Healthcare: An Ever-Evolving Field Embracing

Change and Practical Application

1st Prof. Pushpavati V. Kanaje 2nd Pratik Raj Dahal 3rd Shivam Anant Ghorpade
dept. of Computer Engineering dept. of Computer Engineering dept. of Computer Engineering
JSPM’s RSCOE JSPM’s RSCOE JSPM’s RSCOE
Pune, India Pune, India Pune, India
pkanaje [email protected] [email protected] [email protected]

4th Aditya Jaikumar Sharma 5th Atharva Dinesh Phatak 6th Parth Ravindra Sawant
dept. of Computer Engineering dept. of Computer Engineering dept. of Computer Engineering
JSPM’s RSCOE JSPM’s RSCOE JSPM’s RSCOE
Pune, India Pune, India Pune, India
[email protected] [email protected] [email protected]

Abstract—In this paper, we strive to explore the various

technologies that can be implemented to streamline the process of
getting medication, and to make this a patient-centric experience.
Exploring all the various solutions and methods that we can
implement. Furthermore, these advancements will be beneficial
as it will strive to remove the discrepancies that persist in the
conventional methods. The advent of all the new technologies
open up numerous doors for the medical sector to improve sub-
stantially and to make advances beyond what the existing models
can do. Incorporation of various techniques like telemedicine,
digital health records, and mobile health apps have all been put
into test in the past few years. But, with the surge of new methods
and techniques these existing techniques can further be enhanced
and be made to work a lot more efficiently both figuratively and
literally.
Index Terms—streamline, patient-centric, advancements, ex-
ploring, beneficial, discrepancies, improve, substantially, digital,
health records Fig. 1. Pillars of Quality

I. I NTRODUCTION
Any decent healthcare system has a set of standards: access A procedure focused on improving the overall system by
to healthcare provided must be easily accessible, affordable, enhancing the six pillars of quality – to ensure safe, patient-
and enabling its sustainability in a long-term measure. One centric, timely, effective, equitable, and efficient care. With
major problem with the current healthcare system is how major emphasis on Evidence Based Medicine, this approach
tightly and intricately intertwined it is with public and pri- encourages a paradigm shift toward developing a system
vate healthcare providers that have their set of directives designed to generate and apply evidence-based insights that
and guidelines on how services are accorded to individuals inform healthcare decisions for both patients and providers,
[1]. The fragmentation creates discontinuities in the medical thereby promoting quality and safety in healthcare. In this
record, leading to potential errors, which are very dangerous paper, we strive to encompass all these modules to formulate
in such a sensitive field. These, in turn, mandate the need for a working system that adheres to the Pillars of Quality and
an integrated, centralized framework that collaborates among accounts for all the changes that the new technology has
service providers. brought forth.
There have been numerous research conducted on how Our system integrates best practices in telemedicine, Health
effective the system that is being used to deliver the services Information Exchanges (HIE), Artificial Intelligence, Virtual
to a patient are. As discussed in [2] which estimated a Nursing, Wearable Devices, Electronic Health Records (EHR),
whopping 98,000 patients die annually because of all humane Electronic Medical Records (EMR), and ERP integration [3].
errors, thereby shedding light on a call for action to improve The degree to which respective governing authorities influence
the quality of the service that is currently being imparted. the system varies by country and legal framework (e.g., the
National Health Authority (NHA) in India plays a crucial role • Limited Physical Examination: The absence of physical
in healthcare governance) [4]. However, things like the security examinations does limit the diagnosing capability of the
of data, patient privacy, interoperability, and compliance with clinician. [12]
regulatory standards-all norms as far as topics dealing with
critical data like medical records-will be spoken to along the B. Health Information Exchanges (HIE)
way. Modernizing healthcare necessitates migrating from paper-
based records to digital workflows. Data interoperability, or the
II. PATIENT-C ENTRIC A PPROACH electronic transfer and sharing of data among organizations, is
It involves understanding how patients view and recognize critical in modern healthcare [13]. Research indicates that over
their values and establishes a partnership between health 70% of patients use multiple healthcare facilities, necessitating
providers and patients along with their families. Thus, the efficient data storage, retrieval, and sharing [14]. Data security
approach places the patient in the driving seat in care decisions measures such as encryption, two-factor authentication, and
and aligns medical practices with the patient’s preference and adherence to local cybersecurity recommendations are essen-
needs [5]. tial [15].
The other standards of quality are automatically achieved Pros:
by following the patient-centered approach, which reinforces • Improved Care Coordination: HIE allows for seamlessly
effectiveness and efficiency due to improved communication sharing patient data across institutes, enhancing care
[6]. The communication between the patient and the practi- coordination and reducing redundant tests and treatments
tioner will improve the decision making, information sharing, [13].
relationship establishing, and educating the patient to ensure • Cost Reduction: HIE lowers healthcare utilization, mak-
timely and safe treatment [7]. The patients, by knowing their ing services more accessible [16].
symptoms and taking necessary precautions, achieve better
Cons:
navigation through health care [8].
• Data Privacy Concerns: Despite security measures, data
III. T HE T ECHNOLOGY AT A G LANCE breaches and unauthorized access remain risks [13].
To avoid over extending the scope of the paper, we have • Inconsistent Data Standards: Variation in data standards

discussed every technology along with its implication in the among providers can lead to discrepancies [17].
context of our system which aims to create a framework that
C. Electronic Health Records (EHR)
adapts to the changing technology in the healthcare sector.
With the digitalization and modernization of every sector,
A. Telemedicine healthcare is no exception. Such transformation play a crucial
As defined in [9] telemedicine is “the incorporation of role in ensuring that the services being given are up to the
electronic information and communication technologies to standard. One such technique is the EHR - a systematic
deliver the healthcare services when distance separates the electronic collection of health information about patients such
participants”. Telemedicine has become indispensable when as medication orders, medical history, laboratory results, radi-
it comes to linking the clinicians and the patients [10]. ology reports, vital signs, and the clinicians notes. [18]
Telemedicine application can broadly be categorized into one Incorporation of EHR with the current system ensures that
of these two types: ”real-time” and ”store-and-forward.” The the healthcare organizations can achieve a holistic view of
Real-time approach enables for an immediate communication the entire process and carter to the effective and precise
between the healthcare providers and their patients via phone medication of the patient, hence reducing the expenditure
or video conferencing. Whilst, the store-and-forward methods that is needed to be incurred by the patient in order to
involves the use of gathered data, such as medical images or get his medical track history upon switching to a different
vital statistics, and sending them to healthcare professionals service provider. [19] This will also serve to highlight the
for evaluation at a later stage [11]. opportunities for the healthcare service providers to cut down
Pros: on the cost. [20]
• Increased Accessibility: Telemedicine promotes access Pros:
by reducing the burden of travel, enables self-care, and • Enhanced Patient Care and Safety: EHRs offer up-to-date
improves equity in access to health. patient data, facilitating improved treatment [21].
• Cost Efficiency: Minimizes travel costs to enable the • Cost Reduction: Streamlined data exchange minimizes
delivery of services, which is a way of reducing expenses costs for both patients and providers [22].
for both patients and providers in telemedicine. Cons:
Cons: • Implementation Costs and Training: Initial setup and
• Technology Limitations: Can pose challenges for indi- training for EHRs can be costly and disruptive [23].
viduals with limited access to the internet or devices, • Data Privacy Concerns: The digitization of health records
potentially excluding certain populations from receiving raises security risks, such as unauthorized access and data
care. breaches [24].
D. Electronic Medical Records (EMR)
EMR is similar to EHR with the main difference being,
EMR is used by a single organization to store data about a
patient. [25] Hence, an EHR is a comprehensive report of the
patient’s health whilst the EMR refers to the narrower view
of Patient’s medical history.
Pros: Improved Data Quality: EMRs improve the accuracy
and timeliness of patient data [26].
Cons: Training Requirement: Working with EMRs requires
significant training [27].

E. Virtual Nurse
Chronic illness such as heart disease, hypertension, and
diabetes often require continuous if not frequent monitoring
to ensure the wellness of the patient so, that their conditions
do not deteriorate even further. [28] This constant need for
observation requires for the hiring of a professional healthcare
provider often in the form of a nurse. Hiring a dedicated
professional is often a big financial burden for the patient.
Implementing an AI-powered virtual nurse could enhance
the patient experience by providing personalized care. This Fig. 2. System Diagram
system would assist both doctors and patients by effectively
addressing potential hazards through evidence-based treatment
[29]. By actively monitoring all bodily signals during treat- The integration of data from virtual nursing, and telemedicine
ment, the virtual nurse can help make informed decisions that allows the HIE to monitor in real time and make personalized
contribute to the patient’s overall well-being [30]. adjustments to care. For instance, wearable devices monitor
Pros: the patient’s vitals and update the healthcare professional in
real time or may be quite crucial to monitor chronic conditions
• Personalized Care: Treatment is tailored according to a
or high-risk patients remotely. Virtual nurse services, on the
patient’s vitals and symptoms [31].
other hand, use AI in providing personalized automated care
• Cost Savings: Reduces the need for in-person consulta-
recommendations that ensure timely guidance is accorded
tions and professional hiring [32].
to the patients and monitoring without necessarily having
Cons: consultations face-to-face.
• Reduced Human Interaction: Lack of face-to-face inter- The system integrates ERP to manage resources and
action may affect patient satisfaction [33]. comply with regulations. This is a back-end feature that
• Technology Dependency: System downtime can disrupt smoothes operation efficiency in managing the resources at the
care [34]. healthcare network right from staffing to inventory. In addition,
compliance with standards pertaining to data privacy and
IV. P ROPOSED S YSTEM
security is guaranteed through strict adherence to regulatory
The system diagram depicts the integrated healthcare model, requirements, such as compliance with requirements by the
which is designed through various digital health technologies National Health Authority (NHA), where applicable. In sum,
that make patient care and handling of data easier. EHR and this digitally interconnected environment is patient-centered,
EMR are the central interaction points of the entire architec- with a highlighting emphasis on accessibility and security
ture; they store patient data and medical history. Where the of data while there is efficiency in the delivery of care,
EHR allows more shared data among providers of healthcare, thus reducing the administrative burden from providers of
the EMR offers a more localized view, allowing for easy access healthcare.
to vital information about the patient within the walls of a
single organization. The Patient Portal, connected with both, V. A LGORITHMS U SED IN THE S YSTEM
will permit patients to be able to access their records, manage
their appointments, and access telemedicine services. This is
the bridge to the patient from the provider, allowing the patient
to take more ownership of their personal health information
and engage them further.
On the data-sharing front, the Health Information Ex-
change component provides interoperability and secure trans-
mission of data across a wide variety of healthcare entities.
 TABLE I
A LGORITHMS USED IN THE SYSTEM

Algorithm Use Case Strengths Weaknesses

Random Forest [35] Predicting patient outcomes using High accuracy; handles large Can be slow with large datasets;
EHR and wearable data (e.g., read- datasets well; interpretable feature prone to overfitting without tuning.
mission risk, disease progression). importance.
Support Vector Machine (SVM) [36] Used in telemedicine for diagnos- Performs well in high-dimensional Computationally demanding with
tic classification, identifying dis- spaces; resistant to overfitting. large datasets.
ease types from symptoms.
K-Nearest Neighbors (KNN) [37] Patient similarity matching for per- Simple; interpretable; effective for Sensitive to noise; computationally
sonalized care recommendations in smaller datasets. expensive with large data.
patient portals.
Logistic Regression [38] Commonly used for binary predic- Easy to interpret; computationally Assumes linear relationship; lim-
tive tasks, such as disease pres- efficient; suitable for binary classi- ited to binary or ordinal outcomes.
ence/absence. fication.
K-Means Clustering [39] Segmentation of patient popula- Simple to implement; effective for May not perform well with com-
tions for targeted interventions or clustering large datasets. plex clusters; sensitive to initial
treatments. cluster assignment.
Naive Bayes [40] Disease diagnosis based on pa- Fast; handles large datasets well; Assumes independence of features,
tient symptoms and history; used in good for high-dimensional data. which may not hold in complex
telemedicine for probabilistic pre- medical data.
dictions.
Neural Networks (Deep Learning) [41], [42] Complex image analysis, such as Capable of learning complex pat- Requires large datasets; computa-
identifying anomalies in medical terns; highly accurate in image tionally expensive; challenging to
imaging (e.g., radiology, pathol- recognition tasks. interpret.
ogy).
Decision Tree [43] Treatment recommendation sys- Easy to interpret; visual; useful for Prone to overfitting; can be unsta-
tems by modeling decision-making non-linear relationships. ble with slight data variations.
processes.
Gradient Boosting [44] Predictive modeling for patient out- High predictive accuracy; handles Computationally intensive; prone
comes, such as likelihood of recov- mixed data types well. to overfitting with noisy data.
ery post-treatment.

VI. C ONCLUSION R EFERENCES

[1] A. Kumar, “The Transformation of The Indian Healthcare
System,” Cureus, vol. 15, no. 5, p. e39079. Available:
https://doi.org/10.7759/cureus.39079
The proposed healthcare system uses a patient-centered [2] I. of Medicine (US), “The Changing Nature of Health Care,” in
approach, integrating digital health technologies to improve Evidence-Based Medicine and the Changing Nature of Healthcare: 2007
patient care and data management. Key components like IOM Annual Meeting Summary. National Academies Press (US), 2008.
Available: https://www.ncbi.nlm.nih.gov/books/NBK52825/
Electronic Health Records (EHR) and Electronic Medical [3] “Transforming healthcare with AI: The impact on
Records (EMR) serve as data hubs, facilitating secure, in- the workforce and organizations,” McKinsey. Avail-
teroperable exchanges between healthcare providers through able: https://www.mckinsey.com/industries/healthcare/our-
insights/transforming-healthcare-with-ai
Health Information Exchanges (HIEs). Patients gain greater [4] M. Trivedi, A. Saxena, Z. Shroff, and M. Sharma, “Experi-
access to their own health data via patient portals, which also ences and challenges in accessing hospitalization in a government-
support telemedicine services, empowering them to engage funded health insurance scheme: Evidence from early implemen-
tation of Pradhan Mantri Jan Aarogya Yojana (PM-JAY) in In-
more actively in their healthcare. Additional technologies, dia,” PLOS ONE, vol. 17, no. 5, p. e0266798, 2022. Available:
such as wearable devices, virtual nursing, and AI algorithms, https://doi.org/10.1371/journal.pone.0266798
enable real-time, personalized monitoring, while Enterprise [5] S. Edgman-Levitan and S. C. Schoenbaum, “Patient-centered care:
achieving higher quality by designing care through the patient’s eyes,”
Resource Planning (ERP) systems streamline resources and Israel Journal of Health Policy Research, vol. 10, p. 21, 2021. Available:
ensure regulatory compliance, all within a secure framework. https://doi.org/10.1186/s13584-021-00459-9
[6] E. Wong, F. Mavondo, and J. Fisher, “Patient feedback to improve
Despite these advancements, the system faces challenges quality of patient-centred care in public hospitals: a systematic review
that impact its accessibility and security. Relying heavily on of the evidence,” BMC Health Services Research, vol. 20, no. 1, p. 530,
technology can create barriers for patients lacking digital 2020. Available: https://doi.org/10.1186/s12913-020-05383-3
[7] S. H. Sharkiya, “Quality communication can improve patient-centred
access or literacy, particularly in underserved regions. Data health outcomes among older patients: a rapid review,” BMC
privacy and security remain significant concerns, with the Health Services Research, vol. 23, no. 1, p. 886, 2023. Available:
potential for sensitive health data breaches. Implementation https://doi.org/10.1186/s12913-023-09869-8
[8] A. Kwame and P. M. Petrucka, “A literature-based study of patient-
costs and the need for extensive training add complexity, and centered care and communication in nurse-patient interactions: barriers,
inconsistent data standards across providers may hinder seam- facilitators, and the way forward,” BMC Nursing, vol. 20, no. 1, p. 158,
less care coordination. Addressing these issues is essential to 2021. Available: https://doi.org/10.1186/s12912-021-00684-2
[9] Committee on Evaluating Clinical Applications of Telemedicine,
realizing an inclusive, efficient, and effective healthcare model I. of M. (US), and M. J. Field, “Introduction and Background,”
that truly benefits patients and providers alike. in Telemedicine: A Guide to Assessing Telecommunications in
 Health Care. National Academies Press (US), 1996. Available: [28] S. Sukmawati, “Nursing Care for Chronic Disease,” Advances in
https://www.ncbi.nlm.nih.gov/books/NBK45440/ Healthcare Research, vol. 2, no. 1, Article 1, 2024. Available:
[10] A. Haleem, M. Javaid, R. P. Singh, and R. Suman, “Telemedicine https://doi.org/10.60079/ahr.v2i1.361
for healthcare: Capabilities, features, barriers, and applications,” [29] Tech Reverb Group, “Rise of Medical Virtual Assistants (MVAs)
Sensors International, vol. 2, p. 100117, 2021. Available: — Future of Healthcare,” Healthcare Readers, 2024. Available:
https://doi.org/10.1016/j.sintl.2021.100117 https://healthcarereaders.com/insights/medical-virtual-assistants-mvas-
[11] R. Hirani et al., “Artificial Intelligence and Healthcare: A in-healthcare
Journey through History, Present Innovations, and Future [30] S. Maleki Varnosfaderani and M. Forouzanfar, “The Role of AI
Possibilities,” Life, vol. 14, no. 5, Article 5, 2024. Available: in Hospitals and Clinics: Transforming Healthcare in the 21st Cen-
https://doi.org/10.3390/life14050557 tury,” Bioengineering, vol. 11, no. 4, Article 4, 2024. Available:
[12] Committee on Evaluating Clinical Applications of Telemedicine, https://doi.org/10.3390/bioengineering11040337
I. of M. (US), and M. J. Field, “Findings and Recommenda- [31] T. A. Rincon, “Telehealth and Virtual Nursing: Solutions That Challenge
tions,” in Telemedicine: A Guide to Assessing Telecommunications the Status Quo,” AACN Advanced Critical Care, vol. 34, no. 4, pp.
in Health Care. National Academies Press (US), 1996. Available: 312–313, 2023. Available: https://doi.org/10.4037/aacnacc2023637
https://www.ncbi.nlm.nih.gov/books/NBK45443/ [32] M. Schultz, “Telehealth and Remote Patient Monitoring Innova-
tions in Nursing Practice: State of the Science,” OJIN: The On-
[13] “Health Information Exchange: Understanding the Policy Landscape
line Journal of Issues in Nursing, vol. 28, no. 2, 2023. Available:
and Future of Data Interoperability - PMC,” PMC, 2024. Available:
https://doi.org/10.3912/OJIN.Vol28No02ST01
https://pmc.ncbi.nlm.nih.gov/articles/PMC10751121/
[33] J. Allen, “Exploring Adult Patients’ Perceptions and Experiences of
[14] J. D. D’Amore et al., “Clinical data sharing improves quality measure- Telemedicine Consultations in Primary Care: A Qualitative Systematic
ment and patient safety,” Journal of the American Medical Informatics Review,” International Journal of Medical Students, vol. 10, no. 3,
Association: JAMIA, vol. 28, no. 7, pp. 1534–1542, 2021. Available: Article 3, 2022. Available: https://doi.org/10.5195/ijms.2022.1363
https://doi.org/10.1093/jamia/ocab039 [34] C. Rutledge and T. Gustin, “Preparing Nurses for Roles in
[15] M. S. Jalali, A. Landman, and W. J. Gordon, “Telemedicine, privacy, and Telehealth: Now is the Time!,” OJIN: The Online Journal
information security in the age of COVID-19,” Journal of the American of Issues in Nursing, vol. 26, no. 1, 2021. Available:
Medical Informatics Association, vol. 28, no. 3, pp. 671–672, 2021. https://doi.org/10.3912/OJIN.Vol26No01Man03
Available: https://doi.org/10.1093/jamia/ocaa310 [35] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp.
[16] N. Menachemi, S. Rahurkar, C. A. Harle, and J. R. Vest, “The benefits 5–32, 2001. Available: https://doi.org/10.1023/A:1010933404324
of health information exchange: an updated systematic review,” Journal [36] C. Cortes and V. Vapnik, “Support-vector networks,” Machine
of the American Medical Informatics Association, vol. 25, no. 9, pp. Learning, vol. 20, no. 3, pp. 273–297, 1995. Available:
1259–1265, 2018. Available: https://doi.org/10.1093/jamia/ocy035 https://doi.org/10.1007/BF00994018
[17] J. Walker et al., “The value of health care information exchange and [37] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE
interoperability,” Health Affairs (Project Hope), Suppl Web Exclusives, Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967.
W5-10-W5-18, 2005. Available: https://doi.org/10.1377/hlthaff.w5.10 Available: https://doi.org/10.1109/TIT.1967.1053964
[18] P. Campanella et al., “The impact of electronic health records on [38] “Introduction to the Logistic Regression Model,” in
healthcare quality: a systematic review and meta-analysis,” European Applied Logistic Regression, pp. 1–30, 2000. Available:
Journal of Public Health, vol. 26, no. 1, pp. 60–64, 2016. Available: https://doi.org/10.1002/0471722146.ch1
https://doi.org/10.1093/eurpub/ckv122 [39] J. MacQueen, “Some methods for classification and analysis of
[19] O. Sanyer, J. M. Butler, K. Fortenberry, T. Webb-Allen, and D. Ose, multivariate observations,” in Proceedings of the Fifth Berkeley
“Information sharing via electronic health records in team-based care: Symposium on Mathematical Statistics and Probability, vol. 5, no. 1,
the patient perspective,” Family Practice, vol. 38, no. 4, pp. 468–472, pp. 281–298, 1967. Available: https://projecteuclid.org/ebooks/berkeley-
2021. Available: https://doi.org/10.1093/fampra/cmaa145 symposium-on-mathematical-statistics-and-probability/Proceedings-
[20] N. Nwosu, “Reducing operational costs in healthcare through ad- of-the-Fifth-Berkeley-Symposium-on-Mathematical-Statistics-
vanced BI tools and data integration,” World Journal of Advanced and/chapter/Some-methods-for-classification-and-analysis-of-
Research and Reviews, vol. 22, pp. 1144–1156, 2024. Available: multivariate-observations/bsmsp/1200512992
https://doi.org/10.30574/wjarr.2024.22.3.1774 [40] McCallum, A., Nigam, K. (n.d.). A Comparison of Event Models for
Naive Bayes Text Classification.
[21] M. B. Buntin, M. F. Burke, M. C. Hoaglin, and D. Blumenthal, [41] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,”
“The benefits of health information technology: a review of the Nature, vol. 521, no. 7553, pp. 436–444, 2015. Available:
recent literature shows predominantly positive results,” Health Af- https://doi.org/10.1038/nature14539
fairs (Project Hope), vol. 30, no. 3, pp. 464–471, 2011. Available: [42] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neu-
https://doi.org/10.1377/hlthaff.2011.0178 ral Computation, vol. 9, no. 8, pp. 1735–1780, 1997. Available:
[22] C.-J. Hsiao and E. Hing, “Use and characteristics of electronic health https://doi.org/10.1162/neco.1997.9.8.1735
record systems among office-based physician practices: United States, [43] Quinlan, J. R. (1986). Induction of deci-
2001-2013,” NCHS Data Brief, no. 143, pp. 1–8, 2014. sion trees. Machine Learning, (1), 81–106.
[23] L. Poissant, J. Pereira, R. Tamblyn, and Y. Kawasumi, “The impact of [https://doi.org/10.1007/BF00116251](https://doi.org/10.1007/BF00116251)
electronic health records on time efficiency of physicians and nurses: [44] “XGBoost,” in Proceedings of the 22nd ACM SIGKDD International
a systematic review,” Journal of the American Medical Informatics Conference on Knowledge Discovery and Data Mining, 2024. Available:
Association: JAMIA, vol. 12, no. 5, pp. 505–516, 2005. Available: https://dl.acm.org/doi/10.1145/2939672.2939785
https://doi.org/10.1197/jamia.M1700
[24] W. Raghupathi and V. Raghupathi, “Big data analytics in healthcare:
promise and potential,” Health Information Science and Systems, vol. 2,
p. 3, 2014. Available: https://doi.org/10.1186/2047-2501-2-3
[25] USF Health Online, “EHR vs EMR: What’s the Difference?,”
2017. Available: https://www.usfhealthonline.com/resources/health-
informatics/ehr-vs-emr/
[26] A. Uslu and J. Stausberg, “Value of the Electronic Medical Record
for Hospital Care: Update From the Literature,” Journal of Medi-
cal Internet Research, vol. 23, no. 12, p. e26323, 2021. Available:
https://doi.org/10.2196/26323
[27] A. D. Benedictis et al., “Electronic Medical Records implementation
in hospital: An empirical investigation of individual and organizational
determinants,” PLOS ONE, vol. 15, no. 6, p. e0234108, 2020. Available:
https://doi.org/10.1371/journal.pone.0234108