Linking AI Initiatives to Real-World Outcomes

Use Case

SENTIMENT ANALYTICS: ENHANCED PATIENT EXPERIENCE

 
Client

A large healthcare provider that serves patients in Philadelphia and the surrounding communities in Pennsylvania and southern New Jersey.

Problem

Improve patient experience by analyzing patient sentiments extracted from free text comments in the patient feedback forms.

 

Methodology
  • Combination of Deep Learning based professional service and modularized AI components used according to organization’s cognitive maturity
  • Business transformation with smarter cognitive outcomes
  • Adding industry, business and customer insights to the value chain
  • Seamlessly integrate data across functions
Solution
  • Contexts captured by a word embedding layer: word2vec
  • Machine learning techniques used to automatically categorize opinions as either positive, neutral or negative and relate them to separate business aspects
  • The output is then fed into the Long Short-Term Memory (LSTM) model, a type of Recurrent Neural Network (a complex area of deep learning), to classify texts into desired categories
  • SoftMax based attitude detection algorithm used to identify the user sentiments efficiently
Benefits:
  • Accurate assessment of patient opinions about different performance aspects of the hospitals
  • Client can identify key pain-points for patients through various stages of their healthcare journey
  • Considerable increase in the positive sentiments along with an increase in  performance ratings
 

© Abzooba 2021. All rights reserved  

© Copyright www.aiinc.cloud