Real world usage characteristics of a novel mobile health self-monitoring device: Results from the Scanadu Consumer Health Outcomes (SCOUT) Study

A wide range of personal wireless health-related sensor devices are being developed with hope of improving health management. Factors related to effective user engagement, however, are not well-known. We sought to identify factors associated with consistent long-term use of the Scanadu Scout multi-parameter vital sign monitor among individuals who invested in the device through a crowd-funding campaign. Email invitations to join the study were sent to 4525 crowd-funding participants from the US. Those completing a baseline survey were sent a device with follow-up surveys at 3, 12, and 18 months. Of 3872 participants receiving a device, 3473 used it during Week 1, decreasing to 1633 (47 percent) in Week 2. Median time from first use of the device to last use was 17 weeks (IQR: 5–51 weeks) and median uses per week was 1.0 (IQR: 0.6–2.0). Consistent long-term use (defined as remaining in the study at least 26 weeks with at least 3 recordings per week during at least 80% of weeks) was associated with older age, not having children in the household, and frequent use of other medical devices. In the subset of participants answering the 12-month survey (n = 1222), consistent long-term users were more likely to consider the device easy to use and to share results with a healthcare provider. Thirty percent of this subset overall reported improved diet or exercise habits and 25 percent considered medication changes in response to device results. The study shows that even among investors in a device, frequency of device usage fell off rapidly. Understanding how to improve the value of information from personal health-related sensors will be critical to their successful implementation in care.

The full article can be downloaded below.  

The Association Between Medication Adherence for Chronic Conditions and Digital Health Activity Tracking: Retrospective Analysis

Chronic diseases have a widespread impact on health outcomes and costs in the United States. Heart disease and diabetes are among the biggest cost burdens on the health care system. Adherence to medication is associated with better health outcomes and lower total health care costs for individuals with these conditions, but the relationship between medication adherence and health activity behavior has not been explored extensively.

The aim of this study was to examine the relationship between medication adherence and health behaviors among a large population of insured individuals with hypertension, diabetes, and dyslipidemia.

We conducted a retrospective analysis of health status, behaviors, and medication adherence from medical and pharmacy claims and health behavior data. Adherence was measured in terms of proportion of days covered (PDC), calculated from pharmacy claims using both a fixed and variable denominator methodology. Individuals were considered adherent if their PDC was at least 0.80. We used step counts, sleep, weight, and food log data that were transmitted through devices that individuals linked. We computed metrics on the frequency of tracking and the extent to which individuals engaged in each tracking activity. Finally, we used logistic regression to model the relationship between adherent status and the activity-tracking metrics, including age and sex as fixed effects.

We identified 117,765 cases with diabetes, 317,340 with dyslipidemia, and 673,428 with hypertension between January 1, 2015 and June 1, 2016 in available data sources. Average fixed and variable PDC for all individuals ranged from 0.673 to 0.917 for diabetes, 0.756 to 0.921 for dyslipidemia, and 0.756 to 0.929 for hypertension. A subgroup of 8553 cases also had health behavior data (eg, activity-tracker data). On the basis of these data, individuals who tracked steps, sleep, weight, or diet were significantly more likely to be adherent to medication than those who did not track any activities in both the fixed methodology (odds ratio, OR 1.33, 95% CI 1.29-1.36) and variable methodology (OR 1.37, 95% CI 1.32-1.43), with age and sex as fixed effects. Furthermore, there was a positive association between frequency of activity tracking and medication adherence. In the logistic regression model, increasing the adjusted tracking ratio by 0.5 increased the fixed adherent status OR by a factor of 1.11 (95% CI 1.06-1.16). Finally, we found a positive association between number of steps and adherent status when controlling for age and sex.

Adopters of digital health activity trackers tend to be more adherent to hypertension, diabetes, and dyslipidemia medications, and adherence increases with tracking frequency. This suggests that there may be value in examining new ways to further promote medication adherence through programs that incentivize health tracking and leveraging insights derived from connected devices to improve health outcomes.

The full article can be downloaded below.  

2019 HEALTHCARE PROGNOSIS

For the third year running, our smart friends from across the healthcare industry helped us take the pulse of the health IT sector. Our respondents have correctly called both the survival of the Affordable Care Act (even without bugging Justice Roberts’ chambers) and the lack of tangible progress in drug pricing. This year, we re-checked on startup health, technology adoption and regulatory issues while also taking a look at new topics including blockchain and diversity.

The full Venrock findings can be found at this link.  

Why Do Doctors Overtreat? For Many, It's What They're Trained To Do

Medical education is built on the assumption that the more procedures or treatments doctors see and do, the more competent they'll be when they're independent. It can feel tempting to do more rather than less.

But excessive medical tests and treatments can have financial and personal costs. They contribute to this country's rising health care spending and subject patients to anxiety and the risks of extraneous procedures. A group of medical educators thinks this epidemic of overtreatment, as they call it, starts with the habits that doctors develop during training — habits they're hoping to break with new approaches to medical education.

The full NPR article can be read at this link.  

Recommendations on Digital Interventions for Health System Strengthening

A key challenge is to ensure that all people enjoy the benefits of digital technologies for everyone. We must make sure that innovation and technology helps to reduce the inequities in our world, instead of becoming another reason people are left behind. Countries must be guided by evidence to establish sustainable harmonized digital systems, not seduced by every new gadget.

That’s what this guideline is all about.

At the Seventy-First World Health Assembly, WHO’s Member States asked us to develop a global strategy on digital health. This first WHO guideline establishes recommendations on digital interventions for health system strengthening and synthesizes the evidence for the most important and effective digital technologies.

The nature of digital technologies is that they are evolving rapidly; so will this guideline. As new technologies emerge, new evidence will be used to refine and expand on these recommendations. WHO is significantly enhancing its work in digital health to ensure we provide our Member States with the most up-to-date evidence and advice to enable countries to make the smartest investments and achieve the biggest gains in health. Ultimately, digital technologies are not ends in themselves; they are vital tools to promote health, keep the world safe, and serve the vulnerable.

The full guideline from the World Health Organization can be downloaded below.  

Factors that affect the use of electronic personal health records among patients: A systematic review

Electronic personal health records (ePHRs) are web-based tools that enable patients to access parts of their medical records and other services. In spite of the potential benefits of using ePHRs, their adoption rates remain very low. The lack of use of ePHRs among patients leads to implementation failures of these systems. Many studies have been conducted to examine the factors that influence patients’ use of ePHRs, and they need to be synthesised in a meaningful way.

The current study aimed to systematically review the evidence regarding factors that influence patients’ use of ePHRs.

The search included: 42 bibliographic databases (e.g. Medline, Embase, CINHAL, and PsycINFO), hand searching, checking reference lists of the included studies and relevant reviews, contacting experts, and searching two general web engines. Study selection, data extraction, and study quality assessment were carried out by two reviewers independently. The quality of studies was appraised using the Mixed Methods Appraisal Tool. The extracted data were synthesised narratively according to the outcome: intention to use, subjective measures of use, and objective measures of use. The identified factors were categorised into groups based on Orand Karsh’s conceptual framework.

Of 5225 citations retrieved, 97 studies were relevant to this review. These studies examined more than 150 different factors: 59 related to intention to use, 52 regarding subjectively-measured use, and 105 related to objectively-measured use. The current review was able to draw definitive conclusions regarding the effect of only 18 factors. Of these, only three factors have been investigated in connection with every outcome, which are:perceived usefulness, privacy and security concerns, and internet access.

Of the numerous factors examined by the included studies, this review concluded the effect of 18 factors: 13 personal factors (e.g. gender, ethnicity, and income), four human-technology factors (e.g. perceived usefulness and ease of use), and one organisational factor (facilitating conditions). These factors should be taken into account by stakeholders for the successful implementation of these systems. For example, patients should be assured that the system is secure and no one can access their records without their permission in order to decrease their concerns about the privacy and security. Further, advertising campaigns should be carried out to increase patients’ awareness of the system. More studies are needed to conclude the effect of other factors. In addition, researchers should conduct more theory-based longitudinal studies for assessing factors affecting initial use and continuing use of ePHRs among patients.

The full article can be downloaded below.  

Bringing Modern Machine Learning into Clinical Practice Through the Use of Intuitive Visualization and Human–Computer Interaction

The increasing trend of systematic collection of medical data (diagnoses, hospital admission emergencies, blood test results, scans, etc) by healthcare providers offers an unprecedented opportunity for the application of modern data mining, pattern recognition, and machine learning algorithms. The ultimate aim is invariably that of improving outcomes, be it directly or indirectly. Notwithstanding the successes of recent research efforts in this realm, a major obstacle of making the developed models usable by medical professionals (rather than computer scientists or statisticians) remains largely unaddressed. Yet, a mounting amount of evidence shows that the ability to understand and easily use novel technologies is a major factor governing how widely adopted by the target users (doctors, nurses, and patients, amongst others) they are likely to be. In this work we address this technical gap. In particular, we describe a portable, web-based interface that allows healthcare professionals to interact with recently developed machine learning and data driven prognostic algorithms. Our application interfaces a statistical disease progression model and displays its predictions in an intuitive and readily understandable manner. Different types of geometric primitives and their visual properties (such as size or colour) are used to represent abstract quantities such as probability density functions, the rate of change of relative probabilities, and a series of other relevant statistics which the heathcare professional can use to explore patients’ risk factors or provide personalized, evidence and data driven incentivization to the patient.

The full article can be downloaded below.  

Privacy-Preserving Hierarchical Clustering: Formal Security and Efficient Approximation

Machine Learning (ML) is widely used for predictive tasks in a number of critical applications. Recently, collaborative or federated learning is a new paradigm that enables multiple parties to jointly learn ML models on their combined datasets. Yet, in most application domains, such as healthcare and security analytics, privacy risks limit entities to individually learning local models over the sensitive datasets they own. In this work, we present the €first formal study for privacy-preserving collaborative hierarchical clustering, overall featuring scalable cryptographic protocols that allow two parties to privately compute joint clusters on their combined sensitive datasets. First, we provide a formal defi€nition that balances accuracy and privacy, and we present a provably secure protocol along with an optimized version for single linkage clustering. Second, we explore the integration of our protocol with existing approximation algorithms for hierarchical clustering, resulting in a protocol that can efficiently scale to very large datasets. Finally, we provide a prototype implementation and experimentally evaluate the feasibility and efficiency of our approach on synthetic and real datasets, with encouraging results. For example, for a dataset of one million records and 10 dimensions, our optimized privacy-preserving approximation protocol requires 35 seconds for end-to-end execution, just 896KB of communication, and achieves 97.09% accuracy.

The full article can be downloaded below.

Electronic health records are still waiting to be transformed

In 2018, a Stanford Medicine/Harris Poll found that nearly half of U.S. primary care physicians said that electronic health records actually detract from their effectiveness as clinicians, and 44% said they believed that the primary value of these systems is data storage. Far from being a transformative health care tool to support clinical decision-making, a large portion of physicians feel they have traded physical filing cabinets for digital ones.

Electronic health records still have the potential to make health care more predictive, preventive, and precise — but only if we can achieve sustained collaboration among health care providers, technology companies, and health insurers to address their shortcomings. One step in that direction took place on Stanford’s campus last June, where we convened leaders in patient care, technology, design thinking, and policy to discuss a path forward for electronic health records. In principle, the group agreed on three points:

1. First, electronic health record systems must become interoperable.
2. Electronic health records must be redesigned to better respond to physicians’ needs. 
3. Building a more clinically relevant electronic health record system should incorporate artificial intelligence that can synthesize anonymized patient records; combine them with the medical literature; and provide insights at the point of care. 

The full STAT article can be viewed at this link.  

BCBSA Data Analytics Reveal Shifts in Behavioral, Mental Health

The nation’s behavioral and mental health patterns are changing rapidly as patients and providers change their responses to issues such as depression, ADHD, and pain management, reveals large-scale data analytics from the Blue Cross Blue Shield Association (BCBSA).

In a series of data briefs building off the 25th annual Health of America Report, BCBSA explored critical population health trends such as opioid prescribing rates, the treatment of major depression, and the management of attention disorders in pediatric patients.

The full Health IT Analytics article can be viewed at this link.