Design of Interoperable Electronic Health Record (EHR) Application for Early Detection of Lung Diseases Using a Decision Support System by Expanding Deep Learning Techniques.

Background: Electronic health records (EHRs) are live, digital patient records that provide a thorough overview of a person's complete health data. Electronic health records (EHRs) provide better healthcare decisions and evidence-based patient treatment and track patients' clinical development. The EHR offers a new range of opportunities for analyzing and contrasting exam findings and other data, creating a proper information management mechanism to boost effectiveness, quick resolutions, and identifications. Aim: The aim of this studywas to implement an interoperable EHR system to improve the quality of care through the decision support system for the identification of lung cancer in its early stages. Objective: The main objective of the proposed system was to develop an Android application for maintaining an EHR system and decision support system using deep learning for the early detection of diseases. The second objective was to study the early stages of lung disease to predict/detect it using a decision support system. Methods: To extract the EHR data of patients, an android application was developed. The android application helped in accumulating the data of each patient. The accumulated data were used to create a decision support system for the early prediction of lung cancer. To train, test, and validate the prediction of lung cancer, a few samples from the ready dataset and a few data from patients were collected. The valid data collection from patients included an age range of 40 to 70, and both male and female patients. In the process of experimentation, a total of 316 images were considered. The testing was done by considering the data set into 80:20 partitions. For the evaluation purpose, a manual classification was done for 3 different diseases, such as large cell carcinoma, adenocarcinoma, and squamous cell carcinoma diseases in lung cancer detection. Results: The first model was tested for interoperability constraints of EHR with data collection and updations. When it comes to the disease detection system, lung cancer was predicted for large cell carcinoma, adenocarcinoma, and squamous cell carcinoma type by considering 80:20 training and testing ratios. Among the considered 336 images, the prediction of large cell carcinoma was less compared to adenocarcinoma and squamous cell carcinoma. The analysis also showed that large cell carcinoma occurred majorly in males due to smoking and was found as breast cancer in females. Conclusion: As the challenges are increasing daily in healthcare industries, a secure, interoperable EHR could help patients and doctors access patient data efficiently and effectively using an Android application. Therefore, a decision support system using a deep learning model was attempted and successfully used for disease detection. Early disease detection for lung cancer was evaluated, and the model achieved an accuracy of 93%. In future work, the integration of EHR data can be performed to detect various diseases early.

Discharge Perfection: Assessing Documentation Quality at Mardan Medical Complex, Pakistan (2024 Audit Debut).

Background Patient discharge summaries not only play a vital role in ensuring continuity of care and patient safety but also serve as a communication tool between the primary and tertiary care settings. However, despite their paramount importance, most discharge summaries are either inaccurate or miss essential clinical information, posing considerable danger to patients. This clinical audit assesses the quality of discharge summaries at Mardan Medical Complex, Mardan, Pakistan, to identify areas for improvement. Aim The aim of this study is to assess the discharge summaries of patients at Mardan Medical Complex in Mardan, Pakistan, with a focus on their completeness, accuracy, and timeliness. Methods A cross-sectional, observational, and retrospective study was carried out in the Medical A ward of Mardan Medical Complex, Mardan, Pakistan, from September 2023 to October 2023. Out of the 897 discharge slips, a sample size of 105 participants was determined using Epi Info software. A systematic random sampling technique was used. Data was extracted from the hospital management information system and evaluated using a clinical audit tool based on standard guidelines from the Royal College of Physicians, Islamabad Healthcare Regulatory Authority, and Khyber Pakhtunkhwa Health Care Commission. To analyze the data, descriptive statistics were applied. Results The clinical audit revealed significant deficiencies in discharge summaries. Important patient demographics, such as contact details and safety alerts, were completely absent in 100% of the cases, and 48% of the summaries lacked the father's name. Admission details were similarly inadequate, with nearly all summaries missing critical information like admission time and reasons for admission. Clinical summaries and procedural details were absent in 73% and 87% of the cases, respectively. Discharge planning also showed major gaps, as special instructions according to the primary diagnosis and discharge destination were frequently neglected. Follow-up visits were recommended in only 71% of cases. Additionally, there were significant errors in in-home medication prescriptions, with 61% missing medication doses, 28% missing the route of administration, and 20% lacking the duration of treatment. Conclusions This clinical audit identified critical areas for improvement by revealing significant errors in the quality of discharge summaries at Mardan Medical Complex. It is recommended that standardized discharge slip templates be implemented, healthcare workers receive proper training, and thorough monitoring be conducted before patients are discharged. These measures aim to enhance the standard of documentation. Additionally, regular future clinical audits are essential for tracking the impact of these interventions and ensuring patient safety and continuity of care.

The Potential for Information Sharing Between an Electronic Medical Record System and the Moroccan Transplantation and Dialysis Registry: Examining Semantic Interoperability.

Background and aim In 2005, the Moroccan Ministry of Health established Magredial, a registry to track and monitor patients with end-stage renal disease (ESRD), with the aim of improving healthcare outcomes. After achieving initial success, Magredial's activity decreased, leading to its inactivity by 2015. Currently, efforts are underway to revive Magredial's use. The main goal of this study is to investigate the feasibility of data transfer between the electronic medical records (EMRs) of Hassan II Hospital of Fes, Morocco, and the registry by achieving semantic interoperability between the two systems Materials and methods The initial phase of this study involved a detailed review of existing literature, highlighting the importance of registries, especially in nephrology. This part of the study also aims to emphasize the role of semantic interoperability in facilitating the sharing of data between EMRs and registries. Following that, the study's second phase, which centered on the case study, conducted a detailed analysis of the data architectures in both Magredial and the EMR of the nephrology department to pinpoint areas of alignment and discrepancy. This step required cooperative efforts between the nephrology and IT departments of Hassan II Hospital. Results Our findings indicate a significant interoperability gap between the two systems, stemming from differences in their data architectures and semantic frameworks. Such discrepancies severely impede the effective exchange of information between the systems. To address this challenge, a comprehensive restructuring of the EMR is proposed. This strategy is designed to align disparate systems and ensure compliance with the interoperability standards the Health Level 7 Clinical Document Architecture (HL7-CDA) set forth. Implementing the proposed medical record approach is complex and time-consuming, necessitating healthcare professional commitment, and adherence to ethical standards for patient consent and data privacy. Conclusions Implementing this strategy is expected to facilitate the seamless automation of data transfer between the EMR and Magredial. It introduces a framework that could be a foundational model for establishing a robust interoperability framework within nephrology information systems in line with international standards. Ultimately, this initiative could lead to creating a nephrologist-shared health record across the country, enhancing patient care and data management within the specialty.

The effect of electronic medical records on medication errors, workload, and medical information availability among qualified nurses in Israel- a cross sectional study.

BACKGROUND: Errors in medication administration by qualified nursing staff in hospitals are a significant risk factor for patient safety. In recent decades, electronic medical records (EMR) systems have been implemented in hospitals, and it has been claimed that they contribute to reducing such errors. However, systematic research on the subject in Israel is scarce. This study examines the position of the qualified nursing staff regarding the impact of electronic medical records systems on factors related to patient safety, including errors in medication administration, workload, and availability of medical information. METHODS: This cross-sectional study examines three main variables: Medication errors, workload, and medical information availability, comparing two periods- before and after EMR implementation based on self-reports. A final sample of 591 Israeli nurses was recruited using online private social media groups to complete an online structured questionnaire. The questionnaires included items assessing workload (using the Expanding Nursing Stress Scale), medical information availability (the Carrington-Gephart Unintended Consequences of Electronic Health Record Questionnaire), and medical errors (the Medical Error Checklists). Items were assessed twice, once for the period before the introduction of electronic records and once after. In addition, participants answered open-ended questions that were qualitatively analyzed. RESULTS: Nurses perceive the EMR as reducing the extent of errors in drug administration (mean difference = -0.92 ± 0.90SD, p < 0.001), as well as the workload (mean difference = -0.83 ± 1.03SD, p < 0.001) by ∼ 30% on average, each. Concurrently, the systems are perceived to require a longer documentation time at the expense of patients' treatment time, and they may impair the availability of medical information by about 10% on average. CONCLUSION: The results point to nurses' perceived importance of EMR systems in reducing medication errors and relieving the workload. Despite the overall positive attitudes toward EMR systems, nurses also report that they reduce information availability compared to the previous pen-and-paper approach. A need arises to improve the systems in terms of planning and adaptation to the field and provide appropriate technical and educational support to nurses using them.

Risk of diabetes and expected years in life without diabetes among adults from an urban community in India: findings from a retrospective cohort.

BACKGROUND: Diabetes prevalence has increased over the past few decades, and the shift of the burden of diabetes from the older population to the younger population has increased the exposure of longer durations in a morbid state. The study aimed at ascertaining the likelihood of progression to diabetes and to estimate the onset of diabetes within the urban community of Mumbai. METHODS: This study utilized an observational retrospective non-diabetic cohort comprising 1629 individuals enrolled in a health security scheme. Ten years of data were extracted from electronic medical records, and the life table approach was employed to assess the probability of advancing to diabetes and estimate the expected number of years lived without a diabetes diagnosis. RESULTS: The study revealed a 42% overall probability of diabetes progression, with age and gender variations. Males (44%) show higher probabilities than females (40%) of developing diabetes. Diabetes likelihood rises with age, peaking in males aged 55-59 and females aged 65-69. Males aged 30-34 exhibit a faster progression (10.6 years to diagnosis) compared to females (12.3 years). CONCLUSION: The study's outcomes have significant implications for the importance of early diabetes detection. Progression patterns suggest that younger cohorts exhibit a comparatively slower rate of progression compared to older cohorts.

Strengths, Weaknesses, Opportunities, and Threats (SWOT) Analysis of Hemodialysis Electronic Health Record Implementation.

BACKGROUND AND AIM: The Nephrology Department of Hassan II Hospital in Fez, Morocco, has implemented an Electronic Medical Record (EMR) system for managing patients undergoing acute hemodialysis. This initiative aims to digitize patient monitoring and enhance the management of acute dialysis within the department. Conducting strengths, weaknesses, opportunities, and threats (SWOT) analysis - assessing strengths, weaknesses, opportunities, and threats - was crucial to identifying and understanding the internal strengths and weaknesses, as well as the external opportunities and threats. This article outlines the SWOT analysis findings that may impact the project's success and shape decision-making. It also discusses strategies that could be implemented to allocate resources, mitigate risks, and capitalize on potential advantages. MATERIALS AND METHODS: This study involved a multidisciplinary team, including professors, nephrologists, nephrology residents, and a healthcare information system engineer. Brainstorming sessions were held during the specification drafting phase to pinpoint both internal and external factors affecting the project. User feedback during testing further refined these factors, ensuring the project's alignment with real-world needs and challenges. RESULTS: The study identifies the project's strengths as providing safe and immediate access to information, along with strong communication between the department (application users) and the project manager. The significant EMR weakness is the lack of logistical resources and the absence of a long-term maintenance plan for the application. The opportunity presented by this EMR implementation is its functionality's potential to evolve, enabling the solution to be deployed in other dialysis centers across the region. The project's threat is the potential abandonment of EMR use by future practitioners. CONCLUSION: These SWOT analysis findings enable the development and implementation of strategies to reduce the current deployment's vulnerabilities and ensure the success of future HIS implementations in the nephrology network of the Fez-Meknes region, Morocco.

Machine learning in medication prescription: A systematic review.

BACKGROUND: Medication prescription is a complex process that could benefit from current research and development in machine learning through decision support systems. Particularly pediatricians are forced to prescribe medications "off-label" as children are still underrepresented in clinical studies, which leads to a high risk of an incorrect dose and adverse drug effects. METHODS: PubMed, IEEE Xplore and PROSPERO were searched for relevant studies that developed and evaluated well-performing machine learning algorithms following the PRISMA statement. Quality assessment was conducted in accordance with the IJMEDI checklist. Identified studies were reviewed in detail, including the required variables for predicting the correct dose, especially of pediatric medication prescription. RESULTS: The search identified 656 studies, of which 64 were reviewed in detail and 36 met the inclusion criteria. According to the IJMEDI checklist, five studies were considered to be of high quality. 19 of the 36 studies dealt with the active substance warfarin. Overall, machine learning algorithms based on decision trees or regression methods performed superior regarding their predictive power than algorithms based on neural networks, support vector machines or other methods. The use of ensemble methods like bagging or boosting generally enhanced the accuracy of the dose predictions. The required input and output variables of the algorithms were considerably heterogeneous and differ strongly among the respective substance. CONCLUSIONS: By using machine learning algorithms, the prescription process could be simplified and dosing correctness could be enhanced. Despite the heterogenous results among the different substances and cases and the lack of pediatric use cases, the identified approaches and required variables can serve as an excellent starting point for further development of algorithms predicting drug doses, particularly for children. Especially the combination of physiologically-based pharmacokinetic models with machine learning algorithms represents a great opportunity to enhance the predictive power and accuracy of the developed algorithms.

The lifetime risk of developing type II diabetes in an urban community in Mumbai: findings from a ten-year retrospective cohort study.

BACKGROUND: Incidence and prevalence do not capture the risk of developing diabetes during a defined period and only limited evidence exists on the lifetime risk of diabetes based on longer and continuous follow-up studies in India. Lacunae in evidence on lifetime risk can be attributed primarily to the absence of comprehensive and reliable information on diabetes incidence, mortality rates and lack of longitudinal studies in India. In light of the scarcity of evidence in India, the objective of this study was to estimate the incidence of diabetes and its lifetime risk in an urban community of Mumbai. METHODS: The research study utilized data which is extracted from the electronic medical records of beneficiaries covered under the Contributory Health Service Scheme in Mumbai. The dataset included information on 1652 beneficiaries aged 40 years and above who were non-diabetic in 2011-2012, capturing their visit dates to medical center and corresponding laboratory test results over a span ten years from January, 2012- December, 2021. Survival analysis techniques are applied to estimate the incidence of diabetes. Subsequently, the remaining life years from the life table were utilized to estimate the lifetime risk of diabetes for each gender, stratified by age group. RESULTS: A total of 546 beneficiaries developed diabetes in ten years, yielding an unadjusted incidence rate of 5.3 cases per 1000 person-years (95% CI: 4.9- 5.8 cases/ 1000 person years). The age-adjusted lifetime risk of developing type II diabetes in this urban community is estimated to be 40.3%. Notably, males aged 40 years and above had 41.5% chances of developing diabetes in their lifetime as compared to females with a risk of 39.4%. Moreover, the remaining lifetime risk of diabetes decreased with advancing age, ranging from 26.4% among 40-44 years old to 4.2% among those age 70 years and above. CONCLUSION: The findings stress the significance of recognizing age specific lifetime risk and implementing early interventions to prevent or delay diabetes onset and to focus on diabetes management programs in India.

Street Medicine: Barrier Considerations for Healthcare Providers in the U.S.

In the last decade, a movement known as "street medicine" has emerged. It is a relatively new medical field in which healthcare providers deliver medical care to homeless populations outside of traditional healthcare facilities, on the streets, and in various settings where unsheltered people live. Physicians essentially visit people living in camps, along riverbanks, in alleys, and abandoned buildings to provide medical care. During the pandemic, street medicine in the U.S. was often the first line of defense for people living on the streets. As the practice of street medicine continues to grow and expand across the country, there is an increasing demand to standardize patient care delivered outside traditional healthcare facilities.

Characterization of Inclination Analysis for Predicting Onset of Heart Failure from Primary Care Electronic Medical Records.

The aim of this study is to characterize the performance of an inclination analysis for predicting the onset of heart failure (HF) from routinely collected clinical biomarkers extracted from primary care electronic medical records. A balanced dataset of 698 patients (with/without HF), including a minimum of five longitudinal measures of nine biomarkers (body mass index, diastolic and systolic blood pressure, fasting glucose, glycated hemoglobin, low-density and high-density lipoproteins, total cholesterol, and triglycerides) is used. The proposed algorithm achieves an accuracy of 0.89 (sensitivity of 0.89, specificity of 0.90) to predict the inclination of biomarkers (i.e., their trend towards a 'survival' or 'collapse' as defined by an inclination analysis) on a labeled, balanced dataset of 40 patients. Decision trees trained on the predicted inclination of biomarkers have significantly higher recall (0.69 vs. 0.53) and significantly higher negative predictive value (0.60 vs. 0.55) than those trained on the average values computed from the measures of biomarkers available before the onset of the disease, suggesting that an inclination analysis can help identify the onset of HF in the primary care patient population from routinely available clinical data. This exploratory study provides the basis for further investigations of inclination analyses to identify at-risk patients and generate preventive measures (i.e., personalized recommendations to reverse the trend of biomarkers towards collapse).

Identification of patients with epilepsy using automated electronic health records phenotyping.

OBJECTIVE: Unstructured data present in electronic health records (EHR) are a rich source of medical information; however, their abstraction is labor intensive. Automated EHR phenotyping (AEP) can reduce the need for manual chart review. We present an AEP model that is designed to automatically identify patients diagnosed with epilepsy. METHODS: The ground truth for model training and evaluation was captured from a combination of structured questionnaires filled out by physicians for a subset of patients and manual chart review using customized software. Modeling features included indicators of the presence of keywords and phrases in unstructured clinical notes, prescriptions for antiseizure medications (ASMs), International Classification of Diseases (ICD) codes for seizures and epilepsy, number of ASMs and epilepsy-related ICD codes, age, and sex. Data were randomly divided into training (70%) and hold-out testing (30%) sets, with distinct patients in each set. We trained regularized logistic regression and an extreme gradient boosting models. Model performance was measured using area under the receiver operating curve (AUROC) and area under the precision-recall curve (AUPRC), with 95% confidence intervals (CI) estimated via bootstrapping. RESULTS: Our study cohort included 3903 adults drawn from outpatient departments of nine hospitals between February 2015 and June 2022 (mean age = 47 ± 18 years, 57% women, 82% White, 84% non-Hispanic, 70% with epilepsy). The final models included 285 features, including 246 keywords and phrases captured from 8415 encounters. Both models achieved AUROC and AUPRC of 1 (95% CI = .99-1.00) in the hold-out testing set. SIGNIFICANCE: A machine learning-based AEP approach accurately identifies patients with epilepsy from notes, ICD codes, and ASMs. This model can enable large-scale epilepsy research using EHR databases.

Dissecting clinical and biological heterogeneity in clinical states of bipolar disorder: a 10-year retrospective study from China.

Objectives: To dissect clinical and biological heterogeneity in clinical states of bipolar disorder (BD), and investigate if neuropsychological symptomatology, comorbidity, vital signs, and blood laboratory indicators are predictors of distinct BD states. Methods: A retrospective BD cohort was established with data extracted from a Chinese hospital's electronic medical records (EMR) between 2009 and 2018. Subjects were inpatients with a main discharge diagnosis of BD and were assessed for clinical state at hospitalization. We categorized all subjects into manic state, depressive state, and mixed state. Four machine learning classifiers were utilized to classify the subjects. A Shapley additive explanations (SHAP) algorithm was applied to the classifiers to aid in quantifying and visualizing the contributions of each feature that drive patient-specific classifications. Results: A sample of 3,085 records was included (38.54% as manic, 56.69% as depressive, and 4.77% as mixed state). Mixed state showed more severe suicidal ideation and psychomotor abnormalities, while depressive state showed more common anxiety, sleep, and somatic-related symptoms and more comorbid conditions. Higher levels of body temperature, pulse, and systolic and diastolic blood pressures were present during manic episodes. Xgboost achieved the best AUC of 88.54% in manic/depressive states classification; Logistic regression and Random forest achieved the best AUCs of 75.5 and 75% in manic/mixed states and depressive/mixed states classifications, respectively. Myocardial enzymes and the non-enzymatic antioxidant uric acid and bilirubin contributed significantly to distinguish BD clinical states. Conclusion: The observed novel biological associations with BD clinical states confirm that biological heterogeneity contributes to clinical heterogeneity of BD.

Influencing Appropriate Statin Use in a Charity Care Primary Clinic.

According to the American College of Cardiology/American Heart Association (ACC/AHA) new cholesterol management guidelines in 2019, statin regimen was prescribed to only about 46.4% and 30% of diabetes (DM) patients and patients with atherosclerotic cardiovascular disease (ASCVD), respectively. Atherosclerotic cardiovascular disease accounts for most deaths and disabilities in North America. This study argues that a systematic approach to identifying targeted interventions to adhere to the statin regimen for ASCVD is sparse in previous studies. This study seeks to address the research gap. Besides, the study argues that the statin regimen could improve cholesterol management with the enablers of pharmacy, providers, electronic medical records (E.M.R.), and patients. It paves the way for future research on cardiovascular and statin regimens from different perspectives. Current study has adopted the Qualitative observation method. Accordingly, the study approached the charity care primary clinic serving a large population in the northeastern part of the United States, which constitutes the project's setting. The facility has 51 internal medicine residents. The facility has E.H.R., which is used by the clinical staff. Besides, providers use electronic medication prescribing (E-Scribe). Four PDSA cycles were run in six months. Here, the interventions were intensified during each subsequent cycle. The interventions were then incorporated into routine clinical practice. Based on the observation, the study found a 25% relative improvement by six months based on the baseline data of the appropriate intensity statin prescription for patients with ASCVD or DM by medical resident trainees in our single-center primary care clinic. A total of 77% of cardiovascular disease patients were found to be on an appropriate statin dose at baseline. On the other hand, the proportion of patients with DM who were on proper dose statin was 80.4%. According to the study's findings, PDSA could result in a faster uptake and support of the ACC/AHA guidelines. Evidence indicates that overmedication of persons at low risk and time constraints are some of the most significant impediments to the greater use of prescription medications. Proactive panel management can help improve statins' use by ensuring they are used appropriately.

Chinese herbal medicine for migraine management: A hospital-based retrospective analysis of electronic medical records.

Background: Migraine is a chronic neurological disease causing significant socioeconomic burden and impaired quality of life. Chinese medicine is commonly used for migraine in China. Clinical trials have generated evidence of the effectiveness of Chinese medicine therapies for migraine. However, little is known about how to use these therapies to treat migraine in real-world clinical settings. Methods: In this retrospective study, we analyzed data from the electronic medical records (EMRs) of 2,023 migraine patients who attended the Guangdong Provincial Hospital of Chinese Medicine (GPHCM) between July 2018 and July 2020. Results: More than three-quarters (77.21%) of the patients were female. Most (78.20%) of the patients were aged between 18 and 50 years, 18.49% were aged above 50 years, and the remaining 3.31% were under 18 years. Sleep disorders were the most documented comorbidity occurring in 27.29% of patients, and more common in females (29.77%) than male (18.87%). Fatigue was the most frequently reported trigger of migraine attacks among all patients (9.39%), while menstruation was the most common trigger for female patients (10.24%). Less than a quarter of patients (21.01%) reported a history of taking analgesic medication for their migraine. The median treatment duration reported by the patients was 10 days. Chinese herbal medicine (CHM) was the predominant treatment for migraine at the hospital (88.48%), while pharmacotherapies were prescribed to 28.97% of the patients. CHM was prescribed more often as a sole treatment (53.58% of patients) than combined with pharmacotherapies (27.39% of patients). Among patients who reported improvements after taking CHM, the most frequently used herbs were fu ling and chuan xiong, the most frequent patented CHM product was tong tian oral solution, and the main herbal formulae were chuan xiong cha tiao san and yi qi cong ming tang. Conclusion: CHM formulae, such as chuan xiong cha tiao san and yi qi cong ming tang, patented CHM product tong tian oral solution, and some herbs are potentially effective treatments for migraine. As such, CHM can be used as an alternative to conventional pharmacotherapies for migraine and is worth further evaluation in randomized controlled trials.

Perceived security of BYOD devices in medical institutions.

BACKGROUND: Like other computing devices mobile devices have inherent security risks. With today's wider use of mobile devices in medical institutions, particularly the practice of 'bring-your-own-device' (BYOD), the risk of medical data breaches is concerning. PURPOSE: To investigate security risk perception and safeguard adoption of mobile devices among medical practitioners and IT administrators. Furthermore, to comprehend the perceived costs that practitioners feel these safeguards impose on them. BASIC PROCEDURES: We conducted both quantitative and qualitative studies investigating whether age, gender and occupation have an impact on the perceived security of patient information and the behavior intentions formed when adopting BYOD. In the quantitative component, a survey was completed by 264 healthcare practitioners from three hospitals and affiliated clinics in New York City. In the qualitative component, we interviewed 36 of 264 subjects from the first study, including twelve physicians, twelve nurses, and twelve IT administrators. All participants had direct experience with BYOD devices. The length of each interview averaged forty-five minutes to an hour. MAIN FINDINGS: We found that physicians have a significantly higher intent to comply with safeguards, compared to nurses. IT administrators prefer an encrypted network connection and Two Factor Authentication (2FA), or a biometric authentication method for accessing Electronic Medical records (EMR). All medical practitioners believe that the biggest threat to the security of medical information is theft or misplacement of the device. Physicians and IT administrators have a better understanding of malware and Wi-Fi threats than nurses. PRINCIPAL CONCLUSIONS: This research provides valuable data regarding the healthcare practitioner's safeguard cost, attitudes and intended behaviors regarding the risks and use of mobile devices in healthcare. By understanding a user's perceptions, we can be better aware of how to educate healthcare practitioners, and how to develop policies that will reduce costs and achieve better productivity. We can also see how these processes may be improved by accessing patient information faster and by designing technology more effectively.

IMPLEMENTATION OF THE NATIONWIDE ELECTRONIC HEALTH RECORD SYSTEM IN SERBIA: CHALLENGES, LESSONS LEARNED, AND EARLY OUTCOMES.

Objectives: Many countries around the world have recognized the need for using an electronic health record (EHR) system. However, there is limited literature that could serve as a guide during a lengthy and challenging process of planning, development, and implementation of the e-Health system. Since the EHR system was recently introduced in Serbia, the purpose of this communication is to describe our experience and lessons learned along the way. Methods: The key personnel involved in the implementation of the EHR system in Serbia that began in 2015 conducted in 2019 a retrospective narrative review of the process and early outcomes. Results: An incremental approach in the planning, development, and implementation of the nationwide EHR system was taken. The process was split into phases with the gradual introduction of different regions of the country. The gradual shift from the existing to a new workflow for the prospective users was also implemented. The significant milestones were the achievement of quick legislative changes, the hiring of a professional team of experts in the field, the provision of timely and appropriate information and training to prospective users, the close collaboration between the implementation team and the Ministry of Health and mutual understanding of the aims and expectations, and the flexibility in accepting the evolving nature of the process, goals, and the system model. Conclusions: A successful implementation of the nationwide EHR system is feasible providing careful planning, the assembly of a multi-disciplinary team, the use of a stepwise approach, the early and continued involvement of the intended users, and the willingness to make adjustments along the way. The end-result sets the stage for the reform of the health care system itself.

K-nearest-neighbor algorithm to predict the survival time and classification of various stages of oral cancer: a machine learning approach.

Background:For years now, cancer treatments have entailed tried-and-true methods. Yet, oncologists and clinicians recommend a series of surgeries, chemotherapy, and radiation therapy. Yet, even amidst these treatments, the number of deaths due to cancer increases at an alarming rate. The prognosis of cancer patients is influenced by mutations, age, and various cancer stages. However, the association between these variables is unclear. Methods: The present work adopts a machine learning technique-k-nearest neighbor; for both regression and classification tasks, regression for predicting the survival time of oral cancer patients, and classification for classifying the patients into one of the predefined oral cancer stages. Two cross-validation approaches-hold-out and k-fold methods-have been used to examine the prediction results. Results: The experimental results show that the k-fold method performs better than the hold-out method, providing the least mean absolute error score of 0.015. Additionally, the model classifies patients into a valid group. Of the 429 records, 97 (out of 106), 99 (out of 119), 95 (out of 113), and 77 (out of 91) were classified to its correct label as stages - 1, 2, 3, and 4. The accuracy, recall, precision, and F-measure for each classification group obtained are 0.84, 0.85, 0.85, and 0.84. Conclusions: The study showed that aged patients with a higher number of mutations than young patients have a higher risk of short survival. Senior patients with a more significant number of mutations have an increased risk of getting into the last cancer stage.

Implementing electronic health records on a medical service trip improves the patient care process.

Background: The efficiency of the patient care process of short-term medical service trips is often not assessed. The Gregory School of Pharmacy has organized annual medical camps in rural Uganda, however, the paper health records used for documentation and communication between stations have shown several limitations that hinder an optimal patient care process. Therefore, our objective was to implement an electronic health record system in these medical camps to improve the workflow and optimize the patient care process. Methods: An electronic health record system that functioned over a battery-operated local area network was developed and implemented. Patient health information was entered and reviewed at the different stations using mobile devices. The impact of electronic health records (used in 2019) on the patient care process was assessed using the number of patients served per physician per hour and the number of prescriptions filled per hour and comparing these to paper records (used in 2017). Results: Electronic health records were successfully implemented and communication across stations was fluid, thus improving transitions. Importantly, 45% more patients were served per physician per hour and 38% more prescriptions were dispensed per hour when using electronic (2019) compared to paper records (2017), despite having a smaller team in 2019. Conclusion: Implementation of electronic health records in rural Uganda improved the patient care process and the efficiency of the medical camp.