Knee osteoarthritis (OA) is a popular and progressive degenerate joint disease and require a predictor of risk at the primary stage to predict drug treatment and propose an early intervention. The current methods of deep learning are not sufficient enough to deal with integrating the heterogeneous modality component, modeling of irregular temporal follow ups, and capture of the fine grained variations of pathological types. In order to address such limitations, this paper suggests a new multimodal approach named, RAD-OAEnsemble which introduces three main innovations. First, a novel Cross Bi-modal Heterogeneous Graph Fusion Network (CBHGF-Net) is introduced for the multi-scale semantic fusion of Radiographs and Electronic Health Records (EHRs). Second, a Modified DenseNet with Multi-scale Attention Criss-Cross Blocks (MACC-Blocks) is presented to extract the anatomical features of knee OA patterns by utilizing dilated convolution, criss-cross attention, residual attention gating. Third, a Dual-Stream Tranfo-Convo (DTC) Deep Temporal Embedding module is proposed that consists of a Time-Warped Convolutional Blocks and a Temporal Decay Encoded Informer for the knee OA risk prediction. The suggested approach delivered better outcomes with accuracy of 99.275%, precision of 98.175%, specificity of 99.165%, sensitivity of 98.95%, and F1-score of 98.175% in having considerably a low rate of false positives (1.875%) and false negatives (2.175%). The findings support the relevance of the suggested framework in providing resilient, time-sensitive, and explainable OA progression predictions by multimodal combination and high-fidelity feature learning.
Electronic medical records (EMRs) are critical, highly sensitive private information in health sector, and manage patient health information. The purpose of the study identifies a unique opportunity to develop a secure for maternal child health care. This work uses the Scopus, PubMed, and Web of Science databases to analyse the most productive authors, journals, institutions, and countries, as well as the most cited papers and the citing articles. The investigation used bibliometric analysis to identify the bibliographic data from 501 articles published from 2011 and 2025 and implementation of EMRs for maternal and child healthcare. Based on the findings, the issue is multifaceted and involves various stakeholders, including health care providers, patients, and technological issues within the health sectors. The proposed work can significantly reduce the turnaround time for EMRs sharing, improve decision making for medical care, and reduce the overall cost of medical instruments.
electronic health recordsmaternal carechild health carehealth information security
The healthcare industry, aided by technology, leverages the Internet of Things (IoT) paradigm to offer patient/user-related services that are ubiquitous and personalized. The authorized repository stores ubiquitous data for which access-level securities are granted. These security measures ensure that only authorized entities can access patient/user health information, preventing unauthorized entries and data downloads. However, recent sophisticated security and privacy attacks such as data breaches, data integrity issues, and data collusion have raised concerns in the healthcare industry. As healthcare data grows, conventional solutions often fail due to scalability concerns, causing inefficiencies and delays. This is especially true for multi-key authentication. Dependence on conventional access control systems leads to security flaws and authorization errors caused by static user behaviour models. This article introduces an Opportunistic Access Control Scheme (OACS) for leveraging access-level security. This approach is a defendable access control scheme in which the user permissions are based on their requirement and data. After accessing the healthcare record, a centralized IoT security augmentation and assessment is provided. The blockchain records determine and revoke the access grant based on previous access and delegation sequences. This scheme analyses the possible delegation methods for providing precise users with interrupt-free healthcare record access. The blockchain recommendations are analyzed using a trained learning paradigm to provide further access and denials. The proposed method reduces false rates by 11.74%, increases access rates by 13.1%, speeds up access and processing by 12.36% and 13.23%, respectively, and reduces failure rates by 9.94%. The OACS decreases false rates by 10.64%, processing time by 15.62%, and failure rates by 10.95%.
Internet of Thingshealthcare data securityblockchainmachine learning
The incidence of suicide, self-harm, and mental crises among teenagers is rising, presenting significant global public health issues. Conventional clinical risk evaluations have inadequate predictive accuracy, often overlooking high-risk adolescents. Machine learning models employing electronic health records provide an innovative method for predicting mental health crises through the integration of intricate clinical data patterns. Hence, this review aims to comprehensively examine and synthesize information about machine learning models created using electronic health record data for predicting suicide attempts, self-harm, or mental hospitalization in teenagers. Adhering to Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) principles, we executed an exhaustive search across six databases (2000-2025) for peer-reviewed research utilizing machine learning algorithms on electronic health record data to predict adolescent mental health crises. The inclusion criteria emphasized structured or unstructured electronic health record inputs, teenage cohorts (ages 10-20), and performance indicators like area under the curve (AUC), sensitivity, or specificity. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was utilized to evaluate the risk of bias. Our search yielded five studies (2019-2024) that satisfied the inclusion criteria. All studies were retrospective cohorts conducted in high-income nations. Structured electronic health record data (e.g., diagnoses, prescriptions) were frequently utilized; two studies included natural language processing. Machine learning models demonstrated moderate to high discrimination (AUC 0.68-0.88), exhibiting optimal performance in short-term suicide prediction with hybrid data inputs. All investigations, however, exhibited a significant risk of bias in the analysis domain owing to insufficient external validation and absent calibration data. The positive predictive values consistently remained modest across all models. Overall, machine learning models demonstrate potential for enhancing adolescent suicide risk classification utilizing electronic health record data, surpassing numerous traditional instruments. Nonetheless, issues of generalizability, ethical constraints, and implementation obstacles remain. Thorough validation, calibration, and equity assessments are necessary prior to incorporation into clinical practice.
adolescent mental healthsuicide risk predictionself-harmelectronic health records
Sepsis is a life-threatening condition, and early recognition in the emergency department (ED) is crucial for reducing mortality. However, traditional ED sepsis screening tools (e.g., Systemic Inflammatory Response Syndrome (SIRS) and quick Sequential Organ Failure Assessment (qSOFA)) often lack sensitivity for early detection. Machine learning (ML)-based early warning systems have been proposed to address this gap by analyzing complex clinical data in real time. To address this, we systematically reviewed studies (2015-2025) assessing ML-based sepsis warning systems in adult EDs. Databases searched included PubMed, Embase, Scopus, and Web of Science. Included studies reported diagnostic performance and/or clinical outcomes. Overall, a total of 11 studies (primarily retrospective, with a few prospective) were included. ML models using vital signs, laboratory results, and electronic health record (EHR) data demonstrated high discrimination for sepsis, with area under the receiver operating characteristic curve (AUROC) values often exceeding 0.80, and outperformed traditional scoring tools. Many provided earlier warnings, often two to four hours before sepsis was clinically recognized. Implementation studies showed that ML-based alerts expedited treatment; one multi-center system reduced time to antibiotics by ~1.8 hours when alerts were promptly addressed. Some reports noted reduced organ failure and mortality. However, evidence of improved patient outcomes remains inconsistent, likely due to study heterogeneity and limited prospective validation. ML-based early warning systems show strong potential for improving sepsis recognition and treatment in EDs. Further multi-center trials are needed to confirm their impact on outcomes and guide safe implementation.
sepsisearly warning systemsmachine learningemergency department
Saudi Pharmaceutical Journal · مجلد 33 (5) · 41-41
Antimicrobial resistance (AMR) is rising alarmingly in Saudi Arabia, as evidenced by surveillance data. This retrospective cohort study evaluated the association between parenteral antimicrobial use and bacterial resistance at King Khaled Hospital, Al-Kharj, using electronic health records. Linear regression analyzed antibiotic exposure-resistance relationships over 36 months (January 2022–December 2024). Eligible participants were hospitalized ≥ 48 h and received ≥ 1 parenteral antimicrobial. The required sample size was 384 (calculated via Cochran’s formula). Inclusion mandated laboratory-confirmed bacterial infections (positive cultures with susceptibility testing). Investigated pathogens included Escherichia coli , Klebsiella pneumoniae , Pseudomonas aeruginosa , Acinetobacter baumannii , and Staphylococcus aureus . Among 4,007 participants, 59.02% were female, and 73.07% were Saudis. Findings revealed severe AMR, particularly in Escherichia coli and Klebsiella pneumoniae , with high resistance to multiple antibiotic classes. Acinetobacter baumannii exhibited near-pan-drug resistance (> 90% resistance to most antibiotics). Imipenem use strongly correlated with Escherichia coli resistance (R 2 = 1.000, p-value = 0.009), indicating significant carbapenem-driven selection pressure. Meropenem exposure also closely linked to Klebsiella pneumoniae resistance (R 2 = 0.994, p-value = 0.050). Widespread resistance to β-lactams, fluoroquinolones, and aminoglycosides—combined with near-pan-resistant Acinetobacter baumannii —highlights escalating treatment challenges. Crucially, carbapenem usage (imipenem/meropenem) strongly predicted resistance in Escherichia coli and Klebsiella pneumoniae , reinforcing antimicrobial pressure’s role in resistance development. These results emphasize the urgent need for antimicrobial stewardship at King Khaled Hospital to curb carbapenem overuse and combat resistant infections.
BACKGROUND: In the digital age, maintaining patient confidentiality while ensuring effective care coordination poses significant challenges for healthcare providers, particularly nurses. AIM: To investigate the challenges and strategies associated with balancing patient confidentiality and effective care coordination in the digital age. METHODS: A cross-sectional study was conducted in a general hospital in Egypt to collect data from 150 nurses across various departments with at least six months of experience in patient care. Data were collected using six tools: Demographic Form, HIPAA Compliance Checklist, Privacy Impact Assessment (PIA) Tool, Data Sharing Agreement (DSA) Framework, EHR Privacy and Security Assessment Tool, and NIST Cybersecurity Framework. Validity and Reliability were ensured through pilot testing and factor analysis. RESULTS: Participants were primarily aged 31-40 years (45%), with 75% female and 60% staff nurses. High compliance was observed in the HIPAA Compliance Checklist, especially in Administrative Safeguards (3.8 ± 0.5), indicating strong management and training processes, with an overall score of 85 ± 10. The PIA Tool showed robust privacy management, with Project Descriptions scoring 4.5 ± 0.3 and a total score of 30 ± 3. The DSA Framework had a mean total score of 20 ± 2, with Data Protection Measures scoring highest at 4.0 ± 0.4. The EHR assessments revealed high scores in Access Controls (4.4 ± 0.3) and Data Integrity Measures (4.3 ± 0.3), with an overall score of 22 ± 1.5. The NIST Cybersecurity Framework had a total score of 18 ± 2, with the highest scores in Protect (3.8) and lower in Detect (3.6). Strong positive correlations were found between HIPAA Compliance and EHR Privacy (r = 0.70, p < 0.05) and NIST Cybersecurity (r = 0.55, p < 0.05), reflecting effective data protection practices. CONCLUSION: The study suggests that continuous improvement in privacy practices among healthcare providers, through ongoing training and comprehensive privacy frameworks, is vital for enhancing patient confidentiality and supporting effective care coordination.
International Conference on Smart and Sustainable Technologies (SpliTech) · 1-6
In the evolving healthcare landscape, the Internet of Medical Things (IoMT) enables real-time data collection through connected devices. Concerns about data privacy in electronic health records are driving changes in health assessment. Blended learning is emerging as a solution, allowing simulation training without sharing critical information centrally. The proposed techniques emphasize privacy and efficiency and use federated averaging to analyze edge computation. Smart healthcare addresses the benefits and challenges of integrating AI and edge tech. In this revolutionary approach, federated learning uses server-side federated averaging, combining local client model parameters while reducing edge computation latency and energy consumption The integration of AI and edge technologies not only increases efficiency but also provides forward-looking approaches for personalized and responsive healthcare. Experimental validation with the Covid-pneumonia dataset highlights the effectiveness of the integrated learning approach, confirming the important contribution to privacy protection and efficient machine learning applications in computing in healthcare of the policies established in countries.
federated learningedge computingInternet of Medical ThingsFedAvg
OBJECTIVES: This study was conducted to assess the validity of recording (and the original diagnostic practice) of type 2 diabetes mellitus at a hospital whose records were integrated to a centralised database (the standardised common data model (CDM) of the Saudi National Pharmacoepidemiologic Database (NPED)). DESIGN: A retrospective single-centre validation study. SETTINGS: Data of the study participants were extracted from the CDM of the NPED (only records of one tertiary care hospital were integrated at the time of the study) between 1 January 2013 and 1 July 2018. PARTICIPANTS: A random sample of patients with type 2 diabetes mellitus (≥18 years old and with a code of type 2 diabetes mellitus) matched with a control group (patients without diabetes) based on age and sex. OUTCOME MEASURES: The standardised coding of type 2 diabetes in the CDM was validated by comparing the presence of diabetes in the CDM versus the original electronic records at the hospital, the recording in paper-based medical records, and the physician re-assessment of diabetes in the included cases and controls, respectively. Sensitivity, specificity, positive predictive value and negative predictive value were estimated for each pairwise comparison using RStudio V.1.4.1103. RESULTS: A total of 437 random sample of patients with type 2 diabetes mellitus was identified and matched with 437 controls. Only 190 of 437 (43.0%) had paper-based medical records. All estimates were above 90% except for sensitivity and specificity of CDM versus paper-based records (54%; 95% CI 47% to 61% and 68%; 95% CI 62% to 73%, respectively). CONCLUSIONS: This study provided an assessment to the extent of which only type 2 diabetes mellitus code can be used to identify patients with this disease at a Saudi centralised database. A future multi-centre study would help adding more emphasis to the study findings.
type 2 diabeteselectronic health recordscommon data modelpaper medical records
Saudi Pharmaceutical Journal · مجلد 31 (11) · 101795-101795
Background and objectives: High-quality documentation is critical in medical settings for providing safe patient care. This study was done with the objective of assessing the standard of medical records in anticoagulation clinics and investigating the distinctions between notes written by pharmacists and physicians. Methods: A retrospective cross-sectional analysis of data from electronic health records (EHRs) was performed on patients who received anticoagulation and were observed at anticoagulation clinics from October to December 2020. Patients were monitored in two anticoagulation clinics, one administered by pharmacists and the other by physicians. The quality of the documentation was assessed using a score, and the note was assigned one of five categories according to its score: very good, good, average, poor, and very poor. The data was analyzed using Stata/SE 13.1. P value less than 0.05 was considered significant in all analytical tests. Results: A total of 331 patients were included. While 160 patients (48.3%) were followed by the physician-led clinic, 171 (51.6%) were by the pharmacist-led clinic. The average age of the patients was 54±15. 60.73% of them were female, and 90.3% of them were Saudi nationals. Warfarin was the most widely used anticoagulant (70%), followed by rivaroxaban (15.7%). Compared to physicians, pharmacists demonstrated very strong documentation (54% vs. 18%). The examination of the variables considered in the study revealed that physicians had significantly less drug-drug interaction documentation (17 vs. 71 times) or drug-food interaction documentation (23 vs. 71 times) than pharmacists. In terms of follow-up frequency, pharmacists were found to adhere to the clinic protocol (150 times) more frequently than physicians (104 times). However, there was no significant difference in therapeutic plan documentation between the two groups. (p = 0.416). Conclusion: Pharmacists were more comprehensive in their documentation than physicians in anticoagulation clinics. Unified clinic documentation can ensure consistent documentation within EHRs across all disciplines.
anticoagulation clinicclinical documentation qualitypharmacist-led clinicelectronic health records
Stroke survivors have access to a wide range of drug and non-drug treatments for the resulting physiological and functional problems. However, comprehensive therapies typically fail to meet the demands of a large percentage of patients. The recent clinical studies to improve protocol scientific evidence have resulted in a new development phase for rehabilitation medicine. Stroke rehabilitation supports individuals to lead a normal life. It assists the physicians in offering an effective environment to the patients. The evaluation of a patient’s progress in rehabilitation is based on the clinician’s subjective observations and the patient’s self-reported data. Deep learning techniques offer novel forms of individualized treatment. Nonetheless, missing data is one of the crucial factors that reduces the performance of data classification techniques. Thus, there is a demand for functional recovery prediction models for supporting stroke patients (SPs) to improve their quality of life. In this study, the researchers intend to build a framework for predicting functional outcomes using the electronic health record data of SPs. An attention-based bidirectional gated recurrent unit is used for developing the data imputation model. In addition, a shallow-convolutional neural network is employed for predicting the functional outcomes based on the modified Barthel Index. Data from 356 SPs were utilized for evaluating the performance of the proposed framework with the benchmark metrics and baseline models. The findings reveal that the proposed framework outperforms the state-of-the-art classification by achieving an average accuracy, precision, recall, F1-measure, specificity, and sensitivity of 98.18, 97.48, 98, 97.74, 96.74, and 97.24, respectively. The proposed framework can be implemented in real time to support SPs.
stroke rehabilitationfunctional recovery predictionelectronic health recordsmissing data imputation
amily physicians play a pivotal role in the early detection, diagnosis, and management of mental health disorders within the community. This review article delves into the multifaceted responsibilities of family physicians in the realm of mental health care. Emphasizing the importance of primary care settings as the first point of contact for many patients, the article underscores the need for effective screening tools and methodologies tailored for these environments. The diagnostic precision of family physicians, often challenged by the broad spectrum of mental health symptoms, is explored alongside the potential implications of misdiagnoses. Furthermore, the article evaluates various treatment options, from pharmacological interventions to psychotherapy, and their applicability in primary care settings. The integration of technological advancements, such as electronic health records and telemedicine, is also discussed in the context of enhancing patient care. The review concludes by highlighting the importance of educating primary care physicians to not only pay close attention to the mental health of their patients, but also to be able to accurately screen and diagnose mental health issues using various diagnostic tools. Moreover, it is critical to develop more useful tools that can be used in the context of primary care settings.
general practitionersmental health servicesprimary caremental health screening
The emergence of blockchain know-how currently presents the opportunity for the health sector to adopt such technologies in electronic health records. Blockchain assists in maintaining and sharing the relevant medical records of the patient with the relevant group of healthcare providers and the hospital. Numerous specific applications include traceability of drug and patient monitoring or Electronic Health Records (EHR). While Blockchain assists in maintaining and sharing the relevant medical records of the patient with the relevant group of healthcare providers and the hospital, it is important to note that the moral consciousness of the healthcare professionals is the main guide of the moral consciousness is ethics. This paper presents an overview of the application of blockchain in the healthcare and medical sector, highlighting the specific challenges and concerns. The study adopted a systematic review of secondary literature in answering the research question.
blockchainhealth careelectronic health recordsdecentralization (distributed systems)
Background It has been established that patients with COVID-19 pneumonia are more vulnerable to developing thromboembolic complications. Computed tomography (CT) scan of the chest is an essential investigation modality in patients with COVID-19 pneumonia and has an important role in the diagnosis and identification of complications. Methods A retrospective observational study was conducted on patients admitted with COVID-19 pneumonia who underwent CT scans of the chest. The data regarding demographic information, clinical information, and CT findings were collected from electronic health records. Multivariable regression analysis was used to identify the independent factors associated with thromboembolic complications. Results The study included a total of 276 patients, including 178 (64.5%) men and 98 (35.5%) women. In total, 64 patients were found to have thromboembolic events, yielding a complication rate of 23.2%. Multivariable logistic regression revealed that patients aged 51-65 years (Odds ratio [OR] = 8.9; 95% confidence interval [CI]: 3.0-26.5) and >65 years (OR = 18.7; 95% CI: 7.6-46.1) had a higher likelihood of having thromboembolic complications compared to those aged 18-35 years. Further, the crazy-paving appearance of opacity was identified as an independent factor associated with thromboembolic events (OR = 14.2; 95% CI: 6.9-29.4). Further, patients with severe pulmonary parenchymal involvement were 30 times (OR = 30.6; 95% CI: 9.8-95.5) more likely to have thromboembolic complications compared with those having mild involvement. Conclusions The radiological findings on the CT scan of the chest can provide crucial prognostic information for patients with COVID-19 in terms of thromboembolic events. Clinicians need to keep a high index of suspicion for pulmonary embolism and deep venous thrombosis when they encounter patients with crazy-paving opacity appearances on CT scans, particularly among patients with severe parenchymal involvement.
Journal of Pharmaceutical Research International · مجلد 33 (60B) · 1311-1317
Background: Influenza is one of the infections in which a specific pattern is observed according to seasons which result in severe forms of disease. By providing regular and extensive quality in epidemiological studies, the surveillance system can help in reducing the threat to public health posed by influenza that eventually minimizes the effect of illness. They also help in reporting the health ministry about the relevant information as an aid to reduce the impact of disease on public health. Objective: To assess the incidence of seasonal influenza in Abha City, Saudi Arabia. Methods: This surveillance report conducted among citizens of Abha, Saudi Arabia, 2019. It is based on sentinel surveillance and case-based data collection of laboratory-confirmed cases through electronic health records. All data were obtained from the department of infectious diseases of public health department in Aseer health directorate. Results: The total reported positive cases for influenza viruses were 808 (22.30%) patients in the city of Abha for the year 2019, among them 435 males and 373 females (F= 9.5149; P=0.002038) which 665 (82.3%) were typed as influenza A and 143 (17.7%) as influenza B. (F= 674.46; P=0.001). The prevalence of the disease is commonly seen in the age group of 5-15 (42.35 %) with a mean age of 15.45±4.50 followed by 16 to 50 years age (37.45%) and 51-65 age group (10%). There was no death registered among these cases. In February maximum cases were found, whereas in June and July minimum cases were recorded. The influenza positivity rate showed one primary peak and three secondary peaks that were recorded in February and January, March and December. Conclusion: Importance of conducting effective epidemiological surveillance for influenza virus in various regions in Abha specially in winter season with a peak in the month of February.
seasonal influenzainfluenza incidenceinfluenza A virusinfluenza B