Soubhik Paul

Follower

Following

Co-author

Public Views

Interests

Uploads

Papers by Soubhik Paul

Estimating personalized risk ranking using laboratory test and medical knowledge (UMLS)

by Soubhik Paul and Swarupananda Bissoyi

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013

In this paper, we introduce a Concept Graph Engine (CG-Engine) that generates patient specific pe... more In this paper, we introduce a Concept Graph Engine (CG-Engine) that generates patient specific personalized disease ranking based on the laboratory test data. CG-Engine uses the Unified Medical Language System database as medical knowledge base. The CG-Engine consists of two concepts namely, a concept graph and its attributes. The concept graph is a two level tree that starts at a laboratory test root node and ends at a disease node. The attributes of concept graph are: Relation types, Semantic types, Number of Sources and Symmetric Information between nodes. These attributes are used to compute the weight between laboratory tests and diseases. The personalized disease ranking is created by aggregating the weights of all the paths connecting between a particular disease and contributing abnormal laboratory tests. The clinical application of CG-Engine improves physician&amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s throughput as it provides the snapshot view of abnormal laboratory tests as well as a personalized disease ranking.

A method to summarize Disease Based Temporal state of human organ using laboratory test data and UMLS knowledge

by Soubhik Paul and Swarupananda Bissoyi

2012 IEEE 12th International Conference on Bioinformatics & Bioengineering (BIBE), 2012

A novel concept of Disease Based Temporal Score (DT-Score) is introduced to efficiently represent... more A novel concept of Disease Based Temporal Score (DT-Score) is introduced to efficiently represent periodic laboratory test data. Through this score, temporal state of an organ can be represented by summarizing periodic laboratory test data. The score can be used to indicate early trend for chronic abnormalities and thus results in an effective wellness measure. Many of these chronic abnormalities have a late manifestation and are major contributors for healthcare cost and mortality. Resources of Unified Medical Language System (UMLS) are introduced for automatic generation of relational tree between laboratory test, disease and organs with relative rank. Doctor's annotations are used to create reference score and data mining techniques are employed in deriving a mathematical model for estimating the DT-Score. A novel human body based summarization is employed for an intuitive view of the DT-Score and resultant temporal state of the associated organ. The proposed method enables an efficient temporal summarization of high volume of laboratory data and eventually reduces the cognitive load on physician. This method has potential to impact larger population as this can be effectively built over low cost regular laboratory test.

Download

Soubhik Paul

Uploads

Papers by Soubhik Paul

Log In