The Radiologist’s Real Job Description

We often think of innovation as creating new technology, but innovation also comes in the form of new business models, new regulations, and new ways to perform a craft.  Radiologists are in crossroads among a myriad of such “news,” the more comprehensively discussed among which are the reimbursement changes and regulation changes which have been discussed ad infinitum (e.g. here, herehere, and more).

Rather than discussing the impact of the new healthcare regulations on radiology and the emerging high-tech, social-media-connecting, cloud-based, deep learning, big-data-supporting, iPad-friendly, segmentation-compatible solutions , maybe it is worthwhile to take a few minute to think about innovating at a much lower level.  On the level of our job description.

Photo Credit: debspoons; freedigitalphotos.net

Continue reading

The [machine learning] race is on – Don Dennison

Continue reading

Machine learning, real opportunites: Dr. Keith Dreyer’s keynote sets tone for ISC 2016

Dr. Keith Dreyer opens with a keynote during the Intersociety Summer Conference (ISC) with description of data science and overview of how machine learning have evolved over time.

He describes that machines and humans inherently see things differently. Humans are excellent at object classification, recognition of faces, understanding language, driving, and imaging diagnostics. Continue reading

Five way to keep up coding skills when you are a full time radiologist

Radiologists have a day job (or a night job, depending on your precise definition of “radiologist.”) Many people want to learn the syntax of a computer language, while some want to keep up on existing skills.

If your goals are similar to mine, these might help.  Now these are not ways to learn to write code (I’ll write about that later), but ways to brush up on existing skills.

Here are five things to help keeping up your coding skills:

Work on a Project

Most radiology practices can be improved by better use of technology  Continue reading

Two Questions for Four Data Visualization Types, and Why It Matters

QuoteNot long ago, the ability to create smart data visualizations, or dataviz, was a nice-to-have skill. For the most part, it benefited design- and data-minded managers who made a deliberate decision to invest in acquiring it. That’s changed. Now visual communication is a must-have skill for all managers, because more and more often, it’s the only way to make sense of the work they do.

A June 2016 Harvard Business Review article by Scott Berinato discusses the four types of data visualization, in their traditional “boil complex stuff down to a 2×2 matrix” method no less.  In short, what works depends on the level of details necessary to convey the purpose.

Two axes of data visualization – what works best depends on the purpose

The overall concepts are reminiscent of concepts by Edward Tufte and his many, excellent, books on visualization.

The HBR article is worth a read for anyone interested in business intelligence, data analytics, or data visualization (which, as Berinato says, is probably a misnomer – it’s not the visualization that matters, but the question it seeks to answer).

Aside

Quote Cognitive computing, along with its technological brethren artificial intelligence and machine learning are wading into the provider space now. IT consultancy IDC, in fact, predicted that by 2018 nearly one-third of healthcare systems will be running cognitive analytics to extract real-world evidence from patient data that can inform personalized treatment.

HealthcareITNews

Apixio, the company behind Iris, a big data computing platform for healthcare, just secured $19.3 million in venture investment to bring big data analytics to healthcare, a field notorious for its resistance to change.  It’s an exciting time to be interested in healthcare data science – and it remains to be seen how fast and how far we can go.

Source: http://www.apixio.com/

Password strength – something all radiologists should know

While taking a break from studying for the Core Exam, I stumbled upon this 2016 document from Microsoft about password security (yes, in some circles that is considered “taking a break”).

As radiologists, every day we are being asked to type in some sort of authentication username and password at work.  Every other week, we’re asked to change passwords for security reasons.  Every month, we forget one of those 23 passwords we’ve created over the past 3 years for the VA or another affiliated hospital, or some software you’ve not used for a while, or even just plain forgot. Continue reading

Aside

QuoteThe use of the phrase, “Artificial Intelligence” has exploded within the past few years as the theme of dozens of our most popular movies and television shows, magazines, books, and social media. This is despite the difficulty that many experts have in even defining the meaning of the term, “intelligence”, much less “artificial intelligence”.

Eliot L. Siegel, SIIM.org

Artificial intelligence has been too loosely defined and too over-tread by dystopian science fictions to hold a meaningful definition.

I love Bill Gate’s quote, “Most people overestimate what they can do in one year and underestimate what they can do in ten years,” and think it aptly applies to machine learning as well.

Aside

QuoteThe May 2016 iteration of FHIR… has arrived. Most notable among its new capabilities: support for the Clinical Quality Language for clinical decision support as well as further development of work on genomic data, workflow, eClaims, provider directories and CCDA profiles.

FHIR (Fast Healthcare Interoperability Resources) is healthcare’s solution to breaking down information silos. It’s an exciting time to enter medical imaging.

The Paradox of Standardizing Broad Data

Last October, my team started working on a project to bridge the communication gaps between inpatient general medicine and radiology.  Despite having done a full year of internship before starting residency, we quickly realized that as radiologists we knew very little about healthcare is delivered on the wards.  Understanding how well the imaging workflow runs from ordering to reporting, identifying possible delays by systematically analyzing patient data seemed straightforward.

Hypothesized imaging workflow for admitted medicine patients. Source: post author

A 2-hour meeting, eight weeks of delay, and several email exchanges later, we now rely mostly on manual data collection. This blog post is about what happened. Continue reading