Patient Data Research Articles

Breast cancer prognosis in young BRCA1/BRCA2 mutation carriers: a retrospective hospital-based cohort study

Studies evaluating the prognostic impact of germline BRCA1/2 mutations (gBRCAm) in patients with breast cancer report conflicting results. Therefore, we aimed to investigate outcomes of patients with gBRCA mutations and early onset of breast cancer (< 30 years) compared with those of non-carriers. This retrospective study included 149 patients recruited between 2005 and 2019. The outcomes were overall survival (OS) and disease-free survival (DFS), which were defined as the time from the first diagnosis to death from any cause and the first recurrence, second cancer, or death from any cause, respectively. Key patient data, Kaplan–Meier plots, and outcomes were described according to the BRCA mutation status. Hazard ratios (HR) were calculated using the Cox proportional hazards model. Twenty-eight patients (28/149; 18.8 %) were gBRCAm carriers. The OS median follow-up was 8.2 years. OS was 89.3% [70.4-96.4] in carriers vs 99.2% [95% CI 94.3–99.9] in non-carrier patients at 2 years; 85.2% [65.2-94.2] vs 93.0% [86.5–96.5] at 5 years, and 76.5% [54.7-88.8] vs 85.2% [75.7-91.2] at 10 years. There was no difference in OS between groups in multivariable analysis (HR=1.90 [0.69-5.23], p=0.22). The DFS median follow-up was 6.6 years. Similar results were observed for DFS (HR=1.39 [0.63-3.08], p=0.42). In this large hospital-based cohort of patients with very early onset breast cancer, we found no clear evidence that gBRCA1/2m significantly affects OS after adjusting for known prognostic factors.

Haemodiafiltration or Haemodialysis for Kidney Failure: Totality of Evidence Based on Individual Patient Data Meta-Analysis from Randomised Controlled Trials

Haemodiafiltration or Haemodialysis for Kidney Failure: Totality of Evidence Based on Individual Patient Data Meta-Analysis from Randomised Controlled Trials

APPLICATIONS OF MULTIMODAL GENERATIVE ARTIFICIAL INTELLIGENCE IN A REAL-WORLD RETINA CLINIC SETTING.

This study evaluates a large language model, Generative Pre-trained Transformer 4 with vision, for diagnosing vitreoretinal diseases in real-world ophthalmology settings. A retrospective cross-sectional study at Bascom Palmer Eye Clinic, analyzing patient data from January 2010 to March 2023, assesses Generative Pre-trained Transformer 4 with vision's performance on retinal image analysis and International Classification of Diseases 10th revision coding across 2 patient groups: simpler cases (Group A) and complex cases (Group B) requiring more in-depth analysis. Diagnostic accuracy was assessed through open-ended questions and multiple-choice questions independently verified by three retina specialists. In 256 eyes from 143 patients, Generative Pre-trained Transformer 4-V demonstrated a 13.7% accuracy for open-ended questions and 31.3% for multiple-choice questions, with International Classification of Diseases 10th revision code accuracies at 5.5% and 31.3%, respectively. Accurately diagnosed posterior vitreous detachment, nonexudative age-related macular degeneration, and retinal detachment. International Classification of Diseases 10th revision coding was most accurate for nonexudative age-related macular degeneration, central retinal vein occlusion, and macular hole in OEQs, and for posterior vitreous detachment, nonexudative age-related macular degeneration, and retinal detachment in multiple-choice questions. No significant difference in diagnostic or coding accuracy was found in Groups A and B. Generative Pre-trained Transformer 4 with vision has potential in clinical care and record keeping, particularly with standardized questions. Its effectiveness in open-ended scenarios is limited, indicating a significant limitation in providing complex medical advice.

Assessment of clinician agreement with and knowledge of evidence-based obesity treatment in the primary care setting.

Effective, evidence-based obesity treatment is needed, which often involves use of anti-obesity medications (AOMs). Data on the breadth and quality of guideline-directed obesity treatment implementation in primary care remain limited. This study aimed to assess primary care clinicians' agreement with and knowledge of guideline-directed obesity treatment, as well as to assess the health status of persons with obesity and their use of AOMs. This multimethod study included a prospective survey of primary care clinicians, utilizing a questionnaire that measured agreement on a 5-point Likert scale and knowledge via multiple choice questions. A retrospective analysis was also performed of patient data collected between 30 June 2016 and 30 June 2020 from primary care clinics in the Midwest. Data were analyzed from 27 clinician survey responders, finding agreement toward all measured areas, however less strong for chronic AOM use and resource allocation. The survey identified multiple gaps in knowledge. Researchers assessed 5656 baseline encounters and 2941 corresponding follow-up encounters. Analysis revealed ≥50% of the total patients experienced persistently uncontrolled obesity (mean body mass index of ≥40kg/m2) and weight-related complications. Low rates (≤10%) of AOM use in clinically eligible patients were shown, with phentermine monotherapy being the most commonly used. Clinicians agree with guideline-directed obesity treatment. Persons with obesity who are poorly controlled identify an opportunity for patient care improvement.

Role of Surgery in Potentially Resectable Small-Cell Lung Cancer Based on the Eighth Edition of the TNM Classification: A Population Study of the US SEER Database.

This study aimed to identify a specific SCLC population that would benefit from surgery. This study utilized patient data retrieved from the Surveillance, Epidemiology, and End Results (SEER) database spanning 2010 to 2017. To mitigate clinical biases, the propensity score matching (PSM) technique was employed. Separate cohorts were aligned using PSM according to the AJCC 8th edition TNM classification. The Kaplan-Meier method and a competing risk model were applied to evaluate overall survival (OS) and lung cancer-specific survival (LCSS), respectively. Among the 3394 patients with potentially resectable SCLC included in the study, 3062 underwent chemoradiotherapy and 332 underwent surgical treatment with adjuvant chemotherapy. Surgery was associated with better OS (median OS: 49 months; 95% CI: 35-63 months vs. 27 months; 95% CI: 21-33 months, p < 0.001) and LCSS (SHR, 0.578; 95% CI: 0.411-0.815, p < 0.001) in stage I patients after PSM. However, there was no significant difference in OS and LCSS between the surgery and nonsurgery groups in stage II and III patients after PSM. In the entire cohort, lobectomy was associated with improved OS (median OS: 48.6 vs. 28.7 months, p < 0.0001), but not LCSS (SHR, 0.696; 95% CI: 0.466-1.040, p = 0.078) compared with sublobar resection after PSM. Surgery with adjuvant chemotherapy significantly improved the survival prognosis of patients with early-stage SCLC. However, surgical treatment should be carefully considered in patients with stage II/III disease. Lobectomy is oncologically equal to sublobar resection.

Wartime penetrating traumatic brain injury of the anterior skull base involving the paranasal sinuses: a single-center, first-year experience from Dnipro, Ukraine.

Since February 2022, the number of casualties in the Russian-Ukrainian war have dramatically increased, with a high incidence of penetrating traumatic brain injuries (pTBIs). To date, there has been limited evaluation of pTBI of the anterior skull base involving the paranasal sinuses. The objective of this study was to highlight the authors' experience with this injury pattern and identify specific factors associated with favorable short-term (1-month) outcome and survival. The authors conducted a single-institution retrospective review of patient data collected from the 1st year of the Russian-Ukrainian war at a frontline civilian Ukrainian hospital. To prevent complications from conservative treatment of pTBI with paranasal sinus injury, a protocol of early primary neurosurgical treatment including debridement/hematoma evacuation, repair of dural defects with vascularized pericranial flaps, and titanium plating of external/skull base defects was implemented. Using 1-month postoperative Glasgow Outcome Scale scores, the authors defined a favorable outcome as good recovery/moderate disability and a poor outcome as severe disability/vegetative state/death. Patient demographics, injury characteristics, imaging findings, and postoperative complications were assessed. Logistic regression models were used to estimate the effect of patient characteristics on unfavorable outcome or survival. From February 2022 to February 2023, there were 141 pTBIs (20%) involving the paranasal sinuses, 134 (95%) due to blast fragmentation. One hundred eighteen patients (84%) had a favorable outcome. Most patients with pTBIs (69%) had other nonbrain-related injuries. While 48 patients (34%) presented with preoperative CSF leak, only 1 patient (0.7%) had persistent postoperative CSF leak, which was managed with lumbar drainage. High admission Glasgow Coma Scale (GCS) score, favorable injury lateralization (single hemisphere involved), and low Injury Severity Score (ISS) were associated with significantly increased odds of favorable short-term outcome, whereas high admission GCS scores and no midline shift were associated with significantly increased odds of survival. This was the largest single-year study on neurosurgical treatment of wartime pTBI involving the paranasal sinuses. Implementation of primary neurosurgical intervention at the time of presentation demonstrated promising early results and a shift away from expectant management of this injury pattern. The association of high admission GCS score, low ISS, favorable injury lateralization, and no midline shift on favorable short-term outcomes or survival has not been previously documented with this injury pattern.

TCT-420 Impact of Biolimus-Eluting Stents on Long-Term Outcome in Patients With Acute Coronary Syndromes: An Individual Patient Data Meta-Analysis of the SORT OUT Trials

TCT-420 Impact of Biolimus-Eluting Stents on Long-Term Outcome in Patients With Acute Coronary Syndromes: An Individual Patient Data Meta-Analysis of the SORT OUT Trials

Chain community pharmacists’ requests for patient information during routine care

BackgroundTo optimize service provision, community pharmacists need information (e.g., laboratory values and updated medication lists), which can be difficult to obtain. Contacting prescriber offices is a common approach to obtain information but is often ineffective. Health information exchange (HIE) is one potential solution to this problem, and recent survey research has identified the information needs of independent pharmacists that could be addressed through HIE. However, the information needs of chain community pharmacists are unknown. ObjectivesThe objective of this study was to characterize the patient information requests made by chain community pharmacists during routine practice. MethodsThis electronic card study captured cross-sectional observational data on patient information requests made by chain pharmacists in central Indiana during routine practice. Only one pharmacist meeting eligibility criteria per pharmacy could submit data. Pharmacists were randomized to a two-week data collection period. In real-time, pharmacists recorded the following: type of information requested, reason for request, information source, whether initial or follow up request, modality of communication, and the time required to make the request. Data analysis occurred via descriptive statistics. The Indiana University Institutional Review Board approved all study procedures. ResultsNineteen of the 33 eligible pharmacists (57.6%) consented to the study. Most participants held a PharmD degree (78.9%) and were the pharmacy manager (89.5%) at their location. Updated medication orders/lists (41.3%) and insurance (33.3%) were the most common type of requested information and was primarily used for prescription clarification/filling (93.4%). The prescriber office (53.6%), as well as the patient/caregiver (39.8%), were the most frequent source of this information. Requests were largely completed by telephone (61.2%) and averaged 6.0 minutes (SD: 4.8). ConclusionCommunity pharmacists require key patient data during routine practice. There is a need to develop mechanisms, like HIE, to address gaps in needed information in the community pharmacy setting, regardless of the offered services.

Visual Prognosis in Craniosynostosis Patients: A 20-year Retrospective Cohort Study at a Tertiary Referral Center in Thailand

Objective: This study aims to evaluate the visual prognosis in craniosynostosis patients in order to identify ophthalmologic manifestations in craniosynostosis patients and strabismus surgery outcomes in these patients. Materials and Methods: The medical record charts of craniosynostosis patients were reviewed retrospectively from January 2000 to June 2023. All the relevant patient data, such as age, sex, visual acuity, ophthalmologic examinations, and strabismus surgery outcomes were recorded. Results: In total, 123 patients were included in the study, among whom 65 (52.84%) were male. Overall, there were 70 cases (56.91%) of non-syndromic craniosynostosis, and 53 cases of syndromic craniosynostosis, comprising Crouzon syndrome (15 cases), Apert syndrome (8 cases), Pfeiffer syndrome (2 cases), and other syndromes (28 cases). The mean age at first examination was 3.11 years old. Out of 107 cases with visual impairment at the first visit, 92 (85.98%) showed no visual impairment at the last visit. Among the 87 patients with strabismus, 28 (32.18%) had strabismus at the primary position, with exotropia being the most common type (18 cases). Eight cases underwent strabismus surgery, and 4 cases achieved success (deviation &lt; 10 prism diopters). Other ophthalmologic manifestations were lagophthalmos, exposure keratopathy, ptosis, proptosis, and nasolacrimal duct obstruction. Conclusion: Among the craniosynostosis cases, 85.98% had no visual impairment, with the common ophthalmologic manifestations being refractive errors, strabismus, lagophthalmos, and exposure keratopathy. The syndromic craniosynostosis cases showed worse visual outcomes and a higher incidence of ocular diseases than non-syndromic cases. The success rate for strabismus surgery in craniosynostosis patients was 50%.

A Novel Detection and Classification Framework for Diagnosing of Cerebral Microbleeds Using Transformer and Language.

The detection of Cerebral Microbleeds (CMBs) is crucial for diagnosing cerebral small vessel disease. However, due to the small size and subtle appearance of CMBs in susceptibility-weighted imaging (SWI), manual detection is both time-consuming and labor-intensive. Meanwhile, the presence of similar-looking features in SWI images demands significant expertise from clinicians, further complicating this process. Recently, there has been a significant advancement in automated detection of CMBs using a Convolutional Neural Network (CNN) structure, aiming at enhancing diagnostic efficiency for neurologists. However, existing methods still show discrepancies when compared to the actual clinical diagnostic process. To bridge this gap, we introduce a novel multimodal detection and classification framework for CMBs' diagnosis, termed MM-UniCMBs. This framework includes a light-weight detection model and a multi-modal classification network. Specifically, we proposed a new CMBs detection network, CMBs-YOLO, designed to capture the salient features of CMBs in SWI images. Additionally, we design an innovative language-vision classification network, CMBsFormer (CF), which integrates patient textual descriptions-such as gender, age, and medical history-with image data. The MM-UniCMBs framework is designed to closely align with the diagnostic workflow of clinicians, offering greater interpretability and flexibility compared to existing methods. Extensive experimental results show that MM-UniCMBs achieves a sensitivity of 94% in CMBs' classification and can process a patient's data within 5 s.

Characteristics of oral mucosal pressure injuries in children with orotracheal intubation in intensive care units: An observational study.

Tracheal intubation can be used for ventilation to ensure an unobstructed respiratory tract, and it is the most common respiratory support technique used in paediatric intensive care unit (PICU) patients. Orotracheal intubation is usually the preferred method of tracheal intubation. However, it can cause stress-related damage to the oral mucosa. Identifying the factors that cause oral mucosal pressure injury (OMPI) can prevent its occurrence in children with oral endotracheal intubation. To examine the characteristics of OMPI in children who underwent orotracheal intubation in the PICU and to assess their influencing factors. An observational, prospective study. Data were gathered from the PICU of a tertiary hospital in China between January 2023 and October 2023. The patient data were obtained from the 'General Information Questionnaire', 'Paediatric Critical Illness Score', 'STRONGkids Scale' and 'OMPI Staging and Assessment Tools'. Data analysis was subsequently performed using univariate and logistic regression analyses. A total of 187 children who underwent orotracheal intubation were analysed. During the observation period, 44.92% (n = 84) of the children developed OMPI. It comprised 63.10% (n = 53) of stage I injuries, 33.33% (n = 28) of stage II injuries and 3.57% (n = 3) of stage III injuries. The common injury sites were the lower jaw (48.81%), upper jaw (29.76%), tongue (20.24%) and joints (10.71%). The logistic regression analysis results revealed that high critical illness (OR = 0.835, 95% CI: 0.726-0.961), long intubation time (OR = 1.043, 95% CI: 1.021-1.067), prone ventilation (OR = 6.708, 95% CI: 1.421-31.670), hypothermia (OR = 5.831, 95% CI: 1.208-28.149), use of dental pads (OR = 5.520, 95% CI: 1.150-26.487) and low albumin levels (OR = 6.238, 95% CI: 1.285-30.281) were the main contributing factors for OMPI in children with orotracheal intubation (p < .05). The occurrence of OMPI in children who underwent orotracheal intubation in the PICU was notable and was predominantly observed in stages I and II. Consequently, clinical nursing personnel should proactively recognize risk factors and administer timely interventions to mitigate the occurrence of OMPI in such children. The incidence of OMPI in children who underwent orotracheal intubation was relatively high. Nurses and doctors should closely monitor the risk factors for orotracheal intubation in children to prevent the occurrence of OMPI.

Seroconversion Toxoplasmosis as a predictor for gestational diabetes mellitus among pregnant ladies in Iraq

Background. Toxoplasma gondii (T.g.) can reach many host organs including the pancreas and pancreatic tissue may be directly attacked and compromised by the organisms. Aim. This study aimed to evaluate the risk of toxoplasmosis infestation as a predictor of gestational diabetes mellitus (GDM) among pregnant ladies in Thi-Qar, Southern Iraq. Methodology. A case-control study was conducted on 151 pregnant ladies classified (61) with GDM and (89) healthy pregnant ladies attending a tertiary Endocrine Center. All patient data were gathered from direct interviews and the digital records of the tertiary center, which used an internal network system and Microsoft Access program. Each pregnant woman was diagnosed with new GDM according to the American Diabetes Association (ADA) definition criteria. Results. The mean ages of the whole participants were 28 ±6 years old and more than half of them were in the second decade of life, their mean weight was 75.38±13.29) kg and their body mass index was 29.82 ± 5.23 (Kg/m2). Family history of DM, history of toxoplasmosis infestation, and positive serological test of IgG for toxoplasmosis was significantly predominant among women with GDM rather than those without (p-value= 0.007, 0.002, 0.004 respectively). Conclusions. The second decade of age is the independent risk factor for developing new GDM, while toxoplasmosis infestation and positive IGG were additive-dependent risk factors for developing new GDM in collaboration with other patients' profiles. Pregnant women with GDM were significantly older, heavier in body weight, and obese than those without GDM making them at higher risk factors for getting hyperglycemia.

Pharmacotherapy Effectiveness in Treating Mental Disorders in Kosovo's Specialized Institutions

Abstract: In various global regions, specialized institutions rigorously supervise pharmacological treatments for mental health disorders. In Kosovo, the absence of such dedicated infrastructure highlights the need for continuous evaluations to refine and enhance treatment practices. Objective: This study evaluates the effectiveness of pharmacotherapeutic strategies for mental health disorders at specialized centers in Kosovo. Methodology: The research followed the protocols set by the World Health Organization (WHO). Patient data were collected from medical records. A total of 400 patients were analyzed, selected randomly from different cities with sample sizes ranging from 50 to 90 per city. Results: Medication was administered orally in 106.8% of the cases, with no significant differences in administration methods between centers (Chi-Test = 36, p &gt; 0.22) (Tab. 4). Most prescribed medications were classified as non-essential (85.9%). Of the medications prescribed, 69.2% were antipsychotics, 22.3% were anxiolytics, and 14.8% were antidepressants, making up 100% of all drugs used. Conclusion: In Kosovo's mental health facilities, oral administration is the predominant method (PO), with 22.9% of cases involving parenteral administration. The majority of prescribed medications were non-essential (85.9%). Antipsychotics were the most commonly prescribed (69.2%). Often, second-line medications are used as the initial treatment choice. The use of effective but high-risk medications is common (e.g., Clozapine at 100.0% from the SDA group). Ineffective medications were observed in 2.50% of cases, and a misalignment between treatment and drug indications occurred in 7.50% of cases.

Calibrating Observational Health Record Data Against a Randomized Trial

The conditions required for health record data sources to accurately assess treatment effectiveness remain unclear. Emulation of randomized clinical trials (RCTs) with health record data and subsequent calibration of the results can help elucidate this. To pilot an emulation of the KEYNOTE-189 RCT using a commercially available electronic health record (EHR) data source. This retrospective cohort study used an EHR database spanning from April 2007 to February 2023. Follow-up began on treatment initiation and proceeded until an outcome event, loss to follow-up, end of data, or end of study period (640 days). The population-based cohort was ascertained from EHRs provided by 52 health systems across the US. Eligibility criteria were defined as closely as possible to the benchmark RCT. Patients with non-small cell lung cancer initiating first-line treatment for metastatic disease were included. Patients with evidence of squamous non-small cell lung cancer, primary nonlung malignant neoplasms, or identified EGFR/ALK variations were excluded. Data were analyzed from June to October 2023. Initiation of first-line pembrolizumab and chemotherapy and chemotherapy alone. Chemotherapy in both groups was defined as a combination of pemetrexed and platinum-based (carboplatin or cisplatin) therapy. Outcomes of interest were 12-month survival probability and mortality hazard ratio (HR). A total of 1854 patients (mean [SD] age, 63.7 [9.6] years; 971 [52.4%] men) were eligible, including 589 patients who initiated pembrolizumab and chemotherapy and 1265 patients who initiated chemotherapy only. The cohort included 364 Black patients (19.6%) and 1445 White patients (77.9%). The 12-month survival probabilities were 0.60 (95% CI, 0.54-0.65) in the pembrolizumab group and 0.58 (95% CI, 0.55-0.62) in the chemotherapy-only group, compared with 0.69 (95% CI, 0.64-0.74) in the KEYNOTE-189 pembrolizumab group and 0.49 (95% CI, 0.42-0.56) in the KEYNOTE-189 chemotherapy-only group. The mortality HR was 0.95 (95% CI, 0.78-1.16), compared with 0.49 (95% CI, 0.38-0.64) in the KEYNOTE-189 RCT. In this cohort study piloting an RCT emulation, results were incongruous with the benchmark trial. Differences in patient treatment and data capture between the RCT and EHR populations, confounding by indication, treatment crossover, and accuracy of captured diagnoses may explain these findings. Future feasibility assessments will require data sources to have important oncology-specific measures curated.

PERANCANGAN USER INTERFACE DAN USER EXPERIENCE APLIKASI BERBASIS WEB UNTUK KLINIK TERAPI MENGGUNAKAN METODE USER CENTERED DESIGN (STUDI KASUS: KLINIK RUMAH TERAPI SAHABAT)

Rumah Terapi Sahabat Clinic is located in West Pagesangan, West Nusa Tenggara and has been around for seven years since it was founded in 2015. Based on the results of observations, Focus Group Discussions and interviews, this clinic needs a way to digitize clinical data storage so that it can be accessed easily by clinic staff. In order to meet these needs, a website-based application for clinics is needed with patient and therapist data storage features as well as therapy scheduling. To be able to realize this application, User Interface and User Experience are needed. The method used to do this is User Centered Design. After creating a good User Interface, testing will be carried out using the System Usability Scale and User Experience Questionnaire methods to find out how functional and experienced the clinical staff are while using this Front-end prototype and aspects that can be improved in the future. This research will have results in the form of a front end of a website-based application that suits the needs of clinic staff. While testing using SUS and UEQ, the end result of SUS is 84 or “Acceptable” meanwhile five out of six categories from UEQ are graded “Excellent”

Human-Robot Interaction and Social Robot: The Emerging Field of Healthcare Robotics and Current and Future Perspectives for Spinal Care.

Recent advances in robotics technology and artificial intelligence (AI) have sparked increased interest in humanoid robots that resemble humans and social robots capable of interacting socially. Alongside this trend, a new field of robot research called human-robot interaction (HRI) is gaining prominence. The aim of this review paper is to introduce the fundamental concepts of HRI and social robots, examine their current applications in the medical field, and discuss the current and future prospects of HRI and social robots in spinal care. HRI is an interdisciplinary field where robotics, AI, social sciences, design, and various disciplines collaborate organically to develop robots that successfully interact with humans as the ultimate goal. While social robots are not yet widely deployed in clinical environments, ongoing HRI research encompasses various areas such as nursing and caregiving support, social and emotional assistance, rehabilitation and cognitive enhancement for the elderly, medical information provision and education, as well as patient monitoring and data collection. Although still in its early stages, research related to spinal care includes studies on robotic support for rehabilitation exercises, assistance in gait training, and questionnaire-based assessments for spinal pain. Future applications of social robots in spinal care will require diverse HRI research efforts and active involvement from spinal specialists.

Nurses’ Experiences with the Use of Electronic Nursing Record: A Qualitative Study

Background: The electronic nursing record has contributed to improving nursing practice and ensuring nursing quality, but it is still incomplete in supporting nursing workflow. The purpose of this study is to explore the experience of using the electronic nursing record by nurses working in frontline care for trauma, emergency, and infectious disease-exposed patients.Methods: The study employed a qualitative descriptive design and qualitative content analysis. In-depth interviews were conducted with 10 nurses working in emergency, trauma, and critical care units in the tertiary hospital.Results: The nurses’ experiences with the use of the electronic nursing record emerged into three subjects (improvements to electronic nursing record implementation, benefits of electronic nursing record implementation, electronic nursing record user factors), five categories (information finding and sharing function, information input function, facilitating efficient communication, ensuring record quality, need for education), and eight subcategories.Conclusions: Electronic nursing record supports the visualization of special information such as emergency and infection, and has the advantage of facilitating communication between medical staff. Both support better clinical decision-making. However, system instability and low nursing friendliness delay nursing work in the process of inputting, confirming, and sharing information. Copy-andpaste practices, poor quality of records, and insufficient electronic nursing record education were identified as factors to be changed on the user side. Improvement of nursing-friendly interfaces, optimization of nursing workflows, and participation of nurses in the improvement process are necessary. We should also focus on developing electronic nursing record education programs.

Federated learning for national healthcare systems: Balancing privacy and innovation

Federated Learning provides a revolutionary model for handling the United States' healthcare data while addressing privacy concerns and pushing forward innovations. FL works especially in contrast to other organizational top-down approaches that do not allow for decentralization while training AI over various datasets—patient data, for instance, are considerably sensitive. This shift is important in creating a new generation of AI solutions for healthcare that can be used to prevent deaths, improve care, and cut on expenses. Thus, when applied to healthcare, Federated Learning can help unleash the value of massive and varied datasets while remaining compliant with privacy laws. This paper discusses how FL can be implemented in the healthcare systems of different nations and how this has the potential to greatly enhance medical research, pharmaceuticals, and disease prevention. Most notable, the article describes the concrete obstacles of data heterogeneity, model accuracy, and the ethical implications of FL at scale. The outcomes of this research bring to light FL as a crucial element in how innovation can be effected without infringing the rights of patients by enhancing the capacity for using efficient delivery of healthcare in the country.

Toward a New Era of Smart and Secure Healthcare Information Exchange Systems: Combining Blockchain and Artificial Intelligence

Healthcare Information Exchange (HIE) is becoming a fundamental operation in current healthcare systems. In such systems, electronic health records (EHRs) are digitally stored inside each medical centers and, sometimes, are required to be shared between various healthcare facilities (HCFs). Indeed, sharing patient information is crucial and might be vulnerable to power outages, data misuse, privacy or security violations, and an audit trail. Hence, researchers have focused recently on cutting-edge technologies to develop secure HIE systems and ensure data privacy during transactions. Among such technologies, blockchain and artificial intelligence (AI) occupy a vital role in researchers’ focuses and efforts to detect risky transactions in HIE systems, thus enhancing their security and privacy. While the blockchain allows HCFs to link to each other without requiring a central authority, AI models offer an additional security layer when sharing patient data between HCFs. This paper presents a survey about HIE systems, and the aim is two-fold: we first present the architecture of HIE systems along with their challenges; then, we categorize and classify the current state-the-art-techniques that show the potential of using blockchain and AI technologies in such systems.

A virtual anti-scatter grid for multi-energy photon counting detector systems

Photon-counting (PC) systems are the next technological generation of medical computed tomography (CT) imaging and is being worked on by all major system providers. CT devices that are based on PC detectors enable multi-energy data collection. The information-content of this data can be used to obtain more detailed patient data, which improves the quality of reconstructions, compared to conventional detector systems. However, PC CT systems are subject to radiation scatter as just as any other imaging systems is. Conventionally anti-scatter grids (ASG) are used to reduce the scatter effect. These are however an imperfect solution, especially for PC detectors. In this work, a software-based scatter correction method, thus a virtual ASG is proposed. The method is tailoring a new statistical model in the measurement space and combining it with the statistical inversion method called Markov chain Monte Carlo (MCMC). The method can recover the measurement data from dense projections. We present the method on simulated data of a single photon emission computed tomography (SPECT) problem for which only under-sampled data is available. However, our approach can in principle be generalised to CT, PC-CT, Positron emission tomography (PET), radiotherapy, or even digital radiography problems. The results show that the proposed model performs similarly as physical ASGs and for cases where ASGs are not possible. The model further offers a significant improvement in the quality of the reconstruction image compared to the image reconstruction from original under-sampled data.