Medical Instructed Real-Time Assistant for Patient with Glaucoma and Diabetic Conditions
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Virtual assistants are involved in the daily activities of humans such as managing calendars, making appointments, and providing wake-up calls. They provide a conversational service to customers around-the-clock and make their daily life manageable. With this emerging trend, many well-known companies launched their own virtual assistants that manage the daily routine activities of customers. In the healthcare sector, virtual medical assistants also provide a list of relevant diseases linked to a specific symptom. Due to low accuracy and uncertainty, these generated recommendations are untrusted and may lead to hypochondriasis. In this study, we proposed a Medical Instructed Real-time Assistant (MIRA) that listens to the user’s chief complaint and predicts a specific disease. Instead of informing about the medical condition, the user is referred to a nearby appropriate medical specialist. We designed an architecture for MIRA that considers the limitations of existing virtual medical assistants such as weak authentication, lack of understanding multiple intent statements about a specific medical condition, and uncertain diagnosis recommendations. To implement the designed architecture, we collected the chief complaints along with the dialogue corpora of real patients. Then, we manually validated these data under the supervision of medical specialists. We then used these data for natural language understanding, disease identification, and appropriate response generation. For the prototype version of MIRA, we considered the cases of glaucoma (eye disease) and diabetes (an autoimmune disease) only. The performance measure of MIRA was evaluated in terms of accuracy (89%), precision (90%), sensitivity (89.8%), specificity (94.9%), and F-measure (89.8%). The task completion was calculated using Cohen’s Kappa ( k = 0.848 ) that categorizes MIRA as ‘Almost Perfect’. Furthermore, the voice-based authentication identifies the user effectively and prevent against masquerading attack. Simultaneously, the user experience shows relatively good results in all aspects based on the User Experience Questionnaire (UEQ) benchmark data. The experimental results show that MIRA efficiently predicts a disease based on chief complaints and supports the user in decision making.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Among the papers developing and evaluating a VCA, 6 [59,60,62,65-67] assessed the technology acceptance of the VCA, whereas 3 [63,64,68] assessed the system accuracy. Only one [69] assessed both performance and acceptance.”
From Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review (2021) · cites this paper as [69]
In the citing paper
“The majority (n=10) of the selected papers developed and evaluated VCA [59,60,62-69], whereas 2 [61,70] aimed to report a criterion-based performance evaluation of existing commercial conversational agents (eg, Google Assistant and Apple Siri).”
From Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review (2021) · cites this paper as [69]
In the citing paper
“The majority of the studies (n=10) did not report any behavioral measures [59-63,65-67,69,70], whereas 2 papers [64,68] did.”
From Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review (2021) · cites this paper as [69]
In the citing paper
“In total, 4 of those studies [63,64,68,69] described precise speech recognition performance”
From Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review (2021) · cites this paper as [69]
In the citing paper
“Of the 12 studies, 7 [59,60,62,65-67,69] reported technology acceptance findings, whereas the others (n=5) did not [61,63,64,68,70].”
From Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review (2021) · cites this paper as [69]
29 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148 · cited 1×
“The interpretation of Kappa categorized MIRA as ‘Almost Perfect’ in term of task completion [57].”
MethodAllocation of Physician Time in Ambulatory Practice: A Time and Motion Study in 4 Specialties
Sinsky, C., Colligan, L., Li, L., Prgomet, M., Reynolds, S., Goeders, L., Westbrook, J., Tutty, M., & Blike, G. (2016) · Annals of Internal Medicine · doi:10.7326/m16-0961 · Cited by 1,494 · cited 1×
“According to a survey conducted in [13], primary care physicians spent more time managing electronic medical records (EMRs) than engaging with patients.”
BackgroundMetalearners for estimating heterogeneous treatment effects using machine learning
Künzel, S. R., Sekhon, J. S., Bickel, P. J., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1804597116 · Cited by 1,056 · cited 1×
“In the healthcare sector, the adoption of machine learning facilitated diagnosis [8,9], treatment [10,11], and streamlining of administrative tasks [12].”
BackgroundColor Psychology: Effects of Perceiving Color on Psychological Functioning in Humans
Elliot, A. J., & Maier, M. A. (2014) · Annual Review of Psychology · doi:10.1146/annurev-psych-010213-115035 · Cited by 942 · cited 1×
“We used the color change technique because warm colors have a positive impact on the user’s emotions and behavior as per psychology [55].”
MethodEvaluation of symptom checkers for self diagnosis and triage: audit study
Semigran, H. L., Linder, J. A., Gidengil, C., & Mehrotra, A. (2015) · BMJ · doi:10.1136/bmj.h3480 · Cited by 489 · cited 1×
“Due to the low accuracy and uncertainty of the existing virtual medical assistants, the resulting list of conditions may lead to depression, anxiety, and hypochondriasis [24].”
BackgroundLearning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System
Yan, R., Song, Y., & Wu, H. (2016) · Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval · doi:10.1145/2911451.2911542 · Cited by 338 · cited 1×
“These virtual assistants provide an interactive user interface (text, speech, or both) that have the ability to understand requests, handle complex tasks, and generate an appropriate response using the machine learning model [7].”
BackgroundReporting Mental Health Symptoms: Breaking Down Barriers to Care with Virtual Human Interviewers
Lucas, G. M., Rizzo, A., Gratch, J., Scherer, S., Stratou, G., Boberg, J., & Morency, L.-P. (2017) · Frontiers in Robotics and AI · doi:10.3389/frobt.2017.00051 · Cited by 308 · cited 1×
“Lucus et al., proposed a virtual human interviewer, which conducts an interview with military service members involved in an intense situation and identifies the symptoms associated with their mental state [33].”
BackgroundBickmore, T. W., Trinh, H., Olafsson, S., O'Leary, T. K., Asadi, R., Rickles, N. M., & Cruz, R. (2018) · Journal of Medical Internet Research · doi:10.2196/11510 · Cited by 308 · cited 1×
“The recommendation is predicted based on one symptom and requires approval from the medical specialist [23].”
BackgroundOn the track of Artificial Intelligence: Learning with Intelligent Personal Assistants
Goksel Canbek, N., & Mutlu, M. E. (2016) · International Journal of Human Sciences · doi:10.14687/ijhs.v13i1.3549 · Cited by 213
Machine Learning Classification Techniques for Breast Cancer Diagnosis
Omondiagbe, D. A., Veeramani, S., & Sidhu, A. S. (2019) · IOP Conference Series: Materials Science and Engineering · doi:10.1088/1757-899x/495/1/012033 · Cited by 210 · cited 1×
“In the healthcare sector, the adoption of machine learning facilitated diagnosis [8,9], treatment [10,11], and streamlining of administrative tasks [12].”
Background
Research works printed but not linked: 1
- Glass, J. (1999). Challenges for spoken dialogue systems. Proceedings of the 1999 IEEE ASRU Workshop, MIT Laboratory fot Computer Science.
Cited by
Schachner, T., Keller, R., & v Wangenheim, F. (2020) · Journal of Medical Internet Research · doi:10.2196/20701 · Cited by 267
“Other types of chronic conditions included respiratory [51,58], cardiovascular [50], nervous system [56], rheumatic [57], and autoimmune/eye conditions [59].”
BackgroundInfluentialBérubé, C., Schachner, T., Keller, R., Fleisch, E., v Wangenheim, F., Barata, F., & Kowatsch, T. (2021) · Journal of Medical Internet Research · doi:10.2196/25933 · Cited by 133
“In total, 4 of those studies [63,64,68,69] described precise speech recognition performance, whereas 3 [63,68,69] reported good or very good speech recognition performance, and 1 [64] study found mediocre recognition accuracy, with single-letter responses being slightly better recognized than word-based responses (det…”
InfluentialBin Sawad, A., Narayan, B., Alnefaie, A., Maqbool, A., Mckie, I., Smith, J., Yuksel, B., Puthal, D., Prasad, M., & Kocaballi, A. B. (2022) · Sensors · doi:10.3390/s22072625 · Cited by 113
“Two studies were for type 1 [29,39], one study was for type 2 [28], and one focused on diabetes in general, whether the patients have type 1 or 2 [40].”
BackgroundInfluentialApplication of Chatbots to Help Patients Self-Manage Diabetes: Systematic Review and Meta-Analysis
Wu, Y., Zhang, J., Ge, P., Duan, T., Zhou, J., Wu, Y., Zhang, Y., Liu, S., Liu, X., Wan, E., et al. (2024) · Journal of Medical Internet Research · doi:10.2196/60380 · Cited by 56
Review of artificial intelligence‐based question‐answering systems in healthcare
Budler, L. C., Gosak, L., & Stiglic, G. (2023) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1487 · Cited by 52
Ding, H., Simmich, J., Vaezipour, A., Andrews, N. E., & Russell, T. G. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad222 · Cited by 72
Arnold, A., Kolody, S., Comeau, A., & Miguel Cruz, A. (2024) · Disability and Rehabilitation: Assistive Technology · doi:10.1080/17483107.2022.2065369 · Cited by 59
“…assistants have the potential to alleviate challenges, such as social isolation and loneliness for older adults [22], perform clinical assessments [23], assist with detecting and diagnosing conditions [24–26], monitor behaviour and deliver interventions [27,28], and promote healthy behaviour [29].”
BackgroundA systematic review of intelligent assistants
Islas-Cota, E., Gutiérrez-García, J. O., Acosta, C. O., & Rodríguez, L.-F. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.09.035 · Cited by 56
Wang, H., Jiang, X., Zeng, P., Li, X., Chong, K. K. L., Hou, G., Fang, X., Yu, Y., Yu, X., Fang, J., et al. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1517918 · Cited by 42
The first AI ‐based Chatbot to promote HIV self‐management: A mixed methods usability study
Ma, Y., Achiche, S., Tu, G., Vicente, S., Lessard, D., Engler, K., Lemire, B., Laymouna, M. A., de Pokomandy, A., Cox, J., et al. (2024) · HIV Medicine · doi:10.1111/hiv.13720 · Cited by 35
“Since the first appearance of the ELIZA chatbot as a psychotherapist in 1966 [16], chatbots have been explored in a variety of healthcare applications across mental health [17 – 21], oncology [22 – 26], and diabetes [27, 28].”
An Interactive Dashboard Using a Virtual Assistant for Visualizing Smart Manufacturing
Jwo, J., Lin, C.-S., & Lee, C. (2021) · Mobile Information Systems · doi:10.1155/2021/5578239 · Cited by 31
“A Medical Instructed Real-time Assistant (MIRA) is introduced to diagnose a disease by listening to the users’ complaints and refer them to an appropriate medical specialist nearby as a final recommendation [22].”
MethodA Practical Experience on the Amazon Alexa Integration in Smart Offices
Bogdan, R., Tatu, A., Crişan-Vida, M., Popa, M., & Stoicu-Tivadar, L. (2021) · Sensors · doi:10.3390/s21030734 · Cited by 33
“A distinct application category is that of employing VAs to help the elderly that have visual impairment [24,25], need strengthening of social bonds [26], or daily caring [27,28].”
BackgroundMethodInfluentialApproaches for the Use of AI in Workplace Health Promotion and Prevention: Systematic Scoping Review
Lange, M., Löwe, A., Kayser, I., & Schaller, A. (2024) · JMIR AI · doi:10.2196/53506 · Cited by 24
“Another study developed and evaluated a Medical Instructed Real-Time Assistant that listens to the user’s chief complaint and predicts a specific disease [18].”
BackgroundEmpowering Preventive Care with GECA Chatbot
Maia, E., Vieira, P. N. D. A., & Praça, I. (2023) · Healthcare · doi:10.3390/healthcare11182532 · Cited by 24
“This is a distinguishing feature of GECA because, even though there is a potential risk of hacking or data breaches that could compromise the confidentiality of sensitive health-related information, most existing chatbots do not prioritize security as a critical factor [45].”
BackgroundVázquez, A., Zorrilla, A. L., Olaso, J. M., & Torres, M. I. (2023) · Sensors · doi:10.3390/s23031423 · Cited by 20
Diabetes and conversational agents: the AIDA project case study
Alloatti, F., Bosca, A., Di, L., & Pieraccini, F. (2021) · Discover Artificial Intelligence · doi:10.1007/s44163-021-00005-1 · Cited by 23
“These interfaces can also help doctors, for example by conducting medical history interviews, thus relieving the amount of repetitive and impersonal work [29].”
BackgroundMancone, S., Diotaiuti, P., Valente, G., Corrado, S., Bellizzi, F., Vilarino, G. T., & Andrade, A. (2023) · Behavioral Sciences · doi:10.3390/bs13070550 · Cited by 14
A Survey of Conversational Agents and Their Applications for Self-Management of Chronic Conditions
Park, M. S., Upama, P. B., Anik, A. A., Ahamed, S. I., Luo, J., Tian, S., Rabbani, M., & Oh, H. (2023) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac57700.2023.00162 · Cited by 18
“Rehman and colleagues [80] calculated Cohen’s D to assess task completion and the accuracy of their agent for diabetic conditions.”
BackgroundMethodSecure Health Fog: A Novel Framework for Personalized Recommendations Based on Adaptive Model Tuning
Rehman, U. U., Park, S.-B., & Lee, S. (2021) · IEEE Access · doi:10.1109/access.2021.3101308 · Cited by 11
“For this purpose, we have used an extended version of our previous work, Medical Instructed Real-time Assistant (MIRA), which interacts with the user in a natural way of communication and supports speech/text for interactive conversation [57].”
MethodSelf-citationAltom, D. S., Taha, A. I. A., Hussein, A. A. A. M., Elshiekh, M. A. I., Abdelmajed, A. H., Ibrahim, F. I. A., Mohammed, S., & Tifoor, M. M. E. E. (2025) · Cureus · doi:10.7759/cureus.81001 · Cited by 16
“There were four studies carried out in the US [17,18,21,22], two in Spain [14,20], and one each in Canada [15], Australia [19], the UK [16], and South Korea [13].”
Developing a chatbot/intelligent system for neurological diagnosis and management
Das, A., Sen, V., & Rose, A. C. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-90037-9.00010-2 · Cited by 10
HELENA: An intelligent digital assistant based on a Lifelong Health User Model
Polignano, M., Lops, P., de Gemmis, M., & Semeraro, G. M. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103124 · Cited by 10
Electronic Health Records (EHR) Usability and User Experience Evaluation: A Case Study
Yunus, M. H., Sakkinah, I. S., Rahmawati, U. E., Deharja, A., & Santi, M. W. (2023) · INTENSIF Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi · doi:10.29407/intensif.v7i2.19090 · Cited by 9
“Based on the UEQ benchmark data, the application shows relatively good results in all aspects of the assessment [12].”
MethodVirtual Medical Assistant in English and Kannada Languages
Bai, B. G. M., Prerana, P., Benki, A. A., & Rakesh, R. (2023) · International Conference on Applied Intelligence and Sustainable Computing (ICAISC) · doi:10.1109/icaisc58445.2023.10199524 · Cited by 8
“[4] Mainly focused on providing the user with the most accurate information as much as possible using virtual assistants.”
BackgroundDesigning AI-based Conversational Agent for Diabetes Care in a Multilingual ContextPreprint
Nguyen, T.-T., Sim, K., Kuen, A. T. Y., O’Donnell, R. R., Lim, S. T., Wang, W., & Nguyen, H. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.09490 · Cited by 11
Implementing scripted conversations by means of smart assistants
Pacheco‐Lorenzo, M., Fernández‐Iglesias, M. J., Valladares‐Rodriguez, S., & Anido‐Rifón, L. E. (2023) · Software: Practice and Experience · doi:10.1002/spe.3182 · Cited by 5
Bassi, G., Donadello, I., Gabrielli, S., Salcuni, S., Giuliano, C., & Forti, S. (2021) · JMIR Formative Research · doi:10.2196/27500 · Cited by 5
Zhu, Y., Li, Y., Cui, Y., Zhang, T., Wang, D., Zhang, Y., & Feng, S. (2023) · Electronics · doi:10.3390/electronics12244896 · Cited by 5
“Policy learning is the key technology for dialogue-based disease diagnosis, and it is also widely used in task-oriented dialogue systems [15–17].”
BackgroundTowards a Design Framework for Conversational Agents for Diabetes Prevention
Sawad, A. B., Alakhtar, R. A., Alturki, B., Narayan, B., Lin, S., Prasad, M., & Kocaballi, A. B. (2023) · Australian Conference on Computer-Human Interaction (OzCHI) · doi:10.1145/3638380.3638421 · Cited by 3
MediBot: Intelligent virtual assistant for personalized medical care and guidance
Orozco, J., Rodríguez, L., Viloria-Núñez, C., & M., C. G. Q. (2024) · IEEE Technology and Engineering Management Conference - Latin America (TEMSCON LATAM) · doi:10.1109/temsconlatam61834.2024.10717706 · Cited by 3
“These chatbots help anticipate illnesses and offer empathetic responses, analyze symptoms, predict user conditions, connect users with recommended doctors, and schedule appointments based on availability [2 – 16].”
BackgroundSpecial Issue on “Natural Language Processing: Emerging Neural Approaches and Applications”
Esposito, M., Masala, G. L., Minutolo, A., & Pota, M. (2021) · Applied Sciences · doi:10.3390/app11156717 · Cited by 3
“Moreover, in [23], the authors proposed a Medical Instructed Real-time Assistant (MIRA) that listens to the user’s chief complaint and predicts a specific disease, thus referring the user to a nearby appropriate medical specialist.”
BackgroundWang, H., Zeng, P., Li, X. Y., Chong, K. K. L., & Yu, X. (2024) · Research Square · doi:10.21203/rs.3.rs-4706283/v1 · Cited by 3
Dash, P., Madhanraj, G., Premkumar, B., & Agathian, B. (2025) · doi:10.1109/iccds64403.2025.11209353 · Cited by 2
Multilingual NLP, personalization, and global health
Kaur, P., Devi, L., Sandhu, R., & Ghai, D. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45252-9.00005-0 · Cited by 2
Validation of DigiMoCA, A Conversational Agent for the Cognitive Assessment of Senior Adults
Pacheco-Lorenzo, M. R., Valladares‐Rodríguez, S., Iglesias, M. J. F., & Anido, L. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2537783 · Cited by 2
“This framework proposes the Kappa coefficient (Ping et al., 2025; Rehman et al., 2020; Siegel & Castellan, 1988) as the main indicator for task completion, and it measures how well the CA is able to understand the user and it is extremely important for this application, since misunderstandings may…”
Pacheco-Lorenzo, M. R. (2024) · Investigo Institutional repository of UVigo (Universidade de Vigo)
Ma, Y. (2025) · PolyPublie (École Polytechnique de Montréal)
Pavão, J., Bastardo, R., Silva, A. G., & Rocha, N. P. (2026) · JMIR Human Factors · doi:10.2196/102911
“Natural language processing based on AI frameworks (eg, Google Dialogflow, Microsoft Language Understanding Intelligent Service, Rasa, or Oscova) was used in several studies to improve dialogue flow [85,86,101,110,112,117,120,124,136, 145,167,168,178,179,185,191,195-197, 200,202].”
Technology and decent work in elderly care: a case study
Bregoli, I., Codini, A. P., & Bonera, M. (2026) · Journal of Services Marketing · doi:10.1108/jsm-01-2026-0050 · Cited by 1
Metadata
- Authors
- Rehman, U. U., Chang, D. J., Jung, Y., Akhtar, U., Razzaq, M. A., & Lee, S.
- Affiliations
- Kyung Hee University (KR)
- The Catholic University of Korea Yeouido St. Mary's Hospital (KR)
- Corresponding author
- Lee, Sungyoung
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2020-03-25
- Volume
- 10
- Issue
- 7
- Pages
- 2216
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W3013786371
- Cited by
- 37
- References
- 44
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 5 · 2023: 10 · 2022: 5 · 2021: 9 · 2020: 1
- FWCI
- 5.45
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Institute for Information and Communications Technology Promotion (IITP-2017-0-01629, 2017-0-00655)
- National Research Foundation of Korea (NRF-2016K1A3A7A03951968, NRF-2019R1A2C2090504)
- Topics
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- glaucoma, diabetes mellitus, chief complaint, disease prediction, voice-based authentication, natural language understanding, dialogue corpus, user experience, health anxiety, clinical decision support
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.