International Journal of Interactive Mobile Technologies (iJIM) – eISSN: 1865-7923 – Vol  17 No  16 (2023) 82 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) iJIM | eISSN: 1865-7923 | Vol. 17 No. 16 (2023) | JIM International Journal of Interactive Mobile Technologies Sweetline, B.C., Vijayakumaran, C., Samydurai, A. (2023). Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments. International Journal of Interactive Mobile Technologies (iJIM), 17(16), pp. 82–94. https://doi.org/10.3991/ijim.v17i16.42687 Article submitted 2023-05-17. Resubmitted 2023-06-24. Final acceptance 2023-06-28. Final version published as submitted by the authors. © 2023 by the authors of this article. Published under CC-BY. Online-Journals.org PAPER Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments ABSTRACT One of the newest technologies, mobile health, has the potential to support the provision of care for older adults and offer them individualised treatment. This study’s goal is to evaluate the benefits and challenges of personalised mobile health (PMH) for elderly residential care. Virtual worlds are quickly integrating into the landscape of instructional technologies. One of the most well-known of these settings is Second Life (SL). Despite the potential of SL for health professions education, there aren’t many official SL applications for this purpose, and the effectiveness of these applications hasn’t been evaluated to the fullest extent possible. Similarly, it appears that nothing is known about the use of virtual worlds for continuing medical education. In order to better grasp the fundamentals of the aid of MVIs for personal health monitoring (PHM), we were able to pinpoint the key disease regions, sensors, chan- nels, calculations and communication protocols. The main obstacles limiting MVIs’ degree of integration into the international health care system were also identified. The analysis demonstrates that MVIs offer an excellent possibility for the creation of affordable, per- sonalised health systems that meet the unique equipment requirements of a certain field of medicine. KEYWORDS personalised mobile health (PMH), medical composition, mobile health, patient monitoring 1 INTRODUCTION Population ageing is a worldwide issue that has an impact on everyone. The United Nations’ demographic reports show that the global median age is currently 28 years old. It is expected to rise by 10 years by 2050, reaching 38 years. The per- centage of individuals over 65 in the world rose from 8% to 11% between 1950 and 2009 and is projected to reach 22% by 2050. The effects on social services, wellness, retirement, living conditions, transportation and economic growth are extensive. The annual cost of identifying and treating persistent illnesses is rising dramatically, even in modern health care systems. In recent years, the delivery of health care and B. Christina Sweetline1(), C. Vijayakumaran1, A. Samydurai2 1Department of Computing Technologies, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, India 2Department of Computer Science and Engineering, SRM Valliammai Engineering College, Kattankulathur, Chennai, Tamil Nadu, India cb4592@srmist.edu.in https://doi.org/10.3991/ijim.v17i16.42687 https://online-journals.org/index.php/i-jim https://online-journals.org/index.php/i-jim https://doi.org/10.3991/ijim.v17i16.42687 https://online-journals.org/ https://online-journals.org/ mailto:cb4592@srmist.edu.in https://doi.org/10.3991/ijim.v17i16.42687 iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 83 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments nursing facilities has moved from hospitals to residences, known as home care, as a result of rising illness burdens and expenditures, particularly among the elderly. The goal is to lower hospitalisation and transportation expenses, boost patient free- dom and contact at home and eventually improve health-care quality by lowering medical mistakes. One of the latest technologies, mobile health (m-health), has the capability to be a successful method for enhancing nursing care, enabling distant visits and reducing health-care expenses. The elderly would be given more control over their lives as a result, and tracking would be improved. Mobile communications sys- tems that support health-care delivery while promoting health are referred to as mobile health [1]. A growing number of people are using smartphones to deliver behavioural change interventions because of how widely accessible and available they are. M-Health platforms can be used to provide many BCTs, either as indepen- dent interventions or as components of broader programming. These platforms, as opposed to in-person treatments, allow for the option of receiving real-time response, social contrast and self-monitoring. They also boost the personalisation of the intervention [2]. Additionally, there is no requirement for real-time communication between med- ical specialists and end consumers. The long-term effects are yet to be fully under- stood, but it has been demonstrated by numerous meta-analyses and research studies that m-Health tools (apps) may be helpful in improving lifestyles, dietary habits and preventing illnesses. The majority of m-Health apps that are available to the gen- eral public are weight management-focused and mostly rely on self-monitoring of food consumption and exercise. Some of them have a lot of potential for behaviour modification and leading healthier lifestyles because they also contain health rec- ommendation systems. The behaviour of users is substantially more affected by personalised recommendations than by generic ones. By identifying certain profile signals and configuring interventions accordingly, recommendation systems use algorithms to assist users in forming better habits. Foundation Basin Instrument Parade Recollection Show Retention Signal treating Organization Border Signal training Fig. 1. Some modules in medical virtual instruments Hard digital instrumentation is a strategy in which some virtual instruments operate as embedded devices. This is a reference to virtual instruments created on reconfigurable hardware systems, such as an FPGA (Figure 1). As a result, recom- mendation systems are thought to be useful technological tools to assist users in changing their eating habits and may enable users to make wiser decisions to adopt https://online-journals.org/index.php/i-jim 84 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. a healthier diet and lifestyle. In this investigation, we present a m-Health frame- work for altering dietary behaviour using the CarpeDiem app, whose general fea- tures have already been published. In a word, the Carpe Diem app focuses on the three main pillars of health—sleep, nutrition and exercise—in an effort to encourage healthy lives among the general public. Its state-of-the-art user interface encourages and amuses users while educating them about healthy behaviours, setting alarms and reminders, and motivating them to stick to personal goals. The rest of this examination is divided into the following sections: We outline the materials and methods utilised to conduct the evaluation in Section 2. We present the findings for the most prevalent personal health monitoring (PHM)-based medi- cal equipment features in Section 3. The results are then discussed in Section 4, and Section 5 serves as the conclusion. 2 RELATED WORKS According to Ferré-Bergadà, M., Valls, A., et al. [3] once a person’s level of per- sonalised mobile health (PMH) has been assessed, it is vital to create an acceptable, adaptable and simple improvement process to meet that goal. The technologies used to rank exercises and determine their impact are based on artificial intelligence (AI) techniques for customization and computation. This study carries on this effort to enhance Depending on the requirements of improving each person’s various men- tal health-related features, the app could be improved by adding a mechanism to identify the best order of delivering the exercises to each carer. The goal is to cre- ate a method that will allow the app to quickly choose and rate a group of exer- cises for each carer that will successfully halt the deterioration of particular mental health features. Rosenfeld, E. A., Lyman, C., et al. [4] in their study observe that existing evidence-based m-Health apps, like Motivate, target indicators of depression by pro- viding an app-version of a traditional face-to-face psychotherapy procedure using a wide range of non-overlapping abilities (such as value explanation, mental restruc- turing and activity scheduling). These are frequently delivered in a non-stepwise manner, with all psycho-educational information available right away in hand-out form. This method goes against how users typically use apps, which is in brief, fre- quent spurts. As the user went through the apps, each target talent would build on previously acquired abilities. The intervention would primarily concentrate on short, consecutive skill-oriented exercises that were “gamified,” with minimal, focused psych education. According to Wac, K., Bults, R., Van Beijnum, B., et al. [5] this vision, the Mobi Health project, which was carried out from 2002 to 2004 and was funded by the European Union’s Commission under the 5th Research System under the project number FP5-IST-2001-36006, has started to develop a cutting-edge platform for value-added mobile medical care for individuals as well as physicians. MobiHealth is the term given to this service architecture after that. Incorporating sensors into a wireless body area network and utilising state-of-the-art communications tech- nology, the stage enables distant patient monitoring and treatment. The platform maximises patient mobility while enabling remote management of chronic illnesses. The purpose of our research is to develop a platform that will automatically fore- cast, recognise and treat medical emergencies according to a patient’s monitored health status. https://online-journals.org/index.php/i-jim iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 85 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments Shahriyar, R., Bari, M. F., Kundu, G., et al. [6] state that designing, developing and evaluating mobile devices that enable citizens to take a more active role in their health care are all aspects of mobile health care. People frequently have known medical problems yet are unable or unwilling to visit a doctor regularly. Common health issues include diabetes, obesity, high blood pressure and an irregular heart- beat. In these situations, it is typically recommended that people regularly visit their doctors for standard medical exams. However, if we can give people a more intel- ligent and individualised way to receive medical input, it will save them important time, satisfy their need for individual control over their health and lower the cost of ongoing medical care. Varshney, U., et al. [7] believe that the growth of m-Health is being fuelled by numerous developments in sensing technology, miniaturisation of low-power gadgets and wireless networks. When infrastructure capabilities and health care needs are matched, wireless technology can be used efficiently. One of them is the employment of immediately adaptive and widespread wireless access to improve the accessibility of health care practitioners. Another is the utilisation of trustworthy communication for efficient evacuation between medical devices, patients, health care providers and vehicles. These include body detectors, short-range wireless con- nectivity, computerised user interfaces and position tracking. Olla, P., and Shimskey, C., et al. [8] have stated that while creating a taxonomy, it’s crucial to take into account how to properly divide up a group’s components into subgroups that are mutually exclusive, clear and encompass all potential outcomes. Taxonomy needs to be simple, easy to grasp and practical to be useful in the real world. Instead of using our taxonomy as a final classification system, we want to use it as a springboard for further investigation into the essential elements of the mea- surements and categories of m-Health apps. The World Health Organisation (WHO) wrote a piece about the difficulties of integrating mHealth into medical procedures. Lack of expertise was evaluated as the second-biggest implementation hurdle out of those considered. Sleurs, K., Seys, S. F., Bousquet, J., et al. [9] observe that, from the standpoint of the doctor, mHealth technology offers tools that assist patients in tracking the progression of their diseases and triaging patients so that those who require more testing will be informed. Additionally, using mHealth instruments, patients can be divided into types of diseases that benefit from a certain treatment or do not, based on co-morbidities, lifestyle characteristics and other person-related aspects. Finally, remote surveillance of chronic conditions helps health care systems since it may save needless hospital stays and meetings, which lowers the cost of care. A minority of 10 to15% of adult asthmatics still have uncontrolled asthma despite current treat- ment options, with persistent symptoms and a higher risk of flares, hospitalisations, substantial absenteeism and mortality. Triantafyllidis, A., Velardo, C., et al. [10] In more detail, the personalized mobile health monitoring system’s practical characteristics include, in addition to moni- toring vital signs, self-reporting of signs based on clinically validated instruments, reviewing individual readings through graphical displays, access to self-management education about heart failure and text message interaction with medical personnel. The system’s architecture allows for the seamless recording of user actions, remote service updates delivered via a secure application distribution method, and run- time activation and deactivation of functional components by medical professionals. Below is a description of how this mobile system evolved. Initial qualitative user experience findings and preliminary results are also provided. https://online-journals.org/index.php/i-jim 86 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. 3 METHODS AND MATERIALS 3.1 Personalised endorsement-based mobile internet wealth management The real-time user attention model may determine an operator’s passion based on their browsing preferences, which can be useful. However, there are many fewer standard tags than there are objects. The similarity between users can be determined easily using the user-standard tag matrix [11]. The issue of filling values doesn’t need to be taken into account. Additionally, the algorithm does not need to actively supply goods. The scoring information effectively lowers the level of user interaction and system collaboration. Figure 2 displays the flowchart for the personalised monitor- ing system. Hospital management Doctors management Patient management Nurse management Appointments management Medicine management Fig. 2. Flowchart for personalized monitoring system The similarity of users can be determined in a variety of ways. Cosine similarity is a strategy that is frequently employed. � � � � � � � � � l l l l l l l l m p J m p( ) ( )( ) (1) Equation (1) is used to calculate the degree of similarity between the items in order to retrieve the ones the user is most interested in. � � � � m m m m m P K P J P( ) ( ) (2) To calculate the relevance scores between the materials, utilise equation (2). Q x l l l Q x l l l � � � � � � � � � � � � � � � � � � � � � 2 2 2 ; , ; , ( ) ( ) (3) https://online-journals.org/index.php/i-jim iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 87 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments Based on the appropriateness score, the Top-N items are chosen using Equation (3). X max e R C B S C C C C C l m l y y y y y y y 1 1 1 2 3 4 5 � � � � � ( ), ( ) . ( , , , , )( ) ( ) ( ) ( ) ( ) (4) The user’s fresh curiosity cannot be detected when there is an abundance of data in the future. L ji y C ji J T I � � ��( )*1 1 (5) As a result, in order to maximise strengths and minimise shortcomings, it is required to modify the influence of each algorithm throughout dissimilar periods by adjusting weights. g y f Bx 1 2 2 ( ) � � � (6) Divide the information into a test set and a training collection in order to cal- culate the weight of the system at hand. User data in various environments have distinct properties. �� � � � ji j ji y (7) In order to find the weights b and q with the best efficiency, the personalisation method is trained numerous times using the training set of data, using dissimilar values for b and q each time. B x y e x j x j e x j x j i j b b � � � � . ( ) ( ) 3 3 1 2 1 2 (8) Under typical conditions, a personalised system for suggestion works in steps to make suggestions. The interest modelling step is the first, the item pairing stage is the second and the suggestion result reporting stage is the last. 3.2 Benefits of music virtual instruments Over traditional musical instruments, virtual instruments provide a lot of benefits. In this section [12], we briefly go over a few advantages of music virtual instruments (MVIs) have over their conventional counterparts. These advantages have contrib- uted to MVIs being used more frequently in Ambient Assisted Living (AAL) initiatives. • The MVIs are vendor-agnostic tools, in contrast to the general virtual instru- ments that some vendors advertise. Additionally, because they are modular and self-contained, they may operate without external personal computers. • Music virtual instruments’ portability is their primary benefit. Virtual instruments are a simple way to provide seniors with the mobility and versatility they need without limiting their movement. MVIs are more portable than traditional medi- cal devices used to monitor seniors since a significant element of the instrument https://online-journals.org/index.php/i-jim 88 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. is built as software. This makes it possible for them to be used for evaluating elders at home, which is a key driver of Ambient Assisted Living. • The versatility of an MVI is its next advantage. It is easy to change the settings in real time to fit the specific demands of the patient or doctor thanks to the system’s versatility. Rapid changes in health monitoring standards and technologies make it simple for conventional devices to become obsolete. But since a significant por- tion of the MVI is software-based, it is simpler to ensure that it remains current because design changes can be performed more quickly and easily. Due to MVIs’ adaptability, certain parts of one instrument can be simply changed to be used as another type of instrument. Mobile health monitoring device. Mobile PHM systems offer individualised, intelligent, trustworthy, non-intrusive, continuous and widespread health monitor- ing [2]. They are a component of a body area network, which comprises a mobile base unit collection of wearable wireless sensors with the ability to store energy and transmit wireless data. The user’s body is equipped with sensors, which can process the gathered data both locally within the body sensing and/or remotely via wireless transfer to the mobile base unit (MBU). Real-time data analysis by the MBU enables the user to receive personalised information and fast feedback. To receive medical advice and aid in clinical choices, the analysed data can also be distributed to licenced medical specialists. While mobile PHM systems have several qualities that make them appealing to users worldwide, some of those features may also limit how widely accepted and used they can be. Pervasive surveillance. Personal health monitoring systems’ ubiquitous moni- toring aims to provide health care services to anyone at any time, regardless of loca- tion, moment, or persona. Data processing needs to be integrated into the context of the subject so that communication with the MBU is organic, and the user can receive personalised information in a completely open way. The platform for integrated multisensing. A multi-sensing platform that is integrated into PHM systems can accommodate biosensors that monitor position, environmental variables like heat, humidity and daylight, and physiological param- eters like blood pressure, blood sugar levels and heart rate. Long-term, inconspicu- ous, non-invasive and ambulatory health monitoring is made possible by lightweight and accessibility. Analysing data in real time. Real-time data storage and analysis are performed on the data collected by the sensors by the mobile PHM application of the MBU, giving the user immediate feedback. PHM systems may vibrate, make a loud noise, or flash information on the screen to warn the user in near real-time of anomalous events or rapid changes. Individualised health care. Depending on the biological profile of the user and the clinical setting, mobile PHM devices can be configured to meet the user’s unique health care requirements and desires. The user’s ethnic background, age and gender could be used to define the clinical criteria of the risk factor under research. Digital data gathering. In comparison to conventional data collection techniques with subsequent transmission to computer systems, mobile PHM devices provide quick digitization of the information captured, considerably enhancing quality and efficiency. A substantial clinical database is made available via ongoing monitoring and later distribution to health-care practitioners for data mining evaluation of pos- sible hazards and/or relationships between clinical features. Protocol for flexible connectivity. A mobile PHM system’s method for commu- nication is quite flexible because local interaction within the BAN can be carried out https://online-journals.org/index.php/i-jim iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 89 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments using WiFi, Bluetooth, or ZigBee, and it is possible to communicate with the outside world via 3G or other readily available web protocols. Medics Doctors Web Persistent Mobile Server Personal Area Network Body Area System Hospice server Wide area system Mobile Fig. 3. Construction of a mobile personal health monitor system 3.3 Data privacy, security and confidentiality In Figure 3, construction of a mobile personal health monitor system is exam- ined. The deployment of mobile PHM systems is significantly hampered by concerns over the safety, anonymity and confidentiality of user health data. A heart patient’s proprietary data, for instance, might be manipulated by fraudsters; Regular read- ings might be changed to indicate a serious issue, and incorrect feedback might even cause the patient to experience a heart attack. On the other hand, the information might be helpful to parties the user did not invite, like insurance firms or superiors, and this access might raise privacy issues. In light of these reasons, security concerns in the setting of mobile medical care must be understood by policymakers and pro- gramme managers in order to establish and implement the appropriate rules and safeguards [13]. 4 IMPLEMENTATION AND EXPERIMENTAL RESULTS The MVI’s hardware and communication interface are described in the concept. It consists of the detectors, system platform and communication interface used by the MVI’s local and distant endpoints. Communication systems and model networks. The client-server network model served as the foundation for each MVI in the publications under examina- tion. For transmission to an external attendant at the faraway (doctor) end, the local (client) end would frequently transmit the sensed signals to an access point device nearby the sensors [14]. Regular access points include the platforms mentioned in the previous section. One improvement in MVI network models worth highlighting is the departure from the physician’s connection to a particular remote server to an instantaneous relationship between the results of the bio-signals and a far-off web server or cloud service. This model was used in five of the articles we reviewed. https://online-journals.org/index.php/i-jim 90 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. The use of this strategy has several benefits. The possibility of “geographically sepa- rating” the biosignals is one of these benefits. Table 1. MVI platforms and protocol types Platforms Custom Devices Laptops Mobile/PDA Protocols for Local-MVI Communication 18  7 2 Protocols for Remote MVI Communication 18  3 4 Cellular/wifi 15 10 3 The purpose of MVIs is to support PHM systems, which place a high priority on portability. Unlike the conventional virtual instrument method, the majority of MVIs employ a customised device or a personal digital assistant (PDA) as their platform, as indicated in Table 1. The two instances of cardiac implantable electronic gadgets that only employ mobile phones to communicate with remote systems were left out of the analysis. Outcomes/results. Medical design development, medical uses, health care data management, mathematical modelling of physiologic systems and medical research applications are only a few of the uses for MVIs [18, 19]. But it appears from a review of the scientific literature that the use of MVIs for PHM is mostly concentrated on a small number of unique disease domains. Table 2. Scenarios for monitoring the heart area No Monitoring Scenario Cases 1 Heart-rate tracking  9 2 persistent heart failure  3 3 Spirometry  2 4 Hypertension  3 5 Amount of blood flowing  2 6 Obstructive snoring  2 Total 21 In Figure 4, these domains are displayed. Over half of these instances fall under the category of cardiovascular disease (CVD). Given that CVDs account for the single largest cause of death worldwide, this is reasonable. Table 2 lists the possibilities for constituent monitoring that fall under the cardiovascular area. MVI 13% 5% 43% 39% Heart diseases Fitness monitoring Harmonal Neurological Fig. 4. Medical virtual instruments domains https://online-journals.org/index.php/i-jim iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 91 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments The term “modality” refers to the anticipated impact on the patient’s health. In 93.3% of the cases examined, extracting, examining and reporting a person’s bio-signals was the only goal. Only three MVI systems (8.7%) responded to the anal- ysis’s findings by initiating some sort of treatment. In the first instance, the diabetic patient’s insulin administration was managed, and in the second, a stimulus was used to prevent the patient from snoring while they were sleeping. 0 1 2 3 4 5 6 Monitoring Reduced Bias Lower healthcare cost Detection of Diseases MVI Effect on Healthcare Perception and satisfication Fig. 5. Comparing the use of MVIs with conventional medical devices for PHM Numerous studies claimed that the MVI technique had a beneficial impact on the usefulness of medical equipment. The most significant justification for employing MVIs was identified in this research as miniaturisation in Figure 5. MVIs give doc- tors the ability to measure the evolution of the disease and to make well-informed decisions free from the prejudice of operators using comparable conventional medical tools. According to one of the research projects on MVIs, they can regulate CIEDs and other implanted devices and keep track of leads, battery level and device impedance. Training attempting to change behaviour and uphold healthy diet and lifestyle utilising personalised feedback from electronic health and mobile-health inter- ventions has demonstrated encouraging outcomes in the prevention of NCDs [15]. A student with a child, for instance, should make childcare plans for the online appointment just as they would for the in-person one. Another disadvantage of vir- tual clinical training may be the lack of input from different clinical dosimetrists. This can be improved by having numerous board-certified medical dosimetrists collaborate with the students, which the clinical instructor can arrange [16, 17]. Diagnosis, decision-making, therapy and administration are all parts of a typical health-care workflow. The implementation of MVIs would most likely affect diag- nostics and decision-making. As a result, it might be required to adapt the organisational structure and pro- cess in health care to account for the usage of MVIs. Along the same lines, work- flows based on the utilisation of MVIs must be included in reimbursement plans. The possibility of websites as a tool for separating the monitoring process from the constraints imposed by location is another factor to keep in mind while consid- ering the difficulties and potential futures of MVI in PHM. MVIs can offer sensors that instantly communicate the signals to an always-on, local, or distant website by https://online-journals.org/index.php/i-jim 92 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. utilising miniaturised integrated circuits and microprocessors. This would enable real-time surveillance and permit simultaneous viewing of the signals by all autho- rised parties. Additionally, it would enable MVIs to benefit from the enormous mem- ory and processing power of the web. 5 CONCLUSION Mobile health is a hot topic right now, and numerous apps are being created to support various health care systems. The field that promotes the mental health of carers is fascinating. However, the majority of systems are static programmes that act as self-help manuals. An innovative approach is suggested in this study to make it possible to create personalised smartphone apps that take each user’s demands into account. Current PHM systems are primarily utilised for specialised purposes and health monitoring. In order to become the system of choice in the contemporary health care industry, PHM equipment must offer higher degrees of adaptability and robustness. The analysis reveals that there are still lots of issues to be solved in the investigation of MVIs’ use in personal health monitoring. Because of the burdensome nature of their circumstances, caring for the elderly is frequently complicated. Health systems must adopt technology-based solutions because of the rising number of older people with ongoing medical conditions and the expanding clinical causes of those illnesses. By presenting the basics of PMH used for older patients, the current research effectively created a list of advantages and difficulties for aged care. Because there were often more advantages than obsta- cles in this study, these data on barriers can help people understand the challenges of developing information systems. 6 REFERENCES [1] S. Pahlevanynejad, S.R. Niakan Kalhori, M.R. Katigari, and R.H. Eshpala, “Personalized mobile health for elderly home care: A systematic review of benefits and challenges,” International Journal of Telemedicine and Applications, vol. 2023, pp. 1–10, 2023. https:// doi.org/10.1155/2023/5390712 [2] S. Orte, C. Migliorelli, L. Sistach-Bosch, M. Gómez-Martínez, and N. Boqué, “A tailored and engaging mHealth gamified framework for nutritional behaviour change,” Nutrients, vol. 15, no. 8, p. 1950, 2023. https://doi.org/10.3390/nu15081950 [3] M. Ferré-Bergadà, A. Valls, L. Raigal-Aran, J. Lorca-Cabrera, N. Albacar-Riobóo, T. Lluch-Canut, and C. Ferré-Grau, “A method to determine a personalized set of online exercises for improving the positive mental health of a caregiver of a chronically ill patient,” BMC Medical Informatics and Decision Making, vol. 21, no. 1, pp. 1–13, 2021. https://doi.org/10.1186/s12911-021-01445-6 [4] E.A. Rosenfeld, C. Lyman, and J.E. Roberts, “Introducing RuminAid: The development and focus group testing of a mobile health app for depression,” JMIR Formative Research, 2022. https://www.researchgate.net/publication/361225148_Introducing_RuminAid_The_ Development_and_Focus_Group_Testing_of_a_Mobile_Health_App_for_Depression [5] K. Wac, R. Bults, B. Van Beijnum, I. Widya, V. Jones, D. Konstantas, and H. Hermens, “Mobile patient monitoring: The MobiHealth system,” In 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE, pp. 1238–1241, 2009. https://doi.org/10.1109/IEMBS.2009.5333477 https://online-journals.org/index.php/i-jim https://doi.org/10.1155/2023/5390712 https://doi.org/10.1155/2023/5390712 https://doi.org/10.3390/nu15081950 https://doi.org/10.1186/s12911-021-01445-6 https://www.researchgate.net/publication/361225148_Introducing_RuminAid_The_Development_and_Focus_Group_Testing_of_a_Mobile_Health_App_for_Depression https://www.researchgate.net/publication/361225148_Introducing_RuminAid_The_Development_and_Focus_Group_Testing_of_a_Mobile_Health_App_for_Depression https://doi.org/10.1109/IEMBS.2009.5333477 iJIM | Vol. 17 No. 16 (2023) International Journal of Interactive Mobile Technologies (iJIM) 93 Patient Monitoring for Personalized Mobile Health (PMH) Based on Medical Virtual Instruments [6] R. Shahriyar, M.F. Bari, G. Kundu, S.I. Ahamed, and M.M. Akbar, “Intelligent mobile health monitoring system (IMHMS),” In Electronic Healthcare: Second International ICST Conference, eHealth 2009, Istanbul, Turkey, September 23–15, 2009, Revised Selected Papers, Springer Berlin Heidelberg, vol. 2, (pp. 5–12), 2010. https://doi. org/10.1007/978-3-642-11745-9_2 [7] U. Varshney, “Mobile health: Four emerging themes of research,” Decision Support Systems, vol. 66, pp. 20–35, 2014. https://doi.org/10.1016/j.dss.2014.06.001 [8] P. Olla and C. Shimskey, “mHealth taxonomy: A literature survey of mobile health applications,” Health and Technology, vol. 4, pp. 299–308, 2015. https://doi.org/10.1007/ s12553-014-0093-8 [9] K. Sleurs, S.F. Seys, J. Bousquet, W.J. Fokkens, S. Gorris, B. Pugin, and P.W. Hellings, “Mobile health tools for the management of chronic respiratory diseases,” Allergy, vol. 74, no. 7, pp. 1292–1306, 2019. https://doi.org/10.1111/all.13720 [10] A. Triantafyllidis, C. Velardo, S.A. Shah, L. Tarassenko, T. Chantler, C. Paton, and K. Rahimi, “Supporting heart failure patients through personalized mobile health monitoring,” In 2014 4th International Conference on Wireless Mobile Communication and Healthcare-Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH), IEEE, pp. 287–290, 2014. https://doi.org/10.4108/icst. mobihealth.2014.257217 [11] X. Ye and M. Chen “Personalized recommendation for mobile internet wealth manage- ment based on user behavior data analysis,” Scientific Programming, vol. 2021, pp. 1–8, 2021. https://doi.org/10.1155/2021/9326932 [12] O. Adeluyi and J.A. Lee “Medical virtual instrumentation for ambient assisted living: Part 1 concepts,” Measurement and Control, vol. 48, no. 6, pp. 167–177, 2015. https://doi. org/10.1177/0020294015569262 [13] L.J. Mena, V.G. Felix, R. Ostos, J.A. Gonzalez, A. Cervantes, A. Ochoa,… and G.E. Maestre, “Mobile personal health system for ambulatory blood pressure monitor- ing,” Computational and Mathematical Methods in Medicine, vol. 2013, 2013. https://doi. org/10.1155/2013/598196 [14] O. Adeluyi and J.A. Lee, “Medical virtual instrumentation for personalized health moni- toring: A systematic review,” Journal of Healthcare Engineering, vol. 6, no. 4, pp. 739–777, 2015. https://doi.org/10.1260/2040-2295.6.4.739 [15] M.R. van Dijk, M.P. Koster, S.P. Willemsen, N.A. Huijgen, J.S. Laven, and R.P. Steegers- Theunissen, “Healthy preconception nutrition and lifestyle using personalized mobile health coaching is associated with enhanced pregnancy chance,” Reproductive Biomedicine Online, vol. 35, no. 4, pp. 453–460, 2017. https://doi.org/10.1016/ j.rbmo.2017.06.014 [16] J. Baker and M. Dehghanpour, “Medical dosimetry virtual clinical education: Mentors’ perspectives,” Medical Dosimetry, vol. 48, no. 2, pp. 98–104, 2023. https://doi.org/10.1016/ j.meddos.2023.01.004 [17] S.G. Kumar, S.S. Sridhar, S.S. Azham Hussain, S.V. Manikanthan, and T. Padmapriya, “Personalized web service recommendation through mishmash technique and deep learning model,” Multimedia Tools and Applications, Springer, vol. 81, no. 7, pp. 9091–9109, 2022. https://doi.org/10.1007/s11042-021-11452-4 [18] A. Setyono, H. Haryanto, and E.Z. Astuti, “An adaptive web-based framework for mobile telemonitoring system,” International Journal of Interactive Mobile Technologies (iJIM), vol. 11, no. 1, pp. 40–52, 2017. https://doi.org/10.3991/ijim.v11i1.6031 [19] R. Arumugam and N. Md Noor, “Mobile apps based on keller personalized system of instruction to promote english vocabulary acquisition,” International Journal of Interactive Mobile Technologies (iJIM), vol. 15, no. 23, pp. 4–17, 2021. https://doi.org/10.3991/ ijim.v15i23.27227 https://online-journals.org/index.php/i-jim https://doi.org/10.1007/978-3-642-11745-9_2 https://doi.org/10.1007/978-3-642-11745-9_2 https://doi.org/10.1016/j.dss.2014.06.001 https://doi.org/10.1007/s12553-014-0093-8 https://doi.org/10.1007/s12553-014-0093-8 https://doi.org/10.1111/all.13720 https://doi.org/10.4108/icst.mobihealth.2014.257217 https://doi.org/10.4108/icst.mobihealth.2014.257217 https://doi.org/10.1155/2021/9326932 https://doi.org/10.1177/0020294015569262 https://doi.org/10.1177/0020294015569262 https://doi.org/10.1155/2013/598196 https://doi.org/10.1155/2013/598196 https://doi.org/10.1260/2040-2295.6.4.739 https://doi.org/10.1016/j.rbmo.2017.06.014 https://doi.org/10.1016/j.rbmo.2017.06.014 https://doi.org/10.1016/j.meddos.2023.01.004 https://doi.org/10.1016/j.meddos.2023.01.004 https://doi.org/10.1007/s11042-021-11452-4 https://doi.org/10.3991/ijim.v11i1.6031 https://doi.org/10.3991/ijim.v15i23.27227 https://doi.org/10.3991/ijim.v15i23.27227 94 International Journal of Interactive Mobile Technologies (iJIM) iJIM | Vol. 17 No. 16 (2023) Sweetline et al. 7 AUTHORS B. Christina Sweetline obtained her bachelor’s degree in Computer Science and Engineering from Karpaga Vinayage College of Engineering and Technology, Tamil Nadu, India; did her Master’s degree in Systems Engineering and Operations Research from the College of Engineering Guindy, Anna University, Chennai, Tamil Nadu, India; and is pursuing a Ph.D. Degree at SRM Institute of Science and Technology, Chennai, Tamil Nadu, India-603203. Currently, she is working as an Assistant Professor in the Department of Computer Science and Engineering at SRM Valliammai Engineering College, Kattankulathur, Tamil Nadu, India-603203. She has more than four years of teaching experience at an engineering College. Her research interests include Big Data Analytics and Image Processing (E-mail: cb4592@srmist.edu.in). Dr. C. Vijayakumaran received his Bachelor degree in Computer Science and Engineering from Madras University and his master’s degree from SRM University in 1994 and 2005, respectively. He got his Doctor of Philosophy (PhD) in Computer Science and Engineering from AISECT University, Bhopal, India. Currently, he is working as an Associate Professor in the department of Computing Technologies at the SRM Institute of Science and Technology, Chennai. He has more than 25 years of teaching experience in the Computer Science and Engineering fields. His research interests include Mobile Ad-hoc Networks, Data Science, Computer Vision and Network Security. He is a fellow of the Institute of Engineers, India (E-mail: vijay- akc@srmist.edu.in). Dr. A. Samydurai obtained his bachelor’s degree in Computer Science and Engineering from the University of Madras. Then he obtained his master’s degree in Computer Science and Engineering and PhD in Information Communication and Engineering, majoring in Distributed Systems, Peer-to-Peer Systems, Middleware and Fault Tolerance Systems, from Anna University, Tamil Nadu, India. Currently, he is working as a Professor in the Department of Computer Science and Engineering at SRM Valliammai Engineering College, SRM Nagar, Kattankulathur-603203. His spe- cialisations include Distributed Systems, Cloud Computing, Big Data and Internet of Things and Virtual Reality. He has received many research grants under DST-NIMAT, MEITY and DST-SERB. He is a member of the ISTE, CSI and Indian Science Congress (E-mail: samyduraia.cse@srmvalliammai.ac.in). https://online-journals.org/index.php/i-jim mailto:cb4592@srmist.edu.in mailto:vijayakc@srmist.edu.in mailto:vijayakc@srmist.edu.in mailto:samyduraia.cse@srmvalliammai.ac.in