Mining for Medical ExpertiseSpeaker: Vishnu S Pendyala – San Jose, CA, United States
Topic(s): Information Systems, Search, Information Retrieval, Database Systems, Data Mining, Data Science
There are huge masses of population in the world without access to sufficient healthcare. The World Health Organization (WHO) statistics show that disease and mortality rate greatly depend on access to proper healthcare. The talk will present a vision for automating a crucial healthcare function, medical diagnosis for mass deployment. The ideas that will be presented in the talk aim at automating medical diagnosis using text-mining techniques and the Vector Space Model. The key factor for healthcare's success is the physician's expertise. In this talk, we will examine if that expertise can be modeled as an information corpus and extracted using text mining techniques, particularly using the Vector Space Model, to perform diagnosis.
With the advent of wearable technologies, various physiological parameters, including ECG and blood sugar can be monitored, paving way for correction of any abnormalities. Diagnosis essentially comprises of identifying symptoms and matching those symptoms with the knowledge of the physician about diseases. The knowledge, particularly of experts comprises mainly of their experience dealing with similar cases. A novice will depend more on academic, book knowledge, but an expert differentiates himself by mostly depending on his past experiences in curing the diseases. In the past, Expert Systems, a branch of Artificial Intelligence modeled the expertise using the expensive process of Knowledge Engineering. In this talk, we shall examine automated ways of leveraging the expertise using more recent techniques.
About this LectureNumber of Slides: 30
Duration: 45 - 60 minutes
Languages Available: English, Hindi
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.