A Review on Medical Textual Question Answering Systems Based on Deep Learning Approaches
Source abstract
Abstract
The advent of Question Answering Systems (QASs) has been envisaged as a promising solution and an efficient approach for retrieving significant information over the Internet. A considerable amount of research work has focused on open domain QASs based on deep learning techniques due to the availability of data sources. However, the medical domain receives less attention due to the shortage of medical datasets. Although Electronic Health Records (EHRs) are empowering the field of Medical Question-Answering (MQA) by providing medical information to answer user questions, the gap is still large in the medical domain, especially for textual-based sources. Therefore, in this study, the medical textual question-answering systems based on deep learning approaches were reviewed, and recent architectures of MQA systems were thoroughly explored. Furthermore, an in-depth analysis of deep learning approaches used in different MQA system tasks was provided. Finally, the different critical challenges posed by MQA systems were highlighted, and recommendations to effectively address them in forthcoming MQA systems were given out.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Data Quality and Management · Information Retrieval and Search Behavior
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of IOT Engineering, Hohai University, Changzhou 213022, China
College of Computer and Information, Hohai University, Nanjing 211100, China
Funding
the National Natural Science Foundation of China
References (86)
Show source-provided references
1. Wilensky, R., Chin, D.N., Luria, M., Martin, J., Mayfield, J., and Wu, D. (2000). The Berkeley UNIX consultant project. Intelligent Help Systems for UNIX, Springer.10.1007/978-94-010-0874-7_5 ↗
2. Ludwig, T., Walter, B., Ley, M., Maier, A., and Gehlen, E. (1989). LILOG-DB: Database Support for Knowledge-Based Systems. Datenbanksysteme in Büro, Technik und Wissenschaft, Springer.10.1007/978-3-642-74571-3_15 ↗
3. Olvera-Lobo, M.D., and Gutiérrez-Artacho, J. (2015). Question answering track evaluation in TREC, CLEF and NTCIR. New Contributions in Information Systems and Technologies, Springer.10.1007/978-3-319-16486-1_2 ↗
4. AquaLog: An ontology-driven question answering system for organizational semantic intranets10.1016/j.websem.2007.03.003 ↗
5. An approach for extracting exact answers to Question Answering (QA) system for english sentences10.1016/j.proeng.2012.01.979 ↗
6. A study on different closed domain question answering approaches10.1007/s10772-020-09692-0 ↗
7. Versatile question answering systems: Seeing in synthesis
8. Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering10.1109/TNNLS.2018.2817340 ↗
9. Balikas, G., Krithara, A., Partalas, I., and Paliouras, G. (2015). BioASQ: A challenge on large-scale biomedical semantic indexing and question answering. International Workshop on Multimodal Retrieval in the Medical Domain, Springer.10.1007/978-3-319-24471-6_3 ↗
10. Multi-label biomedical question classification for lexical answer type prediction10.1016/j.jbi.2019.103143 ↗
11. Analysis of PubMed user sessions using a full-day PubMed query log: A comparison of experienced and nonexperienced PubMed users10.2196/medinform.3740 ↗
12. Using Linked Data for Integrating Educational Medical Web Databases Based on BioMedical Ontologies
13. Hamon, T., Grabar, N., and Mougin, F. (2014, January 19). Natural Language Question Analysis for Querying Biomedical Linked Data. Proceedings of the 1st Natural Language Interfaces for Web of Data Workshop (NLIWoD)—ISWC, Riva del Garda, Italy.
14. Attentive convolutional gated recurrent network: A contextual model to sentiment analysis10.1007/s13042-020-01135-1 ↗
15. Piskorski, J., and Yangarber, R. (2013). Information extraction: Past, present and future. Multi-Source, Multilingual Information Extraction and Summarization, Springer.10.1007/978-3-642-28569-1_2 ↗
16. Text summarization using Wikipedia10.1016/j.ipm.2014.02.001 ↗
17. A survey of the usages of deep learning for natural language processing10.1109/TNNLS.2020.2979670 ↗
18. A closed-domain question answering framework using reliable resources to assist students10.1017/S1351324918000141 ↗
19. Usability survey of biomedical question answering systems10.1186/1479-7364-6-17 ↗
20. Automatically extracting information needs from complex clinical questions10.1016/j.jbi.2010.07.007 ↗
21. Roberts, K., and Patra, B.G. (2017, January 4–8). A semantic parsing method for mapping clinical questions to logical forms. Proceedings of the American Medical Informatics Association Annual Symposium Proceedings, Washington, DC, USA.
22. A passage retrieval method based on probabilistic information retrieval model and UMLS concepts in biomedical question answering10.1016/j.jbi.2017.03.001 ↗
23. Ye, D., Zhang, S., Wang, H., Cheng, J., Zhang, X., Ding, Z., and Li, P. (2018, January 18–21). Multi-level composite neural networks for medical question answer matching. Proceedings of the 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), Guangzhou, China.10.1109/DSC.2018.00028 ↗
24. Niu, Y., and Hirst, G. (2021, March 15). Analysis of Semantic Classes in Medical Text for Question Answering. Available online: https://www.aclweb.org/anthology/W04-0509.pdf.
25. An inception convolutional autoencoder model for chinese healthcare question clustering10.1109/TCYB.2019.2916580 ↗
26. Intelligent Question Answering in Restricted Domains Using Deep Learning and Question Pair Matching10.1109/ACCESS.2020.2973728 ↗
27. A survey on question answering systems with classification
28. Biomedical question answering: A survey10.1016/j.cmpb.2009.10.003 ↗
29. Zhang, X., Wu, J., He, Z., Liu, X., and Su, Y. (2018, January 2–7). Medical exam question answering with large-scale reading comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11970 ↗
30. A deep learning approach for predicting the quality of online health expert question-answering services10.1016/j.jbi.2017.06.012 ↗
31. Lee, M., Cimino, J., Zhu, H.R., Sable, C., Shanker, V., Ely, J., and Yu, H. (2006, January 11–15). Beyond information retrieval—Medical question answering. Proceedings of the American Medical Informatics Association Annual Symposium Proceedings, Washington, DC, USA.
32. Development, implementation, and a cognitive evaluation of a definitional question answering system for physicians10.1016/j.jbi.2007.03.002 ↗
33. A survey of medical question answering systems
34. Kodra, L., and Meçe, E.K. (2017). Question answering systems: A review on present developments, challenges and trends. Int. J. Adv. Comput. Sci. Appl., 8.10.14569/IJACSA.2017.080931 ↗
35. IARNN-Based Semantic-Containing Double-Level Embedding Bi-LSTM for Question-and-Answer Matching10.1155/2019/6074840 ↗
36. Question answering for biology10.1016/j.ymeth.2014.10.023 ↗
37. Consumer health information and question answering: Helping consumers find answers to their health-related information needs10.1093/jamia/ocz152 ↗
38. A semantic approach for question classification using WordNet and Wikipedia10.1016/j.patrec.2010.06.012 ↗
39. A survey of text question answering techniques
40. Malayalam question answering system10.1016/j.protcy.2016.05.155 ↗
41. A Question Answering System on Holy Quran Translation Based on Question Expansion Technique and Neural Network Classification10.3844/jcssp.2016.169.177 ↗
42. A survey on question answering technology from an information retrieval perspective10.1016/j.ins.2011.07.047 ↗
43. An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition10.1186/s12859-015-0564-6 ↗
44. Question answering using statistical language modelling10.1016/j.csl.2011.11.001 ↗
45. Architecture and evaluation of BRUJA, a multilingual question answering system10.1007/s10791-011-9177-5 ↗
46. Noh, J., and Kavuluru, R. (2018, January 17–20). Document retrieval for biomedical question answering with neural sentence matching. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.10.1109/ICMLA.2018.00036 ↗
47. Knowledge representations and inference techniques for medical question answering10.1145/3106745 ↗
48. A literature review on question answering techniques, paradigms and systems
49. SemBioNLQA: A semantic biomedical question answering system for retrieving exact and ideal answers to natural language questions10.1016/j.artmed.2019.101767 ↗
50. Hou, W., and Tsai, B.H. (2014, January 3–6). An Answer Validation Concept Based Approach for Question Answering in Biomedical Domain. Proceedings of the International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, Kaohsiung, Taiwan.10.1007/978-3-319-07455-9_16 ↗
51. AskHERMES: An online question answering system for complex clinical questions10.1016/j.jbi.2011.01.004 ↗
52. Cairns, B.L., Nielsen, R.D., Masanz, J.J., Martin, J.H., Palmer, M.S., Ward, W.H., and Savova, G.K. (2011, January 22–26). The MiPACQ clinical question answering system. Proceedings of the American Medical Informatics Association Annual Symposium Proceedings, Washington, DC, USA.
53. Burns, C.S., Nix, T., Shapiro, R.M., and Huber, J.T. (2021). MEDLINE search retrieval issues: A longitudinal query analysis of five vendor platforms. PLoS ONE, 16.10.1371/journal.pone.0234221 ↗
54. CliniQA : Highly Reliable Clinical Question Answering System
55. Zhu, X., Yang, X., and Chen, H. (2018, January 17–19). A Biomedical Question Answering System Based on SNOMED-CT. Proceedings of the International Conference on Knowledge Science, Engineering and Management, Changchun, China.10.1007/978-3-319-99365-2_2 ↗
56. Murdock, J.W., Tesauro, G., and Tj, I. (2012). Statistical approaches to question answering in Watson. Mathematics Awareness Month Theme Essay, IBM TJ Watson Research Center.
57. Question answering systems in biology and medicine-the time is now10.1093/bioinformatics/btr327 ↗
58. Ni, J., Chen, Y., Chen, Y., Zhu, J., Ali, D., and Cao, W. (2020). A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods. Appl. Sci., 10.10.3390/app10082749 ↗
59. Yan, Y., Zhang, B., Li, X., and Liu, Z. (2020). List-wise learning to rank biomedical question-answer pairs with deep ranking recursive autoencoders. PLoS ONE, 15.10.1371/journal.pone.0242061 ↗
60. Zhang, S., Zhang, X., Wang, H., Cheng, J., Li, P., and Ding, Z. (2017). Chinese medical question answer matching using end-to-end character-level multi-scale CNNs. Appl. Sci., 7.10.3390/app7080767 ↗
61. Applying deep matching networks to Chinese medical question answering: A study and a dataset10.1186/s12911-019-0761-8 ↗
62. Recurrent neural networks for classifying relations in clinical notes10.1016/j.jbi.2017.07.006 ↗
63. A question-entailment approach to question answering
64. Iyyer, M., Boyd-Graber, J., Claudino, L., Socher, R., and Daumé III, H. (2014, January 25–29). A neural network for factoid question answering over paragraphs. Proceedings of the 2014 Conference on Empirical METHODS in Natural Language processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1070 ↗
65. Cai, R., Zhu, B., Ji, L., Hao, T., Yan, J., and Liu, W. (2017, January 18–21). An CNN-LSTM attention approach to understanding user query intent from online health communities. Proceedings of the 2017 IEEE international conference on data mining workshops (ICDMW), New Orleans, LA, USA.10.1109/ICDMW.2017.62 ↗
66. Chinese medical question answer selection via hybrid models based on CNN and GRU10.1007/s11042-019-7240-1 ↗
67. Soft Error Resilience of Deep Residual Networks for Object Recognition10.1109/ACCESS.2020.2968129 ↗
68. MEANS: A medical question-answering system combining NLP techniques and semantic Web technologies10.1016/j.ipm.2015.04.006 ↗
69. Sentiment analysis using deep learning approaches: An overview10.1007/s11432-018-9941-6 ↗
70. He, B., Guan, Y., and Dai, R. (2018, January 3–6). Convolutional Gated Recurrent Units for Medical Relation Classification. Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.10.1109/BIBM.2018.8621228 ↗
71. Stroh, E., and Mathur, P. (2021, March 15). Question Answering Using Deep Learning. Available online: http://cs224d.stanford.edu/reports/StrohMathur.pdf.
72. Convolutional recurrent neural network with template based representation for complex question answering
73. Duan, N., Tang, D., Chen, P., and Zhou, M. (2017, January 7–11). Question generation for question answering. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.10.18653/v1/D17-1090 ↗
74. A review and future perspectives of arabic question answering systems10.1109/TKDE.2016.2607201 ↗
75. A mobile-based question-answering and early warning system for assisting diabetes management10.1155/2018/9163160 ↗
76. Pampari, A., Raghavan, P., Liang, J., and Peng, J. (November, January 31). emrQA: A Large Corpus for Question Answering on Electronic Medical Records. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1258 ↗
77. Bhaskar, P., Pakray, P., Banerjee, S., Banerjee, S., Bandyopadhyay, S., and Gelbukh, A.F. (2021, March 15). Question Answering System for QA4MRE@CLEF 2012. Available online: http://ceur-ws.org/Vol-1178/CLEF2012wn-QA4MRE-BhaskarEt2012b.pdf.
78. Zhu, M., Ahuja, A., Juan, D.C., Wei, W., and Reddy, C.K. (2020, January 16–20). Question Answering with Long Multiple-Span Answers. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, Online Event.10.18653/v1/2020.findings-emnlp.342 ↗
79. Katz, B., Felshin, S., Yuret, D., Ibrahim, A., Lin, J., Marton, G., Mcfarland, A.J., and Temelkuran, B. (2002, January 26–28). Omnibase: Uniform Access to Heterogeneous Data for Question Answering. Proceedings of the International Conference on Application of Natural Language to Information Systems, Salford, UK.10.1007/3-540-36271-1_23 ↗
80. Medical record search engines, using pseudonymised patient identity: An alternative to centralised medical records10.1016/j.ijmedinf.2010.10.003 ↗
81. Text Summarization using QA Corpus for User Interaction Model QA System
82. Soni, S., and Roberts, K. (2019, January 1). A paraphrase generation system for ehr question answering. Proceedings of the 18th BioNLP Workshop and Shared Task, Florence, Italy.10.18653/v1/W19-5003 ↗
83. Nguyen, V. (August, January 28). Question answering in the biomedical domain. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, Florence, Italy.
84. PHR based diabetes index service model using life behavior analysis10.1007/s11277-016-3715-9 ↗
85. Mobile apps for the management of diabetes10.2337/dc17-0853 ↗
86. Artificial intelligence in medical practice: The question to the answer?10.1016/j.amjmed.2017.10.035 ↗