Limits...
Information discovery on electronic health records using authority flow techniques.

Hristidis V, Varadarajan RR, Biondich P, Weiner M - BMC Med Inform Decis Mak (2010)

Bottom Line: As the use of electronic health records (EHRs) becomes more widespread, so does the need to search and provide effective information discovery within them.Querying by keyword has emerged as one of the most effective paradigms for searching.We compare the effectiveness of two fundamentally different techniques for keyword search of EHRs.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing and Information Sciences, Florida International University, Miami, Florida, USA. vagelis@cis.fiu.edu

ABSTRACT

Background: As the use of electronic health records (EHRs) becomes more widespread, so does the need to search and provide effective information discovery within them. Querying by keyword has emerged as one of the most effective paradigms for searching. Most work in this area is based on traditional Information Retrieval (IR) techniques, where each document is compared individually against the query. We compare the effectiveness of two fundamentally different techniques for keyword search of EHRs.

Methods: We built two ranking systems. The traditional BM25 system exploits the EHRs' content without regard to association among entities within. The Clinical ObjectRank (CO) system exploits the entities' associations in EHRs using an authority-flow algorithm to discover the most relevant entities. BM25 and CO were deployed on an EHR dataset of the cardiovascular division of Miami Children's Hospital. Using sequences of keywords as queries, sensitivity and specificity were measured by two physicians for a set of 11 queries related to congenital cardiac disease.

Results: Our pilot evaluation showed that CO outperforms BM25 in terms of sensitivity (65% vs. 38%) by 71% on average, while maintaining the specificity (64% vs. 61%). The evaluation was done by two physicians.

Conclusions: Authority-flow techniques can greatly improve the detection of relevant information in EHRs and hence deserve further study.

Show MeSH

Related in: MedlinePlus

Sample explaining sub graph of an ObjectRank2 result - HospitalizationID 2406 for query "respiratory distress". Figure 6 displays an explaining sub graph for HospitalizationID 2406 for query "respiratory distress". The figure gives a better picture of why this entity was ranked higher for query "respiratory distress" and its relationship with other entities that contain the query keywords. Detail descriptions of each entity are displayed as tool tip texts when the user points at them.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2984470&req=5

Figure 6: Sample explaining sub graph of an ObjectRank2 result - HospitalizationID 2406 for query "respiratory distress". Figure 6 displays an explaining sub graph for HospitalizationID 2406 for query "respiratory distress". The figure gives a better picture of why this entity was ranked higher for query "respiratory distress" and its relationship with other entities that contain the query keywords. Detail descriptions of each entity are displayed as tool tip texts when the user points at them.

Mentions: We briefly describe what happens when the user clicks the "Adjacent Entities" link, which "explains" the result. We believe that when complex ranking methods like BM25 and CO are employed, the users need information about why certain results are ranked high. Varadarajan et al. [29] described a novel technique to explain the results of authority-flow based techniques. For both CO and BM25 methods, we provide an "adjacent entities" link that pictorially explains each result. In the case of CO, an explaining graph is displayed using the principles described in [29]. For BM25, a similar explaining graph is displayed by including all entities that neighbor the target entity and also contain the query keywords. Figure 6 shows the explaining graphs, as shown in our user interface for CO. It might be easy to just view the Figure as a sub graph where the result entity is the central part surrounded by the neighbouring entities which can either contain the query keywords, thus making them relevant, or, could just act as intermediate entities helping connect the keyword entities with the result entity. For better clarity, we use colour coding to differentiate the entities, as can be seen in Figure 6.


Information discovery on electronic health records using authority flow techniques.

Hristidis V, Varadarajan RR, Biondich P, Weiner M - BMC Med Inform Decis Mak (2010)

Sample explaining sub graph of an ObjectRank2 result - HospitalizationID 2406 for query "respiratory distress". Figure 6 displays an explaining sub graph for HospitalizationID 2406 for query "respiratory distress". The figure gives a better picture of why this entity was ranked higher for query "respiratory distress" and its relationship with other entities that contain the query keywords. Detail descriptions of each entity are displayed as tool tip texts when the user points at them.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2984470&req=5

Figure 6: Sample explaining sub graph of an ObjectRank2 result - HospitalizationID 2406 for query "respiratory distress". Figure 6 displays an explaining sub graph for HospitalizationID 2406 for query "respiratory distress". The figure gives a better picture of why this entity was ranked higher for query "respiratory distress" and its relationship with other entities that contain the query keywords. Detail descriptions of each entity are displayed as tool tip texts when the user points at them.
Mentions: We briefly describe what happens when the user clicks the "Adjacent Entities" link, which "explains" the result. We believe that when complex ranking methods like BM25 and CO are employed, the users need information about why certain results are ranked high. Varadarajan et al. [29] described a novel technique to explain the results of authority-flow based techniques. For both CO and BM25 methods, we provide an "adjacent entities" link that pictorially explains each result. In the case of CO, an explaining graph is displayed using the principles described in [29]. For BM25, a similar explaining graph is displayed by including all entities that neighbor the target entity and also contain the query keywords. Figure 6 shows the explaining graphs, as shown in our user interface for CO. It might be easy to just view the Figure as a sub graph where the result entity is the central part surrounded by the neighbouring entities which can either contain the query keywords, thus making them relevant, or, could just act as intermediate entities helping connect the keyword entities with the result entity. For better clarity, we use colour coding to differentiate the entities, as can be seen in Figure 6.

Bottom Line: As the use of electronic health records (EHRs) becomes more widespread, so does the need to search and provide effective information discovery within them.Querying by keyword has emerged as one of the most effective paradigms for searching.We compare the effectiveness of two fundamentally different techniques for keyword search of EHRs.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computing and Information Sciences, Florida International University, Miami, Florida, USA. vagelis@cis.fiu.edu

ABSTRACT

Background: As the use of electronic health records (EHRs) becomes more widespread, so does the need to search and provide effective information discovery within them. Querying by keyword has emerged as one of the most effective paradigms for searching. Most work in this area is based on traditional Information Retrieval (IR) techniques, where each document is compared individually against the query. We compare the effectiveness of two fundamentally different techniques for keyword search of EHRs.

Methods: We built two ranking systems. The traditional BM25 system exploits the EHRs' content without regard to association among entities within. The Clinical ObjectRank (CO) system exploits the entities' associations in EHRs using an authority-flow algorithm to discover the most relevant entities. BM25 and CO were deployed on an EHR dataset of the cardiovascular division of Miami Children's Hospital. Using sequences of keywords as queries, sensitivity and specificity were measured by two physicians for a set of 11 queries related to congenital cardiac disease.

Results: Our pilot evaluation showed that CO outperforms BM25 in terms of sensitivity (65% vs. 38%) by 71% on average, while maintaining the specificity (64% vs. 61%). The evaluation was done by two physicians.

Conclusions: Authority-flow techniques can greatly improve the detection of relevant information in EHRs and hence deserve further study.

Show MeSH
Related in: MedlinePlus