首页|Investigators at Faculty of Engineering and Technology Discuss Findings in Machi ne Learning [Contextual Classification of Clinical Records Wi th Bidirectional Long Short-term Memory (Bi-lstm) and Bidirectional Encoder Repr esentations From ...]
Investigators at Faculty of Engineering and Technology Discuss Findings in Machi ne Learning [Contextual Classification of Clinical Records Wi th Bidirectional Long Short-term Memory (Bi-lstm) and Bidirectional Encoder Repr esentations From ...]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Machine Learning. According to news originating from Vadodara, India, by NewsRx corresp ondents, research stated, “Deep learning models have overcome traditional machin e learning techniques for text classification domains in the field of natural la nguage processing (NLP). Since, NLP is a branch of machine learning, used for in terpreting language, classifying text of interest, and the same can be applied t o analyse the medical clinical electronic health records.” Our news journalists obtained a quote from the research from the Faculty of Engi neering and Technology, “Medical text consists of lot of rich data which can alt ogether provide a good insight, by determining patterns from the clinical text d ata. In this paper, bidirectional-long short-term memory (Bi-LSTM), bi-LSTM atte ntion and bidirectional encoder representations from transformers (BERT) base mo dels are used to classify the text which are of privacy concern to a person and which should be extracted and can be tagged as sensitive. This text data which w e might think not of privacy concern would majorly reveal a lot about the patien t’s integrity and personal life. Clinical data not only have patient demographic data but lot of hidden data which might go unseen and thus could arise privacy issues. Bi-LSTM with attention layer is also added on top to realize the importa nce of critical words which will be of great importance in terms of classificati on, we are able to achieve accuracy of about 92%. About 206,926 sen tences are used out of which 80% are used for training and rest fo r testing we get accuracy of 90% approx. with Bi-LSTM alone.”
VadodaraIndiaAsiaCyborgsEmerging TechnologiesMachine LearningFaculty of Engineering and Technology
NETL
NSTL
