Ankur Agrawal

A tribal abstraction network for SNOMED CT target hierarchies without attribute relationships

OBJECTIVE Large and complex terminologies, such as Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT), are prone to errors and inconsistencies. Abstraction networks are compact summarizations of the content and structure of a terminology. Abstraction networks have been shown to support terminology quality assurance. In this paper, we introduce an abstraction network derivation methodology which can be applied to SNOMED CT target hierarchies whose classes are defined using only hierarchical relationships (ie, without attribute relationships) and similar description-logic-based terminologies. METHODS We introduce the tribal abstraction network (TAN), based on the notion of a tribe-a subhierarchy rooted at a child of a hierarchy root, assuming only the existence of concepts with multiple parents. The TAN summarizes a hierarchy that does not have attribute relationships using sets of concepts, called tribal units that belong to exactly the same multiple tribes. Tribal units are further divided into refined tribal units which contain closely related concepts. A quality assurance methodology that utilizes TAN summarizations is introduced. RESULTS A TAN is derived for the Observable entity hierarchy of SNOMED CT, summarizing its content. A TAN-based quality assurance review of the concepts of the hierarchy is performed, and erroneous concepts are shown to appear more frequently in large refined tribal units than in small refined tribal units. Furthermore, more erroneous concepts appear in large refined tribal units of more tribes than of fewer tribes. CONCLUSIONS In this paper we introduce the TAN for summarizing SNOMED CT target hierarchies. A TAN was derived for the Observable entity hierarchy of SNOMED CT. A quality assurance methodology utilizing the TAN was introduced and demonstrated.

Algorithmic detection of inconsistent modeling among SNOMED CT concepts by combining lexical and structural indicators

SNOMED CT is important for clinical applications, such as Electronic Health Record (EHR) encoding. However, inconsistency in modeling its concepts may prevent SNOMED CT from providing proper support for clinical use. This study provides an effective methodology for locating inconsistently modeled SNOMED CT concepts. One can expect lexically similar concepts to be modeled similarly. Positional similarity sets, sets of lexically similar concepts having only one different word at the same position of their names, are introduced. Concepts in such sets have a higher likelihood of being unjustifiably inconsistently modeled. A technique to incorporate three structural indicators into the selected sets is provided to further improve the likelihood of finding inconsistently modeled concepts. An analysis of a sample of 50 such sets and for each of these three indicators is performed. The sample of positional similarity sets is found to have 18.6% inconsistent concepts. The use of structural indicators is shown to further improve the likelihood of finding inconsistently modeled concepts up to 41.6% with high statistical significance when compared to the previous sample of positional similarity sets. Positional similarity sets with different structural indicators are shown to help identify inconsistencies in concept modeling with high likelihood. Furthermore, such sets enable the comparison of concept modeling in the context of other lexically similar concepts, which enhances the effectiveness of corrections by auditors. Such quality assurance methods can be used to supplement IHTSDOs own efforts in order to improve the quality of SNOMED CT.

A contextual auditing method for SNOMED CT concepts

SNOMED CT has been regarded as the most prominent clinical health terminology to be used in Electronic Health Records. However, modelling inconsistencies are preventing SNOMED CT from providing proper support for clinical use. This study introduces positional similarity sets as an effective contextual technique to identify such inconsistencies and improve the modelling of SNOMED CT concepts. Positional similarity sets are sets of lexically similar concepts having only one different word at the same position of their names. A technique to incorporate three structural indicators into the selected sets is provided to improve the likelihood of finding inconsistently modelled concepts. The results show that the likelihood of finding inconsistencies using such positional similarity sets is up to 41.6%. Such quality assurance methods can be used to supplement IHTSDOs own efforts in order to improve the quality of SNOMED CT.

Efficient Video Editing for Mobile Applications

Recording, storing and sharing video content has become one of the most popular usages of smartphones. This has resulted in demand for video editing apps that the users can use to edit their videos before sharing on various social networks. This study describes a technique to create a video editing application that uses the processing power of both GPU and CPU to process various editing tasks. The results and subsequent discussion shows that using the processing power of both the GPU and CPU in the video editing process makes the application much more time-efficient and responsive as compared to just the CPU-based processing.

Developing a Search Algorithm and a Visualization Tool for SNOMED CT

With electronic health records rising in popularity among hospitals and physicians, the SNOMED CT medical terminology has served as a valuable standard for those looking to exchange a variety of information linked to clinical knowledge bases, information retrieval, and data aggregation. However, SNOMED CT is distributed as a flat file database by the International Health Terminology Standards Development Organization and visualization of data can be a problem. This study describes an algorithm that allows a user to easily search SNOMED CT for identical or partial matches utilizing indexing and wildcard matching through a graphical user interface developed in the cross-platform programming language Java. In addition to this, the algorithm displays corresponding relationships and other relevant information pertaining to the search term. The outcome of this study can serve as a useful visualization tool for those looking to delve into the increasingly standardized world of electronic health records as well as a tool for healthcare providers who may be seeking specific clinical information contained in the SNOMED CT database.

Quantifying the Relationship between Hit Count Estimates and Wikipedia Article Traffic

This paper analyzes the relationship between search engine hit counts and Wikipedia article views by evaluating the cross correlation between them. We observe the hit count estimates of three popular search engines over a month and compare them with the Wikipedia page views. The strongest cross correlations are recorded with their delays in days. We present the results in both graphs and quantitative data among different search engines. We also investigate the predicting trends between the hit counts and Wikipedia article traffic.

Automated Menu Recommendation System Based on Past Preferences

Data mining plays an important role in ecommerce in today’s world. Time is critical when it comes to shopping as options are unlimited and making a choice can be tedious. This study presents an application of data mining in the form of an Android application that can provide user with automated suggestion based on past preferences. The application helps a person to choose what food they might want to order in a specific restaurant. The application learns user behavior with each order - what they order in each kind of meal and what are the products that they select together. After gathering enough information, the application can suggest the user about the most selected dish in the recent past and since the application started to learn. Applications, such as these, can play a major role in helping make a decision based on past preferences, thereby reducing the user involvement in decision making.