Patient Electronic Medical Record Research Articles

Improving Access to Community-Based Services for Sexual Assault Survivors

ABSTRACT Background Emergency department (ED) encounters are often the only healthcare provider encounter for patients seeking care after a reported sexual assault (SA), making the encounter a crucial opportunity to connect patients to support services in the community. An opportunity existed at an urban Level II trauma center to standardize SA discharge planning. Aims This quality improvement project aimed to improve access to SA support services. Methods The Model for Improvement guided two plan–do–study–act (PDSA) cycles. Implementation included (a) creation of a QR-code-accessible SA resource website, (b) ED standardized patient print and electronic medical record after-visit summaries with follow-up guidelines and the QR code, (c) ED staff education, and (d) a community stakeholder survey to assess facilitators and barriers to support services. Results During the first PDSA cycle, 19 reported SA survivors were seen in the ED (18 adult, one pediatric) and 14 SA resource website visits. During the second PDSA cycle, 13 reported SA survivors (10 adult, three pediatric) were seen in the ED and 29 website visits. Stakeholder survey data revealed barriers to support services were transportation, overloaded support services, and survivor knowledge of existing services. Conclusion The QR code intervention model is a discrete method of improving access to resources and is applicable to other vulnerable populations. The multiagency SA response team will utilize partner survey data to improve access to community resources such as housing and transportation.

Differences in Symptom Burden in Primary Brain Tumor Patients Based on Sex, Race, and Ethnicity: a Single-Center Retrospective Study.

Symptom burden affects quality of life and prognosis in primary brain tumor (PBT) patients. Knowing whether symptom burden varies based on sex, race, or ethnicity may affect the interpretation of the relationship between symptoms and survival may reveal issues with applying the tools to measure symptom burden to different groups and may identify inequities in symptom management that need to be addressed at a system level. To determine whether symptoms in PBT patients vary across demographic groups, we conducted a retrospective chart review of symptom burden collected as part of routine care in a diverse population. Patient demographics and scores on the MD Anderson Symptom Inventory-Brain Tumor (MDASI-BT) module were extracted from the electronic medical record for patients seen in the Inova Neuro-oncology Clinic between March 2021 and June 2022. MDASI-BT scores were compared based on side of tumor, sex, race, and ethnicity for the entire population and for the subset with gliomas. We included 125 people, of whom 85 had gliomas. For both the entire group and the subgroup with gliomas, about 40% were female and about 40% were non-White race. No differences in symptom burden were seen between males and females. Pain and numbness/tingling symptom burden were higher in both the entire population and the glioma subgroup for people of Hispanic/Latino/Spanish ethnicity and for people of races other than White or Middle Eastern self-identification. Pain, weakness, and numbness/tingling varied significantly across racial and ethnic groups. Further research is needed to validate this finding in other populations and determine its cause.

Development of a novel multipoint traction device for gastric and colorectal endoscopic submucosal dissection and evaluation of its efficacy and safety.

Proper traction allows safer and easier endoscopic submucosal dissection; however, single-point traction may not be sufficient. In this study we assessed the safety, efficacy, and feasibility of our newly developed multipoint traction device. During an ex vivo study using a Konjac training model, two experts and two trainees resected 80 mock lesions of 20-mm diameter by performing endoscopic submucosal dissection with and without multipoint traction. The primary outcome was the success rate of the procedure involving traction. The secondary outcomes were the submucosal dissection time, dissection speed, and perforation during endoscopic submucosal dissection. During the in vivo study, to clarify the initial clinical outcomes, we used data from the electronic medical record of patients at our institution who underwent gastric and colorectal endoscopic submucosal dissection, which was performed by experts with our newly developed multipoint traction device, from March to December 2022. The ex vivo study indicated that all traction procedures were successful. Higher resection speeds were observed with endoscopic submucosal dissection with traction than without traction (P < 0.001). Perforations were not observed. During the first in vivo clinical study, traction was feasible during 20 gastric and colorectal endoscopic submucosal dissection procedures. No adverse events occurred. Our multitraction device can increase the submucosal dissection speed and simplify endoscopic submucosal dissection techniques, thus safely reducing technical challenges. The application of this device for endoscopic submucosal dissection could lead to safer and more efficient procedures. Clinical registration UMIN Clinical Trials Registry, Japan (registration number UMIN000053384).

Endobiogenic Biology of Function Indices in a Cohort of Kidney Transplant Recipients.

Background and Objectives: Endobiogeny is a global systems approach to human biology based on the concept that the endocrine system manages the metabolism. Biology of function (BoF) indices are diagnostic tools in endobiogenic medicine that reflect the action of the endocrine system on the cells and the metabolic activity of an organism. Kidney transplant recipients are a very specific patient population due to their constant use of immunosuppressive agents such as steroids and anamnesis of chronic kidney disease. The aim of this study was to assess the tendencies of endobiogenic BoF indices in a kidney transplant recipient population and to determine the relationship between BoF index values and histology-proven kidney transplant rejection. Materials and Methods: A total of 117 kidney transplant recipients undergoing surveillance or indication allograft biopsy were included in this study. Endobiogenic BoF indices were calculated from complete blood count tests taken before the kidney biopsy. Histology samples were evaluated by an experienced pathologist according to the Banff classification system. Clinical and follow-up data were collected from an electronic patient medical record system. Results: Overall, <35% of the patients had BoF index values assumed to be normal, according to the general population data. Additionally, >50% of the patients had lower-than-normal adaptation, leucocyte mobilization, genital, and adjusted genital ratio indices, while the Cata-Ana, genito-thyroid ratio, adrenal gland, and cortisol indices were increased in >50% of the transplant recipients. The adaptation index was significantly higher in patients with biopsy-proven transplant rejection and demonstrated an AUC value of 0.649 (95%CI 0.540-0.759) for discriminating rejectors from patients without transplant rejection. Conclusions: Most of the kidney transplant recipients had abnormal BoF index values, reflecting increased corticotropic effects on their cells. The adaptation index distinguished patients with biopsy-proven transplant rejection from those without it.

Impact of a multi-disciplinary team-based care model for patients living with diabetes on health outcomes: a mixed-methods study

BackgroundIndividuals facing socioeconomic hardship experience higher than average rates of chronic disease, such as diabetes, with less access to evidence-based treatment. One solution to address these inequities is a team-based care (TBC) model, defined as one in which at least two providers work collaboratively with a patient and their caregiver(s) to make healthcare decisions. This paper seeks to describe the implementation of a TBC model within a safety-net healthcare setting and determine the extent to which it can be an effective, patient-centered approach to treating individuals with diabetes.MethodsSemi-structured interviews were conducted with staff (n = 15) and patients (n = 18). Clinical data were extracted from the electronic medical record of patients (n = 1,599) seen at a safety-net health system in Chicago, Illinois, United States. The mixed methods study was guided by implementation science and participatory research principles. Staff interviews were 60 min and covered patient care activities, work flow, perceived patient experience, and facilitators/barriers to care coordination. Patient interviews were 60 min and covered satisfaction, attitudes about diabetes management, quality of life, and technology. Patient interviews were co-analyzed by research staff and members of a patient advisory committee. Clinical data were collected at an index visit, two years prior and at one-year follow up (n = 1,599).ResultsFour themes emerged from the interviews: (1) patients perceived the TBC model to be patient centered and of high quality; (2) technology can be an innovative tool, but barriers exist; (3) diabetes management is a complex process; and (4) staff communication enhances care coordination, but misinterpreting roles reduces care coordination. From pre-enrollment to the follow-up period, we found a statistically significant increase in missed visits, decrease in hemoglobin A1c (HbA1c), decrease in body mass index, and decrease in the percent of patients with high blood pressure. We found that each medical visit during the follow-up period was associated with an HbA1c decrease of 0.26 points.ConclusionsA TBC model is a patient-centered approach to providing care to patients with complex health needs, such as diabetes, patients were satisfied with the care they were receiving, and the model was associated with an improvement in clinical outcomes.

Osteoporosis Management in Patients with Hip Fracture post Fall

Introduction: Osteoporosis increases the risk of fragility fracture. Hip fractures are associated with poor outcomes. Men are under-screened and under-treated for osteoporosis, which tends to be secondary, and men have higher mortality and worse outcomes after hip fracture than do women. This study aimed to describe patients admitted with hip fracture following minimal trauma and to explore any gender differences in calcium and vitamin D deficiency and use of osteoporosis medication before admission. Methods: A retrospective cross-sectional study included all patients admitted to Bankstown-Lidcombe Hospital with a fracture of the hip post fall, with or without surgery, from January 1, 2019, to December 31, 2019. Each patient's electronic medical record was reviewed to collect data. The data were extracted and analysed using GraphPad Prism 9.5.1. Unpaired Student's t-tests and Fisher's exact test were used in the analysis. Results: A total of 203 patients were included with a mean age of 83.5 ± 8.8 years and a range of 40 to 103 years, with over half (51.2%) aged 81 to 90 years. Fifty-nine (29.1%) were male. Of 196 patients with vitamin D levels available, 78 (39.8%) had a deficiency, including 30 of 57 (52.6%) males and 48 of 139 (34.5%) females. Males were twice as likely to be vitamin D deficient as were females on admission (OR 2.106; 95% CI 1.143 to 3.939; p = 0.0243). Of 203 patients, 39 (19.2%) were on osteoporosis treatment before admission, including 6 of 59 (10.2%) male and 33 of 144 (22.9%) female patients. Males were 2.6 times more likely to have had no osteoporosis treatment before admission than were females (OR 2.626; 95% CI 1.059 to 6.340; p = 0.0486). Conclusions: Males were more likely to have vitamin D deficiency and not be prescribed osteoporosis medication before admission in a cohort of patients admitted to the hospital with hip fracture post minimal trauma. To prevent hip fracture and resultant hospitalization, increased awareness is needed in diagnosing and managing osteoporosis in men, ideally occurring in the community.

IUD Insertion Under Conscious Sedation: Patient Characteristics with Clinical Decisions

Study ObjectiveUptake of intrauterine devices (IUDs) in the adolescent population may be limited by anxiety and pain anticipated during the insertion procedure. Our institution offers conscious sedation for IUD insertion to mitigate this concern. The objective of this study was to identify characteristics and outcomes of teens choosing between two types of conscious sedation for insertion of a levonorgestrel IUD. MethodsThis was a single-site, retrospective cohort study over a one-year period reviewing the electronic medical record of patients who had an attempted IUD insertion using conscious sedation. Conscious sedation included nitrous gas (termed “light” sedation) or intravenous midazolam and fentanyl (termed “moderate” sedation). Patient demographics, medical and gynecological histories were analyzed. ResultsThere were 69 attempted IUDs insertions during the study period. Most (75.36%) were placed under light sedation, and 92.75% were successfully inserted. The only significant factor associated with choice in type of conscious sedation was prior sexual activity, which increased odds by 10.0 that they would choose light sedation (95% CI 1.23 – 81.34, p=0.031). Differences between other factors (age, history of sexual assault, tampon use, and gender identity) were not statistically significant between successful and failed insertions. ConclusionsIn conclusion, a history of sexual activity significantly differed between patients in our cohort who selected light sedation over moderate sedation. No other factors influenced choice in sedative or success of IUD insertion. Knowing the characteristics of patients who choose nitrous versus IV sedation, and how it relates to successful insertion, may help guide pre-procedural counseling for patients regarding sedation for IUD insertion.

Trauma in the lives of parents experiencing severe perinatal mental illness.

The perinatal period is a time of 'high risk' for new and recurrent episodes of mental illness with 0.1-0.2% of birthing parents requiring admission to specialist mental health units in the months after birth. The prevalence and role of trauma in the lives of birthing parents (most commonly mothers) experiencing severe perinatal mental illness is not well known. In a new perinatal mental health unit in Sydney Australia, a retrospective audit of trauma prevalence was undertaken using patient completed questionnaires and electronic medical record data. Descriptive analysis was undertaken. Prevalence of trauma in the lives of mothers with severe mental illness was found to be higher than that reported in general or community mental health settings, with 76% of mothers reporting lifetime trauma exposure and 24% meeting criteria for complex PTSD. The majority reported trauma experiences likely to impact attachment and also reported difficulties in responding to their infants' cues and needs. The findings suggest a need for more research, awareness, and consideration of the role of trauma in experiences of perinatal mental illness, with implications for developing trauma informed models for responding to parental mental illness.

Redesigning Diabetes Care for Treatment Inertia: A Population Health Model.

In the past 2 decades, health care has witnessed technological and pharmacological advancements leading to innovations in diabetes management. Despite these advances, published guidelines, and treatment algorithms, most people with diabetes remain above glycemic targets. Thus, the authors designed a novel care model aimed at improving several causative factors, including therapeutic inertia, limited access to endocrinology and cardiovascular specialists, time constraints, and complexity in incorporating clinical practice guidelines. The model involves collaboration between the diabetes specialty team and primary care providers (PCPs). The intervention reviewed uncontrolled diabetes data and the patient's electronic medical record (EMR) and sent personalized, evidence-based recommendations to the provider using the task function in the EMR. Other services (eg, diabetes education) were utilized to optimize patient care to achieve optimal glycemic targets and address cardiometabolic risk. The overall mean hemoglobin A1c (HbA1c) decreased pre-post intervention by almost 1%, and 52.1% (347 of 666) of the cohort had ≥-0.5% change in HbA1c post-intervention. All pathways exhibited a decrease in HbA1c. Team-based approaches to managing diabetes patient care were the most effective. The interventions effectively utilized the resources across the health system without placing additional load or burden on primary care or diabetes specialty care teams. In the future, the authors hope to address the limitations of the current gap caused by increasing diabetes numbers, decreasing availability of PCPs and endocrinologists, and fee-for-service models using the innovative specialty consultant-primary care connection and knowledge exchange offered by this novel model, which can only be sustained with payer's support.

Abstract 559: Investigating DDX3X as a target to improve outcomes in Black and Native American endometrial cancer patients

Abstract Introduction: The goal of this project was to identify and test a new molecular target that will help reduce the worse outcomes of endometrial cancer, especially in Black and Native American patients. Endometrial cancer is rapidly on the rise in the developed world. It has overtaken many other types of cancer in both incidence and mortality. Black populations are disproportionately impacted by endometrial cancer, both in Oklahoma and across the United States. In Oklahoma specifically, Native Americans are the most heavily impacted group. Methods: Machine learning techniques were used to analyze comprehensive metabolic panel (CMP) data from electronic medical record of patients in the University of Oklahoma (OU) network of hospitals and clinics. This data was broken down by endometrial cancer status, race, and age. Plasma samples of endometrial cancer patients were collected from the OU Health Sciences Center Biobank. These samples were analyzed by mass spectrometry. Endometrial cancer cell lines Ishikawa (low-grade) and ARK-1 and ARK-4 (high grade) were cultured in EMEM. For treating the cells, we used RK-33, a small molecule inhibitor of DDX3X. MTT assays were performed in 96-well plates at increasing concentrations of RK-33 for 48 hours. Western blots were used to determine effect of the drug on cellular DDX3X and yH2AX protein levels. Results: Machine learning analysis EMR data revealed a difference between races in albumin levels of women with endometrial cancer. Black and Native American patients had lower albumin, which is known to correlate to worse outcomes. IPA analysis of plasma proteomics revealed several proteins that were differentially expressed between races. Among these was DDX3X, the X-linked form of DDX3, a DEAD-box RNA helicase which is involved in DNA damage repair. Patient data indicated that patients with high DDX3X expression tended to have lower survival rates. MTT analysis determined that Ishikawa has a lower IC50 than the high-grade cell lines, but all responded. Western blotting confirmed that treatment with RK-33 reduced the amount of DDX3X in the cells and increased y-H2AX, indicating more DNA damage. Conclusions: This study demonstrates that DDX3X is a valid molecular target in endometrial cancer. The differential expression across race groups indicates that Black and Native Americans may stand to benefit the most from a novel drug targeting this difference. Because DDX3X is involved in DNA damage repair, combining the treatment with a DNA-damaging drug may increase response to the drug as well. Citation Format: James D. Lausen, Doris M. Benbrook. Investigating DDX3X as a target to improve outcomes in Black and Native American endometrial cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 559.

Nurse-Led Cardiac Rehabilitation Care Coordination Program: Improving Functional Outcomes for Patients Through Automatic Referral and Effective Care Coordination.

The aim of this investigation was to evaluate the impact of automated cardiac rehabilitation (CR) referral and nurse care coordination on patient and program outcomes. Specifically, the aim was to identify whether differences exist in physical and psychological function at CR Phase 2 enrollment and completion and CR Phase 2 participation and completion for hospitalized patients who receive in-person CR nurse visits versus phone consultation. Using a retrospective pre-/post-intervention descriptive design, a purposive sampling technique was used to select groups with matching clinical attributes. Dates were selected to mitigate the impact of COVID-19 on CR program enrollment and completion. Data were abstracted from the patient electronic medical record, telemetry documentation, and CR referral tracking tool. Patient descriptors included age, sex, cardiac diagnosis/procedure (post-coronary artery bypass graft surgery, myocardial infarction, percutaneous coronary intervention, heart failure, and aortic valve repair and replacement) and cardiac risk stratification category. Patient functional outcomes included the 6-min walk test and metabolic equivalents of task levels for functional capacity; psychological function was measured by the Patient Health Questionnaire assessment. Program outcomes included discharge to CR Phase 2 enrollment, CR sessions, and completion. Each group had 52 patients. Age was 64 ± 12yr, 68% were male. Perhaps indications for CR included coronary artery bypass graft surgery (44%), myocardial infarction (19%), percutaneous coronary intervention (20%), heart failure (10%), aortic valve repair and replacement (8%). Cardiac risk was low in 30%, intermediate in 65%, and high in 5%. The post-intervention group compared with the pre-intervention group had a shorter discharge to CR Phase 2 enrollment (35 ± 18 d vs 41 ± 28 d, P = .078) and significantly fewer sessions required for CR completion. Automated CR referral and nurse care coordination visits for hospitalized patients decreased the transition period between CR Phase 1 and 2. Patients were physically and psychologically prepared for earlier CR Phase 2 enrollment and successfully completed the program in fewer days than the pre-intervention group.

Lutetium-177 Labelled Anti-PSMA Monoclonal Antibody (Lu-TLX591) Therapy for Metastatic Prostate Cancer: Treatment Toxicity and Outcomes.

Whilst prostate cancer is the fourth most common cancer globally, effective therapies for patients with advanced disease are lacking. In recent years, interest in using theranostic agents to treat castrate-resistant prostate cancer (CRPC) and metastatic prostate cancer has emerged. Lu-TLX591 monoclonal antibody is a potential agent of significance; however, to date, reports on its toxicity and efficacy have been limited to small clinical trials in heavily pretreated patients. This retrospective study describes the real-world toxicity and efficacy profile of Lu-TLX591. Eighteen patients received Lu-TLX591 at two private oncology centres in Australia. Patients were eligible if they had CRPC or metastatic prostate cancer and prostate-specific membrane antigen (PSMA)-avid disease confirmed by PSMA-positron emission tomography (PET). Patients received two cycles of Lu-TLX591 monoclonal antibody (177 Lu-DOTA-rosopatamab) each dosed from 1.01-2.85 GBq, 14 days apart. Patient side effects, blood test results and radiology reports were recorded on the patient's electronic medical record (eMR). Prominent side effects included fatigue (55.6%), anorexia (16.7%), nausea (11.1%), and transfusion reactions (11.1%). All-grade haematological toxicities included lymphopenia (61.1%), anaemia (22.2%), leukopenia (27.8%), neutropenia (27.8%), and thrombocytopenia (27.8%). Grade 4 toxicity included lymphopenia (6.7%) and thrombocytopenia (6.7%). Patients' prostate-specific antigen (PSA) responses were as follows; ≥ 30% PSA decline (27.8%), ≥ 50% PSA decline (11.4%) and any PSA decline (38.9%). Follow-up radiology revealed 54.5% stable disease, 45.4% disease progression and 9.1% disease regression. Lu-TLX591 was safely administered at acceptable toxicity and its efficacy reflects previous clinical trials. Larger studies are required and are underway (NCT04786847; NCT05146973; NCT04876651) to determine Lu-TLX591 effectiveness amongst different prostate cancer populations and compare its efficacy against peptide-based radiopharmaceutical agents.

Rabies post-exposure prophylaxis in the emergency department

Study objectivesRabies is a zoonotic single-stranded RNA lyssavirus that can cause acute infections of the central nervous system (CNS) including encephalomyelitis, encephalitis, and meningoencephalitis that is progressively fatal. Rabies is more common in developing countries, but approximately 23,000 people in the United States (US) are estimated to have been exposed or to have received post exposure prophylaxis (PEP) yearly. Nebraska Medicine follows the Advisory Committee on Immunization Practices (ACIP) guidelines for the vaccination series, as well as the 20 units/kg administration of immunoglobulin (RIG).Nebraska Medicine Medical Center (NMC) and Bellevue Medical Center (BMC) treat the scheduling of the complete rabies vaccine series differently. At both campuses, patients receive their immunoglobulin and first vaccine in the Emergency Department (ED). At NMC, patients are scheduled to receive the remainder of their vaccination series at the outpatient infusion center by the ED pharmacist. At BMC, the subsequent vaccinations are given as “Nurse Only” return visits to the ED. The objective of this study was to compare patient compliance of two different processes for follow-up rabies vaccine series completion. This project's primary aim was to determine the rate of patient compliance for follow up rabies vaccine doses. The secondary aims of this project were to determine if there was a difference in patient follow-up compliance between the two campuses, patient specific factors that impact compliance, and potential cost savings if a dose rounding protocol for RIG was utilized. MethodsThis retrospective chart review was completed as a quality improvement project. Data from patients who had received either rabies immunoglobulin and/or a rabies vaccine, were >18 years of age, and were not admitted were collected for a 3-year period from July 1, 2019, to June 30, 2022. Data were abstracted from the patient's EMR (electronic medical records) using a SQL (Structured query language) query of pre-identified data elements. When unable to abstract with SQL query, data elements were manually abstracted. All data abstracted was collated and descriptive analysis performed. ResultsA total of 723 individual encounters were identified during the study period. After combining rabies series for each individual patient, 173 unique patients remained. After exclusions were applied, 143 patients were included: 104 patients from NMC, and 39 from BMC. For the primary outcome, appropriate completion between the two campuses was 78.3%. When comparing the two campuses, completion rates were higher at NMC (82% vs. 69%), although not statistically significant (p = 0.12). Appropriate completion of vaccine series was statistically significant for both payor and exposure type. Application of a dose rounding policy with those >45 kg, rounding to the nearest vial, as well as rounding down if at the midpoint interval, 56 fewer vials would have been used between the two campuses. This would have resulted in a potential cost savings of $57,928.64 over the study period.

Ethical, legal, and information management aspects in the context of patient safety

Health systems around the world currently generate diverse health data related to their patients; their potential for use in the routine of health professionals is recognized; however, at the same time, patient safety is also widely discussed since, over the years, the patient's electronic medical record absorbs sensitive information, accumulated over time. In this sense, this study aimed to address ethical, legal, and information management aspects in the context of patient safety. This is a scoping review, conducted based on the methodological structure developed by the Joanna Briggs Institute and the checklist Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews, set in five stages: 1) identification of the research question, 2) bibliographic survey to search for relevant studies, 3) selection of studies, according to the criteria defined in this review, 4) data mapping and 5) presentation of results. The results showed that a) the articles, in general, pay much attention to patient safety, both in terms of data and also in terms of health; b) International patient safety goals were created to standardize care in private and public hospitals, c) The articles address patient safety by international patient safety goals and d) information leakage is becoming increasingly common, and actions are needed to minimize these situations. The conclusion shows that there is a lack of objective studies regarding the use of information technology in patient safety and that, due to the importance of these topics, both in public health and economic issues, more studies are necessary for an effective implementation that can generate practical results to patients and the country's healthcare system.

Investigation on Preserving Privacy of Electronic Medical Record using Split Learning

Artificial Intelligence is deployed in multiple areas, including healthcare. Utmost research is done in AI enabled healthcare industry because of the demands like accurate result, data security, exact prediction, huge volume of data, etc. In conventional deep learning models, the training happens with the dataset that are stored in a single device. This requires a huge storage space and highly efficient machines to train the data. Usage of big data, demands for innovative models that can be deployed and used in confined storage. Split learning is one such collaborative distributed deep learning model that allows the data to be stored in a split fashion. Split learning supports desirable features like less storage, more privacy to raw data, ability to work with resource constraints, etc., making it suitable for storing electronic medical record of patients. This paper discusses the advantages of using split learning for healthcare, the possible configurations of split learning that supports data privacy in healthcare and finally discusses the open research challenges in implementing split learning for healthcare.

Nursing workload: use of artificial intelligence to develop a classifier model.

to describe the development of a predictive nursing workload classifier model, using artificial intelligence. retrospective observational study, using secondary sources of electronic patient records, using machine learning. The convenience sample consisted of 43,871 assessments carried out by clinical nurses using the Perroca Patient Classification System, which served as the gold standard, and clinical data from the electronic medical records of 11,774 patients, which constituted the variables. In order to organize the data and carry out the analysis, the Dataiku® data science platform was used. Data analysis occurred in an exploratory, descriptive and predictive manner. The study was approved by the Ethics and Research Committee of the institution where the study was carried out. the use of artificial intelligence enabled the development of the nursing workload assessment classifier model, identifying the variables that most contributed to its prediction. The algorithm correctly classified 72% of the variables and the area under the Receiver Operating Characteristic curve was 82%. a predictive model was developed, demonstrating that it is possible to train algorithms with data from the patient's electronic medical record to predict the nursing workload and that artificial intelligence tools can be effective in automating this activity.

TELEDENTISTRY IN A JURIDICAL PERSPECTIVE: CRIMINAL, CIVIL AND ADMINISTRATIVE ASPECTS

Introduction: To address the limitations resulting from the implementation of health protocols in providing healthcare services to patients, a solution was found in the utilization of information and communication technology to support healthcare services for patients in the form of telehealth, often known as telemedicine. Review: According to Article 1, Paragraph 21 of Law Number 17 of 2023 regarding Health, telemedicine is defined as the provision and facilitation of healthcare services, including public health, health information services, and self-care services, through telecommunications and digital communication technology. One of the aspects of telemedicine in the field of dentistry is teledentistry, which can be a solution for optimizing dental and oral healthcare services for individuals and the community. However, there are various issues in its implementation, especially related to legal issues such as licensing, patient electronic medical record privacy and confidentiality, clinical guidelines, and others that are highly vulnerable to data discrepancies, falsification, or digital patient data leakage. Conclusion: These issues can potentially lead to medical disputes that may enter the legal realm. On the other hand, teledentistry services also play a crucial role in improving public health, especially in dental and oral health in Indonesia, particularly during the COVID-19 pandemic. Therefore, the development of teledentistry services needs to be continuously improved, both in terms of systems and regulations, to provide security and legal certainty for the Indonesian population.

Open injuries and obesity as emerging risk factors for vascular injury in knee dislocations: A retrospective study

PurposeKnee dislocations (KDs) are rare in orthopaedic trauma but can have devastating effects. Failing to diagnose a concomitant vascular injury can lead to amputation. Different methods are used for the diagnosis of a vascular injury and the best approach is under debate.This study aims to examine the risk factor(s) of vascular injury in patients with KDs, examine variables that differ between obese patients and non-obese patients with KDs, and analyse the modalities used to identify vascular injuries in the KD population. MethodsThe electronic patient medical record system at a major trauma centre was retrospectively reviewed to identify knee dislocations from 2015 to 2022. These were stratified based on age, gender, BMI, mechanism of injury, vascular injury, non-vascular complications, and laterality. Co-variates were inputted into a univariable regression analysis, followed by a multivariable regression analysis to identify risk factors of vascular injury in patients with knee dislocations. Co-variates were also compared between obese and non-obese patients using two-tailed t-tests for continuous variables and chi-squared test for categorical variables. ResultsForty patients were identified with a KD, with twenty-eight males and twelve females. The average age was 42.9 years, seventeen patients had a BMI of thirty or over, and eleven patients (27.5%) had a vascular injury. Open injuries (OR: 2.21; 95% CI: 1.19–11.30; p = 0.038) and obesity (OR: 2.66; 95% CI: 1.45–18.69; p = 0.027) are risk factors for vascular injury in patients with knee dislocation. Compared to non-obese patients, obese patients had a higher rate of open injury (p = 0.028), vascular injury (p = 0.017), low-energy injuries (p = 0.014), non-vascular complications (p = 0.017), and amputation (p = 0.036). ConclusionOpen injuries and obesity are risk factors for vascular injury in patients with KD. Compared to non-obese patients, obese patients have low-energy injuries and an increased rate of non-vascular complications, meaning that clinicians could err on the side of caution when investigating vascular injury.Level of evidence: IV.

Legal Protection of Patient's Electronic Medical Record: Indonesian Legal Perspective

Health is the most fundamental factor of every citizen, particularly in Indonesia. Considering that many people need health services, patients’ data are pivotal as they contain patients’ health and medical records, identity, examination, medication, and other services patients receive in health services. Medical record in Indonesia is regulated by the Minister of Health Regulation No. 269 of 2008 on Medical Record and the Minister of Health Regulation No .22 of 2022 on Electronic Medical Record. The transition to electronic medical records is expected to finish on 31 December 2023. Electronic Medical Records (EMRs), which are now being implemented across the healthcare system in Indonesia, have the potential to fulfill the rights of citizens in the healthcare sector. On the other hand, data security for patients requires protection, as electronic systems may be vulnerable to data breaches and misuse by unauthorized individuals. The objective of this research is to examine the legal protection for patients when their electronic medical record data is misused and to elucidate patients' rights in the realm of healthcare, particularly concerning medical records. The research employs a normative juridical approach with a legislative regulation focus. Article 29 of Minister of Health Regulation No. 22 of 2022 already addresses data protection for patients' personal information, although continuous monitoring of the implementation of patient's Electronic Medical Records is still necessary. The findings of this study emphasize the necessity of ensuring data protection guarantees for patients stored within electronic systems.

Patterns of Nonadherence to Hydroxyurea in Pediatric Sickle Cell Disease

Background: Sickle cell disease (SCD) affects an estimated 100,000 American children and adults (CDC, 2017). Hydroxyurea is the first-line disease-modifying treatment for SCD. Daily oral hydroxyurea significantly reduces the frequency of pain and serious medical complications associated with SCD, including dactylitis and acute chest syndrome (Wang et al., 2011). However, adherence to hydroxyurea is less than optimal at 74% among pediatric patients, with 20% of children who are prescribed hydroxyurea taking less than 50% of their prescribed doses (Louiselle et al., 2016). Suboptimal hydroxyurea adherence is associated with increased risk for medical complications, diminished quality of life, and higher health care costs and utilization (e.g., Badawy et al., 2017; Thornburg et al., 2010). Factors associated with hydroxyurea nonadherence in pediatric SCD include female sex, older age, more adherence barriers (e.g., difficulty obtaining refills), lower socioeconomic status, and lower parent treatment knowledge. Purpose: This study aims to characterize trajectories of pediatric hydroxyurea adherence to identify subgroups that may be at highest risk for hydroxyurea nonadherence (e.g., sociodemographic factors), critical time periods for adherence support interventions (e.g., adolescence), and minimal adherence thresholds to optimize hydroxyurea efficacy. Methods: Retrospective chart review across two institutions (i.e., Cincinnati Children's Hospital Medical Center and Nemours Children's Hospital, Delaware) are ongoing. Participants will include patients with SCD ages 2 to 21 years who were prescribed hydroxyurea from March 2007 to February 2017. Researchers are extracting the following data from patient electronic medical records (EMRs) to estimate hydroxyurea adherence: hemoglobin F levels (HbF), mean corpuscular volume (MCV), and absolute neutrophil count (ANC). Additional clinical information will be extracted from patient EMRs including demographic information, SCD genotype, SCD complications, acute care utilization, medical and social complexity, and concomitant medication use. Descriptive statistics will be used to summarize demographic and clinical characteristics of the sample. MCV will be the primary measure of hydroxyurea adherence and Hgb F and ANC will be secondary measures. If the final sample size is sufficiently large, we will conduct group-based trajectory modeling (GBTM) to analyze patterns of hydroxyurea adherence changes over time and identify hydroxyurea adherence trajectory subgroups. Multinomial logistic regression analyses will be used to analyze potential predictors of hydroxyurea adherence trajectory subgroup membership. Results: Preliminary results revealed that as of February 2017, 88% of eligible patients (based on age) were prescribed hydroxyurea.Data from the first 30 completed chart reviews indicates that half of the sample was female (sex assigned at birth), all identified as Black or African American, all but two participants had HbSS, and the mean age 13.0 years ( SD=8.0, range=2.47 to 26.81). Average MCV across an average of 21 time points ( SD=14.2, range=5-74) was 94.3 ( SD=11.2, range=58.4-114.2). As of February 2017, 53% of individuals had MCV values at or above 100. Specifically, 60% of 5-9 year olds, 47% of 10-15 year olds, and 46% of 16+ year olds had MCV values at or above 100. Average Hgb F across an average of 21 time points ( SD=15.3, range=3-81) was 22.9 ( SD=9.3, range=2.6-44.8). As of February 2017, 50% of individuals had HbF values at or above 20.0. Specifically, 55% of 5-9 year olds, 32% of 10-15 year olds, and 55% of 16+ year olds had HbF values at or above 20.0. Average ANC (at non-ill visits) across an average of 20.0 time points ( SD=13.6, range=5-71) was 3,965 ( SD=1,227; range=1,600-6,910). As of February 2017, 31% of individuals had ANC values less than 3,000. Specifically, 20% of 5-9 year olds, 34% of 10-15 year olds, and 30% of 16+ year olds had ANC values less than 3,000. Discussion:Results from this study have the potential to help researchers and clinicians better understand patterns and correlates of hydroxyurea adherence in pediatric SCD patients that can be targeted in future interventions.