This article introduces the CoMediC platform, an important innovation in the field of medical data collection and management, designed to enhance collaboration among researchers, healthcare professionals, and patients. CoMediC aims to optimize the eficiency and quality of medical data collection, processing, and analysis by integrating advanced services such as dynamic project management, data normalization, real-time communication, and enhanced security measures. The platform stands out for its ability to facilitate participatory and collaborative collection of multimodal data, providing a secure and adaptive environment for a variety of research projects. Furthermore, CoMediC ofers customizable roles with specific permissions tailored to the needs of each project and is characterized by its efectiveness in normalizing and processing data for robust analysis. The article presents an overview of CoMediC's architecture and features, highlighting its essential components and providing detailed descriptions along with practical examples of its implementation. The validation of the platform according to an experimental protocol has demonstrated its relevance for real projects of multimodal medical data collection, afirming its crucial role in advancing medical research and personalized healthcare.
The digital era has revolutionized the collection, management, and use of medical data. However, this
change is accompanied by significant challenges, such as security, standardization, and efective use
of data [
The collection and management of medical data present significant obstacles in the healthcare domain
[
For this we create CoMediC platform which aims to achieve several essential objectives in the field of medical data management. Firstly, the goal is to create and build a platform that’s can efectively gather, process, and standardize medical data from diferent sources. Additionally, the platform provides a wide variety of services that facilitate the development of data collection projects, management of members, generation of personalized forms, and medical data management. By ofering dynamic and adaptive data collection methods, CoMediC empowers users to gather diverse datasets for comprehensive analysis and decision-making. Additionally, robust security measures, including JWT (JSON Web Tokens), Two-Factor Authentication (2FA), password management, and blockchain integration, ensure the confidentiality and integrity of medical data, enhancing trust and regulatory compliance. Additionally, CoMediC aims to facilitate remote collaboration among healthcare professionals, including doctors. It achieves this by ofering tools for team coordination, secure sharing of images and medical data, and decision assistance for therapeutic procedures. The CoMediC platform aims to become a central instrument in the healthcare ecosystem by simplifying and improving medical data management while encouraging collaboration and expertise exchange among healthcare practitioners.
The CoMediC platform is a significant development in the realm of medical data collection and administration, ofering a secure and cooperative setting for researchers, healthcare providers, and patients. CoMediC seeks to improve the eficiency and quality of medical data collecting, processing, and analysis by including advanced features including project management, data normalization, real-time collaboration, and improved security. This platform facilitates the creation and management of data collection projects, performing data processing and normalization operations, real-time collaboration with other participants in the medical field, and ensure the confidentiality and security of sensitive information. CoMediC supports collaboration and medical research by ofering a safe and user-friendly environment, consequently promoting the progress of knowledge and practices in the healthcare field. When we examine the fundamental principles of the CoMediC platform, we are prompted to consider essential questions that illuminate its ability to adapt, include active participation, and efectively collect diverse medical data to improve healthcare practices, these questions are:
1- How can the CoMediC platform create a collaborative environment for academics, healthcare professionals, and patients, encouraging their active involvement in collecting and analysis of data? 2-In what ways does the adaptability of the CoMediC platform allows users to customize data collection projects according to specific research objectives and clinical requirements? 3-What modalities of medical data does the CoMediC platform support, and how does it ensure comprehensive and accurate data collection to facilitate robust analysis and decision-making in healthcare contexts?
4-How does the CoMediC platform uses advanced technologies and methodologies to improve security measures, protecting sensitive medical information and ensuring compliance to privacy requirements?
Our paper is structured as follows: Section 2 presents a review of existing systems and research on medical data management, followed by a comparative analysis of existing platforms. In the next section, we delve into the architecture of CoMediC, detailing its key components and functionalities in the Architecture and Security section. Subsequently, we outline the methodology for managing data collection projects in the Project Management for Data Collection section and describe the data processing workflows employed in the Data Processing and Standardization section. Following this, we discuss the security measures implemented within CoMediC in the security measures section. Section 4 contains the validation protocol for assessing CoMediC’s eficacy in data collection, where we focus on mental health and addiction studies. Finally, we conclude by summarizing the key findings and discussing potential future advancements in the Conclusion section.
In recent years, there has been an increasing focus on developing platforms and websites specifically
designed for the collection of medical data. These platforms aim to streamline the process of data
entry, storage, and retrieval, ultimately contributing to improved patient outcomes and more eficient
healthcare delivery. In medical data collection and management, current systems and research have
shifted toward the implementation of specialized platforms and websites that facilitate secure and
eficient data collection [
In comparison to existing platforms, CoMediC demonstrates several unique features and advantages. While Electronic Health Record (EHR) systems demonstrate proficiency in the storage and retrieval of patient medical records, they may encounter obstacles related to data privacy and interoperability that restrict their applicability to diverse research projects [21]. Likewise, while platforms such as REDCap provide specialized functionalities to support experiments, their use may be limited when it comes to diverse healthcare domains [22]. In addition, it should be noted that while platforms like OpenClinica and CliniOps ofer comprehensive solutions for the management of clinical data, their applicability is frequently restricted to particular domains, which impacts the entire healthcare industry [23]. However, specialized platforms that concentrate on particular medical domains ofer valuable insights but are deficient in the adaptability necessary for broad implementation. Although mobile health (mHealth) applications improve patient engagement, they encounter obstacles regarding regulatory compliance and data security [24]. On the other hand, CoMediC provides a unified solution that serves as an intermediary between specialized platforms, supporting all areas of the healthcare sector. This includes pharmaceutical and biomedical organizations, healthcare institutions, researchers, and healthcare professionals. Providing a variety of services including member management, data analysis, processing, and standardization, CoMediC facilitates dynamic, adaptive, multimodal, and generic data collection methods, empowering users to gather diverse datasets for comprehensive analysis and decision-making. Additionally, the platform serves as a comprehensive solution for healthcare, enabling eficient collaboration and data management across diverse participants. With robust security measures like JWT (JSON Web Tokens), Two-Factor Authentication (2FA), password management, and blockchain integration, it ensures the confidentiality and integrity of medical data, enhancing trust and regulatory compliance. Table 1 describes a comparison of diferent features in various medical data management platforms.
The CoMediC platform demonstrates a commitment to improving the cooperative gathering of medical data through its structure. The platform is created with carefully developed layers, each accomplishing specific purposes, to enable smooth user interaction, efective data management, and system integrity. Figure 1 shows the architecture of our platform, highlighting the interaction between the many layers of the CoMediC platform. It emphasizes the functions and relationships of each layer within the larger system.
User Interface Layer: The CoMediC platform’s User Interface Layer functions as the main interface for a wide range of users, such as administrators, healthcare practitioners, patients, researchers, and others. Users are assigned roles such as administrators, initiators, or participants, each with unique tasks and privileges to ensure successful collaboration.
-Administrators are responsible for supervising important duties such as managing user accounts, managing roles and permissions, and tracking activities. Their responsibilities involve managing user accounts, controlling access, administering databases, and monitoring member actions using timestamps for audit purposes.
-Initiators drive project activities by creating projects, designing data collection forms, generating feedback, and adding members. In addition, they have the capability to import existing data into projects, and ensuring continuous progress and high eficiency.
-Participants, including researchers, doctors, and patients, actively contribute to the process of data collecting and analysis. They participate in projects, collect data, consult notifications, and get their medical data. Patients can actively participate in questionnaires, encouraging participation in healthcare.
Platform Core Layer: The CoMediC platform’s design includes the Platform Core Layer, which consists of essential modules that are required for the system’s operation and functionality. This layer consists of several modules, including user administration, project management, form management, data collection management, feedback management, chat, and forum.
-User management: The user management module is responsible for controlling users with various roles, ensuring eficient role-based access control and user administration.
-Project management and data collection: These modules play an essential role in data gathering initiatives by supporting eficient project coordination and the development of personalized data collection forms, resulting in eficient data collection operations.
-Feedback: The feedback module encourages participant involvement by facilitating the collection of valuable input after each project. Each project includes a customized feedback form that is suited to its individual needs.
-Chat and forum: These modules facilitate communication and collaboration among users by ofering platforms for real-time messaging through chat module and exchanging questions and ideas within the forum.
Data Processing Layer: CoMediC’s data management infrastructure is specifically built to easily collect, possess, and standardize a wide range of medical data formats. This allows for comprehensive evaluation and analysis, resulting in improved healthcare insights.
-Data collection module: The data collection feature facilitates the gathering and integration of raw data from many sources. This module ensures comprehensive data capture, including text, numerical, and multimedia formats, to support multi-modal data analysis and interpretation.
-The data processing module: It is a module that consists of algorithms and methodologies that are used to preprocess and transform raw data into useful information. This module includes methods for improving the quality and relevance of data through processes such as cleaning, transformation, and augmentation. These approaches are aimed at preparing the data for further analysis.
-Normalization module: Normalization approaches at the Data Processing Layer aim to standardize and unify data formats and structures to ensure consistency and compatibility. This ensures uniformity among diverse data sources, facilitating smooth integration and analysis across various projects and datasets.
Server Layer: This layer is composed of file server, database server and mail server. -File Server: This server is responsible for managing and storing files. It facilitates the storage and organization of many file formats, including documents, videos, pictures, and other media. The File Server ofers eficient and organized file access for users and applications through the network. It typically consists of functionality for sharing files, controlling access, and backing up data to ensure the integrity and availability of information.
-Database Server: This server is responsible for hosting and managing databases that store structured data for the application. It ofers several functions such as data querying, indexing, transaction management, and data replication to efectively manage the data requirements of the application. The Database Server is capable of supporting many types of databases, including relational databases (such as MySQL and PostgreSQL) and NoSQL databases (such as MongoDB and Redis), depending on the specific needs of the application. In our case we used a MongoDB.
-Mail Server: This server is responsible for sending, receiving, and management of emails inside its network. The services provided include the management of email delivery, receipt, redirection, and archiving for both users and applications.
Security layer: The security of a web application is an essential and important aspect. In order increase the security of our system, we included various measures such as Two-Factor Authentication (2FA), JSON Web Tokens (JWT), password management, and blockchain technology. Two-Factor Authentication (2FA) improves security by requiring users to provide two distinct forms of identification, while JSON Web Tokens (JWT) provide a secure means of authorization and authentication. Implementing password security measures such as password encryption, enforcing requirements, and implementing policies such as password expiration and account lockout are essential elements of good password management techniques. In addition, blockchain technology provides security and integrity through its transparent and decentralized data storage capabilities.
The management of medical data collection projects within the CoMediC platform is based on an eficient method with the goal of ensuring accuracy and uniformity through the process. This methodology includes several key steps, such as the initial project planning, allocation of necessary resources, definition of specific data collection objectives, design of forms specific to the project’s needs, and the creation of precise procedures for data collection, storage, and analysis. In addition, the methodology contains mechanisms for continuous monitoring and evaluation to track the progress of the project, identify any potential challenges or issues, and implement appropriate corrective measures to ensure the quality and relevance of the collected data.
The CoMediC platform provides a range of tools and features specifically designed for managing projects and cooperation among all of the participants involved in medical data collection. These tools include intuitive dashboards that provide an overview of project progress, task management functions to monitor activities and deadlines, notification systems to inform members of updates or important events, and real-time communication features such as discussion forums and instant messaging to facilitate collaboration and information exchange among participants. By including these tools and functionalities into the platform, CoMediC aims to optimize the management of medical data collection projects and promote eficient and transparent communication among any participants involved.
CoMedic platform uses advanced technologies to enable researchers and healthcare practitioners to preprocess, standardize, and harmonize multimodal data. This guarantees the generation of highly qualified datasets that are favorable to accurate analysis, perceptive interpretation, and well-informed decision-making in diverse medical scenarios. Figure 2 describes diferent steps employed in our platform to achieve this goal. Here is a summary of the techniques employed: 1-Data Processing methods: -Data Cleaning: Applies algorithms to identify and correct errors, anomalies, and missing values in the data. This includes applying methods such as detecting anomalies, filling in missing values, and correcting errors in order to improve the quality of the data.
-Feature Engineering: Refers to the process of converting raw data into significant features that efectively collect pertinent information for analysis purposes. Methods such as dimensionality reduction, feature scaling, and transformation facilitate the eficient representation of data.
-Data Augmentation: Increases the volume and variety of the dataset by generating synthetic data points. Methods including : oversampling, undersampling, and data synthesis through the use of generative models enhance the quality of the dataset.
2-Harmonization and Standardization Methods: -Normalization: The process of rescaling data to a standard range or distribution, which guarantees consistency and comparability among diferent features or datasets. Methods such as z-score normalization, min-max scaling, and resilient scaling are used to modify data distributions in order to enhance analysis.
-Alignment: The process of bringing together data from many sources and organizing it in a consistent and compatible way, making it easier to combine and work with. Data alignment techniques, such as using timestamps, physical coordinates, or semantic mapping, guarantee the consistency and coherence of data.
-The integration of machine learning: This involves the use of algorithms to automate data processing operations and improve standardization procedures [25]. Supervised learning is used to fill in missing data, unsupervised learning is used to group similar data together, and deep learning is used to extract important features from the data. These techniques improve the eficiency and eficacy of data processing pipelines.
CoMediC platform has incorporated a number of strong security mechanisms, including Two-Factor Authentication (2FA), JSON Web Tokens (JWT), password management, and blockchain technology.
1. Two-Factor Authentication (2FA): CoMediC employs two-factor authentication (2FA) to improve the security of user authentication by adding an additional layer of protection. Enabling 2FA requires users to submit two forms of identity verification in order to access their accounts. This greatly reduces the possibility of unauthorized access, as even if a user’s password is obtained, access cannot be allowed without the additional authentication method, such as a code transmitted to their mobile device [26].
2. JSON Web Tokens (JWT): JWT ofers a reliable and secure approach to authorization and authentication within the CoMediC platform. JWTs serve as a safe means of transmitting authentication credentials between the client and server, enabling users to access protected resources without the need for frequent reauthentication [27]. This improves the security of the platform by prohibiting unwanted access to important data and functionalities.
3. Password Management: CoMediC implements strong password management techniques to protect user accounts from illegal access and data threats. User passwords are maintained securely through the use of encryption techniques. Additionally, strict requirements for password complexity are enforced to guarantee that users create passwords that are both strong and safe. In addition, security measures such as password expiration and account lockout are applied to improve security and prevent brute-force attacks [28].
4. Blockchain Technology: The CoMediC platform uses blockchain technology to improve security and integrity through transparent and decentralized data storage. The use of blockchain technology ensures that medical data saved on the platform is securely encrypted and cannot be modified or changed ensuring the integrity and preventing unauthorized changes [29]. This builds trust and assurance among users by ensuring the validity and legality of medical records.
In vision of the future, our platform is positioned to completely transform the way medical data is managed and how collaboration takes place in the healthcare industry. With its extensive features and strong architecture, this product has the potential to become a fundamental component in healthcare innovation and research.
We expect widespread use in several sectors, such as academic research, healthcare institutions, organizations, and pharmaceutical corporations. Specialized tools with user-friendly interfaces for data visualization and advanced functions for data validation and normalization will be advantageous for researchers. Eficiently incorporating into existing workflows would improve the way healthcare professionals provide care, guaranteeing that data accuracy and adherence to regulatory requirements are maintained. The primary objective of our platform is to promote interdisciplinary collaboration and facilitate data-driven decision-making in the future. Through the facilitation of partnerships and provision of access to extensive datasets, it will stimulate advancements in medical research and personalized medicine. In addition, by using machine learning algorithms and techniques, our platform guarantees the efective processing and standardization of data. This provides users with highly qualified data for analysis, which enhances decision-making and leads to better patient outcomes.
Through continuous eforts, we prioritize data security through the use of data security mechanisms such as JWT (JSON Web Tokens), 2FA (Two-Factor Authentication), and blockchain integration, These measures guarantee the reliability and confidentiality of medical information while facilitating efortless cooperation and advancement within the healthcare system.
In the realm of mental health and addiction therapy, our platform serves as a dynamic tool used to meet the evolving needs of mental health professionals, researchers, and individuals seeking support. Our platform intends to transform the process of collecting, managing, and using mental health and addiction-related data by using advanced features in data gathering, analysis, and collaboration. Through simulations presented as scenarios, we explore how our platform can empower participants and drive positive outcomes in various mental health and addiction contexts, facilitating the creation of innovative projects aimed at advancing research, treatment monitoring, and recovery support. The information presented here is the result of thorough research and consultation with experienced psychiatric, guaranteeing its reliability and relevance in the field of mental health and addiction. Obtained through cautious work and verified through collaboration with field specialists, this data is a fundamental component of the CoMediC platform. Both patients and healthcare practitioners use it. Patients actively participate in our dynamic questionnaire, while healthcare practitioners use it to gather information for diagnostic and treatment plans. Moreover, academics derive significance from this data, employing it to drive progress in the field of mental health and addiction studies. Table 2 presents the several categories established in consultation with psychiatric experts, demonstrating the data used in each scenario:
Our platform has the potential to be applied in diferent ways to meet specific requirements in the field of mental health and addiction. Here, we demonstrate three simulations that illustrate the application of our specialized data to provide experimental solutions in these fields: Scenario 1: Research Collaboration in Mental Health.
CoMediC’s platform facilitates comprehensive mental health research by allowing access to a diverse dataset that includes personal and sociodemographic information. Scientists employ this data to examine the frequency and distribution of mental health diseases among diferent demographic groups. Researchers examining the impact of socioeconomic status on depression rates leverage CoMediC’s dataset to identify gaps in mental health outcomes across persons from various social and economic classes. In addition, CoMediC’s platform promotes interdisciplinary collaboration, allowing researchers to share findings and improve methodology in real-time. Researchers use CoMediC’s advanced data analysis techniques to identify hidden patterns and trends in mental health data, resulting in innovative insights and discoveries. Essentially, CoMediC’s data enables researchers to conduct detailed studies on mental health diseases, providing information for public health policies and directing the creation of specific interventions to improve mental health outcomes for diferent populations.
Scenario 2: Psychiatric Treatment Monitoring Psychiatric.
Use CoMediC’s platform to monitor patients’ progress and apply treatment strategies eficiently. Psychiatrists employ CoMediC to analyze previous consumption data and clinical assessments, enabling them to monitor patients’ treatment response and detect potential reasons for relapse. As an example, a psychiatrist uses CoMediC’s data to observe mood changes, track medication compliance, and evaluate the efectiveness of treatment in a patient with bipolar illness. Through the examination of longterm data patterns, the psychiatrist is able to detect early indicators of relapse and make appropriate modifications to the treatment plan, resulting in improved management of the patient’s condition. In addition, CoMediC’s platform facilitates secure and continuous interaction between patients and healthcare practitioners, allowing for timely interventions and proactive support for persons receiving mental treatment. Psychiatric practitioners advance treatment outcomes and improve the overall quality of care for patients with mental health illnesses by using CoMediC’s data-driven approach.
Scenario 3: Support for Addiction Recovery.
CoMediC’s platform serves as a helpful tool for individuals in addiction rehabilitation, providing assistance in their path towards recovery. Individuals engage in self-monitoring exercises and use tools provided by CoMediC to track their progress, identify causes for substance use, and connect with peer support networks. For example, someone in the process of recovering from opioid addiction uses CoMediC to record cravings, monitor their progress in obtaining recovery, and communicate with others who are experiencing similar dificulties. Through the analysis of this data, addiction therapists are able to identify patterns and develop personalized strategies to to prevent relapse. In addition, CoMediC’s platform ofers access to therapies based on expertise and systems for peer support, enabling individuals to efectively manage challenges and maintain recovery over the long term. CoMediC uses data-driven insights and peer support networks to facilitate long-term recovery and improve the quality of life for those with medical conditions.
The CoMediC platform is a powerful solution for the collection, management, and analysis of medical data. It ofers a wide range of tools and features that address the diferent needs of researchers, healthcare providers, and patients.
CoMediC has made important contributions to the field of medical data during its evolution. The software ofers project management capabilities that are easy for users to use, employs diferent algorithms to normalize data, provides real-time communication methods, and includes strong security measures. These developments facilitated the collecting, processing, and analysis of medical data to be more eficiently and collaboratively, leading to better healthcare results.
In the future, CoMediC plans to continue develop and expand in order to improve its capabilities and address the changing needs of the medical community. Possible future advancements might involve increasing security mechanisms, specifically through the integration of blockchain technology. Additionally, include the integration of supplementary machine learning and deep learning techniques to enable advanced data analysis, improved compatibility with other healthcare systems, and the integration of modern technology such wearable devices for collecting real-time data. In addition, CoMediC aims to increase its activities in medical fields and international areas, supporting stronger cooperation and exchange of information among a wide range of participants.
CoMediC invites collaboration and adoption from the wider medical and scientific community to improve its capabilities and contribute to the progress of medical research and healthcare practices. By employing CoMediC, researchers, healthcare professionals, and institutions have a robust platform for making decisions based on data, engaging in collaborative research projects, and eventually improving patient care results. Collectively, we may use the abilities of CoMediC to encourage advancement, exploration, and beneficial transformation in the realm of medicine.
During the preparation of this work, the author(s) used ChatGPT for rephrasing and improving clarity of certain paragraphs, as well as Grammarly for grammar and spelling checks. All content generated or suggested by these tools was critically reviewed and edited by the authors. The author(s) afirm full responsibility for the accuracy, originality, and integrity of the final manuscript. [11] E. F. Patridge, T. P. Bardyn, Research electronic data capture (redcap), Journal of the Medical
Library Association: JMLA 106 (2018) 142. [12] P. A. Harris, R. Taylor, B. L. Minor, V. Elliott, M. Fernandez, L. O’Neal, L. McLeod, G. Delacqua, F. Delacqua, J. Kirby, et al., The redcap consortium: building an international community of software platform partners, Journal of biomedical informatics 95 (2019) 103208. [13] M. Cavelaars, J. Rousseau, C. Parlayan, S. de Ridder, A. Verburg, R. Ross, G. R. Visser, A. Rotte,
R. Azevedo, J.-W. Boiten, et al., Openclinica, Journal of clinical bioinformatics 5 (2015) 1–2. [14] M. Hardy, J. Samuela, M. Kama, M. Tuicakau, L. Romani, M. J. Whitfeld, C. L. King, G. J. Weil, A. C. Grobler, L. J. Robinson, et al., The safety of combined triple drug therapy with ivermectin, diethylcarbamazine and albendazole in the neglected tropical diseases co-endemic setting of fiji: A cluster randomised trial, PLoS neglected tropical diseases 14 (2020) e0008106. [15] V. Agarwala, S. Khozin, G. Singal, C. O’Connell, D. Kuk, G. Li, A. Gossai, V. Miller, A. P. Abernethy, Real-world evidence in support of precision medicine: clinico-genomic cancer data as a case study, Health afairs 37 (2018) 765–772. [16] A. S. Panayides, A. Amini, N. D. Filipovic, A. Sharma, S. A. Tsaftaris, A. Young, D. Foran, N. Do, S. Golemati, T. Kurc, et al., Ai in medical imaging informatics: current challenges and future directions, IEEE journal of biomedical and health informatics 24 (2020) 1837–1857. [17] F. A. Reegu, H. Abas, Y. Gulzar, Q. Xin, A. A. Alwan, A. Jabbari, R. G. Sonkamble, R. A. Dziyauddin, Blockchain-based framework for interoperable electronic health records for an improved healthcare system, Sustainability 15 (2023) 6337. [18] C. Rosa, A. N. Campbell, G. M. Miele, M. Brunner, E. L. Winstanley, Using e-technologies in clinical trials, Contemporary clinical trials 45 (2015) 41–54. [19] S. R. Steinhubl, E. D. Muse, E. J. Topol, The emerging field of mobile health, Science translational medicine 7 (2015) 283rv3–283rv3. [20] K. Lee, H. Kwon, B. Lee, G. Lee, J. H. Lee, Y. R. Park, S.-Y. Shin, Efect of self-monitoring on long-term patient engagement with mobile health applications, PloS one 13 (2018) e0201166. [21] R. Tertulino, N. Antunes, H. Morais, Privacy in electronic health records: a systematic mapping study, Journal of Public Health 32 (2024) 435–454. [22] L. Van Bulck, M. Wampers, P. Moons, Research electronic data capture (redcap): tackling data collection, management, storage, and privacy challenges, European journal of cardiovascular nursing 21 (2022) 85–91. [23] T. Tuti, M. Bitok, C. Paton, B. Makone, L. Malla, N. Muinga, D. Gathara, M. English, Innovating to enhance clinical data management using non-commercial and open source solutions across a multi-center network supporting inpatient pediatric care and research in kenya, Journal of the American Medical Informatics Association 23 (2016) 184–192. [24] B. Aljedaani, M. A. Babar, et al., Challenges with developing secure mobile health applications:
Systematic review, JMIR mHealth and uHealth 9 (2021) e15654. [25] W. Abada, A. Bouramoul, Using machine learning techniques to predict people at-risk for drug addiction: A bayesian-based model, in: 2022 4th International Conference on Pattern Analysis and Intelligent Systems (PAIS), IEEE, 2022, pp. 1–7. [26] K. Reese, T. Smith, J. Dutson, J. Armknecht, J. Cameron, K. Seamons, A usability study of five {two-factor} authentication methods, in: Fifteenth Symposium on Usable Privacy and Security (SOUPS 2019), 2019, pp. 357–370. [27] N. Fotiou, I. Pittaras, V. A. Siris, S. Voulgaris, G. C. Polyzos, Oauth 2.0 authorization using blockchain-based tokens, arXiv preprint arXiv:2001.10461 (2020). [28] B. Ur, J. Bees, S. M. Segreti, L. Bauer, N. Christin, L. F. Cranor, Do users’ perceptions of password security match reality?, in: Proceedings of the 2016 CHI conference on human factors in computing systems, 2016, pp. 3748–3760. [29] B. Zaabar, O. Cheikhrouhou, F. Jamil, M. Ammi, M. Abid, Healthblock: A secure blockchain-based healthcare data management system, Computer Networks 200 (2021) 108500.