Evaluating the predictability of medical conditions from social media posts

We studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 disease categories; it was particularly effective at predicting diabetes and mental health conditions including anxiety, depression and psychoses. Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors. Analogous to the genome, social media data linked to medical diagnoses can be banked with patients’ consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool, and elucidate disease epidemiology. In what we believe to be the first report linking electronic medical record data with social media data from consenting patients, we identified that patients’ Facebook status updates can predict many health conditions, suggesting opportunities to use social media data to determine disease onset or exacerbation and to conduct social media-based health interventions.

The full article can be downloaded below.  

Blockchain In Healthcare: How It Could Make Digital Healthcare Safer And More Innovative

Digital healthcare trends are largely driven by the need for better patient care, faster and more accurate analysis, and on-demand access to medical data. The pace of innovation in digital healthcare began gaining momentum with artificial intelligence (AI), and it is set to further accelerate as the industry turns to blockchain technology.

Blockchain technology is being leveraged to remodel the collaborative exchange of vital research and useful healthcare data, thereby enabling key stakeholders such as clinical researchers, doctors, pharmacists, and other healthcare providers to gain secure, faster, simplified and reliable access to electronic medical information. The industry already has a similar platform called the health information exchange (HIE). Many healthcare technology vendors -- including my company, a medical data and image management cloud-based service -- can integrate with HIE systems.

The full Forbes article can be viewed at this link.  

Approaches for Departments, Schools, and Health Systems to Better Implement Technologies Used for Clinical Care and Education: Best Practices

New technologies create opportunities and challenges that significantly impact education, health care, and business. Leaders in academic health centers and departments of psychiatry already exploring TP (telepsychiatry) or TBH (telebehavioral health) must also consider integrating social media, mobile health, apps, and other emerging technologies related to clinical care, training, faculty development, and administrative missions. Successful implementation of technology requires hands-on leadership, needs assessments, participation by all levels of the organization, and continuous quality/performance improvement to support a positive e-culture. Additional research is needed to develop consensus regarding priorities, prototypes, standardization, and best implementation strategies.

Best Practices

• Assessing Readiness for Change - Institutions have to assess readiness to change at the participant, program, and organizational levels.  Programs need good communication, collaboration, and teamwork.
• Create/Hardwire the Culture - For health care, technology use requires clinical skills, technical support, and team workflow adjustment—so planning and evaluation must cover these landscapes.
• Write Policies and Procedures - The overall administrative approach should attend to process, procedures, policy, and evaluation in order to plan, implement, and manage a program. Input from all levels of the organization—including clinician, manager, and technology stakeholders—should help ensure fidelity to the plan, reduce uncertainty, and improve effectiveness.
• Establish the Curriculum and Competencies - Clinical and administrative-based issues related to care include documentation, EHR, medico-legal, billing, cultural, confidentiality, and privacy.  Implementing an e-culture and teaching associated competencies successfully will likely require a mixture of methods to increase learners’ skill level over time.
• Train Learners and Faculty - All programs will best serve their trainees’ professional development needs by identifying faculty thought leaders or champions of these increasingly important modalities. They can link to others through national educational organizations.
• Evaluate/Manage Change - Change requires leadership and management approaches for technology across multiple clinical, academic, and administrative missions. Change may be facilitated by use of opinion-leader visits and discussions, survey instruments, focus groups, site visits, in-person and on-line courses, and external consultants. Inevitable, foreseen, and unforeseen negative consequences of such disruptions require skillful management.

The full article can be downloaded below.  

More Medical Mega-Breaches Thanks To Third-Party Insecurity

When you hear from a company that “the safety, security and privacy of our customers’ information is our highest priority,” you can be pretty sure that the safety, security and privacy of that data recently got compromised.

Even if the breach didn’t happen directly to that specific company. As cybersecurity experts have been preaching to organizations for years now, even if your own security is rigorous, that’s not enough. If a third party that has access to your data has weak security, you are just as insecure as it is. If it gets breached, you do too.

The full Forbes article can be viewed at this link.  

Transforming healthcare experiences: Exploring the impact of digital health technology on healthcare professionals and patients

The 2019 Future Health Index is based on primary research conducted across 15 countries. The research explores the experiences of healthcare professionals and individuals – which includes both current and previous patients – in their health systems through two pillars of the Quadruple Aim: improved patient experience and improved staff experience.

Evolution and developments in digital health technology, such as digital health records (DHRs), telehealth and artificial intelligence (AI), offer benefits that could lead to better health outcomes and reduced costs, paving the way toward achieving the Quadruple Aim.

This year’s research sets out to understand knowledge and appetite for using digital health technologies and how they affect experiences of healthcare. DHRs, telehealth and AI were selected due to their growing levels of adoption, as well as their potential to transform healthcare experiences.

The full 2019 Future Health Index from Philips can be downloaded below.  

An Overview of Mobile Cloud Computing for Pervasive Healthcare

Mobile devices, along with wearable sensors, allow patients to access healthcare services from anywhere at any time. The longstanding constraints of computational capability and storage space on mobile devices can be alleviated by outsourcing computation- or data-intensive tasks to remote cloud centers. Thus, mobile cloud computing (MCC) has been recognized as a promising approach to provide pervasive healthcare services to people in their daily life. As the development and adoption of MCC techniques in healthcare, new optimization strategies have been explored and studied to help mobile cloud healthcare services to be deployed in a more effective and efficient manner. In this survey, we demonstrate how MCC techniques have been extensively deployed in various healthcare applications and, specifically, describe the general architecture and design considerations one should take into account while designing an MCC for healthcare scenarios. Given a large number of factors that may affect the performance of the MCC and even result in catastrophic consequences in healthcare, this paper presents the state-of-the-art optimization methods on the MCC for meeting the diverse priorities and achieving the optimal tradeoff among multiple objectives. Finally, the security and privacy issues of the MCC in healthcare are also discussed.

The full article can be downloaded below.  

How Startups And Providers Can Drive Transformation In Health Care: Best Practices

All technology improvements are iterative. Even the ones that seem like breakthroughs have taken a long time to come to fruition. For startups and providers that want to capitalize on opportunities in the industry and help to drive it forward, here are three things you must do:

Best Practices

• Understand the landscape - Founders and CTOs should always design their systems in such a way that the data is portable or can be made portable with relative ease. It’s much harder to retrofit tech systems to match new standards than it is to design and build them from scratch in a way that ensures that they’re portable and adaptive to standardization.
• Align with the right partners - Especially given the interoperability issues within the industry, startups will generally be more successful if they align themselves with established players (think Google, GE and IBM Watson Health) to help them navigate a technically and politically divided industry landscape.
• Keep your promises - Health care providers and startups can’t forget their most important asset in pursuit of big data breakthroughs -- the trust of their patients. Moreover, now that the value of patient data has been clearly established, it is a target. No data is ever completely secure, and the more that health care data is aggregated into larger and larger pools, the greater the risk that bad actors will gain access to it, either through hacking or nefarious business practices. As such, providers should anonymize patient data whenever possible, obfuscating all but what is absolutely required to develop requisite insights.

The full Forbes article can be viewed at this link.  

Telehealth, Children, and Pediatrics: Should the Doctor Make House Calls Again, Digitally?

This Article explores the different challenges that arise in incorporating telehealth into pediatrics, especially for entrepreneurs. First, this Article explains how telehealth has been applied, specifically in pediatrics. Next, the Article explores the various legal barriers involving telehealth with particular attention to these issues as they relate to pediatric care, including: Physician-patient relationship, standard of care, informed consent, liability/liability insurance, equipment, and security. This Article then examines the benefits and disadvantages that have been raised in the use of telehealth in relation to pediatric care. Finally, this Article concludes by offering recommendations to those entrepreneurs who hope to have an influence on the future development of telehealth in pediatrics.

The full article can be downloaded below.  

Why It Matters: Prescribers Can Now Access Accurate Medication History Data for Virtually Every American

Surescripts processed 17.7 billion secure health data transactions last year. More than 2.5 billion of those were requests for patient medication history data to be delivered from pharmacies and pharmacy benefit managers (PBMs) directly into care providers’ EHR software.

Continued network expansion and rapid provider adoption of powerful technologies like electronic medication history are a good thing. But what real benefit does high quality medication history data offer? How is this technology helping doctors, nurses and other clinicians deliver safe, efficient and cost-effective healthcare?

I met with Stacy Ward-Charlerie, Manager of Product Innovation, to gain a deeper understanding of the critical role that accurate and complete medication history plays for patients and providers at the point of care.

The full Surescripts article can be read at this link.  

Stites and Pianykh, 2016

OBJECTIVE. Despite the long history of digital radiology, one of its most critical aspects—
information security—still remains extremely underdeveloped and poorly standardized.
To study the current state of radiology security, we explored the worldwide security of
medical image archives.
MATERIALS AND METHODS. Using the DICOM data-transmitting standard, we
implemented a highly parallel application to scan the entire World Wide Web of networked
computers and devices, locating open and unprotected radiology servers. We used only legal
and radiology-compliant tools. Our security-probing application initiated a standard DICOM
handshake to remote computer or device addresses, and then assessed their security posture
on the basis of handshake replies.
RESULTS. The scan discovered a total of 2774 unprotected radiology or DICOM servers
worldwide. Of those, 719 were fully open to patient data communications. Geolocation
was used to analyze and rank our findings according to country utilization. As a result, we
built maps and world ranking of clinical security, suggesting that even the most radiology-advanced
countries have hospitals with serious security gaps.
CONCLUSION. Despite more than two decades of active development and implementation,
our radiology data still remains insecure. The results provided should be applied to raise
awareness and begin an earnest dialogue toward elimination of the problem. The application
we designed and the novel scanning approach we developed can be used to identify security
breaches and to eliminate them before they are compromised.