced compliance produce negative outcomes? When individuals feel compelled to conform to the behavior of the majority, does it lead to an unexpected backfire effect? We conducted a randomized field experiment of more than 10,000 individuals for a two-month period on an online physical activity community to examine if there is a dark side to social influence. We studied the effect of social norms on users’ goal setting and goal achievement behavior. While social influence increases the rate of goal setting, strikingly, we also observe a dark side to social influence in that such influence yields lower rates of goal achievement. Our findings have important implications for the design of interventions in the context of mHealth technologies.

Image result for social influence

 Read the paper here!

Published by Che-Wei Liu, Gordon Gao, Ritu Agarwal

Aug 312017

Ever since the advent of the smartphone, the idea of using commercial portable technology to monitor and improve individual health and fitness has caught the imagination of healthcare innovators.  The evolution of new digital health tools has allowed an increase in user engagement and provided a doorway to personal health beyond the professional provider.  Phones, smart watches, and dedicated wearables are able to monitor, record, and measure items such as heart rate, steps, and blood sugar.  They have been built up to a highly personalized level of sophistication.  

The technology is available, but the missing component is the clinical studies and results.

With so many different products available to the public, there has been difficulty establishing a baseline for an effective telehealth product.  As stated by Eric Bender in his article Putting Digital Health Monitoring Tools to the Test, “many early attempts to truly test the efficacy of such digital technologies have shown them to be a flop in clinical trials — in large part because participants drop out. An analysis of five health apps built with Apple iPhone software, for example, found that only about one-eighth of participants, or less, were still hanging in after 10 weeks. Another recent study out of Singapore found that about 200 people outfitted with fitness trackers showed no better health outcomes than a similar control group after a year. And when Cedars-Sinai Medical Center in Los Angeles invited about 66,000 patients registered on its portal to share data from their fitness trackers, less than 1 percent did so, according to a paper published last year in the journal PLOS One, part of the open-access Public Library of Science.”

Technology is a touchpoint where health professionals can reach patients consistently.  Both the public and private sector are keen on finding out how these new devices improve public health and behavior, but until then, the effectiveness of each tool is up to speculation.  

Image result

For further reading on the development of , follow the links and resources below!


Putting Digital Health Monitoring Tools to the Test






Aug 262017

How far is artificial intelligence from carrying out a medical diagnosis?  AI is a buzzword in the HealthIT field, but its potential has yet to be fully realized.  According to a study published in June, “mobile devices can potentially extend the reach of dermatologists outside of the clinic”.  Much of skin cancer is diagnosed visually, and researchers attempted to determine the ability of a cell phone camera to detect and diagnose symptoms through a dermoscopic analysis.  The researchers noted that many initial results didn’t yield accurate recognition, but after a large sample size had been accumulated there was a rise in the number of correct determinations of skin cancer.  It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021, and using these mobile devices as instruments to detect carcinomas and other visually prominent health issues can be a huge step forwards in solving a lack of medical practitioners in remote areas of the globe. 

Despite the promise that developing technologies are showing, there are surprisingly few practical areas where healthcare is currently being applied.  Currently there are too few outlets where both the developing technology and current workflow with patients are in alignment.  This has relegated much of the evolution of artificial intelligence to the research realm only.  In an article by Evan Sweeney, “data scientists at Booze Allen Hamilton and an emergency physician at Georgetown University School of Medicine highlighted these shortcomings in an article for Health Affairs, highlighting the fact that EHRs don’t have the capability to use machine learning or cognitive computing, and a lack of robust outcome data is holding back third-party applications.

In the short term, the most practical applications for AI may reside in taking on “mundane” data-driven tasks, like reviewing patient charts. To make use of AI’s capabilities in the long term, the healthcare industry needs to find ways to “feed extremely data hungry” with more robust and useful information on clinical outcomes that are not common in EHRs today.

“While we believe machine learning holds great promise, it is far from clear how it will transform health and health care in the short to mid-term,” the researchers wrote. “Today, policy makers and industry executives face decisions about when and how to invest in machine learning to optimize organizational effectiveness and efficiency without wasting capital funds on premature or nonvalue-adding technologies.””

For further reading on the growth of Artificial Intelligence, follow the links and resources below!







Jun 302017

Having already been a third party vendor for health care products over the past decade, Amazon is considering expanding its scale of distribution in health care industry.  From online bookstore to a behemoth commerce company, Amazon has the consumer market necessary for such a jump.  But what are the implications for other distributors of medical supplies?  

Amazon’s brazen introduction into the field could awaken increased competition among other distributors, something that would bring costs down and encourage innovation.  The intricacies of health care as an industry are complex, and may take a long time for any new challenger to overcome, but the logistics and infrastructure are already in place for Amazon.  

Through the rapidly expanding initiative called Amazon Business, a wide selection of medical supplies, from sutures to beds, have been made available over the past year.  According to Amazon executives, Amazon Business has generated roughly $1 billion in sales and is poised for continued growth.  In a February 2016 report, the US was estimated to have an annual 4.2% increase in the sale of disposable medical supplies, raising the market to $54.1 billion by 2020.  Groundbreaking research has lead to the creation of new products based on improved materials and designs that will benefit growth.  However, many of these developments in minimally invasive and noninvasive techniques will reduce the need for disposable medical supplies. This shifts the balance of funding from replaceable materials to permanent equipment.  Capitalizing on this, Amazon has also made moves into the pharmaceutical industry, recently hiring health care experts and listing job openings for similar positions.  Will the next evolution of health care be labelled with Amazon Prime?

Further Reading:





May 092017

The Fitbit has been around since its inception in 2007, and the entire market of modern wearables followed its release.  Currently, roughly 21% of the US population owns wearable technology, but according to Ben Wood, an analyst from CCS Insight, “the reality is these devices have stalled in the marketplace.” How do current healthcare systems benefit from this popular platform, and what is the next step in wearable electronics?  

The biggest pro of health wearables is their instantaneous single-parameter measurement, transmission, and collection of data.  Smart wearables have the potential to offer an unobtrusive, 24/7 platform for specialized health services.  Not only is it accessible and high-quality monitoring for potential patients, but it is also a cost-effective solution. The current technological development is of a high level; however, several issues still remain open.

Beyond advances in technology, the real challenge that prevents the effectiveness of wearables is the clinical validation and flow of data into electronic health record (EHR) systems.  Much of the information stored on these devices is simply not configured to a format that physicians can use.  While there is software available that can sync the two systems, this process is often too slow or cumbersome for potential time constraints.
Standardization and interoperability in the succeeding generation of smartwatches and devices is the next big step towards improving a patient’s lifestyle.  It is very important to have simultaneous access to different kinds of health-related data, such as patient’s health record.  This would give health professionals the much needed ability to remotely monitor and treat the health of an individual according to their personal health status.  Easy communication between the device to the health provider is a step towards improving disease prevention and rehabilitation standards.  






Apr 142017

With the advent of the iPhone, mobile medical applications have increased in use for both patients and consumers.  Companies capitalize on the relative cheapness of iOS development to build platforms around mobile health and fitness, and a plethora of these apps are available on the market now.  Catchphrases such as “scientifically proven” and “medically tested” abound in many of these consumer marketed applications, but oftentimes the evidence to back up these claims are absent.  Regulation and accountability of the mobile world has become somewhat of a grey zone in terms of who should control the screening and vetting process.  Federal departments, such as the Food and Drug Administration (FDA) and Federal Trade Commission (FTC), have historically limited their jurisdiction to specific medical topics.  This begs the question: who is responsible for this regulation?    

Recently, state regulators have started investigating the claims of many fitness and health applications to ascertain their correctness.  The Office of the Attorney General of New York (NYOAG) has cracked down on many of the heart rate monitoring apps and the marketing claims they have promoted.  One such application is Cardiio, a heart rate monitor that advertised to “measure your heart rate, learn how the numbers relate to your general wellness, perform effective workouts to get in shape, and track your progress” in addition to calculating life expectancy based on heart rate.  The NYOAG found that Cardiio, Inc.’s assertions that Cardiio-Heart Rate Monitor can calculate a user’s potential life expectancy and estimate how the user “stacks up” against “the average person” in the USA did not contain sufficient disclosures that these calculations were hypothetical and estimates not intended to measure accurately life expectancy.  As a result of the investigation, many changes were made to the original application to notify users that the data was not always accurate.  The emboldened tag, “The Cardiio app has not been tested with individuals with health conditions…and has not been cleared or approved by the U.S. Food and Drug Administration” is a reminder to be wary of the advertised benefits of healthcare apps.   

An important outcome of the recent claims settled was the methods used to categorize the variety of medical applications in the app store.  Medical devices are separated into classes by the FDA, ranging from low risk Class I devices such as dental floss, to higher risk Class III apparatus such as a heart replacement valve.  Many medical mobile applications have been moved from Class I to Class II, representing a greater amount of regulation and control.  While mobile applications provide a faster and more adaptable method of healthcare support, we should be aware of the evidence necessary to show their effectiveness and safety.




Assurance of Discontinuance with Cardiio, Inc.