TY - JOUR
T1 - Multi-Label Classification for Doctor's Behavioral Pattern Matching During Online Medical Interview using Machine Learning
AU - Juanita, Safitri
AU - Purwitasari, Diana
AU - Purnama, I. Ketut Eddy
AU - Abdillah, Abid Famasya
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© 2023, School of Electrical Engineering and Informatics. All rights reserved.
PY - 2023/9
Y1 - 2023/9
N2 - In recent years, many studies on medical texts have attracted the attention of researchers. Medical text studies have few multi-label data targets because it is challenging to understand dependencies between labels. Therefore, this study investigates a collection of medical texts by addressing complex problems in the behavioural pattern of Doctor’s answer text in Online Health Consultation (OHC) by suggesting a pattern of six medical interview functions ranging from fostering doctor-patient relationships to treatment-related behaviours and responding to emotions. There are many proposed MLC methods to solve a multi-label problem. However, this study proposes an MLC model that can improve MLC accuracy, especially in multilingual medical datasets: English and Indonesian. This study proposes 16 MLC models using two feature extraction methods, compares all proposed models, and evaluates model performance using three perspectives. The results show that from 3 perspectives, the MLC model that consistently outperforms other models in the English dataset is a T-BR-RF model (TF/IDF, Binary Relevance, and Random Forest). In contrast, using the Indonesian dataset, the T-BR-AD Model (TF/IDF, Binary Relevance and Adaboost) outperforms other MLC models. The feature extraction method that helps optimize the performance of MLC models is TF-IDF compared to the Word2Vec method.
AB - In recent years, many studies on medical texts have attracted the attention of researchers. Medical text studies have few multi-label data targets because it is challenging to understand dependencies between labels. Therefore, this study investigates a collection of medical texts by addressing complex problems in the behavioural pattern of Doctor’s answer text in Online Health Consultation (OHC) by suggesting a pattern of six medical interview functions ranging from fostering doctor-patient relationships to treatment-related behaviours and responding to emotions. There are many proposed MLC methods to solve a multi-label problem. However, this study proposes an MLC model that can improve MLC accuracy, especially in multilingual medical datasets: English and Indonesian. This study proposes 16 MLC models using two feature extraction methods, compares all proposed models, and evaluates model performance using three perspectives. The results show that from 3 perspectives, the MLC model that consistently outperforms other models in the English dataset is a T-BR-RF model (TF/IDF, Binary Relevance, and Random Forest). In contrast, using the Indonesian dataset, the T-BR-AD Model (TF/IDF, Binary Relevance and Adaboost) outperforms other MLC models. The feature extraction method that helps optimize the performance of MLC models is TF-IDF compared to the Word2Vec method.
KW - Behavioral Pattern Matching
KW - Medical Interview Functions
KW - Medical Text
KW - Multi-label Classification
KW - Online Health Consultation
UR - http://www.scopus.com/inward/record.url?scp=85175490640&partnerID=8YFLogxK
U2 - 10.15676/ijeei.2023.15.3.5
DO - 10.15676/ijeei.2023.15.3.5
M3 - Article
AN - SCOPUS:85175490640
SN - 2085-6830
VL - 15
SP - 435
EP - 452
JO - International Journal on Electrical Engineering and Informatics
JF - International Journal on Electrical Engineering and Informatics
IS - 3
ER -