Adaptation of IDPT System Based on Patient-Authored Text Data Using NLP

EasyChair Preprint 3586

Abstract

Background: Internet-Delivered Psychological Treatments (IDPT) system has the potential to provide evidence-based mental health treatments for a far-reaching population at a lower cost. However, most of the current IDPT systems are tunnel-based and does not adapt based on patients need. In this paper, we explore the possibility of applying Natural Language Processing (NLP) for personalizing the mental health intervention according to the patient's needs. Objective: The primary objective of this study is to present an adaptive strategy based on NLP techniques that analyses patient authored text data and extract depression symptoms based on clinically established assessment questionnaire, PHQ-9. Method: We propose a novel word-embeddings (Depression2Vec) to extract depression symptoms from the patient-authored text data and compare with three state-of-the-art NLP techniques. We also present an adaptive IDPT system that personalizes treatments for mental health patients based on the proposed depression symptoms detection technique. Result: Our results indicate that the proposed DepressionVec performs mostly similar to WordNet but outperforms in the same cases for extracting symptoms from the patient authored text. Conclusion: While the extraction of symptoms from text is challenging, our proposed method can substantially extract depression symptoms from text data, which can be used to deliver personalized intervention.

Keyphrases: Internet-delivered interventions, NLP, Personalization, Tailored Intervention, adaptive treatments

@booklet{EasyChair:3586,
  author    = {Suresh Kumar Mukhiya and Usman Ahmed and Fazle Rabbi and Ka I Pun and Yngve Lamo},
  title     = {Adaptation of IDPT System Based on Patient-Authored Text Data Using NLP},
  howpublished = {EasyChair Preprint 3586},
  year      = {EasyChair, 2020}}