Automatic symptoms identification from a massive volume of unstructured medical consultations using deep neural and BERT models

Faris, Hossam; Faris, Mohammad; Habib, Maria; Alomari, Alaa

doi:10.1016/j.heliyon.2022.e09683

Cited by 6 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Looking at the multi-label classification research summarized in Table 3, we can see that the majority covered classifying news-which, in nature, tends to be structured text without spelling mistakes-while others covered social media text with a balanced data set, and revealed acceptable scores. At the same time, the most relevant research that covered an imbalanced medical consultation data set revealed comparable performance to our models in terms of F1 score (achieving 35.46%) [50]. We assume that the characteristics of the used data set play a critical role in the quality of the developed classifiers.…”

Section: Discussionmentioning

confidence: 59%

“…CNN-either stand-alone or augmented with other techniques-has shown notably good performance for text classification [6,11,12,24,26,34]. It can be observed that RNNs are not widely used for problems that require sequential dependencies, and many text classification research has used their variations, LSTM/BiLSTM and GRU/BiGRU instead, either stand-alone or in combination with other algorithms [6,11,23,28,32,[34][35][36]39,50]. When an RNN is used, it is often combined with other algorithms [6,12].…”

Section: Discussionmentioning

confidence: 99%

“…The authors used an ensemble approach with a hard-voting technique and AraBERT, resulting in an F1 score of 59% for the sarcastic class and an accuracy of 68%. Faris et al [50] conducted experiments with AraBERT v1 and v2 for multi-class and multi-label text classification of medical consultations obtained from Altibbi, comprising 578,000 consultations with unclear labels. The authors compared the performance of AraBERT + Bidirectional LSTM with Bidirectional LSTM using custom-built static word embeddings (AltibbiVec) and evaluated the performance using precision and recall.…”

Section: Bert-based Arabic Text Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Text Classification of Patient Experience Comments in Saudi Dialect Using Deep Learning Techniques

Alhazzani,

Al-Turaiki,

Alkhodair

2023

Applied Sciences

View full text Add to dashboard Cite

Improving the quality of healthcare services is of the utmost importance in healthcare systems. Patient experience is a key aspect that should be gauged and monitored continuously. However, the measurement of such a vital indicator typically cannot be carried out directly, instead being derived from the opinions of patients who usually express their experience in free text. When it comes to patient comments written in the Arabic language, the currently used strategy to classify Arabic comments is totally reliant on human annotation, which is time-consuming and prone to subjectivity and error. Thus, fully using the value of patient feedback in a timely manner is difficult. This paper addresses the problem of classifying patient experience (PX) comments written in Arabic into 25 classes by using deep learning- and BERT-based models. A real-world data set of patient comments is obtained from the Saudi Ministry of Health for this purpose. Features are extracted from the data set, then used to train deep learning-based classifiers—including BiLSTM and BiGRU—for which pre-trained static word embedding and pre-training vector word embeddings are utilized. Furthermore, we utilize several Arabic pre-trained BERT models, in addition to building PX_BERT, a customized BERT model using the PX unlabeled database. From the experimental results for the 28 classifiers built in this study, the best-performing models (based on the F1 score) are found to be PX_BERT and AraBERTv02. To the best of our knowledge, this is the first study to tackle PX comment classification for the Arabic language.

show abstract

Section: Discussionmentioning

confidence: 59%

Section: Discussionmentioning

confidence: 99%

Section: Bert-based Arabic Text Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Text Classification of Patient Experience Comments in Saudi Dialect Using Deep Learning Techniques

Alhazzani,

Al-Turaiki,

Alkhodair

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Meanwhile, Chen et al [36] utilized coronary heart disease, also known as angina, as an example to construct a pre-trained diagnostic model for traditional Chinese medicine texts based on the BERT model, completing text classification tasks for different types of coronary heart disease medical cases. Faris et al [37] designed a method for symptom identification and diagnosis based on BERT to assist doctors in handling consultations in multiple languages from users. BERT-based and CNN-based medical application methods are summarized in Table 1.…”

Section: Related Workmentioning

confidence: 99%

Adaption BERT for Medical Information Processing with ChatGPT and Contrastive Learning

Min,

Fan,

Dou

et al. 2024

Electronics

View full text Add to dashboard Cite

Calculating semantic similarity is paramount in medical information processing, and it aims to assess the similarity of medical professional terminologies within medical databases. Natural language models based on Bidirectional Encoder Representations from Transformers(BERT) offer a novel approach to semantic representation for semantic similarity calculations. However, due to the specificity of medical terminologies, these models often struggle with accurately representing semantically similar medical terms, leading to inaccuracies in term representation and consequently affecting the accuracy of similarity calculations. To address this challenge, this study employs Chat Generative Pre-trained Transformer (ChatGPT) and contrastive loss during the training phase to adapt BERT, enhancing its semantic representation capabilities and improving the accuracy of similarity calculations. Specifically, we leverage ChatGPT-3.5 to generate semantically similar texts for medical professional terminologies, incorporating them as pseudo-labels into the model training process. Subsequently, contrastive loss is utilized to minimize the distance between relevant samples and maximize the distance between irrelevant samples, thereby enhancing the performance of medical similarity models, especially with limited training samples. Experimental validation is conducted on the open Electronic Health Record (OpenEHR) dataset, randomly divided into four groups to verify the effectiveness of the proposed methodology.

show abstract

Categorization of Arabic Medical Questions Using a Deep Learning Approach

Bahbib,

Tamym,

Yakhlef

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Automatic symptoms identification from a massive volume of unstructured medical consultations using deep neural and BERT models

Cited by 6 publications

References 44 publications

Text Classification of Patient Experience Comments in Saudi Dialect Using Deep Learning Techniques

Text Classification of Patient Experience Comments in Saudi Dialect Using Deep Learning Techniques

Adaption BERT for Medical Information Processing with ChatGPT and Contrastive Learning

Categorization of Arabic Medical Questions Using a Deep Learning Approach

Contact Info

Product

Resources

About