Abstract
Automated question classification is a fundamental component of automated question-answering systems, which plays a critical role in promoting medical and healthcare services. Developing an automated question classification system depends heavily on natural language processing and data mining techniques. Question classification methods based on classical machine learning techniques face limitations in capturing the hidden relationships of features, as well as, handling complex languages and very large-scale datasets. Therefore, this paper proposes a deep learning approach for question classification, since deep learning methods have the powerful capability to extract implicit, hidden relationships and automatically generate dense representations of features. The proposed question classification model depends on unidirectional and bidirectional long short-term memory networks (LSTM and BiLSTM), which essentially developed to handle the Arabic language in the field of healthcare. The features are represented and created using a domain-specific word embedding model (Word2Vec) that is constructed by training around 1.5 million medical consultations from Altibbi company. Altibbi is a telemedicine company that is used as a case study and a source for curating and collecting the data. The proposed deep learning approach is a multi-class classification algorithm that automatically labels and maps the questions into 15 categories of medical specialities. The proposed deep learning model is evaluated using several evaluation metrics, including accuracy, precision, recall, and F1-score. Markedly, the proposed model achieved a superb classification capacity in terms of classification accuracy rate, which gained 87.2%.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2015) Tensorflow: large-scale machine learning on heterogeneous systems
Abdallah A, Kasem M, Hamada M, Sdeek S (2020) Automated question answer medical model based on deep learning technology. arXiv:200510416
Agrawal S, Mishra N (2019) Question classification system for health care: a review. In: Proceedings of the Third International Conference on Advanced Informatics for Computing Research, Association for Computing Machinery, New York, NY, USA, ICAICR ’19, 10.1145/3339311.3339341
Ahmed W, Ahmed A, Babu AP (2017) Web-based arabic question answering system using machine learning approach. Int J Adv Res Comput Sci 8:1
Akselrod-Ballin A, Chorev M, Shoshan Y, Spiro A, Hazan A, Melamed R, Barkan E, Herzel E, Naor S, Karavani E et al (2019) Predicting breast cancer by applying deep learning to linked health records and mammograms. Radiology 292(2):331–342
Aydoğan M, Karci A (2020) Improving the accuracy using pre-trained word embeddings on deep neural networks for turkish text classification. Phys A Stat Mech Appl 541(123):288
Banerjee I, Ling Y, Chen MC, Hasan SA, Langlotz CP, Moradzadeh N, Chapman B, Amrhein T, Mong D, Rubin DL et al (2019) Comparative effectiveness of convolutional neural network (cnn) and recurrent neural network (rnn) architectures for radiology text report classification. Artif Intell Med 97:79–88
Chollet F et al (2015) Keras. https://keras.io
Dash S, Acharya BR, Mittal M, Abraham A, Kelemen A (2020) Deep learning techniques for biomedical and health informatics. Springer, Berlin
Edara DC, Vanukuri LP, Sistla V, Kolli VKK (2019) Sentiment analysis and text categorization of cancer medical records with lstm. J Ambient Intell Hum Comput 2019:1–17
Estrada S, Lu R, Conjeti S, Orozco-Ruiz X, Panos-Willuhn J, Breteler MM, Reuter M (2020) Fatsegnet: a fully automated deep learning pipeline for adipose tissue segmentation on abdominal dixon MRI. Magn Reson Med 83(4):1471–1483
Faes L, Wagner SK, Fu DJ, Liu X, Korot E, Ledsam JR, Back T, Chopra R, Pontikos N, Kern C et al (2019) Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study. Lancet Dig Health 1(5):e232–e242
Faris H, Habib M, Faris M, Alomari M, Alomari A (2020) Medical speciality classification system based on binary particle swarms and ensemble of one vs. rest support vector machines. J Biomed Informatics 2020:103525
Florentia (2020) Florentia clinic
Gong JW, Cormack TG (2020) Re: vision loss as a presenting symptom of type ii diabetes mellitus. Br J Gener Pract 2020:5
Hasan AM, Rassem TH, Noorhuzaimi M et al (2018) Combined support vector machine and pattern matching for arabic islamic hadith question classification system. In: International conference of reliable information and communication technology, Springer, pp 278–290
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Jain DK, Jain R, Upadhyay Y, Kathuria A, Lan X (2019) Deep refinement: capsule network with attention mechanism-based system for text classification. Neural Comput Appl 2019:1–18
Jones KS (1972) A statistical interpretation of term specificity and its application in retrieval. J Document 1972:5
Kim J, Jang S, Park E, Choi S (2020) Text classification using capsules. Neurocomputing 376:214–221
Kumar A, Sarkar S, Pradhan C (2020) Malaria disease detection using cnn technique with sgd, rmsprop and adam optimizers. In: Deep learning techniques for biomedical and health informatics. Springer, pp 211–230
Kwak GHJ, Hui P (2019) Deephealth: Deep learning for health informatics. arXiv:190900384
Lauritsen SM, Kalør ME, Kongsgaard EL, Lauritsen KM, Jørgensen MJ, Lange J, Thiesson B (2020) Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artif Intell Med 2020:101820
Li Y, Yang T (2018) Word embedding for understanding natural language: a survey. In: Guide to big data applications. Springer, pp 83–104
Liu F, Weng C, Yu H (2019a) Advancing clinical research through natural language processing on electronic health records: traditional machine learning meets deep learning. In: Clinical Research Informatics. Springer, pp 357–378
Liu G, Guo J (2019) Bidirectional lstm with attention mechanism and convolutional layer for text classification. Neurocomputing 337:325–338
Liu HI, Ni CC, Hsu CH, Chen WL, Chen WM, Liu YT (2020) Attention based r&cnn medical question answering system in chinese. In: 2020 International conference on artificial intelligence in information and communication (ICAIIC), IEEE, pp 341–345
Liu J, Shang W, Lin W (2018) Improved stacking model fusion based on weak classifier and word2vec. In: 2018 IEEE/ACIS 17th international conference on computer and information science (ICIS), IEEE, pp 820–824
Liu J, Yang Y, Lv S, Wang J, Chen H (2019b) Attention-based bigru-cnn for chinese question classification. J Ambient Intell Hum Comput 2019:1–12
Longuenesse E, Chiffoleau S, Kronfol N, Dewachi O (2012) Book: Public health in the arab world section: the context of public health chapter: Public health, the medical profession and state building–a historical perspective. HAL multidisciplinary open archive
Luhn HP (1957) A statistical approach to mechanized encoding and searching of literary information. IBM J Res Dev 1(4):309–317
Mairittha T, Mairittha N, Inoue S (2020) Improving fine-tuned question answering models for electronic health records. In: Adjunct Proceedings of the 2020 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2020 ACM International Symposium on Wearable Computers, pp 688–691
Mayo (2020) mayo clinic
Mikolov T, Chen K, Corrado G, Dean J, Sutskever L, Zweig G (2013) word2vec. https://www.codegooglecom/p/word2vec22
Mulani J, Heda S, Tumdi K, Patel J, Chhinkaniwala H, Patel J (2020) Deep reinforcement learning based personalized health recommendations. In: deep learning techniques for biomedical and health informatics. Springer, pp 231–255
Naili M, Chaibi AH, Ghezala HHB (2017) Comparative study of word embedding methods in topic segmentation. Procedia Comput Sci 112:340–349
Nakua EK, Otupiri E, Dzomeku VM, Owusu-Dabo E, Agyei-Baffour P, Yawson AE, Folson G, Hewlett S (2015) Gender disparities of chronic musculoskeletal disorder burden in the elderly ghanaian population: study on global ageing and adult health (sage wave 1). BMC Musculoskel Disord 16(1):204
Novomed (2020) Novomed centers
Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543
Rawat BPS, Weng WH, Raghavan P, Szolovits P (2020) Entity-enriched neural models for clinical question answering. arXiv:200506587
Řehůřek R, Sojka P (2010) Software Framework for Topic Modelling with Large Corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, ELRA, Valletta, Malta, pp 45–50
Ren J, Liu N, Wu X (2020) Clinical questionnaire filling based on question answering framework. Int J Med Informatics 141(104):225
Romeo S, Da San MG, Belinkov Y, Barrón-Cedeño A, Eldesouki M, Darwish K, Mubarak H, Glass J, Moschitti A (2019) Language processing and learning models for community question answering in arabic. Inf Process Manag 56(2):274–290
Ryu JY, Kim HU, Lee SY (2018) Deep learning improves prediction of drug-drug and drug-food interactions. Proc Nat Acad Sci 115(18):E4304–E4311
Sammut C, Webb GI (eds) (2010) TF–IDF, Springer US, Boston, MA, pp 986–987. https://doi.org/10.1007/978-0-387-30164-8_832
Schmidt L, Weeds J, Higgins J (2020) Data mining in clinical trial text: transformers for classification and question answering tasks. arXiv:200111268
Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673–2681
Shah AM, Yan X, Shah SAA, Mamirkulova G (2019) Mining patient opinion to evaluate the service quality in healthcare: a deep-learning approach. J Ambient Intell Hum Comput 2019:1–18
Soliman AB, Eissa K, El-Beltagy SR (2017) Aravec: a set of arabic word embedding models for use in arabic nlp. Procedia Comput Sci 117:256–265
Soltanolkotabi M, Javanmard A, Lee JD (2019) Theoretical insights into the optimization landscape of over-parameterized shallow neural networks. IEEE Trans Inf Theory 65(2):742–769
Statista (2020) The world’s most spoken languages
Vidhya K, Shanmugalakshmi R (2020) Deep learning based big medical data analytic model for diabetes complication prediction. J Ambient Intell Hum Comput 2020:1–12
Vu MH, Löfstedt T, Nyholm T, Sznitman R (2020) A question-centric model for visual question answering in medical imaging. IEEE Trans Med imaging 2020:8
Wang Y, Sohn S, Liu S, Shen F, Wang L, Atkinson EJ, Amin S, Liu H (2019) A clinical text classification paradigm using weak supervision and deep representation. BMC Med Inform Decis Mak 19(1):1
Worell J (2001) Encyclopedia of women and gender, two-volume set: sex similarities and differences and the impact of society on gender, vol 1. Academic Press, Cambridge
Yegnanarayana B (2009) Artificial neural networks. PHI Learning Pvt, New York
Yilmaz S, Toklu S (2020) A deep learning analysis on question classification task using word2vec representations. Neural Comput Appl 57:1–20
Zhang L, Lin J, Liu B, Zhang Z, Yan X, Wei M (2019) A review on deep learning applications in prognostics and health management. IEEE Access 7:162,415–162,438
Zhang Q, Mu L, Zhang K, Zan H, Li Y (2018) Research on question classification based on bi-lstm. In: Workshop on Chinese Lexical Semantics, Springer, pp 519–531
Zhou J, Lu Y, Dai HN, Wang H, Xiao H (2019) Sentiment analysis of chinese microblog based on stacked bidirectional lstm. IEEE Access 7:38,856–38,866
Zhu Y, Li L, Lu H, Zhou A, Qin X (2020) Extracting drug-drug interactions from texts with biobert and multiple entity-aware attentions. J Biomed Informatics 2020:103451
Acknowledgements
This work has been supported in part by: Ministerio español de Economía y Competitividad under project TIN2017-85727-C4-2-P (UGR-DeepBio).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Faris, H., Habib, M., Faris, M. et al. Classification of Arabic healthcare questions based on word embeddings learned from massive consultations: a deep learning approach. J Ambient Intell Human Comput 13, 1811–1827 (2022). https://doi.org/10.1007/s12652-021-02948-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-02948-w