Medical Specialty Recommendations by an Artificial Intelligence Chatbot on a Smartphone: Development and Deployment
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Background: The COVID-19 pandemic has limited daily activities and even contact between patients and primary care providers. This makes it more difficult to provide adequate primary care services, which include connecting patients to an appropriate medical specialist. A smartphone-compatible artificial intelligence (AI) chatbot that classifies patients’ symptoms and recommends the appropriate medical specialty could provide a valuable solution. Objective: In order to establish a contactless method of recommending the appropriate medical specialty, this study aimed to construct a deep learning–based natural language processing (NLP) pipeline and to develop an AI chatbot that can be used on a smartphone. Methods: We collected 118,008 sentences containing information on symptoms with labels (medical specialty), conducted data cleansing, and finally constructed a pipeline of 51,134 sentences for this study. Several deep learning models, including 4 different long short-term memory (LSTM) models with or without attention and with or without a pretrained FastText embedding layer, as well as bidirectional encoder representations from transformers for NLP, were trained and validated using a randomly selected test data set. The performance of the models was evaluated on the basis of the precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). An AI chatbot was also designed to make it easy for patients to use this specialty recommendation system. We used an open-source framework called “Alpha” to develop our AI chatbot. This takes the form of a web-based app with a frontend chat interface capable of conversing in text and a backend cloud-based server application to handle data collection, process the data with a deep learning model, and offer the medical specialty recommendation in a responsive web that is compatible with both desktops and smartphones. Results: The bidirectional encoder representations from transformers model yielded the best performance, with an AUC of 0.964 and F1-score of 0.768, followed by LSTM model with embedding vectors, with an AUC of 0.965 and F1-score of 0.739. Considering the limitations of computing resources and the wide availability of smartphones, the LSTM model with embedding vectors trained on our data set was adopted for our AI chatbot service. We also deployed an Alpha version of the AI chatbot to be executed on both desktops and smartphones. Conclusions: With the increasing need for telemedicine during the current COVID-19 pandemic, an AI chatbot with a deep learning–based NLP model that can recommend a medical specialty to patients through their smartphones would be exceedingly useful. This chatbot allows patients to identify the proper medical specialist in a rapid and contactless manner, based on their symptoms, thus potentially supporting both patients and primary care providers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The role of telehealth during COVID-19 outbreak: a systematic review based on current evidence
Monaghesh, E., & Hajizadeh, A. (2020) · BMC Public Health · doi:10.1186/s12889-020-09301-4 · Cited by 1,941 · cited 1×
“The COVID-19 pandemic has encouraged the development of telemedicine and the use of digital platforms [1].”
BackgroundHuckins, J. F., daSilva, A. W., Wang, W., Hedlund, E., Rogers, C., Nepal, S. K., Wu, J., Obuchi, M., Murphy, E. I., Meyer, M. L., et al. (2020) · Journal of Medical Internet Research · doi:10.2196/20185 · Cited by 759
The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review
Milne-Ives, M., de Cock, C., Lim, E., Shehadeh, M. H., de Pennington, N., Mole, G., Normando, E., & Meinert, E. (2020) · Journal of Medical Internet Research · doi:10.2196/20346 · Cited by 626 · cited 1×
“In a recent systematic review on the effectiveness of AI chatbots in health care, the bots performed well in terms of both usability and satisfaction, and overall positive or mixed effectiveness was reported in most studies [6].”
BackgroundNatural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review
Sheikhalishahi, S., Miotto, R., Dudley, J. T., Lavelli, A., Rinaldi, F., & Osmani, V. (2019) · JMIR Medical Informatics · doi:10.2196/12239 · Cited by 558 · cited 1×
“Most NLP-related medical studies have used EMRs such as clinical notes and discharge notes [21,29,30].”
BackgroundPhysicians’ perceptions of chatbots in health Care: cross-sectional web-based survey
Palanica, A., Flaschner, P., Thommandram, A., Li, M., & Fossat, Y. (2019) · Journal of Medical Internet Research · doi:10.2196/12887 · Cited by 384 · cited 1×
“…of an AI chatbot over human HCPs include the absence of face-to-face interaction; minimization of bias based on certain patient demographic characteristics such as age, gender, and race; greater cost-effectiveness; and 24/7 availability since the chatbot does not get fatigued or sick [5].”
BackgroundSurvey of conversational agents in health
Montenegro, J. L. Z., da Costa, C. A., & da Rosa Righi, R. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.03.054 · Cited by 322 · cited 1×
“Most AI chatbots utilize deep learning–based natural language processing (NLP), which can analyze natural human language input and respond appropriately in a conversational manner [4].”
BackgroundBidirectional RNN for Medical Event Detection in Electronic Health Records
Jagannatha, A. N., & Yu, H. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1056 · Cited by 314 · cited 1×
“As the fundamental LSTM architecture, a 256-cell bidirectional LSTM served as the backbone of the model with or without an added attention layer [15,16].”
MethodTrust me, i'm a chatbot: how artificial intelligence in health care fails the Turing Test
Powell, J. (2019) · Journal of Medical Internet Research · doi:10.2196/16222 · Cited by 115
Ross, E. L., Jamison, R. N., Nicholls, L., Perry, B. M., & Nolen, K. D. (2020) · Journal of Medical Internet Research · doi:10.2196/16939 · Cited by 62
Zand, A., Sharma, A., Stokes, Z., Reynolds, C., Montilla, A., Sauk, J., & Hommes, D. (2020) · Journal of Medical Internet Research · doi:10.2196/15589 · Cited by 48
Efficacy of Smart Speaker–Based Metamemory Training in Older Adults: Case-Control Cohort Study
Kim, J., Shin, E., Han, K., Park, S., Youn, J. H., Jin, G., & Lee, J.-Y. (2021) · Journal of Medical Internet Research · doi:10.2196/20177 · Cited by 28 · cited 1×
“A recent study reported that a smart speaker was an effective solution for bringing an AI-based digital health system for older Korean adults [34].”
Background
Cited by
Chow, J. C. L., & Li, K. (2025) · Information · doi:10.3390/info16070549 · Cited by 84
Chow, J. C. L., & Li, K. (2024) · JMIR Bioinformatics and Biotechnology · doi:10.2196/64406 · Cited by 75
Chen, C., Lam, K. T., Yip, K. M., So, H. K., Lum, T. Y. S., Wong, I. C. K., Yam, J. C., Chui, C. S. L., & Ip, P. (2025) · JMIR Human Factors · doi:10.2196/65785 · Cited by 35
“AI Chatbots can send reminders to patients to take their medications on time, improving medication adherence [24].”
Metadata
- Authors
- Lee, H., Kang, J., & Yeo, J.
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2021-05-06
- Volume
- 23
- Issue
- 5
- Pages
- e27460
- ISSN
- 1438-8871 (ISSN-L)
- OpenAlex
- W3156311852
- Cited by
- 47
- References
- 11
- FWCI
- 1.81
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.