Integration of AI in EHRs Proposal (2023-2024 PDF)

MEDICAL RESEARCH 3 SBU-COM AY 2023-2024 RESEARCH CAPSULE PROPOSAL FORMAT A. PROJECT PROFILE Research Title: Integration of AI with Electronic Health Records (EHRs) Proponent: Hipolito, Aaron Rigge J School/ College/ Year/ C...

MEDICAL RESEARCH 3 SBU-COM AY 2023-2024 RESEARCH CAPSULE PROPOSAL FORMAT A. PROJECT PROFILE Research Title: Integration of AI with Electronic Health Records (EHRs) Proponent: Hipolito, Aaron Rigge J School/ College/ Year/ Course: SBU COM – YL 3 College of Medicine Email address: [email protected] Research Area/ Discipline: Artificial Intelligence in Electronic Health Records B. PROJECT PLAN Artificial intelligence (AI) included into Electronic Health Records (EHRs) has become a major focus point in healthcare since it presents both possible and negative aspects for enhancing patient care and the efficiency of healthcare systems. EHRs— digital records compiling comprehensive patient data including medical histories, medicines, laboratory results, and treatment plans—allow centralized, easily available patient information. Conventional EHRs can struggle with data overload, limited interoperability, and lack of strong analytical skills, therefore diminishing their capability to provide good clinical treatment notwithstanding their general appeal. Encouragement of EHR systems to use massive volumes of both structured and unstructured health data will help to create intelligent analysis and a disruptive answer to these limits. General clinical decision-making, diagnosis accuracy, and data management have shown themselves able to be improved by predictive analytics, natural language processing (NLP), and machine learning (ML). The ability of artificial intelligence to spot patterns in patient data helps one to forecast the course of disease development, improve tailored treatment plans, and spot big hazards before serious symptoms start. By helping to evaluate a patient's likelihood of acquiring chronic diseases, predictive models enable early interventions and thereby help to lower healthcare costs. Natural language processing (NLP) helps to automatically understand and organize free-text clinical notes by allowing the gathering of important data and thereby boosts the completeness and searchability of patient records. Background of the Study: Although there are several difficulties with implementation, especially with relation to data privacy, security, and the standardization of artificial intelligence algorithms, the possible benefits of artificial intelligence in electronic health records are fairly strong. There are serious ethical and legal questions when one maintains patient privacy while allowing major data access for artificial intelligence processing. The Health Information Privacy Code requires strict guidelines and that medical records be kept in order to protect patient identity. Moreover, the consistent lack of interoperability among EHR systems in hospitals could result in fragmented or partial data sets, therefore influencing the dependability and quality of artificial intelligence produced insights. Overcoming these challenges calls for a regulatory framework protecting data privacy and an infrastructure allowing basic data interchange, hence promoting creativity. New research highlight the transforming power of artificial intelligence-integrated electronic health records in many medical contexts. Topol's 2019 study shows how artificial intelligence (AI) transcends its role in diagnosis by means of enormous health data analysis to foresee outcomes and prescribe treatments, therefore supporting clinical decision-making. Research by Wang et al. (2021) shows that population health management depends heavily on AI's predictive powers in electronic health records, especially in identifying high-risk  individuals, therefore directing the management of chronic diseases and resource allocation. Still, a lot of studies show the risks and limits of too great reliance on artificial intelligence without proper control, including diagnostic errors resulting from algorithmic flaws or data biases (Smith & Liu, 2020). These results show how important a balanced integration is to improve EHR performance by combining human supervision with analytical capability of artificial intelligence. Given limited resources and challenges to healthcare access, the possible influence of AI-enhanced EHRs in the Philippines is especially remarkable. Being a developing country, the Philippine healthcare system sometimes faces financial and logistical difficulties, particularly in rural and underdeveloped areas where professional access to medical resources is rare. By means of remote monitoring, customized care plans, and real-time data analytics—which help to tackle these challenges—AI-driven EHR systems could boost healthcare accessibility and quality and so improve healthcare quality. One such is the use of artificial intelligence in telemedicine, which has grown in relevance in front of the COVID-19 outbreak. By means of AI integration with EHRs in telehealth systems, health practitioners can provide data-driven consultations and remotely monitor patient health indicators, hence improving the provision of great healthcare for remote populations. Furthermore, tailored medicine is a field where EHRs featuring AI-integrated technology show great potential. Unlike anticipatory treatment, conventional methods typically use EHR data for documentation. Artificial intelligence could assess particular patient data including lifestyle decisions and genetic information in order to create tailored therapy recommendations. Customized medications based on personal risk factors and genetic predispositions could enable Filipino patients have more efficient treatments, thereby improving outcomes and raising patient satisfaction. Emphasizing the need of invention, a 2023 University of the Philippines National Institutes of Health (UP- NIH) research supports patient-centered, data-driven treatment to improve health outcomes. Emphasizing results, operational effectiveness, and quality of treatment in the Philippines, this paper attempts to investigate how artificial intelligence might be utilized with electronic health records and assess how this might influence the provision of healthcare. Examining contemporary usage, potential benefits, and current challenges, this study aims to provide reasonable assessments of how AI-enhanced EHRs might support a more robust, efficient, and inclusive healthcare system in the Philippines. The project intends to increase the corpus of knowledge already available for artificial intelligence in healthcare by providing data-driven recommendations for the application of AI to address local healthcare issues to legislators and medical practitioners. Particularly with regards to providing timely, accurate, and tailored treatment, the growing complexity and volume of patient data in Electronic Health Records (EHRs) seriously challenge healthcare management. Although they are essential, conventional EHR systems may have limited analytical capabilities, data overload, and interoperability issues, therefore reducing their value in clinical decision-making. As healthcare advances toward data-driven, customized treatment approaches to provide complete data analysis and real-time insights, EHR system update is significantly needed. Statement of the Problem: Modern data analytics, predictive modeling, patient-specific insights made possible by artificial intelligence (AI) mixed with EHRs help to lower these restrictions. Important challenges include the need for interoperable data across healthcare systems, the likelihood of algorithmic biases on patient treatment driving AI-enhanced EHRs less popular, and even if they bring data privacy issues. Particularly the Philippines suffers from these issues since restricted access to healthcare and good utilization of resources depend on one another. By  means of real-time patient monitoring, illness risk assessment, and support of customized care regimens, AI-integrated EHRs could be transforming neglected areas of healthcare accessibility and quality. This seeks to maximize EHR systems by means of artificial intelligence integration, therefore enhancing operational efficiency and healthcare outcomes in the Philippines. especially understood at the following: How may artificial intelligence increase EHRs' analytical and predictive ability in identifying at-risk patients thereby facilitating early interventions? In Philippine healthcare settings, how may EHRs featuring artificial intelligence integration serve to improve clinical decision-making accuracy and efficiency? More especially with regard to infrastructure readiness, interoperability, and data security in the Philippines, what challenges and constraints surround the acceptance of AI- enhanced EHR systems? This work solves a fundamental gap in modern EHR capabilities by assessing how artificial intelligence integration may turn patient data into relevant insights, therefore linking healthcare practices with the needs of a modern, data-intensive environment. Especially in low resource settings like the Philippines, this work presents important fresh ideas on how artificial intelligence might influence EHR efficacy, thereby directing the creation of safe and scalable AI systems to enhance the provision of healthcare. The outcomes could also guide policymakers, clinicians, and technology developers in creating AI-EHR systems that give patient safety first priority, improve healthcare outcomes, and enable more tailored, effective treatment in both metropolitan and rural environments. Systems that enhance healthcare outcomes, give patient safety first priority, and enable more customized, efficient treatment in metropolitan and rural settings allow General: This study aims to investigate how the integration of Artificial Intelligence (AI) with Electronic Health Records (EHRs) can enhance healthcare delivery by improving patient outcomes, clinical decision-making, and operational efficiency in the Philippines. The project seeks to address challenges such as data overload, interoperability, and the need for personalized care, with a focus on adapting AI-driven EHR systems to the specific needs and limitations of the local healthcare environment. Specific: Research Objectives: 1. To evaluate the impact of AI-integrated EHRs on the accuracy and efficiency of clinical decision-making, particularly in Filipino healthcare settings where resources may be limited 2. To identify and analyze the challenges associated with implementing AI-enhanced EHRs, including data privacy concerns, interoperability issues, and infrastructure readiness within the Philippine healthcare system 3. To identify and analyze the challenges associated with implementing AI-enhanced EHRs, including data privacy concerns, interoperability issues, and infrastructure readiness within the Philippine healthcare system By means of the conversion of raw patient data into meaningful insights, artificial intelligence (AI) combined with Electronic Health Records (EHRs) can improve healthcare delivery by enabling proactive, customized, and efficient treatment. This Research Significance: study has great intellectual value since it helps us to better grasp how artificial intelligence may solve data management issues, enhance clinical decision-making, and maximize electronic health record systems. This study aims to provide  original insights into the Philippine healthcare environment, marked by data fragmentation and resource restrictions, which can lead to workable solutions relevant to like-minded developing healthcare systems. Examining the potential of AI-enhanced EHRs to improve healthcare access and quality, this paper is relevant to legislators in underdeveloped areas, healthcare providers, and Filipino consumers. Through data-driven decision support and predictive analytics, which help medical professionals in early identification of high-risk patients, optimization of treatment regimens, and reduction of preventable consequences, this study has more general benefits. Regarding chronic diseases, artificial intelligence could enable quick interventions and customized treatment recommendations, so enhancing patient results and general quality of life. AI-enhanced EHRs could provide more time for doctors to concentrate on patient care by removing human data entry and accelerating administrative tasks. In cultures with little resources, like the Philippines, where doctors have too demanding schedules, operational efficiency is essential. By improving EHR interoperability, artificial intelligence could help to enable seamless data interchange between hospitals and hence improve continuity of treatment. While also advancing scientific knowledge by analyzing the practical application of AI to improve EHR systems in developing nations, the study acts as a model for healthcare systems with limited resources and offers insights into the scalability and adaptability of AI-driven solutions across many healthcare environments. Mostly helping the scientific community, patients, policymakers, and healthcare professionals, this study will also help AI-driven EHR systems that offer real-time clinical insights, help with decision-making, and save administrative costs would help healthcare staff including managers, doctors, and nurses. This would lead to a situation whereby exact and quick clinical choices enhance patient treatment. Emphasizing data privacy, interoperability, and infrastructure needs, legislators and regulatory authorities can use the results of the study to create rules and suggestions for the safe integration of artificial intelligence into systems of electronic health records. Thus, the research provides a foundation for developing morally reasonable and pragmatic rules on the application of artificial intelligence in the medical field. Particularly for people from disadvantaged areas with few healthcare facilities, this study will mostly help Filipino patients. Early health risk assessment, tailored treatment plans, and remote monitoring made possible by AI-enhanced electronic health records help to advance health justice in rural and economically underprivileged communities. Furthermore, relevant to the scientific and technological communities is this work. It highlights specific issues and opportunities for artificial intelligence applications in underdeveloped countries, therefore giving data scientists, artificial intelligence researchers, and EHR developers relevant insights. The findings of the study are expected to inspire more developments in EHR systems and encourage originality in artificial intelligence uses in the medical field. The main results of the research will be data-driven recommendations for the ethical and successful application of artificial intelligence in electronic health records, therefore complementing the goals of the Philippine healthcare system. These outputs—which include case studies, technical guidelines, and regulatory recommendations—should propel next developments in AI-based EHR systems. In the Philippines and comparable countries, this will help to build a more strong and easily available healthcare system. Health Informatics Theory Theoretical Background: (Theoretical/ According to Hersh (2009), modern health informatics theory Philosophical Underpinning and stresses the analytical management and organizing of patient Conceptual Framework) data to maximize the provision of healthcare. Through emphasizing efficient data management, accessibility, and quality, health informatics offers the fundamental basis for EHR systems. and enhancing data analysis and turning unprocessed EHR data into actionable insights, artificial intelligence (AI) conforms with this notion and so enabling more accurate and fast therapeutic judgments (Safran et al., 2019). Data-Information-Knowledge-Wisdom (DIKW) Framework By use of information and knowledge extraction, the DIKW framework—which Ackoff, 1989 amended by Rowley, 2007— offers a hierarchy that converts data into wisdom. This hierarchy is fundamental in EHRs in turning enormous patient data into clinically useful knowledge. Especially at the knowledge and wisdom levels, where data-driven insights become instruments for predictive and preventative healthcare, artificial intelligence fits inside this model by accelerating data processing and advancing the DIKW hierarchy (Frické, 2009). Machine Learning and Predictive Analytics Theory Fundamental to artificial intelligence (AI), machine learning (ML) generates predictions (Obermeyer & Emanuel, 2016) by use of algorithms learning from data patterns. Through trend analysis of patient data, predictive analytics supports clinical decisions in healthcare by allowing doctors to estimate disease progress and modify treatments. This concept underlines how artificial intelligence might enhance EHRs by recognizing at-risk patients and therefore enabling early interventions and individualized treatment options (Topol, 2019). Human-Computer Interaction (HCI) Theory Human-computer interaction theory investigates consumer behavior toward technology to improve user experience, efficiency, and satisfaction (Zhang & Walji, 2011). Artificial intelligence-enhanced EHRs depend on HCI to ensure that powerful AI capabilities are easy understandable for healthcare providers to implement. Aimed at increasing user acceptance and enjoyment, this theory helps evaluate how healthcare practitioners see AI-driven insights, handle data input, and interpret AI outputs (Kushniruk & Borycki, 2008). Sociotechnical Systems Theory Sociotechnical systems theory, as discussed by Baxter and Sommerville (2011), emphasizes the interdependence between technical and social elements in technology implementation. Applied to EHRs, this theory provides a basis for understanding how AI affects healthcare workflows, communication, and user interaction. Recognizing these social and technical interdependencies is critical to designing AI-enhanced EHRs that align with existing healthcare practices while supporting new workflows driven by AI insights (Sittig & Singh, 2010). Theory of Diffusion of Innovations Rogers’ (2003) Diffusion of Innovations Theory explains the adoption of new technologies, considering factors such as perceived benefits and compatibility with current practices. This theory provides insight into the factors influencing AI adoption in EHRs, including perceived usefulness, complexity, and alignment with healthcare workflows. Understanding these factors is crucial for designing AI-integrated EHRs that are both user-friendly and impactful (Greenhalgh et al., 2004). Health Belief Model (HBM) The Health Belief Model (Rosenstock, Strecher, & Becker, 1988; updated by Champion & Skinner, 2008) focuses on users’ perceptions of health-related behaviors and their motivations for adopting new tools. In the context of AI in EHRs, HBM aids in understanding healthcare providers’ perceptions of AI tools, weighing perceived benefits against potential barriers like data privacy risks or increased workload. Addressing these concerns is essential to improve AI adoption in healthcare (Janz & Becker, 1984). Quality of Care Theory Donabedian’s quality of care model (1988; updated by Kruk & Freedman, 2008) evaluates healthcare systems based on structure, process, and outcomes. This model applies to AI- enhanced EHRs by assessing how AI-driven data insights improve the quality of care, focusing on diagnostic accuracy, timely intervention, and patient-centered treatment. AI’s potential to positively impact these outcomes is a critical component of this study, which seeks to validate improvements  in clinical quality through enhanced EHR capabilities (Smith et al., 2018). Information Processing Theory Information Processing Theory (Atkinson & Shiffrin, 1968; revised by Cowan, 2001) describes how individuals perceive, process, and retrieve information, which in healthcare translates to cognitive demands on providers. AI’s role in reducing this cognitive load by automating data analysis and providing real- time insights aligns with this theory, suggesting that AI- enhanced EHRs can streamline decision-making and reduce clinician burnout (Miller, 2003). Big Data and Analytics Theory Big Data theory—which focuses data processing and advanced pattern detection—is fundamental to artificial intelligence in EHRs (Chen et al., 2012). Artificial intelligence's ability to study enormous volumes of EHR data supports big data analytics by offering insights not easily found from traditional EHRs. This theoretical basis helps artificial intelligence to offer complex analysis, recognize healthcare trends, and create data-driven projections for better patient outcomes (Raghupathi & Raghupathi, 2014). Conceptual Framework Inspired by these concepts, the conceptual framework for this study looks at how artificial intelligence might be introduced into EHRs with an aim on boosting clinical decision support and therefore improving healthcare outcomes. This method accentuates artificial intelligence applications such predictive analytics, natural language processing, and pattern recognition by looking at how these capabilities turn EHR data into useable insights that assist healthcare practitioners. By considering both sociotechnical and cognitive variables influencing AI acceptability and impact, the study aims to evaluate AI's contribution in increasing EHR utility and healthcare delivery. By means of this approach, the research enhances the knowledge of artificial intelligence's changing capacity in healthcare, especially in settings of limited resources like the Philippines. Driven by research on how artificial intelligence (AI) might enhance data management, clinical decision-making, and patient outcomes inside healthcare systems, the quickly expanding field of integration of artificial intelligence (AI) with Electronic Health Records (EHRs) is under development. This section provides a synopsis of relevant research and literature, therefore guiding the discussion of how artificial intelligence integration in EHRs fits more generally healthcare trends, particularly in low-resource areas like the Philippines. One of the primary reasons integrating artificial intelligence with EHRs is motivated is handling the data overload and inefficiencies coming from managing vast numbers of patient data. Artificial intelligence (particularly machine learning (ML) and natural language processing (NLP), Lee et al. (2022) assert has showed significant potential in organizing and understanding EHR data, thereby enhancing clinical decision support. By recognizing trends and projecting patient concerns, Related Literature and Studies: these instruments enable clinicians to apply preventive treatment options, hence improving patient outcomes. Likewise, Topol (2019) emphasizes how artificial intelligence could enhance healthcare operations by turning unprocessed data into meaningful insights that lead customized treatment, hence aiding diagnostics. Since predictive analytics enables clinicians to predict patient health issues and design early treatments, it is a main focus of attention in AI-EHR integration. Obermeyer and Emanuel (2016) using AI-driven prediction models in EHRs for population health management describe how these systems could identify high- risk patients and maximize resource allocation. By concentrating on patients most likely to benefit from preventative care, predictive analytics could help the Philippines solve resource constraints in the framework of this study. Raghupathi (2014) stress even more how artificial intelligence's capacity to leverage massive data inside EHRs has transformed healthcare and allowed more exact predictions and evidence-based therapies. Through data interoperability and accessibility, the more general field of health informatics provides ideas on how artificial intelligence-enhanced EHRs could support the continuum of treatment. Studies reveal that poor clinical decision-making in healthcare facilities is sometimes hampered by insufficient patient records resulting from malfunctioning data systems inside them. Including artificial intelligence into EHRs has shown promise in creating interoperable systems allowing perfect information flow between healthcare providers, claims Safran et al. (2019). Particularly the Philippines depends on better interoperability since weak connectivity and incompatible data formats usually prevent efficient healthcare delivery. Artificial intelligence (AI) improved EHR systems could thus provide a more consistent patient record system, hence enhancing coordination and quality of care. Effective deployment of EHRs enabled by artificial intelligence depends on user interaction and technological acceptability. Research by Zhang and Walji (2011) underline the need of user- centered design and human-computer interaction (HCI) ideas in healthcare systems and suggest that straightforward interfaces and ease of use can raise clinician acceptance of new technologies. In the Philippines, where medical professionals can be less knowledgeable with modern artificial intelligence technologies, ensuring efficient implementation depends on making sure AI-enhanced EHR systems are user-friendly. In the same line, Greenhalgh et al. (2004) look at the factors influencing technology adoption in healthcare and find that general acceptability depends largely on perceived simplicity of use, utility, and compatibility with present methods. These findings suggest that systems should be developed with an eye toward usability, so providing healthcare professionals with seamless, readily available capabilities supporting their daily operations, so facilitating effective artificial intelligence integration in EHRs. Apart from the technological and operational benefits, other research manage the ethical questions associated to artificial intelligence integration in healthcare, notably with regard to data protection and patient permission. According to Janz and Becker (1984), the Health Belief Model (HBM) proposes how likely healthcare workers are to employ artificial intelligence tools depending on their perspective on hazards including ethical consequences and data breaches. Emphasizing the need of robust security standards and open data use to establish confidence among users and patients, the application of HBM to AI-enhanced EHRs helps highlight these probable impediments. Research by Sittig and Singh (2010) stress the need of a sociotechnical approach to artificial intelligence in EHRs, which considers not just the technology but also the healthcare environment and the human aspects implicated. A sociotechnical approach helps to identify possible implementation challenges unique to settings like the Philippines, where financial restrictions and infrastructure shortcomings could impede good uptake. By examining how artificial intelligence may notably alleviate problems faced by undeveloped countries in keeping with the global trend of deploying AI technologies to maximize healthcare delivery, this paper adds to the body of knowledge. AI-enhanced EHRs have enormous promise to improve healthcare access and outcomes in locations with limited resources by accelerating data processing, helping clinical decision-making, and motivating preventative treatment. By focusing on the Philippines and looking at local factors affecting the acceptance and usefulness of AI-driven EHR systems, this paper aims to address a knowledge gap in present understanding. Since they show knowledge of how artificial intelligence may be applied to increase overall EHR functionality and healthcare quality, the outcomes could be a great tool for  other low-resource healthcare situations. Twofold is the contribution of this paper: it provides a framework for managing the special challenges in developing countries and clarifies the useful applications of artificial intelligence in EHRs. Research Design An RCT design is chosen to measure the effectiveness of AI- enhanced EHRs on healthcare outcomes in a controlled setting. Healthcare providers or departments in selected facilities will be randomly assigned to either an intervention group or a control group Target Population The target population includes healthcare providers in the Philippines who will use EHR systems in their clinical settings Step by step Methods: 1: Obtain ethics approval 2: Identify eligible healthcare facilities and providers who use EHR systems and obtain consent from administrators and potential participants. 3: Randomly assign participants or departments within healthcare facilities 5: Collect baseline data from both groups 6: Conduct follow-up data collection over a six-month period 7: Administer semi-structured interviews with healthcare providers 8: Analyze quantitative and qualitative data using statistical tests Data Collection Methods Quantitative Data Collection: Clinical and operational data will Research Design and Methods: be collected from both the intervention and control groups. Key metrics will include patient outcomes, time spent on administrative tasks, and predictive accuracy of AI tools in the intervention group. Data will be collected over a predefined period to measure changes in healthcare delivery. Qualitative Data Collection: To supplement the quantitative findings, semi-structured interviews will be conducted with healthcare providers in the intervention group. Data Analysis Quantitative: Independent t-tests, chi-square tests, and regression analysis Qualitative: Content analysis, Thematic analysis, and Framework analysis Ethical Consideration This study will strictly adhere to ethical guidelines to protect participant rights, privacy, and data integrity. Informed consent will be obtained from all participants, with full disclosure of the study’s purpose, methods, potential risks, and benefits. Participation will be voluntary, and participants will have the right to withdraw at any stage. Data confidentiality will be maintained and access to sensitive patient and provider information will be restricted to authorized research personnel only. This research is expected to generate insightful analysis and concrete results that can direct the integration of artificial intelligence (AI) into Electronic Health Records (EHRs) into the Philippine healthcare system. Among the expected results are Expected Output: technological recommendations, best practices, data-driven insights, and useful tools meant to increase provider experiences, patient outcomes, and healthcare efficiency. Target journal/s for publication of your Journal of Medical Internet Research research output: International Journal of Medical Informatics Greenhalgh, T., Robert, G., Macfarlane, F., Bate, P., & Kyriakidou, O. (2004). Diffusion of innovations in service References: organizations: Systematic review and recommendations. Milbank Quarterly, 82(4), 581-629. https://doi.org/10.1111/j.0887-378X.2004.00325.x  Hersh, W. (2009). A stimulus to define informatics and health information technology. BMC Medical Informatics and Decision Making, 9, 24. https://doi.org/10.1186/1472-6947-9- 24 Janz, N. K., & Becker, M. H. (1984). The Health Belief Model: A decade later. Health Education Quarterly, 11(1), 1-47. https://doi.org/10.1177/109019818401100101 Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the future — Big data, machine learning, and clinical medicine. New England Journal of Medicine, 375(13), 1216-1219. https://doi.org/10.1056/NEJMp1606181 Raghupathi, W., & Raghupathi, V. (2014). Big data analytics in healthcare: Promise and potential. Health Information Science and Systems, 2(3), 1-10. https://doi.org/10.1186/2047-2501-2-3 Safran, C., Bloomrosen, M., Hammond, W. E., Labkoff, S., Markel-Fox, S., Tang, P. C., & Detmer, D. E. (2019). Toward a national framework for the secondary use of health data: An American Medical Informatics Association White Paper. Journal of the American Medical Informatics Association, 14(1), 1-9. https://doi.org/10.1197/jamia.M2273 Sittig, D. F., & Singh, H. (2010). A new sociotechnical model for studying health information technology in complex adaptive healthcare systems. Quality & Safety in Health Care, 19(Suppl 3), i68-i74. https://doi.org/10.1136/qshc.2010.042085 Topol, E. J. (2019). Deep medicine: How artificial intelligence can make healthcare human again. Basic Books. Zhang, J., & Walji, M. (2011). TURF: Toward a unified framework of EHR usability. Journal of Biomedical Informatics, 44(6), 1056-1067. https://doi.org/10.1016/j.jbi.2011.08.005 C. IMPLEMENTING SCHEDULE Project Duration (in months) Date: 9 months Planned Start Date (Month / Year): November 4, 2024 Planned Completion Date (Month / Year): September 4, 2025 Major Activities: See Annex A Date Submitted: November 4, 2024 D. BUDGET SUMMARY Annex A – Sample Implementation Plan (AY 2023 -2024) Project Title: Integration of AI in EHR Systems for Improved Healthcare Delivery Proponent: Hipolito, Aaron Rigge J. Collaborators/Co-Researchers: N/A Duration of the Project: 10 months Start: November 4, 2024 End: September 4, 2025 Expected Activity or Work Gantt Chart Objective Output Plan Aug Sep Oct Nov Dec Jan Feb Mar Apr May Evaluate AI- Implementation Baseline data EHR efficiency report collection Identify user Qualitative Conduct experience insights report interviews with AI Assess clinicalComparative Data analysis & operational data analysis outcomes results Disseminate Publication & Report writing findings presentation materials Finalization Submission of Final Overall output manuscript Note: The table may be adjusted to accommodate entries.  Annex B – Sample Budget Summary per line-item (AY 2023-2024) Project Title: Integration of AI in EHR Systems for Improved Healthcare Delivery Proponent: Hipolito, Aaron Rigge J. Collaborators/ N/A Co-Researchers: (For funded research only) Duration of the Project 10 months Start: November 4, 2024 End: September 4,2025 Months in Funding Item Monthly rate School Total project Institution (if any) DIRECT COST Personal Services (PS) Main Proponent - - - - - Co-Researcher (if any) - - - - - Project Staff (if any) - - - - - Sub-total - - - - - MAINTENANCE AND OTHER OPERATING EXPENSES (MOOE) Travel/Transportation Expenses 3,000 - 3,000 Communication Expenses 2,000 - 2,000 Meals/Venue (Representation Expenses/ Accommodation - Expenses) 3,000 3,000 Printing, photocopying, and Binding Expenses - (such as reports and documents) 4,000 4,000 Consultancy Services / Analytical Services - (services for specific work requiring technical skills not available in the proponent) 5,000 5,000 Contractual Services (fieldworker, research assistant, encoder, - transcriber) 7,000 7,000 Data collection expense - Permits for the Conduct of Research - (Ethics review, Biosafety committee) 3,000 3,000 Patent Search Services (if any): - Attendance to trainings/seminars/conferences related to - research projects (for externally-funded projects only when applicable) - Contingency 5,000 - 5,000 Sub-total - 32,000 Other Expenses Administrative Cost (with external grant) Sub-total GRAND TOTAL 32,000