Identifying risk factors for heart disease over time: Overview of 2014 i2b2/UTHealth shared task Track 2

Abstract

The second track of the 2014 i2b2/UTHealth Natural Language Processing shared task focused on identifying medical risk factors related to Coronary Artery Disease (CAD) in the narratives of longitudinal medical records of diabetic patients. The risk factors included hypertension, hyperlipidemia, obesity, smoking status, and family history, as well as diabetes and CAD, and indicators that suggest the presence of those diseases. In addition to identifying the risk factors, this track of the 2014 i2b2/UTHealth shared task studied the presence and progression of the risk factors in longitudinal medical records. Twenty teams participated in this track, and submitted 49 system runs for evaluation. Six of the top 10 teams achieved F1 scores over 0.90, and all 10 scored over 0.87. The most successful system used a combination of additional annotations, external lexicons, hand-written rules and Support Vector Machines. The results of this track indicate that identification of risk factors and their progression over time is well within the reach of automated systems.

Agile text mining for the 2014 i2b2/UTHealth Cardiac risk factors challenge

“…The range of the F-scores for these categories in figure 8 is 14.5, which represents the second smallest range out of the top 10 participants in the challenge [2]. …”

“…The i2b2/UTHealth 2014 Cardiac Risk Factors Challenge [1, 2] requires document-level annotations for cardiac risk factors such as diabetes, obesity, high blood pressure and smoking status, along with a time attribute for the document.…”

Identification of Risk Factors in Clinical Texts through Association Rules

“…Moreover, the DM capacity for treatment of heterogeneous data sources is increasingly adopted. (Stubbs et al, 2015) (Goryachev et al, 2006). We mention here two more examples how text mining delivers useful information about risk factors and adverse drug events.…”

Counting trees in Random Forests: Predicting symptom severity in psychiatric intake reports

“…To assist decision making, relevant information in such reports needs to be extracted, for which machine learning methods are typically used. This extracted information can be used as input for several applications, such as the identification of diagnostic criteria for heart failure [1, 2] or the prediction of diagnosis and procedure codes [3]. Since the effectiveness of data-driven algorithms not only depends on data size, but also on the quality of data representation, robust information extraction techniques are required [4, 5].…”

“…The second track of the 2014 i2b2/UTHealth shared task [2] hypothesized that, to identify medical risk factors in longitudinal medical records, and in particular to assess the severity of a risk factor, identifying indicators of a disease would be more informative than identifying the actual diagnosis. If hypertension, for instance, can be managed through diet and exercise, it would be considered less severe than when it requires anticoagulants.…”