Natural language understanding to assess Oral Health-Related Quality of life
Asst. Prof. Lamyia Anweigi1, Iheb Ben Naceur1, Jomana Awad1, Mohamed Ahmeda2, Noha Barhom1, Prof. Faleh Tamimi1
1 College of Dental Medicine, QU Health, Qatar University, Doha, Qatar,
2 Newcastle University's School of Dental Sciences
Objectives
Natural Language Understanding (NLU) is a subfield of artificial intelligence concerned with the computational understanding of human language. This technology can provide objective quantitative assessment of interviews in qualitative research. Thus, we hypothesize that NLU could assess oral health's impact on quality of life by analysing semi-structured interviews.
Materials and Methods
To test our hypothesis, the transcripts of semi-structured interviews conducted on 10 participants (aged 16–25 years) suffering from hypodontia were analysed using IBM Watson NLU Text Analysis. The automated analysis identified entities and keywords in the transcripts. It produced a quantitative analysis of sentiment (positive, negative) and emotions (joy, sadness, anger, fear, and disgust) for the specific interview questions.
Results
NLU analysis of the transcripts showed a predominantly negative sentiment towards hypodontia and its management; 93.2% of the identified entities presented a negative sentiment, while only 6.8 % had a positive sentiment. NLU analysis revealed that patient sentiment correlated inversely with age (R= -0.49), treatment waiting time (R= -0.22), and OHIP score(R= -20). Negative sentiment and sadness were strongest when patients were asked about the history of their dental problems and their feelings about their teeth, but they expressed joy and positive sentiment when asked about the successful dental work provided. Also, the keywords associated with negative sentiment were mainly those related to treatment length and delays.
Conclusions
In summary, NLU could detect patient's negative sentiments towards oral health conditions, and it could be helpful in qualitative dental research.