Blog

Zebras -vs- Horses

Watching the development of a newborn unfold is both exciting and terrifying. As a physician and now parent of a newborn, I can say with certainty that the logical side of me struggles when diagnosing my own child. My baby wasn’t even a day old when I was already convinced that she might have Hirschsprung Disease. Later I learned the nurse had changed her diaper (during my brief nap or rather, collapse, due to pure exhaustion) and forgot to mention her intestines are indeed doing their job. As you progress you learn, as in medical school, to assume the more common problems and be aware of when you should go down the less common diagnosis route. A blocked tear duct in babies can look scary but is relatively common (1 in 25) and often clears by non-invasive methods; babies really do cry relentlessly sometimes and this is completely ‘normal’ - you learn to realize when it’s simply just the trials and tribulations of a growing child- and when it’s not. In medicine this is referred to as the Zebras -vs- Horses Phenomenon - aka look for the most common diagnosis not the most rare first. 


We rely on obtaining as much information about a topic as possible to mitigate risk and unknowns in business and in our daily lives.  That knowledge becomes the backbone of our decision support. The trouble is, there is so much information produced daily, that in our hectic lives we can rarely go through it all, let alone sift through the information to only focus on pertinent knowledge to retain.  But are you finding the most up-to-date information? Is the information you are relying on for your decision support, years or even decades old?

Decision support straight to your inbox

Linguamatics NLP provides an Alerting capability to reduce the time required to review and provide results that are appropriate to your needs. Alerting allows you to schedule NLP search queries to be run at desired intervals, whether it is monthly, weekly, or even daily to keep up-to-date with your newest indexed information. 

This knowledge can be delivered via email to an individual or groups with the most recent and relevant information at your fingertips at all times. This broadens the benefits gained from an NLP approach – recipients of these emails can be across the organization, not just Linguamatics hands-on users.

The range and application of the alerting can be as broad as you need. You are not limited to one question but can schedule as many query alerts as you would like, to differing groups of recipients, as appropriate. This flexibility enables many different groups (e.g. different therapeutic area leads, medical affairs teams, safety assessment groups, to name but a few) to keep up-to-date.


Using NLP workflows to identify key social determinants of health

A year has gone by since I last blogged about the importance of social determinants of health (SDoH). Since then so much has happened in our lives. The COVID-19 pandemic has affected us all, in ways we could never imagine and it will continue to do so into the future.  When you review the SDoH risk factors, you realize that, due to the pandemic, responsible citizens are now enforcing one of these risk factors for safety reasons: social isolation.  It wasn’t too long ago that social isolation was branded a warning sign for mental health issues - not a recommendation for maintaining physical health.  


How research at Kaiser Permanente found that NLP can assist in identifying hospitalizations for worsening heart failure

Heart health is nothing to be taken lightly.  A healthy functioning heart is a key factor in providing every part of your body the blood it needs to provide nutrients and oxygen and remove the waste necessary for life. If there is presence of disease there are times when the heart decompensates, meaning that the heart is no longer able to maintain an efficient circulation allowing for this imperative exchange amongst tissues. According to the Center for Disease Control, in 2017 approximately 6.5 million adults in the United States had heart failure, and it was a major factor of mortality in 1 of 8 deaths. In 2017 it was reported that average wait times for a replacement heart in the U.S. is 191 days, and the cost can approach 1.4 million dollars. So, it is of no surprise that it is better to take care of the heart you have and imperative to capture decompensation as early as possible. Unfortunately, sometimes decompensation can be missed.

NLP workflows in contrast to manual abstraction

Imperative information is often hidden within free text and reports that are attachments within the Electronic Health Record (EHR). A myriad of key cardiology measures can be abstracted from EHRs, be it text based notes to test reports that are PDF attachments, for example: ejection fraction measurement; symptoms such as shortness of breath, fatigue and palpitations; New York Heart Association classifications, and B-type natriuretic peptide (BNP).


In the rapidly evolving fight against COVID-19, IQVIA is committed to deploying our resources and capabilities to help everyone in healthcare do what needs to be done, and to keep things moving forward. Pharmaceutical and healthcare organizations, governments, and the broader scientific communities around the world are working to assess the impact of the virus, and how this can be tackled.

As part of this effort, it’s critical to have access to the best evidence from a broad range of data, including scientific literature, clinical trials and other textual sources. For intelligence from unstructured text, Linguamatics can help. Our Natural Language Processing (NLP) technology enables fast, systematic, and comprehensive insight generation from unstructured text. These sources can include scientific literature, clinical trial records, preprints, internal sources, social media, and news. Capturing key information from these many sources and synthesizing into one place – an Evidence Hub – gives users a deeper understanding of everything that’s going on. This approach can speed answers to key questions to confront the COVID-19 pandemic, such as: