LITERATURE REVIEW: Effectiveness of Chatbot to Reduce the Risk of Coronary Heart Disease using Android-based application

Agnes Atmadjaja, Minarni Watinin, Stefani Nurhadi


Background: An innovative approach in the form of a discussion platform designed to help users deal with health issues related to coronary artery disease. Chatbot platforms allow the collection of users' data, which is analyzed through natural language processing and behavioral analysis, to provide each user with a customized solution based on their current situation. The data collected and analyzed is accessible. The platform is developed using chatbot technology. Users can interact with chatbots to generate personal chat data stored on the platform. Conflicting information and sensitivity to Coronary Heart Disease (CHD) issues hinder effective communication. Recent technological solutions to maintain weight loss are limited. A chatbot would be suitable to support weight loss as it requires no human intervention, is available 24 hours a day, and supports natural communication while maintaining anonymity. The health system needs an effective and low-cost way to provide optimal health outcomes using conversation-enabled Artificial Intelligence (AI). Humans can interact well with this AI in the form of a fully automated and self-contained text-based mobile tutoring service. CHD is a serious health problem worldwide with multiple and interrelated causes. At the same time, chatbots are becoming more popular for interacting with users in mobile health apps.
Objective: We evaluated an Android application. Its main goal is to prevent lifestyle-related diseases that are a risk for CHD, which has been considered at risk for multiple coronary artery disease (CAD), with the overarching goal of gaining compassion through mobile health improvements. The insights gained in this preview article will be used to plan future health care systems and to design an AI capable of advanced healthcare, chronic disease prevention, and self-treatment.
Results: The Role of Artificial Intelligence in preventing Coronary Heart Disease (CHD) is done through health screenings. The app warns the user to exercise regularly and maintain food intake by reducing foods high in calories and adding foods high in fiber.
Conclusion: Usage of AI in healthcare is associated with CHD prevention, which alters healthy lifestyles. It can also encourage a change in attitude, a high level of user concern for health, and obtain complete health information. Research on artificial intelligence and its use in telemedicine needs to be continued, with clinical trials examining the impact on blood pressure, body mass index, smoking, diabetes mellitus, and user engagement and feedback.

Save to Mendeley


Coronary Heart Disease; Education; Chatbot; Artificial Intelligence; Connected Health; Health Communication; Smartphone; mobile health

Full Text:



Statistai, Last accessed 25 March 2022i.

WHO, Last accessed 25 March 2020i.

Gariepy, G., Nitkai, D., Schmitzi, N. : The association between obesity and anxiety disorders in the population: a systematic review and meta-analysisi. International journal of obesity, 24(3), 407-419 (2010).

Danieli Jurafsku & James H. Martini. Speech and Language Processing (3rd ed. Draft), https: //, Last accessed 25 march 2020i.

Informationi Datai Centeri of the Indonesiani Ministry of Health. Heart health situation. Jakarta: 2014.

Ministryi of Health RIi. Guidelinesi for surveillancei of heart and bloodi vessel diseasei. Jakarta: 2007i.

Worldi Health Rankingsi. Malaysiai: coronary heart diseasei. (internet) WHO publish data May 2014i.

Basici Health Research (Riskesdas). The prevalence of coronary heart disease in Indonesia. Research and Development Agency of the Indonesian Ministry of Health. Jakarta: 2013.

BPJS Health. (2020, January). Data from the catastrophic heart hospital in Surabaya. KCU Surabaya.

WHOi. 2013 Global action plan for the prevention and control of non-communicable disease 2013-2020. Geneva: World Health Organizationi. i

WHO. 2014 Non communicable diseases country profilesi. Geneva: World Health Organizationi. doi: 10.1111/jgs.1271

low, WYi, Lee, YK, & Samy, AL. (2015) “Non-communicable idiseases in the Asia-Pacific region: prevalence, riski factors and community-based iprevention,” International Journal of iOccupational medicine and Environmental healthi, vol. 28, no. 2, pp. 20-26. doi: 10.2478/s13382-014-0326-0. i

The Ministryi of Health of the Republic of Indonesiai. (2014). Heart health situation. Data and Information Center, 8, 2.

Dorje, T., i Zhao, G., Scheer, A., iTsokey, L., Wang, J., Chen, Y., … iMaiorana, A. (2018). SMARTphonei and social media-based Cardiac iRehabilitation and Secondary Preventioni ( SMART-CR / SP ) for ipatients with coronary heart disease in China : a randomised icontrolled trial iprotocol.

Neubeck, L., i Coorey, G., Peiris, D., Mulley, J., Heeley, E., iHersch, F., & Redfern, iJ. (2016). risk iof , cardiovascular diseasei : The Consumer Navigation of Electronic Cardiovascular Tools ( CONNECT ) i web application. International Journal of Medical Informaticsi, 1–14.

Honeyman, iE., iVarnfield, M., & Karunanithi, M. (2014). Interventionali Cardiologyi Mobile healthi applicationsi ini cardiaci care, 6, 227–240.

Alligood,M.R., iTomey,A.M. i (2014). Nursing theoriests and their work (Sixth ed.) Mosby: iSaint Louisi.

Dennis EA, iPotter KL, Estabrooksi PA et al. (2012) Weighti gain preventioni for college freshmeni: comparing two sociali cognitivei theory-based interventionsi with and withouti expliciti self-regulationi training. J Obes 2012, 10.

Calugi S, Marchesinii G, Eli Ghoch M et al. (2017) Thei influ- ence ofi weight-loss expectationsi on weighti lossi and of weight-loss satisfactioni on weighti maintenancei in severe obesity. J Acad Nutr Dietetics 117i, 32–38.

Bastian T, Mairei A, Dugas J et al. (2015) Automatici identi- fication ofi physical activity types andi sedentary behaviorsi from triaxial accelerometer: laboratory-based calibrations are not enough. i J Appl Physiol 118, 716–722

Chew H.S.J., iAng W.H.D.A, & Lau Y. (2021). Thei potential of artificiali intelligence in enhancingi adulti weight lossi: a scoping review. Review Article, 28.

Stein, N. M. P. Hi., & Brooks, K. M. S. P. D. (2017) i. A Fullyi Automatedi Conversational Artificiali Intelligence for Weight Lossi: Longitudinali Observationali Study Among Overweighti and Obesei Adults. JMIR Diabetes, 2(2).

Wischeri N. Australian Onlinei Diabetes Services. 2014i May 12. The usei of technologyi in diabetes self-managementi: Diabetes educationi, care and support services in Australiai URL:

the-use-of-technology-in-diabetes-self-management.html [accessedi 2022-03-26] [WebCite Cache ID 6tMN8WDyz]

Ali EEi, Chew L, Yap KY. Evolutioni and currenti statusi of mhealthi research: a systematici review. BMJ Innov 2016 Jan 05;2(1):33-40i. [doi: 10.1136/bmjinnov-2015-000096]

Cheni C, Garrido T, iChock D, iOkawa G, Liang L. iThe Kaiser Permanente Electronic Healthi Record: transformingi and streamliningi modalities of care. Healthi Aff (Millwood) 2009;28(2):323-333 [FREE Full text] [doi: 10.1377/hlthaff.28.2.323] [Medline: 19275987] i

Bramleyi L, Matiti M. Howi does it really feel to be in my shoesi? Patients' experiencesi of compassioni withini nursingi carei and their perceptionsi of developingi compassionate nurses. J Clin Nurs 2014 Oct;23(19-20):2790-2799 [FREE Full text] [doi: 10.1111/jocn.12537] [Medline: 24479676] i

Zahrawardanii D, Herlambangi KS, Anggrahenyi HD. Analysisi of risk factors for coronaryi heart disease at dr. Kariadi Semarang. Muhammadiyahi Medicali Journali 2013; 1(2).

osmiatin M. Analisis factor-faktor risiko terhadap kejadian penyakit jantung koroner pada wanita lanjut usia di RSUPN dr. Cipto Mangunkusumo Jakarta. (Skripsi). Jakarta: Universitas Indonesia; 2012.

Yusuf S, Hawken S, Ounpuu S. effect of potentially modifiable risk factors associated with myocardial infarction in 52 countries (the INTERHEART study). Lancet. 2004 Sep 11-17; 364 (9438): 937-52.

Mozaffarian D, Katan MB, Ascherio A. trans fatty acids and cardiovascular disease. N Engl J Med. 2006 Apr 13; 354(15): 1601-13



  • There are currently no refbacks.