Healthcare informatics

In an era defined by uncertainty, volatility, and exponential data growth, organizations face unprecedented challenges in anticipating risks with clarity and confidence. The AI-Driven Risk Forecasting Theory offers a groundbreaking framework that addresses this global dilemma by harnessing the predictive power of artificial intelligence. At its core, the theory introduces a unified, explainable structure that fuses Machine Learning Integration, Data Infrastructure Quality, and Algorithmic Design-mediated through ethical and regulatory oversight-to produce risk forecasts that are not only accurate but also transparent and accountable. The theory is operationalized through four novel models: the Neural Predictive Harmony Model (NPHM), Data Fidelity-Outcome Correlation Model (DFOCM), Algorithmic Foresight Transfer Model (AFTM), and AI Compliance-Risk Accuracy Mediation Model (ACRAMM). These models collectively embody the mathematical relationships between AI capabilities and forecasting outcomes, capturing systemic feedback and ethical governance mechanisms. Together, they form a dynamic ecosystem that evolves with shifting risk parameters and regulatory landscapes. By utilizing an interdisciplinary methodology-including predictive analytics, regulatory modeling, and domain-specific applications-the theory demonstrates measurable improvements in forecasting precision across finance, cyber security, healthcare, and environmental risk. For example, in the financial sector, AI-driven models anticipate market shocks with greater lead time, enabling preemptive mitigation strategies. In healthcare, early detection of systemic failures and patient-level risks contributes to reduced mortality and optimized resource allocation. Moreover, the framework emphasizes explainability and auditability, ensuring that AIgenerated forecasts can be validated, traced, and aligned with stakeholder expectations. This ethical layer not only fosters trust among regulators and the public but also protects against algorithmic bias, ensuring equitable outcomes in high-stakes environments. Its broader implication lies in enabling AI systems to forecast with trust, respond in real time, and adapt under governance-forming a cornerstone for the emerging field of Risk Intelligence. As organizations transition from reactive to proactive risk postures, the AI-Driven Risk Forecasting Theory provides the strategic infrastructure to support resilient decision-making. Ultimately, this theory bridges the gap between innovation and responsibility in the digital age. It sets the stage for a new era where artificial intelligence is not merely a tool for prediction, but a trusted partner in navigating complexity, safeguarding societal well-being, and shaping a more stable and informed future. Prof. Dr. Mbonigaba Celestin is a renowned academician and professional with a Postdoctoral Fellowship in AI-Driven Accounting and Blockchain Systems, a Ph.D. in Accounting Sciences, an MBA in Finance, and a Bachelor's in Accounting Sciences. He also holds certifications such as CPA, PMP, CIA, and CFA, showcasing his expertise across diverse professional domains. With over 15 years of experience in academia and administration, he has received numerous national and international awards for excellence in both fields.

Families of ethnic minority persons with dementia often seek help at later stages of the disease. Little is known about the effectiveness of various methods in supporting ethnic minority dementia patients' caregivers. The objective of the study was to identify smartphone and computer usage among family caregivers of dementia patients (i.e., Korean and Vietnamese Americans) to develop dementia-care education programs for them. Participants were asked various questions related to their computer or smartphone usage in conjunction with needs-assessment interviews. Flyers were distributed at two ethnic minority community centers in Southern California. Snowball recruitment was also utilized to reach out to the families of dementia patients dwelling in the community. Thirty-five family caregivers, including 20 Vietnamese and 15 Korean individuals, participated in this survey. Thirty participants (30 of 35, 85.7%) were computer users. Among those, 76.7% (23 of 30) reported daily usage ...

This study examined the benefits and challenges of school lunch program in Iwo local government of Osun State. It was a survey. The population consisted of all teachers in the 60 public primary school of the local government which is 623. A sample of 244 respondents was drawn from the schools using simple random technique. Questionnaire was used for data collection. Data were analyzed using mean. Findings revealed, among others that, the school lunch program has helped to increase daily attendance of the pupils in the schools and eliminate classroom hunger among the pupils. Recommendations were made for the government to create general level of awareness on cleanliness among the people handling the foods by employing private agencies to follow certain hygiene norms for food preparation and service and to also involve some accredited representatives of the parent/teachers' association in whatever that will be given for the project:

Critical issues facing India's healthcare system include fragmented patient data, inconsistent and opaque pricing, a lack of interoperability between labs and hospitals, and a slow uptake of digital infrastructure in rural areas. Inefficiencies, redundant diagnostics, treatment delays, and financial burdens are caused by these problems, especially for middle-and lower-income groups. By combining hospitals and approved labs into a single, interoperable digital platform, this case study suggests a Unified Healthcare Data and Pricing System for India. The suggested framework guarantees robust consent-driven access controls, universal acceptance of certified diagnostic reports, standardized and transparent pricing, and smooth patient record sharing. The Digital Personal Data Protection Act 2023, the National Health Policy 2017, and the proposed Digital Information Security in Healthcare Act (DISHA) all protect data privacy. For time-sensitive interventions, an audit-trail emergency override protocol is also suggested. This model addresses systemic inequities, improves continuity of care, lowers unnecessary costs, and increases patient empowerment by coordinating technology solutions with policy frameworks. The system has the potential to make India's healthcare system a more patient-centered, cost-effective, and egalitarian ecosystem.

Medical errors in hospitals and clinics are not rare and may cause severe harm to patients . While Bates et al. reported that medical errors cause more than one million injuries in United States hospitals every year, Bosman [3] reported 1.7 medical errors per patient. Furthermore, medical errors are one of the top ten causes of mortality . Blendon et al. [5] reported that the mortality rate due to medical errors is higher than the mortality rate as the result of accidents. Moreover, such errors impose huge costs on the health sector .

The purpose of this work is to describe the dynamics of the COVID-19 pandemics accounting for the mitigation measures, for the introduction or removal of the quarantine, and for the effect of vaccination when and if introduced. The methods used include the derivation of the Pandemic Equation describing the mitigation measures via the evolution of the growth time constant in the Pandemic Equation resulting in an asymmetric pandemic curve with a steeper rise than a decrease and mitigation measures. The Pandemic Equation predicts how the quarantine removal and business opening lead to a spike in the pandemic curve. The effective vaccination reduces the new daily infections predicted by the Pandemic Equation. The pandemic curves in many localities have similar time dependencies but shifted in time. The Pandemic Equation parameters extracted from the well advanced pandemic curves can be used for predicting the pandemic evolution in the localities, where the pandemics is still in the initial stages. Using the multiple pandemic locations for the parameter extraction allows for the uncertainty quantification in predicting the pandemic evolution using the introduced Pandemic Equation. Compared with other pandemic models our approach allows for easier parameter extraction amenable to using Artificial Intelligence models.

The revolution of Internet of Things (IoT) technologies has changed the healthcare system by assimilating the various technological, social and economical aspects. It emits the healthcare system from conventional to the more customized system. In the current global COVID-19 pandemic circumstance IoT play a crucial function to combat corona virus infections. The early diagnose of COVID-19 is very necessary in order to prevent the disease from spreading globally. In this paper we survey the significant role of IoT-based technologies along-with some associative advanced technologies to early detect the COVID-19 infections. We review the sate-of-the art architecture and applications to combat COVID-19 infections and propose an IoTbased framework which helps to early detect and monitoring the COVID-19 infections.

Sleep Paralysis (SP) is a complex and multifaceted phenomenon situated at the intersection of neurobiology, psychiatry, genetics, and cultural belief systems. This study offers a comprehensive investigation into SP, integrating findings from neurophysiological, psychological, and sociocultural domains. Neurobiological evidence highlights disruptions during the rapid eye movement (REM) sleep cycle-specifically the persistence of REM atonia into wakefulness-as a core mechanism underlying SP, often accompanied by vivid hallucinations and sensory distortions. Psychiatric analyses reveal a strong association between SP and mental health conditions such as post-traumatic stress disorder (PTSD), anxiety, and depression, underscoring the influence of emotional trauma on REM regulation. Genetic studies indicate that polymorphisms in circadian rhythm-related genes (e.g., PER, CLOCK, ARNTL2), calcium channel genes (e.g., CACNA1C), and recently, the anti-aging gene Sirtuin 1 (SIRT1), may contribute to SP susceptibility through their regulation of sleep-wake cycles and stress responses. Cultural frameworks further shape SP experiences, with interpretations ranging from demonic visitations to ancestral contact, influencing both coping strategies and emotional outcomes. In response to these findings, this paper advocates for a culturally sensitive, biopsychosocial model for SP treatment-one that integrates traumainformed therapy, genetic profiling, and community-based education. It concludes that SP is not merely a sleep disturbance but a deeply subjective and neurogenetically influenced experience, requiring interdisciplinary approaches for effective understanding and intervention. Future directions include exploring pharmacogenomics, real-time neuroimaging during SP episodes, and culturally informed VR therapies to bridge clinical practice with individual lived experience.

This report examines the transformation of customer experience through AI in CRM platforms. The introduction highlights the relevance of the topic, defining the research objectives and methodology. The theoretical framework explores the fundamental concepts related to AI and CRM, as well as the evolution of these technologies. Key AI technologies, including machine learning, Natural Language Processing, predictive analytics, and computer vision, are discussed in terms of their contribution to optimizing CRM systems. The report distinguishes between traditional CRM systems that do not use AI and modern AI-powered CRM platforms. It analyzes how AI reshapes the structure, functionalities, and operations of CRM by automating processes, enhancing personalization, and providing predictive analytics. The next section focuses on the impact of AI on customer experience. Key aspects of this transformation include service personalization, process automation, predictive support, and the use of intelligent assistants to improve customer communication. In conclusion, the main findings are summarized, and future AI trends in CRM are outlined.

The objective of this study was to evaluate the features of diet and nutrition apps available in the Google Play Store. A search was conducted in August 2017 using the Google Play Store database to identify apps related to diet and nutrition. Terms entered into the app search engine included 'diet apps' and 'nutrition apps'. The first 50 apps resulting from each search term was assessed. Duplicates were removed, and a comparative analysis was performed on the remaining diet and nutrition apps. A total of 86 diet and nutrition apps were identified. One hundred percent (n = 86) of the apps retrieved were freely available. More than half of the apps were applicable to a target user group of all ages (94%, n = 81). Stratified analysis across unique diet and nutrition apps (total, n = 72) showed a higher average rating for the diet apps (4.4) in comparison to that for the nutrition apps (4.3). Diet apps were more likely to be recently updated than the nutrition apps (72% ...

Objectives: Predicting the length of stay (LOS) of patients in a hospital is important in providing them with better services and higher satisfaction, as well as helping the hospital management plan and managing hospital resources as meticulously as possible. We propose applying data mining techniques to extract useful knowledge and draw an accurate model to predict the LOS of heart patients. Methods: Data were collected from patients with coronary artery disease (CAD). The patient records of 4,948 patients who had suffered CAD were included in the analysis. The techniques used are classification with three algorithms, namely, decision tree, support vector machines (SVM), and artificial neural network (ANN). LOS is the target variable, and 36 input variables are used for prediction. A confusion matrix was obtained to calculate sensitivity, specificity, and accuracy. Results: The overall accuracy of SVM was 96.4% in the training set. Most single patients (64.3%) had an LOS ≤5 days, whereas 41.2% of married patients had an LOS >10 days. Moreover, the study showed that comorbidity states, such as lung disorders and hemorrhage with drug consumption have an impact on long LOS. The presence of comorbidities, an ejection fraction <2, being a current smoker, and having social security type insurance in coronary artery patients led to longer LOS than other subjects. Conclusions: All three algorithms are able to predict LOS with various degrees of accuracy. The findings demonstrated that the SVM was the best fit. There was a significant tendency for LOS to be longer in patients with lung or respiratory disorders and high blood pressure.

In recent decades, information and communication technologies have changed the way of life in all aspects including health care. Scientific texts show that application of information technology for making the best decision in the medical arena is crucial . Many data are produced in this field. However, there is a lack of programs, systems and formal structures to convert this data into meaningful health information. Hence, it could be said with certainty that health care organizations have strong data but weak knowledge . Panzarasa et al. [4] showed that medical knowledge in current health care systems was not essentially used. In its re-

The current global issue of the COVID-19 pandemic has prompted the push and utilization of all available means to halt its spread. COVID-19 is a highly infectious disease, and continuously monitoring early symptoms could help avert catastrophic devastation. This paper proposes an innovative use of the Internet of Things (IoT) enabled system to efficiently and effectively detect early COVID-19 signs at a relatively low cost. This study adopted an experimental approach in designing and constructing a low-cost hardware system using a Wi-Fi enabled microcontroller, a temperature sensor, and a heart rate sensor for students. The proposed system detected and distinguished normal and abnormal temperature, regular and irregular heartbeat and constantly displayed the student's status in a mobile application. Consistent tests proved that the developed IoT-enabled system was reliable, responsive, and cost-effective. The mass production of this device will aid in the early detection of the disease, thereby mitigating the spread among students, particularly in underdeveloped countries. The paper's merit stems from the microcontroller's intelligence programming and the sensor's operation via the mobile application, which enables low-cost early identification of abnormal temperature and heartbeat irregularities.

Dengue remains a significant problem that needs to be addressed urgently in Thailand. Although Thailand has spread the dengue fever for more than sixty years, however, it is still found dengue patients in every province and spread to various areas. There is also a variable pattern of disease occurring each year, so it is necessary to have tools to help forecast area to allow the related organization and the people in the area plan to prevent dengue fever that may occur next year. This research aimed to create innovation for predicting dengue fever regions, namely ThaiDengue, by collecting data from dengue patients in Chatuchak District, Bangkok, Thailand, from January 2014 to December 2018. There was a total of 358,524 dengue patients from the Bureau of vector-borne diseases applied to the prediction of patients in the next year with the ARIMA model (1,1,0) (1,1,0). It is predicted that in 2019, Thailand will have dengue patients around 95,000 cases, which has the number of dengue p...

Artificial Intelligence (AI) is rapidly transforming the healthcare landscape, enabling clinicians to diagnose diseases more efficiently, treat patients more precisely, and expedite medical research particularly in imaging, surgery, and pharmacological development. AI can analyze massive genomic and imaging datasets within seconds. By 2022, approximately 18.7% of U.S. hospitals had integrated AI to improve workflow efficiency [1], and projections estimate that by 2025, 66% of physicians will incorporate AI into their clinical practice [2]. However, as AI becomes more embedded in-patient care, the urgency for robust ethical frameworks grows. Data privacy, transparency, and accountability are central to this discourse. Despite AI's potential, significant concerns remain. Around 38.6% of AI systems exhibit factual bias [3], which can distort clinical decisions. Additionally, 32% of healthcare data breaches have compromised sensitive information [4], and rural communities continue to face barriers to AI access [5]. To address these challenges, we must prioritize bias mitigation, enforce HIPAA-based data protections, and champion digital inclusion policies. Crucially, we must also protect empathy and patient-centered care values that remain fundamental to ethical medicine [6]. AI-powered Clinical Decision Support Systems (AI-CDSS) undeniably enhance efficiency and accuracy. However, they lack the human attributes of empathy, ethical discernment, and contextual understanding [7]. For instance, a palliative care physician once sensed a terminal patient's silent fear of being a burden an emotional nuance no algorithm could detect providing the reassurance she needed to face her final days with dignity [8]. As a practicing consultant surgeon, I've witnessed firsthand how anatomical judgment and patient context shape decisions elements no algorithm can fully replicate. This affirms the notion that AI should serve as a support tool, not a substitute for human clinicians. Explainable AI (XAI), comprehensive training, and enforceable ethical guidelines are essential to maintaining this balance. The real dilemma is not whether to adopt AI, but how with compassion, transparency, and accountability. Real-world applications underscore AI's remarkable capabilities. At the Mayo Clinic, AI has improved early disease detection and streamlined radiology workflows, achieving diagnostic accuracies of 94.2% for rib fractures [9], 93.46% for intracranial hemorrhages [10], and 91% in brain MRI evaluations [11]. At Memorial Sloan Kettering, AI reduces false positives in prostate cancer diagnoses by 50%, and achieves a 97.2% success rate in personalized treatment planning [12].

There remain significant barriers to the use of personal health records (PHRs), which limit potential benefits in underserved patient populations. Novel strategies must be developed to achieve the desired impact of PHRs on patient engagement and health outcomes. This paper describes the health information needs and technology preferences of adults seeking care in Community Health Centers (CHCs), which provide care to low-income, uninsured and underinsured patients. We offer design suggestions emerging from interviews with 43 CHC patients and 49 CHC staff members that explored many themes including: patient barriers to accessing health care, health information needs of patients between clinic visits, patient and clinic staff preferences for technology use, and PHR implementation approaches used in CHCs. Our findings provide a roadmap to greater engagement of patients via PHRs by expanding functionality, providing tailored patient messaging, and incorporating adult learning strategies.

This article proposes the use of the RDF, RDFS and OWL as a basis for data modeling for semantic oriented development of enterprise applications. RDF and OWL ware introduced to guaranty a semantic web to permit a web of interconnected data instead of a static web so that computer can explore web contents. Several efforts have been made to establish rules to convert data of existing enterprise applications into equivalent RDF/OWL data, to make them available on the semantic web. However, the most applications were developed using classical relational database modeling methodologies. Here beyond publishing data for the semantic web, we give motivations for the necessity of a RDF/OWL semantic data modeling, as well as an approach in form of best practices for this modeling. We also show the effectiveness of our approach by comparing it to the classical relational data modeling.

The most important barriers to the implementation of electronic health records (EHRs) are people's attitudinalbehavioral limitations and organizational changes. Given its complexity, applicability of EHRs is very important, especially for physicians. Objectives: This study aimed to investigate the physicians' attitudes towards the implementation of EHRs in a university-affiliated teaching hospital in Tehran, Iran. Methods: This cross sectional study was conducted in a university-affiliated teaching hospital in Tehran, Iran in the second half of 2016. The attitudes of all physicians working in this hospital (n, 169) towards the implementation of EHRs were investigated, using census sampling method. The required data were collected using the translated and localized Morton's standard questionnaire (2008). The collected data were analyzed using SPSS version 21.0 and AMOS version 18.0. P value less than 0.05 was considered statistically significant. The results showed that the studied conceptual model had a good fit and was structurally confirmed. Moreover, the results showed that independent variables could predict 51% of variations in the dependent variable of "physicians' attitudes". The results of structural equation modeling (SEM) also showed that variables of "perceived usefulness" (r, 0.52) and "perceived ease of use" (r, 0.26) had major effects on the physicians' positive attitudes (P < 0.001), and "perceived ease of use" (r, 0.33) had a significant effect on "perceived usefulness" (P < 0.001). The results showed that physicians working in the studied hospital agreed with the implementation of EHRs, and they had the required abilities and readiness to implement EHRs. According to these results, development of standards related to information security and privacy, as well as standards for conveying messages, especially for physicians and users who work directly with the system, is recommended.

Background Out-of-hospital Emergency Medical Services (OHEMS) require fast and accurate assessment of patients and efficient clinical judgment in the face of uncertainty and ambiguity. Guidelines and protocols can support staff in these situations, but there is significant variability in their use. Therefore, the aim of this study was to increase our understanding of physician decision-making in OHEMS, in particular, to characterize the types of decisions made and to explore potential facilitating and hindering factors. Methods Qualitative interview study of 21 physicians in a large, publicly-owned and operated OHEMS in Croatia. Data was subjected to an inductive content analysis. Results Physicians (mostly young, female, and early in their career), made three decisions (transport, treat, and if yes on either, how) after an initial patient assessment. Decisions were influenced by patient needs, but to a greater extent by factors related to themselves and patients (microsystem), thei...

Background: Solitary death (kodokushi) has recently become recognized as a social issue in Japan. The social isolation of older people leads to death without dignity. With the outbreak of COVID-19, efforts to eliminate solitary death need to be adjusted in line with changes in lifestyle and accompanying changes in social structure. Health monitoring services that utilize wearable devices may contribute to this end. Our goals are to outline how wearable devices might be used to (1) detect emergency situations involving solitary older people and swiftly connect them with medical treatment, to (2) reduce the frequency of deaths that remain undiscovered and (3) to reduce social isolation by promoting social interaction. Methods: Theoretical and philosophical approaches were adopted to examine ethical issues surrounding the application of wearable devices and cloud-based information processing systems to prevent solitary death in the world with/after COVID-19. (1) Technology cannot replace social connections; without social support necessary to foster understanding of the benefits of health management through wearable devices among older adults, such devices may remain unused, or not used properly. (2) Maturity of the technology; systems face the difficult task of detecting and responding to a wide range of health conditions and life-threatening events in time to avert avoidable morbidity and mortality. (3) Autonomy and personhood; promoting the voluntary use of wearable devices that are a part of larger efforts to connect isolated individuals to a community or social services might be effective. Legal force should be avoided if possible. There is some concern that landlords may require an older person to sign a contract agreeing to wear a device. The autonomy of solitary older people should be respected. (4) Governance: policies must be developed to limit access to data from wearables and the purposes for which data can be used. If thoughtfully deployed under proper policy constraints, wearable devices offer a way to connect solitary older people to health services and could reduce cases of solitary death while respecting the personhood of the user.

BackgroundSolitary death (kodokushi) has recently become recognized as a social issue in Japan. The social isolation of older people leads to death without dignity. With the outbreak of COVID-19, efforts to eliminate solitary death need to be adjusted in line with changes in lifestyle and accompanying changes in social structure. Health monitoring services that utilize wearable devices may contribute to this end. Our goals are to outline how wearable devices might be used to (1) detect emergency situations involving solitary older people and swiftly connect them with medical treatment, to (2) reduce the frequency of deaths that remain undiscovered and (3) to reduce social isolation by promoting social interaction.MethodsTheoretical and philosophical approaches were adopted to examine ethical issues surrounding the application of wearable devices and cloud-based information processing systems to prevent solitary death in the world with/after COVID-19.Main body(1) Technology cannot re...

Diagnostic procedure, one of the most essential steps in healthcare, determines the protocol for the treatment of a patient. Doctors can provide a more accurate diagnosis and better treatment by comparing patients' recent and older test reports. However, patients typically neglect to properly store their older reports, making it more difficult to find the reports later for doctor's appointments. In this paper, we've presented an application for Analytics and Visualization of Clinical Pathology Reports or "AVCPR", which allows patients to upload and store images of their clinical pathology reports, and lets doctors access and analyze their patients' health records in an organized and more convenient than the traditional way along with dynamic visualization. Instead of relying on clinicians and healthcare organizations, AVCPR establishes a patient-centric platform where systematically stored patient records can be accessed by patients themselves, and shareable to doctors and possibly to researchers in the future. The application consists of a standard authentication system, user dashboard, profile and settings, report upload interface, automatic structured information extraction and recording system, organized record of reports with risk factor indicator color table, and comparison chart for both patients and doctors. CCS CONCEPTS • Applied Computing → Life and medical Science; Health informatics.

This paper presents a comprehensive examination of machine learning (ML) methods employed in the identification and management of diabetes. With the rising prevalence of diabetes globally, there is a pressing need for accurate and efficient diagnostic tools. ML techniques offer promising avenues for enhancing diagnostic accuracy, risk prediction, and personalized treatment approaches. This study reviews a range of ML algorithms applied to various datasets for diabetes detection, including supervised, unsupervised, and hybrid approaches. The examination of each algorithm's performance aims to identify the one displaying superior accuracy, precision, sensitivity, and specificity. Additionally, the decision-making process is evaluated to enhance the model. Through rigorous evaluation and comparison, insights are drawn regarding the effectiveness and applicability of each model in the context of diabetes prediction. The findings contribute to advancing the understanding of machine learning methodologies in healthcare and offer valuable guidance for developing robust predictive models for diabetes diagnosis and management. The study aims to contribute valuable insights into the application of machine learning techniques for diabetes prediction.

This paper presents an in-depth exploration of various machine-learning models for predicting breast cancer recurrence. Leveraging a comprehensive dataset, we systematically evaluate the performance of multiple algorithms, considering factors such as accuracy, sensitivity, specificity, and computational efficiency. The forecasting system was developed using fourteen varied machine learning (ML) methods to predict the likelihood of breast cancer recurrence. The prognostic model's performance was evaluated using multiple measures including the area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score. Following this assessment, the most appropriate machine learning (ML) algorithm was selected, and the significance of features was identified. Through rigorous experimentation and analysis, we identify key insights into the strengths and limitations of different approaches, offering valuable guidance for selecting the most suitable model for breast cancer recurrence prediction. The findings contribute to enhancing the accuracy and interpretability of breast cancer recurrence prediction systems, thereby facilitating informed clinical decision-making.

Rising outpatient healthcare costs, particularly due to brand-name and nonoptimized drug prescriptions, have created an urgent need for intelligent, costsaving interventions. Traditional prescribing often overlooks equally effective, lower-cost drug alternatives, leading to significant financial inefficiencies without improving patient outcomes. This study proposes an AI-powered drug substitution model designed to optimize outpatient prescription practices by recommending clinically equivalent and more cost-effective alternatives. The primary goal is to reduce unnecessary healthcare expenditures while preserving treatment quality and physician autonomy. We developed a machine learningbased recommendation system using a comprehensive dataset that includes electronic health records, pharmacy claims, drug equivalency databases, and insurance formulary information. The model was trained to identify optimal drug substitutions based on diagnosis, prescription history, cost, and insurance coverage. Evaluation metrics included substitution precision, potential cost savings, and physician usability testing.

Background: The Ministry of Health of Malaysia has invested significant resources to implement an electronic health record (EHR) system to ensure the full automation of hospitals for coordinated care delivery. Thus, evaluating whether the system has been effectively utilized is necessary, particularly regarding how it predicts the work performance of health care providers. Methods: Convenience sampling was employed for data collection in three government hospitals for seven months. A standardized efficacy survey for EHR systems was administered to primary health care providers (specialists, medical officers, and nurses) as they participated in medical education programs. Empirical data were assessed by employing partial least squares-structural equation modeling for hypothesis testing.Results: The results demonstrated that knowledge quality had the highest score for predicting performance and had a large effect size, whereas system compatibility was the strongest component of system...

We collected over 50 million tweets referencing COVID-19 to understand the public's gendered discourses and concerns during the pandemic. We filtered the tweets based on English language and among three gender categories: men, women, and sexual and gender minorities. We used a mixed-method approach that included topic modelling, sentiment analysis, and text mining extraction procedures including words' mapping, proximity plots, top hashtags and mentions, and most retweeted posts. Our findings show stark differences among the different genders. In relation to women, we found a salient discussion on the risks of domestic violence due to the lockdown especially towards women and girls, while emphasizing financial challenges. The public discourses around SGM mostly revolved around blood donation concerns, which is a reminder of the discrimination against some of these communities during the early days of the HIV/AIDS epidemic. Finally, the discourses around men were focused on the high death rates and the sentiment analysis results showed more negative tweets than among the other genders. The study concludes that Twitter influencers can drive major online discussions which can be useful in addressing communication needs during pandemics.

Heart failure (HF) is a common, chronic, and complex clinical syndrome that significantly diminishes quality of life . The lifetime risk of HF through the ages of 45-95 years is 20% to 45% . More than 37 million people around the world suffer from HF [3]; however, the prevalence of HF varies worldwide. The American Heart Association estimated that the HF prevalence is between 1.26% to 6.7% , with the expectation that it will increase by 32% from 2012 to 2030 . In Iran, its prevalence has been reported to be high

Objectives: Heart failure (HF) is a common disease with a high hospital readmission rate. This study considered class imbalance and missing data, which are two common issues in medical data. The current study’s main goal was to compare the performance of six machine learning (ML) methods for predicting hospital readmission in HF patients.Methods: In this retrospective cohort study, information of 1,856 HF patients was analyzed. These patients were hospitalized in Farshchian Heart Center in Hamadan Province in Western Iran, from October 2015 to July 2019. The support vector machine (SVM), least-square SVM (LS-SVM), bagging, random forest (RF), AdaBoost, and naïve Bayes (NB) methods were used to predict hospital readmission. These methods’ performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Two imputation methods were also used to deal with missing data.Results: Of the 1,856 HF patients, 29.9% had at least one h...

Clinical informatics, as an evolving interdisciplinary field, lies at the intersection of healthcare delivery, biomedical research, and information science. It focuses on the effective collection, organization, interpretation, and application of medical data to enhance decision-making, optimize healthcare outcomes, and streamline clinical operations. This field is governed and supported by robust institutional frameworks such as the International Medical Informatics Association (IMIA), the American Medical Informatics Association (AMIA), and the American Board of Medical Specialties (ABMS), which have institutionalized informatics through policy development, education, and board certification. Clinical informatics has diversified into multiple subspecialties, including public health informatics, imaging informatics, and translational bioinformatics, among others. Core epistemological structures like ontology, taxonomy, and the Data-Information-Knowledge-Wisdom (DIKW) hierarchy underpin the cognitive transformation of data into usable clinical insight. Emerging domains such as human-computer interaction, social computing, and cybersecurity extend the reach of informatics into critical areas of digital health and organizational operations. As healthcare systems become increasingly digitized, clinical informatics is no longer ancillary but integral to improving safety, efficiency, and value in healthcare. This paper explores the institutional foundations, taxonomic principles, and specialized applications of clinical informatics in the context of 21st-century healthcare transformation.

The patient of Parkinson's disease (PD) is facing a critical neurological disorder issue. Efficient and early prediction of people having PD is a key issue to improve patient's quality of life. The diagnosis of PD specifically in its initial stages is extremely complex and time-consuming. Thus, the accurate and efficient diagnosis of PD has been a significant challenge for medical experts and practitioners. In order to tackle this issue and to accurately diagnosis the patient of PD, we proposed a machine-learning-based prediction system. In the development of the proposed system, the support vector machine (SVM) was used as a predictive model for the prediction of PD. The L1-norm SVM of features selection was used for appropriate and highly related features selection for accurate target classification of PD and healthy people. The L1-norm SVM produced a new subset of features from the PD dataset based on a feature weight value. For the validation of the proposed system, the K -fold cross-validation method was used. In addition, the metrics of performance measures, such as accuracy, sensitivity, specificity, precision, F1 score, and execution time, were computed for model performance evaluation. The PD dataset was in this paper. The optimal accuracy achieved the best subset of the selected features that might be due to various contributions of the PD features. The experimental findings of this paper suggest that the proposed method can be used to accurately predict the PD and can be easily incorporated in healthcare for diagnosis purpose. Currently, the computer-based assisted predictive system is playing an important role to assist in PD recognition. In addition, the proposed approach fills in a gap on feature selection and classification using voice recordings data by properly matching the experimental design.

Abstract:
Cardiovascular diseases are the most common diseases around the world and result in high morbidity and mortality rates. It proves the need to develop new approaches to the disease’s early diagnosis and prevention. Portable health monitoring is characterized by state-of-the-art sensors. It produces a continuous flow of physiological data in real-time. It presents a great opportunity for preventative Cardiovascular disease management. Using deep learning algorithms that is used to accurately and effectively. It creates preventive early diagnosing models for diseases. The authors discuss the integration of wearable health technology and deep learning towards the improvement of individual-oriented technologies in cardiology. The collected data are cleaned for noise and further normalized to provide uniform input in deep learning models. To detect anomalies that are likely to lead to cardiovascular risks, state-of-the-art algorithms. The models are trained and validated using a dataset of wearable device data and clinically diagnosed Cardiovascular disease cases. Wearable health devices combined with deep learning algorithms provide an innovative platform for cardiovascular disease screening and prevention. The incorporation of the proposed system proved its efficiency and accuracy in the identification of potential probable Cardiovascular disease risk, making it possible for early, real-time, noninvasive, and personalized healthcare services. This approach improves early detection but also provides handy information to the patients. This type of research includes the acquisition of larger databases and better models, and incorporating those into more offices and healthcare practices.

In the context of modern healthcare, the integration of sensor networks into electronic health record (EHR) systems introduces new opportunities and challenges related to data privacy, security, and interoperability. This paper proposes a secure, distributed web system architecture that integrates realtime sensor data with a custom Customer Relationship Management (CRM) module to optimize patient monitoring and clinical decision-making. The architecture leverages IoT-enabled medical sensors to capture physiological signals, which are transmitted through secure communication channels and stored in a modular EHR system. Security mechanisms such as data encryption, role-based access control, and distributed authentication are embedded to address threats related to unauthorized access and data breaches. The CRM system enables personalized healthcare management while respecting strict privacy constraints defined by current healthcare standards. Experimental simulations validate the scalability, latency, and data protection performance of the proposed system. The results confirm the potential of combining CRM, sensor data, and distributed technologies to enhance healthcare delivery while ensuring privacy and security compliance.

Objectives: This study explored the current status of nursing informatics education in South Korea and developed a standardized curriculum for it. Methods: Data were collected in two stages: first, an online survey conducted from December 2020 to February 2021 among 60 nursing schools to analyze the current status of nursing informatics education; and second, a two-round Delphi survey with 15 experts from March to April 2021 to determine the mean and standard deviation of the demand for each learning objective in nursing informatics education. A standardized curriculum proposal was developed based on the results of the two-round Delphi survey. Results: Nursing informatics was most commonly taught in the fourth year (34%), with two credits. The proportion of elective major subjects was high in undergraduate and graduate programs (77.4% and 78.6%, respectively), while the proportion of nursing informatics majors was low (21.4%). The curriculum developed included topics such as nursing information system-related concepts, definitions and components of healthcare information systems, electronic medical records, clinical decision support systems, mobile technology and health management, medical information standards, personal information protection and ethics, understanding of big data, use of information technology in evidence-based practice, use of information in community nursing, genome information usage, artificial intelligence clinical information systems, administrative management systems, and information technology nursing education. Conclusions: Nursing informatics professors should receive ongoing training to obtain recent medical information. Further review and modification of the nursing informatics curriculum should be performed to ensure that it remains up-to-date with recent developments.

Objectives: This study explored the current status of nursing informatics education in South Korea and developed a standardized curriculum for it.Methods: Data were collected in two stages: first, an online survey conducted from December 2020 to February 2021 among 60 nursing schools to analyze the current status of nursing informatics education; and second, a two-round Delphi survey with 15 experts from March to April 2021 to determine the mean and standard deviation of the demand for each learning objective in nursing informatics education. A standardized curriculum proposal was developed based on the results of the two-round Delphi survey.Results: Nursing informatics was most commonly taught in the fourth year (34%), with two credits. The proportion of elective major subjects was high in undergraduate and graduate programs (77.4% and 78.6%, respectively), while the proportion of nursing informatics majors was low (21.4%). The curriculum developed included topics such as nursing i...

Various kinds of real world complex systems including physical, biological, and social systems can be represented in terms of complex networks. Some important examples are the World Wide Web, electric power grids, scientific collaboration networks, airport networks, the Hajj network, and social networks of friendship . In the fields of medicine and biology, the complex networks of diseases such as HIV/ AIDS, smallpox, and dengue virus have also been investigated to analyze the spreading phenomenon . The dengue virus network includes the mosquito 'Aedes aegypti' . Dengue is an arbovirus that spreads infections through mosquitoes

ABSTRAK Jaringan Syaraf Tiruan (JST) merupakan salah satu metode dalam kecerdasan buatan yang meniru cara kerja sistem saraf manusia dalam memproses informasi. Kemampuannya dalam mempelajari pola dari data, melakukan klasifikasi, dan menghasilkan prediksi menjadikannya sebagai teknologi yang penting dalam pengembangan sistem cerdas. Artikel ini bertujuan untuk mengkaji secara mendalam konsep dasar JST, mulai dari struktur dan mekanisme kerja, metode pelatihan seperti backpropagation, hingga penerapannya dalam berbagai bidang seperti kesehatan, pendidikan, dan industri. Penelitian ini menggunakan pendekatan studi literatur dari berbagai sumber terpercaya untuk menggambarkan bagaimana JST diimplementasikan dalam konteks nyata serta menelaah kelebihan dan tantangan yang dihadapi dalam penggunaannya. Hasil kajian menunjukkan bahwa JST memiliki potensi besar dalam meningkatkan efisiensi proses, akurasi analisis data, dan kemampuan sistem dalam beradaptasi terhadap kondisi yang berubah. Namun demikian, keberhasilan implementasi JST sangat bergantung pada kualitas data, pemilihan arsitektur yang tepat, serta dukungan sumber daya komputasi yang memadai. Dengan pemahaman yang baik terhadap karakteristik dan tantangan tersebut, JST dapat menjadi fondasi utama dalam pengembangan sistem cerdas yang adaptif dan berkelanjutan.

Personalized medicine is rapidly advancing with deep learning and predictive analytics, starting from using electronic health records to improve clinical decision-making. These technologies advance disease prognosis, treatment customization, and management of healthcare resources, taking the sector toward a proactive approach. Though it looks forward to optimizing patientcentric decision support via DL and predictive analytics in improving clinical decision-making, personalization of treatment, health outcomes forecasting, optimal resource allocation, and patient satisfaction, data integration issues and privacy, as well as issues of interpretability are the challenges on the way. This will integrate deep neural networks with predictive models for the analysis of structured and unstructured EHR data for better accuracy using feature engineering, data augmentation, and hyperparameter tuning. The performance evaluation is done on the basis of real-world patient data, thereby leading to significant improvements in prediction reliability, treatment personalization, and efficiency of decision-making over traditional models. Despite implementation challenges, these technologies promise improved treatments, reduced healthcare costs, and better patient outcomes. Future efforts should emphasize broader integration and ethical considerations.

Automated summarization of Healthcare Records utilizing large language models (LLMs) represents a groundbreaking evolution in the management and analysis of extensive medical data. By harnessing the sophisticated capabilities of LLMs, healthcare professionals are empowered to swiftly produce concise and coherent summaries of patient records. This significantly reduces the administrative burden associated with documentation, resulting in enhanced productivity and improved decision-making processes. LLMs excel in extracting essential clinical information, identifying trends, and emphasizing critical components from unstructured data sources, which include physician notes, diagnostic reports, and comprehensive patient histories. The use of this technology not only streamlines efficiency but also mitigates the risk of human error, thereby facilitating a more accurate representation of patient care. Furthermore, personalized healthcare can be better achieved as LLMs provide clinicians with relevant insights tailored to individual patient needs. Despite these advantages, several challenges must be meticulously addressed to maximize the effectiveness of LLMs in healthcare summarization. Key concerns include ensuring strict data privacy protocols, effectively managing the complexities of medical terminology, and maintaining high accuracy in the summarization process. As the field continues to evolve, ongoing research and development will be crucial in refining these models and mitigating their limitations, ultimately unlocking the full potential of LLMs to revolutionize healthcare delivery.

Background
Sri Lanka has a well-established National Blood Transfusion Service that provides quality assured blood bank service. However, the information flow is inefficient and less utilized for evidence-based decision-making. The statistics unit of National Blood Centre is unable to produce Annual Statistics Report timely due to the difficulty in analysing and making reports manually utilizing the considerable amount of data collected throughout the year. To address this, an electronic Health Information Management System was proposed as a solution for the inefficiency of the data flow for statistical purposes.
Method
A Monthly Statistics Reporting System was designed and developed using DHIS2, which is a Free and Open Source Software (FOSS) to fulfil the requirements of the National Blood Transfusion Service. To evaluate the new system, a qualitative study was conducted using semi-structured interviews amongst a selected study population of 17 participants within the NBC Cluster, which includes 11 blood banks in Colombo area. The gathered data was analysed using a thematic analysis techniques and the emerging categories and themes were used in the subsequent discussions.
Results
Problems of calculation, usability, reliability, utilization of data and availability of reports were identified in the paper-based system. Results shows that the new electronic system has high usefulness, ease of use, ease of learn, satisfaction and cost effectiveness with accepted enhanced features of the interface. According to the interviews, participants expressed that the likelihood of using this system in the future is high. 
Conclusion
Almost all the participants in this research readily accepted new electronic information management system. Therefore, it will assure the sustainability of the new system. Because of the real time updated dashboard, it will help most of the blood bank functions by facilitating administrative decision-making efficiently.
Keywords— Blood Transfusion Services; Health Information Systems; DHIS2; Electronic Reporting; Sri Lanka

Purpose: This article explores the potential of artificial intelligence (AI) to transform clinical trials and disease modeling, focusing on how AI can enhance healthcare efficiency, precision, and personalization.

Methodology: The study involves reviewing existing literature and conducting detailed investigations of various AI models, ranging from basic machine learning algorithms to sophisticated deep learning models like convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and transformer models.

Findings: Our analysis demonstrates that AI algorithms can significantly reduce human screening time, improve risk stratification, and provide more accurate predictions compared to conventional techniques [17], [18]. However, these benefits are accompanied by challenges, including data quality issues, algorithmic bias, understanding the "black box" nature of AI tools, regulatory constraints, and patient privacy and consent concerns.

Unique Contribution to Theory, Practice, and Policy: The article highlights AI's enormous potential to revolutionize clinical research. It recommends that successful implementation requires collaboration with the medical community to ensure ethical and responsible use, addressing the challenges of data quality, transparency, regulatory compliance, and patient rights.

Service that provides quality assured blood bank service. However, the information flow is inefficient and less utilized for evidence-based decision-making. The statistics unit of National Blood Centre is unable to produce Annual Statistics Report timely due to the difficulty in analysing and making reports manually utilizing the considerable amount of data collected throughout the year. To address this, an electronic Health Information Management System was proposed as a solution for the inefficiency of the data flow for statistical purposes. A Monthly Statistics Reporting System was designed and developed using DHIS2, which is a Free and Open Source Software (FOSS) to fulfil the requirements of the National Blood Transfusion Service. To evaluate the new system, a qualitative study was conducted using semi-structured interviews amongst a selected study population of 17 participants within the NBC Cluster, which includes 11 blood banks in Colombo area. The gathered data was analysed using a thematic analysis techniques and the emerging categories and themes were used in the subsequent discussions. Problems of calculation, usability, reliability, utilization of data and availability of reports were identified in the paperbased system. Results shows that the new electronic system has high usefulness, ease of use, ease of learn, satisfaction and cost effectiveness with accepted enhanced features of the interface. According to the interviews, participants expressed that the likelihood of using this system in the future is high. Almost all the participants in this research readily accepted new electronic information management system. Therefore, it will assure the sustainability of the new system. Because of the real time updated dashboard, it will help most of the blood bank functions by facilitating administrative decision-making efficiently.

The complex nature of tropical disease variants with confusable symptoms has led to prescription errors and consequentially, many deaths. Soft-computing techniques have been proposed to handle vagueness and imprecision in the diagnosis process. This paper presents a systematic review on the use of soft-computing techniques in the diagnosis of tropical diseases. The results show that Africa, Asia-Pacific and European countries have done more research in areas that focus on the use of soft computing techniques in the diagnosis of tropical diseases, followed by the Americas. Of the twelve (12) tropical diseases commonly researched, malaria, dengue fever, skin diseases, and typhoid fever top the list. The soft-computing classifiers were evenly distributed between single and hybrid paradigms. Most of the classification engines were based on fuzzy logic (15), neural network (5), support vector machine (4), and decision tree (4). Some of the systems were not deployed and most health organi...

Artificial intelligence (AI) is rapidly transforming various sectors and internal medicine is no exception. This field, focused on the diagnosis, treatment and management of complex adult diseases, is witnessing a paradigm shift with the integration of AI technologies. This abstract explores the multifaceted ways AI is revolutionizing internal medicine, encompassing advancements in diagnosis, personalized treatment approaches and enhanced patient care. AI-powered tools are enabling physicians to analyze vast amounts of patient data, including medical images, electronic health records and genomic information, to identify patterns and insights that may be missed by human observation. This leads to more accurate and timely diagnoses, particularly in areas like radiology, pathology and cardiology. Furthermore, AI is facilitating the development of personalized treatment plans tailored to individual patient characteristics, optimizing therapeutic interventions and improving patient outcomes. By automating routine tasks, AI is also freeing up physicians' time, allowing them to focus on more complex cases and enhance patient interaction. However, the successful implementation of AI in internal medicine requires careful consideration of ethical implications, data privacy and the need for human oversight. This abstract highlight the transformative potential of AI in internal medicine while acknowledging the challenges that need to be addressed to ensure its responsible and effective integration into clinical practice.

Artificial intelligence (AI) is rapidly transforming various sectors and internal medicine is no exception. This field, focused on the diagnosis, treatment and management of complex adult diseases, is witnessing a paradigm shift with the integration of AI technologies. This abstract explores the multifaceted ways AI is revolutionizing internal medicine, encompassing advancements in diagnosis, personalized treatment approaches and enhanced patient care. AI-powered tools are enabling physicians to analyze vast amounts of patient data, including medical images, electronic health records and genomic information, to identify patterns and insights that may be missed by human observation. This leads to more accurate and timely diagnoses, particularly in areas like radiology, pathology and cardiology. Furthermore, AI is facilitating the development of personalized treatment plans tailored to individual patient characteristics, optimizing therapeutic interventions and improving patient outcomes. By automating routine tasks, AI is also freeing up physicians' time, allowing them to focus on more complex cases and enhance patient interaction. However, the successful implementation of AI in internal medicine requires careful consideration of ethical implications, data privacy and the need for human oversight. This abstract highlight the transformative potential of AI in internal medicine while acknowledging the challenges that need to be addressed to ensure its responsible and effective integration into clinical practice.

electronic health records (EHRs), wearable devices, medical imaging, lab results, genomic sequencing, and even patient-generated data from mobile apps. Think of AI like a medical student. The more patient cases it "sees," the better it gets at diagnosing, predicting, and recommending treatments. In other words, data is to AI what oxygen is to humans. The better the data, the smarter the AI. Types of Healthcare Data Used in AI AI in healthcare thrives on diverse and high-quality datasets. Here are the major types of data feeding modern algorithms: • Structured Data Includes lab results, vitals, medication history, demographic information-easily organized and fed into AI models.

Integrating artificial intelligence (AI) with multi-modal engineering systems is poised to revolutionize personalized medicine, an innovative approach that tailors healthcare interventions based on the unique physiological, genetic, and lifestyle characteristics of each patient. This paper explores how AI enables the comprehensive analysis of vast and complex datasets sourced from wearable sensors, advanced imaging technologies, genomic sequencing, and electronic health records. By synthesizing diverse types of information, AI enhances diagnostic accuracy, facilitates early disease detection, and supports the development of highly individualized treatment plans, thereby significantly improving therapeutic outcomes for patients. Despite these promising advancements, the implementation of AI in personalized medicine faces several critical challenges, including the complexity of integrating heterogeneous data, ensuring robust patient privacy and data security, and improving the interpretability of AI-driven models for clinical decision-making. Addressing these challenges requires strong interdisciplinary collaboration among clinicians, data scientists, engineers, and ethicists. Through these concerted efforts, AI can be effectively harnessed to deliver high-performance, ethical, and patient-centered healthcare solutions.