Potentials of using Chatbots in Health Care Applications
Annotated Bibliography
Nadarzynski, T., Miles, O., Cowie, A., & Ridge, D. (2019). Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study. Digital health, 5, 2055207619871808.
The study talks about artificial intelligence being used in the healthcare sector primarily focusing on the chatbot services. The acceptability of these services in healthcare are explored in the study with the participants who are willing to take e-health services from chatbots. The study confirmed after analyzing the survey by binary regressions with a single predictor that most participants are interested to acquire the e-health AI-led chatbots services they also highlighted the low trust factor which leads to lower engagements and acceptance. The study had some methodological issues like the survey was taken without any actual interaction with the chatbot, and participants were online users and students whereas, health professionals were missing from the data and its result. The article has been cited 7 times and is essential to understanding the perception of users towards this AI-led chatbots.
Fadhil, A. (2018). Can a chatbot determine my diet?: Addressing the challenges of chatbot application for meal recommendations. arXiv preprint arXiv:1802.09100.
The author in this article discusses the background and the factors which motivate in developing chatbot systems for individuals seeking nutrition recommendation. The challenges associated with these systems are discussed in all aspects like technical, behavioural, and theoretical. The research after careful review of literature the challenges are discussed in depth where it is recommended to consider theoretical models for the chatbot, the behavior is to be defined to create an effective responsive system, and technical challenges like a rule-based bot, AI-based bots, UX Design, logical flow, and linguistics constraints exist in the development of the chatbots. The study is limited to study the challenges and does not take into account the theoretical models and behavioral techniques. The 11 times cited study is resourceful to understand the challenges associated with developing chatbot systems.
Kowatsch, T., Nißen, M., Shih, C.-H. I., Rüegger, D., Volland, D., Filler, A., . . . Brogle, B. (2017). Text-based healthcare chatbots supporting patient and health professional teams: preliminary results of a randomized controlled trial on childhood obesity.
The research is focused on the rising problem on the limited resources in the healthcare industry for patients who require constant monitoring and consultancy, this study sheds some light on how text-based healthcare chatbots should be designed. The study confirmed that the creation of text-based healthcare chatbots for the intervention group was evaluated positively around 99.5% for both healthcare professionals and patients by engaging with patients as long as 4 months. The strong study which is based on a randomized controlled trial is effective to understand the perception and experience of the chatbot and also the result of its intervention also improved the objective of the communication to improve their result. The study is cited by 27 authors and is useful in developing an understanding of how healthcare bots support patients and healthcare professionals.
Cameron, G., Cameron, D., Megaw, G., Bond, R., Mulvenna, M., O’Neill, S., . . . McTear, M. (2018). Best practices for designing chatbots in mental healthcare–A case study on iHelpr. Paper presented at the Proceedings of the 32nd International British Computer Science Human-Computer Interaction Conference 32.
The paper which is authored by reputable authors is focused on the design and development of the platform iHelpr for mental healthcare. The authors outline the best practices and experiences for platform development. The study concluded that designing the chatbot conversation which should be robust in a way to effectively engage the patients in an environment where they feel safe. The engaging conversational flow is the primary design aspect of the chatbot which surpasses all user interfaces. The study is limited to the development of a single platform but has reviewed extensive literature and applications for any designer to review in the pre-development phase of the chatbot. The paper was presented in the reputed international British computer science human-computer interaction conference and is useful for many developers of chatbots in healthcare.
Ni, L., Lu, C., Liu, N., & Liu, J. (2017). Mandy: Towards a smart primary care chatbot application. Paper presented at the International Symposium on Knowledge and Systems Sciences.
The presented paper is focused on a chatbot application called Mandy which is developed to assist the healthcare workers by conducting a pre-consulting interview in neutral language, the paper also compares the system with the currently existing systems. The research confirmed that the chatbot assistant Mandy is not developed to clinically diagnose the patients according to their medical issues. The work is limited and requires more systems to be added to the current application like adding more diseases, symptom verification, develop according to the behavioural trait of a healthcare professional, and prediction accuracy analysis. Though the research is only cited 22 times, it contributes towards a technical understanding of developing an application to assist healthcare professionals.
Cameron, G., Cameron, D., Megaw, G., Bond, R., Mulvenna, M., O’Neill, S., . . . McTear, M. (2017). Towards a chatbot for digital counselling. Paper presented at the Proceedings of the 31st British Computer Society Human-Computer Interaction Conference.
The authors presented the paper keeping the development of chatbot in mind for digital counselling specifically on mental health. The authors developed a demo chatbot application to incorporate digital intervention by being used as a diagnostic tool or counselling. The authors concluded that users are more comfortable with chatbot interaction which can widen the scope of the technology. The presented paper, however, is limited to a basic application and does not include any technical considerations for the developed application, the paper requires to develop a comprehensive conversational flow for diagnosis as well as counselling. The paper is relevant to the study as this was the foundation of the development of iHelpr in the later year which was also presented in the international British computer science human-computer interaction conference.
Wang, W., & Siau, K. (2018). Living with Artificial Intelligence–Developing a Theory on Trust in Health Chatbots.
