Search

Neighborhood socioeconomic context where Latinx children live may influence body weight status. Los Angeles County and Orange County of Southern California both are on the list of the top ten counties with the largest Latinx population in the USA. This heterogeneity allowed us to estimate differential impacts of neighborhood environment on childrens body mass index z-scores by race/ethnicity using novel methods and a rich data source. We geocoded pediatric electronic medical record data from a predominantly Latinx sample and characterized neighborhoods into unique residential contexts using latent profile modeling techniques. We estimated multilevel linear regression models that adjust for comorbid conditions and found that a childs place of residence independently associates with higher body mass index z-scores. Interactions further reveal that Latinx children living in Middle-Class neighborhoods have higher BMI z-scores than Asian and Other Race children residing in the most disadvantaged communities. Our findings underscore the complex relationship between community racial/ethnic composition and neighborhood socioeconomic context on body weight status during childhood.

Background: The integrity of clinical research and machine learning models in healthcare heavily relies on the quality of underlying clinical laboratory data. However, the preprocessing of this data to ensure its reliability and accuracy remains a significant challenge due to variations in data recording and reporting standards. Methods: We developed lab2clean, a novel algorithm aimed at automating and standardizing the cleaning of retrospective clinical laboratory results data. lab2clean was implemented as two R functions specifically designed to enhance data conformance and plausibility by standardizing result formats and validating result values. The functionality and performance of the algorithm were evaluated using two extensive electronic medical record (EMR) databases, encompassing various clinical settings. Results: lab2clean effectively reduced the variability of laboratory results and identified potentially erroneous records. Upon deployment, it demonstrated effective and fast standardization and validation of substantial laboratory data records. The evaluation highlighted significant improvements in the conformance and plausibility of lab results, confirming the algorithm's efficacy in handling large-scale data sets. Conclusions: lab2clean addresses the challenge of preprocessing and cleaning clinical laboratory data, a critical step in ensuring high-quality data for research outcomes. It offers a straightforward, efficient tool for researchers, improving the quality of clinical laboratory data, a major portion of healthcare data. Thereby, enhancing the reliability and reproducibility of clinical research outcomes and clinical machine learning models. Future developments aim to broaden its functionality and accessibility, solidifying its vital role in healthcare data management. [ABSTRACT FROM AUTHOR]

Introduction Deployment-limiting medical conditions (DLMCs) such as debilitating injuries and conditions may interfere with the ability of military service members (SMs) to deploy. SMs in the United States (U.S.) Department of the Navy (DoN) with DLMCs who are not deployable should be placed in the medically restricted status of limited duty (LIMDU) or referred to the Physical Evaluation Board (PEB) for Service retention determination. It is critical to identify SMs correctly and promptly with DLMCs and predict their return-to-duty (RTD) to ensure the combat readiness of the U.S. Military. In this study, an algorithmic approach was developed to identify DoN SMs with previously unidentified DLMCs and predict whether SMs on LIMDU will be able to RTD. Materials and Methods Five years of historical data (2016–2022) were obtained from inpatient and outpatient datasets across direct and purchased care from the Military Health System (MHS) Data Repository (MDR). Key fields included International Classification of Diseases diagnosis and procedure codes, Current Procedure Terminology codes, prescription medications, and demographics information such as age, rank, gender, and service. The data consisted of 44,580,668 medical encounters across 1,065,224 SMs. To identify SMs with unidentified DLMCs, we developed an ensemble model combining outputs from multiple machine learning (ML) algorithms. When the ML ensemble model predicted a SM to have high risk scores, despite appearing healthy on administrative reports, their case was reviewed by expert clinicians to investigate for previously unidentified DLMCs; and such feedback served to validate the developed algorithms. In addition, leveraging 1,735,422 encounters (60,433 SMs) from LIMDU periods, we developed four separate ML models to estimate RTD probabilities for SMs after each medical encounter and predict the final LIMDU outcome. Results The ensemble model had 0.91 area under the receiver operating characteristic curve (AUROC). Out of 236 (round one) and 314 (round two) SMs reviewed by clinicians, 127 (54%) and 208 (66%) SMs were identified with a previously unidentified or undocumented DLMC, respectively. Regarding predicting RTD for SMs placed on LIMDU, the best performing ML model achieved 0.76 AUROC, 68% sensitivity, and 71% specificity. Conclusion Our research highlighted potential benefits of using predictive analytics in a medical assessment to identify SMs with DLMCs and to predict RTD outcomes once placed on LIMDU. This capability is being deployed for real-time clinical decision support to enhance health care provider's deployability assessment capability, improve accuracy of the DLMC population, and enhance combat readiness of the U.S Military. [ABSTRACT FROM AUTHOR]

Introduction Asthma is the most common diagnosis in military personnel who endorse chronic dyspnea. Service members have unique occupational risk factors, and there is concern that airborne exposures in the deployed environment as well as other occupational exposures may contribute to the development of asthma or exacerbate pre-existing disease. Asthma phenotyping with clinical biomarkers such as serum immunoglobulin E (IgE) levels and eosinophil (EOS) counts is useful in defining treatment strategies for the management of asthma. This study sought to characterize the phenotype of medically separated military personnel with career-limiting asthma to define potential management strategies and guide future research evaluating the unexplained prevalence of asthma in this population. Materials and Methods A retrospective chart review of active duty service members (ADSM) who underwent fitness for duty evaluation via medical evaluation board between 2005 and 2016 and were separated with a minimum 30% conditional disability rating for asthma was performed. Only ADSM who were diagnosed with asthma by a pulmonologist and had spirometry data available were included in the analysis. Demographics, spirometry data, and laboratory data to include IgE levels, radioallergosorbent panels, and EOS counts were analyzed from the DoD electronic medical record. Results A total of 141 service members were evaluated with a mean age of 42 ± 6.8 years, mean serum EOS count of 300 ± 358 cells/μL, and mean IgE level of 305 ± 363 IU/mL. The patients were further categorized into 4 subgroups based on serum EOS count and IgE level: group A with IgE < 100 IU/mL and EOS < 300 cells/μL (n  = 45; 33%), group B with IgE > 100 IU/mL and EOS < 300 cells/μL (n  = 44; 32%), group C with IgE < 100 IU/mL and EOS > 300 cells/μL (n  = 6; 1%), and group D with IgE > 100 IU/mL, EOS > 300 cells/μL (n  = 46; 34%). Among the cohorts, there were no statistically significant differences in demographics, body mass index, spirometry, smoking history, or disability rating. Conclusion The majority of ADSM with a defined asthma history do not have concordant elevations in serum IgE and blood EOS suggestive of a Th2-high phenotype. Asthma in this population is heterogeneous, and phenotyping using clinical biomarkers may be useful to define optimal treatment strategies. [ABSTRACT FROM AUTHOR]

Objectives Iron-deficiency anemia (IDA) is a common health problem worldwide, and up to 10% of adult patients with incidental IDA may have gastrointestinal cancer. A diagnosis of IDA can be established through a combination of laboratory tests, but it is often underrecognized until a patient becomes symptomatic. Based on advances in machine learning, we hypothesized that we could reduce the time to diagnosis by developing an IDA prediction model. Our goal was to develop 3 neural networks by using retrospective longitudinal outpatient laboratory data to predict the risk of IDA 3 to 6 months before traditional diagnosis. Methods We analyzed retrospective outpatient electronic health record data between 2009 and 2020 from an academic medical center in northern Texas. We included laboratory features from 30,603 patients to develop 3 types of neural networks: artificial neural networks, long short-term memory cells, and gated recurrent units. The classifiers were trained using the Adam Optimizer across 200 random training-validation splits. We calculated accuracy, area under the receiving operating characteristic curve, sensitivity, and specificity in the testing split. Results Although all models demonstrated comparable performance, the gated recurrent unit model outperformed the other 2, achieving an accuracy of 0.83, an area under the receiving operating characteristic curve of 0.89, a sensitivity of 0.75, and a specificity of 0.85 across 200 epochs. Conclusions Our results showcase the feasibility of employing deep learning techniques for early prediction of IDA in the outpatient setting based on sequences of laboratory data, offering a substantial lead time for clinical intervention. [ABSTRACT FROM AUTHOR]

Introduction Soldiers on the battlefield are affected by heavy body armor and excessive march load. It is well known, but the long-term effects of this extra weight on the musculoskeletal system of military veterans, specifically the lumbar spine, are unclear. In Iraq and Afghanistan, most body armors weighed over 33 pounds (15 kg). These armors were 3 times heavier than those used in Vietnam. Chiropractors at the Fargo VA Hospital are seeing more young veterans with non-traumatic lower back pain. This article presents a perspective on the impact of body armor weight and excessive carry load on lumbosacral disc herniation with radicular pain in military veterans. Materials and Methods This study is a retrospective case series. We used a convenient sampling method. We selected the first 10 military veterans who came to a Fargo VA chiropractor in late fall 2023. Each veteran filled out a VA Form 10-5345 to give us permission to access their electronic health records. All 10 veterans also completed a survey. The survey asked about their active combat status, the type and weight of their body armor, how long they wore the armor each day, how much weight they carried, and their opinion on the cause of their lower back pain (service related or not). The Fargo VA does not require an institutional review board for a case series. Results This study found that military veterans experience lower back pain at an average age of 35 years. This is at least 5 years earlier than non-service men. Lower back pain with disc herniation typically occurs at the L4-L5 and L5-S1 disc levels. All 10 veterans in the study believe that their lower back pain is related to their service. Sixty percent of the participants in the study have a service-connected disability because of back pain. Conclusions For military veterans, onset of lower back pain from a disc herniation at a young age may be linked to carrying heavy body armor and loads. However, the small sample size of this case series limits causal relationship inferences. [ABSTRACT FROM AUTHOR]

Comprehensive health records (CHRs) that encompass patients' medical and dental information is here and now. CHRs enable health care providers to deliver personalized, precision medicine/dentistry effectively and efficiently. The objective of this report is to provide an overview of strengths, weaknesses, and opportunities associated with a comprehensive health care record system that integrates medical and dentalrecords. Strengths and benefits of CHRs (elevated patient safety, collaborative care, holistic patient care, enhanced research capabilities) are explained, and practical challenges associated with operating multiple record systems (specifically in medical and dental imaging), data migration and integration are explored. [ABSTRACT FROM AUTHOR]

Background/Aim: Osteoarthritis (OA) is a prevalent degenerative joint disease that significantly impacts quality of life, particularly when affecting the hands. However, whether patients with OA are associated with higher risk of developing upper limb disorders, specifically trigger finger (TF) and carpal tunnel syndrome (CTS), remains unclear. This study aimed to evaluate the risk of upper limb disease in OA patients. Patients and Methods: Using the US Collaborative Network, a subset of the TriNetX research network, we identified patients diagnosed with OA and matched them 1:1 with non-OA controls based on propensity scores. Matching covariates included age, sex, race, and comorbidities. The cohort consisted of 1,554,182 patients in each group. The hazard ratio of TF and CTS, as well as related surgical interventions, was assessed over a 5-year follow-up period. Results: Patients with OA had a 1.30-fold increased risk of TF [95% confidence interval (CI)=1.27-1.33] and a 1.50- fold increased risk of CTS (95%CI=1.48-1.53) compared to controls. The hazard ratios for undergoing surgical interventions were 1.61 for TF (95%CI=1.51-1.71) and 1.97 for CTS (95%CI=1.78-2.19). These risks remained significant across various sensitivity analyses and stratifications according to age and sex. Conclusion: OA significantly increases the risk of TF and CTS. These findings highlight the need for vigilant monitoring and management of upper limb disorders in OA patients to improve overall patient care and outcomes. Future research is warranted to focus on pathological mechanisms of OA and their impact on upper limb health to develop targeted interventions. [ABSTRACT FROM AUTHOR]

Background/Aim: Thyroid diseases are prevalent endocrine disorders that significantly affect overall health. Although the impact of pre-existing thyroid dysfunction on total knee replacement (TKR) outcomes has been studied, the potential for TKR to increase the risk of developing thyroid disorders remains unexplored. Patients and Methods: We examined electronic medical records from a large U.S. research network in the TriNetX research network. The study focused on patients with osteoarthritis, comparing those who had total knee replacement surgery (TKR) between 2005 and 2018 to a non-TKR group who did not have the surgery. Propensity score matching was employed to control for critical confounders. The hazard ratios (HRs) for the risk of thyroid diseases in TKR patients versus non-TKR controls were assessed. Results: Postmatching, the TKR cohort demonstrated a significantly higher risk of developing thyroid diseases compared to the non-TKR cohort (unadjusted HR=1.218, 95%CI=1.169-1.269). This elevated risk persisted after adjusting for confounders (adjusted HR=1.126, 95%CI=1.061-1.196). Stratification analysis indicated that female TKR patients and those aged ≥65 years were at higher risk of developing thyroid diseases than their respective control groups. Conclusion: This study suggests a potential link between TKR and an increased risk of thyroid diseases, particularly among older adults and females. Potential mechanisms include inflammatory processes, surgical stress, autoimmune responses, and pharmacological effects. Healthcare providers should be vigilant in monitoring and managing thyroid dysfunction in TKR patients. Further research is necessary to elucidate the underlying mechanisms and develop preventive strategies. [ABSTRACT FROM AUTHOR]

Objective Background Methods Results Conclusions To evaluate the effectiveness, tolerability, and safety of topical amitriptyline as a potential route of administration for the management of burning mouth syndrome.Burning mouth syndrome is a complex, idiopathic, and debilitating orofacial pain disorder that impairs quality of life, with a prevalence of up to 18% in menopausal women. Available drugs to alleviate its burning sensation have inconsistent and limited efficacy. Given its physicochemical properties, excellent tolerability, and ability to target peripheral pathways, topical amitriptyline seems a promising mechanistically specific analgesic drug for burning mouth syndrome.In this retrospective cross‐sectional real‐world evidence study, patients with burning mouth syndrome who were prescribed topical amitriptyline for 8 weeks were identified. Eligibility criteria stemmed from ICHD‐3, ICOP, and consensus definitions. The primary outcome measure was mean daily pain intensity (on a 0–10 scale); secondary outcomes included adverse events and patient global impression of improvement. Data are given as the mean ± SD.A total of 15 patients fulfilling the eligibility criteria were included and analyzed. Mean daily pain was 6.7 ± 2.1 at baseline and 3.7 ± 2.3 after treatment, with a mean reduction of 3.1 ± 2.8 (p = 0.002). Half of the patients experienced a decrease in pain by at least 50% (p = 0.008). Several mild adverse events were reported, such as somnolence or dry mouth.Topical amitriptyline may be a safe and potent route of administration in the treatment of burning mouth syndrome, a hypothesis to be tested in further controlled trials. [ABSTRACT FROM AUTHOR]

Background: The COVID‐19 pandemic transformed healthcare delivery with the rapid adoption of telehealth and digital technologies to access healthcare. Interventions are needed to ensure that older people in underserved communities do not face new technology‐driven healthcare disparities. This article describes pioneering electronic medical record (EMR) embedded tools to assess and support each diverse patient's digital health literacy. Methods: We designed and validated a rapid EMR‐embedded Digital Health Engagement Tool (DHET) to assess each patient's digital literacy in English and Spanish. We built a separate, EMR‐generated auto‐scoring function to assess patient use of telehealth and healthcare navigation as recorded within the EMR. Combined, the tools created a complete digital literacy assessment for each patient. We then deployed the tools to conduct a pilot study to elucidate disparities. Results: A total of 112 ethnic/racial diverse older patients were enrolled (mean age was 78, ranging from 57 to 96) years (SD = 8.04). The female participants were 72.3%. Among the participants, non‐Hispanic Whites were 47.3%; Hispanic 25.0%; non‐Hispanic Asian 19.6%; non‐Hispanic others (including multi‐race and non‐Hispanic Black/African Americans) 8.0%. Digital literacy disparities were revealed for older adults, particularly those over 70 years old, female gender, and those reporting relying on a helper. Conclusion: New EMR‐embedded tools enable healthcare systems to assess the ability of patients to navigate and utilize EMR capabilities, such as video telehealth appointments, messaging providers, reviewing labs/radiology reports, and requesting prescriptions. The study identified significant challenges for older patients in navigating EMRs and calls for healthcare systems to better support patient learning. [ABSTRACT FROM AUTHOR]

Background: Neonatal acute kidney injury (AKI) is a common yet underdiagnosed condition in neonates with significant implications for long-term kidney health. Lack of timely recognition and documentation of AKI contributes to missed opportunities for nephrology consultation and follow-up, potentially leading to adverse outcomes. Methods: We conducted a quality improvement (QI) project to address this by incorporating an automated real-time electronic medical record (EMR)-AKI alert system in the Neonatal Intensive Care Unit (NICU) at Le Bonheur Children's Hospital. Our primary objective was to improve documentation of neonatal AKI (defined as serum creatinine (SCr) > 1.5 mg/dL) by 25% compared to baseline levels. The secondary goal was to increase nephrology consultations and referrals to the neonatal nephrology clinic. We designed an EMR-AKI alert system to trigger for neonates with SCr > 1.5 mg/dL, automatically adding AKI diagnosis to the problem list. This prompted physicians to consult nephrology, refer neonates to the nephrology clinic, and consider medication adjustments. Results: Our results demonstrated a significant improvement in AKI documentation after implementing the EMR-AKI alert, reaching 100% compared with 7% at baseline (p < 0.001) for neonates with SCr > 1.5 mg/dL. Although the increase in nephrology consultations was not statistically significant (p = 0.5), there was a significant increase in referrals to neonatal nephrology clinics (p = 0.005). Conclusions: Integration of an EMR alert system with automated documentation offers an efficient and economical solution for improving neonatal AKI diagnosis and documentation. This approach enhances healthcare provider engagement, streamlines workflows, and supports QI. Widespread adoption of similar approaches can lead to improved patient outcomes and documentation accuracy in neonatal AKI care. [ABSTRACT FROM AUTHOR]

To study the epidemiology and microbiological landscape in patients (≤21 yrs) diagnosed with endophthalmitis across a multi-tier ophthalmology network in India. This cross-sectional hospital-based study included 1,041 patients (≤21 yrs) diagnosed with endophthalmitis, between April 2012 and May 2022. The data were collected using an electronic medical record system. Bacteria (24%) was the most common etiology followed by fungus (2%). The majority of the patients were male (66%) with a mean age of 8.37 ± 5.99 years. The most common age group was middle childhood (6-11 years) with 365 (35.06%) patients. The patients were more commonly from the lower socio-economic status (60.81%) and urban geography (49%). The common cause of endophthalmitis was trauma (59.33%) and amongst the 279 culture positive eyes, the predominant bacteria isolated was Streptococcus pneumoniae followed by Bacillus species and fungus included predominantly Aspergillus and Candida species. The most common surgical intervention performed was intraocular antibiotics (74%) followed by pars plana vitrectomy (52%). The most common etiology of endophthalmitis in children is bacterial and traumatic in nature and presented from the lower socio-economic status. A half of the eyes warranted a vitreo-retinal surgical intervention. A cross-sectional study on the microbiological landscape in pediatric endophthalmitis showed that the most common cause of endophthalmitis was trauma and the predominant bacteria isolated was Streptococcus spp. and Bacillus spp. Additionally, majority of the patients were from the lower socio-economic status and urban geography and the most common surgical intervention performed was injection of intraocular antibiotics. [ABSTRACT FROM AUTHOR]

Background Expanding access to clinical trials in community settings is a potential approach to addressing disparities in accrual of historically underrepresented populations. However, little is known about the characteristics of practices that do not participate in research. We investigated differences in patient and practice characteristics of US community oncology practices with high vs low engagement in clinical research. Methods We included patients from a real-world, nationwide electronic health record–derived, de-identified database who received active treatment for cancer at community oncology practices between November 1, 2017, and October 31, 2022. We assessed patient and practice characteristics and their associations with high vs low research engagement using descriptive analyses and logistic regression models. Results Of the 178 practices, 70 (39.3%) events had high research engagement, treated 57.8% of the overall 568 540 patient cohort, and enrolled 3.25% of their patients on cancer treatment trials during the 5-year observation period (vs 0.27% enrollment among low engagement practices). Practices with low vs high research engagement treated higher proportions of the following patient groups: ages 75 years and older (24.2% vs 21.8%), non-Latinx Black (12.6% vs 10.3%) or Latinx (11.6% vs 6.1%), were within the lowest socioeconomic status quintile (21.9% vs16.5%), and were uninsured or had no documented insurance (22.2% vs 13.6%). Conclusions Patient groups historically underrepresented in oncology clinical trials are more likely to be treated at community practices with limited or no access to trials. These results suggest that investments to expand the clinical research footprint among practices with low research engagement could help address persistent inequities in trial representation. [ABSTRACT FROM AUTHOR]

Background/Aims: Since the onset of the coronavirus disease 2019 (COVID-19) pandemic, 103.4 million cases and 1.1 million deaths have occurred nationally as of November 2023. Despite the benefit of mitigating measures, the pandemic's effect on participant safety is rarely documented. Methods: This study assessed noncompliance occurring from July 2019 to August 2021 that were stratified by the date of noncompliance (before or after restrictions). Events were described by size, site, noncompliance type, primary category, subcategory, and cause. In addition, noncompliance associated with COVID-19 was analyzed to determine characteristics. Results: In total, 323 noncompliance events occurred across 21,146 participants at risk in 35 protocols. The overall rate of noncompliance increased from 0.008 events per participant to 0.022 events per participant after the COVID-19 restrictions (p < 0.001). For onsite protocols, the median within protocol change in rates was 0.001 (interquartile range = 0.141) after the onset of COVID-19 restrictions (p = 0.54). For large-sized protocols (n ≥ 100), the median within protocol change in rates was also 0.001 (interquartile range = 0.017) after COVID-19 restrictions (p = 0.15). For events related to COVID-19 restrictions, 160/162 (99%) were minor deviations, 161/162 (99%) were procedural noncompliance, and 124/162 (77%) were an incomplete study visit. Conclusion: These noncompliance events have implications for clinical trial methodology because nonadherence to trial design can lead to participant safety concerns and loss of trial data validity. Protocols should be written to better facilitate the capture of all safety and efficacy data. This recommendation should be considered when changes occur to the protocol environment that are outside of the study team's control. [ABSTRACT FROM AUTHOR]

Aims: This study aimed to examine the diagnostic pathways and outcomes of patients with heart failure (HF), stratified by left ventricular ejection fraction (EF), and to highlight deficiencies in real‐world HF diagnosis and management. Methods and results: We conducted a retrospective cohort study in Salford, United Kingdom, utilizing linked primary and secondary care data for HF patients diagnosed between January 2010 and November 2019. We evaluated characteristics, diagnostic patterns, healthcare resource utilization, and outcomes. Patients were categorized according to baseline (the latest measure prior to or within 90 days post‐diagnosis) as having HF with reduced EF (HFrEF), mildly reduced EF (HFmrEF), or preserved EF (HFpEF). The data encompassed a 2 year period before diagnosis and up to 5 years post‐diagnosis. A total of 3227 patients were diagnosed with HF between January 2010 and November 2019. The mean follow‐up time was 2.6 [±1.9 standard deviation (SD)] years. The mean age at diagnosis was 74.8 (±12.7 SD) years, and 1469 (45.5%) were female. HFpEF was the largest cohort (46.6%, npEF = 1505), HFmrEF constituted 16.1% (nmrEF = 520), and HFrEF 18.5% (nrEF = 596) of the population, while 18.8% (nu = 606) of patients remained unassigned due to insufficient evidence to support categorization. At baseline, measurement of natriuretic peptide (NP; brain NP and N‐terminal pro‐B‐type NP) and echocardiographic report data were available for 592 (18.3%) and 2621 (81.2%) patients, respectively. A total of 2099 (65.0%) of the HF cohort had access to a cardiology‐led outpatient clinic prior to the HF diagnosis, and 602 (18.7%) attended cardiac rehabilitation post‐diagnosis. The 5 year crude survival rate was 37.8% [95% confidence interval (CI) (35.2–40.7%)], 42.3% [95% CI (38.0–47.2%)], and 45.5% [95% CI (41.0–50.4%)] for HFpEF, HFrEF, and HFmrEF, respectively. Conclusions: Low survival rates were observed across all HF groups, along with suboptimal rates of NP testing and specialist assessments. These findings suggest missed opportunities for timely and accurate HF diagnosis, a pivotal first step in improving outcomes for HF patients. Addressing these gaps in diagnosis and management is urgently needed. [ABSTRACT FROM AUTHOR]

Background and Objectives: Patients with type 2 diabetes (T2D) have a high prevalence of non-alcoholic fatty liver disease (NAFLD) (55%) and are at increased risk for developing non-alcoholic steatohepatitis, a severe form of NAFLD. Early detection of advanced fibrosis in patients with T2D and NAFLD is crucial and can prevent progression to chronic liver disease, cirrhosis, and hepatocellular carcinoma. However, screening for liver disease and risk-stratification pathways are not established in patients with T2D. We evaluated the efficacy of using the automated fibrosis-4 (FIB-4) index in routine clinical settings to identify patients requiring further specialist evaluation. Materials and Methods: In this prospective cohort study, individuals diagnosed with T2D were recruited from diabetes clinics at a tertiary university hospital. Demographic, clinical, and laboratory data were comprehensively collected. The FIB-4 index was automatically calculated and integrated into the hospital's electronic medical records (EMRs), which were then stratified by age. Patients with advanced fibrosis (FIB-4 index ≥ 1.3) were referred to a specialist. Student's t-test or the Mann–Whitney U test was used to analyze variables associated with advanced fibrosis. Logistic regression was used to identify predictors of advanced fibrosis. Results: Among the 318 patients with T2D, 9.7% had advanced fibrosis. The majority were females (54.7%) and Saudi nationals (89.6%). Several factors, including age, platelet count, total bilirubin, serum albumin, total cholesterol, low-density lipoprotein, transaminases, and gamma-glutamyl transferase (GGT), showed significant associations with advanced fibrosis (all p < 0.05). Older age, elevated total bilirubin and GGT levels, and prolonged international normalized ratio emerged as independent predictors of advanced fibrosis. Conclusions: Integrating the FIB-4 index into the EMR during the routine care of patients with T2D proved to be a valuable tool in effectively identifying individuals at risk of advanced fibrosis. Our findings emphasize the need for further research to refine screening strategies in this high-risk population. [ABSTRACT FROM AUTHOR]

Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients. [ABSTRACT FROM AUTHOR]

Background: Diagnoses entered by general practitioners into electronic medical records have great potential for research and practice, but unfortunately, diagnoses are often in uncoded format, making them of little use. Natural language processing (NLP) could assist in coding free-text diagnoses, but NLP models require local training data to unlock their potential. The aim of this study was to develop a framework of research-relevant diagnostic codes, to test the framework using free-text diagnoses from a Swiss primary care database and to generate training data for NLP modelling. Methods: The framework of diagnostic codes was developed based on input from local stakeholders and consideration of epidemiological data. After pre-testing, the framework contained 105 diagnostic codes, which were then applied by two raters who independently coded randomly drawn lines of free text (LoFT) from diagnosis lists extracted from the electronic medical records of 3000 patients of 27 general practitioners. Coding frequency and mean occurrence rates (n and %) and inter-rater reliability (IRR) of coding were calculated using Cohen's kappa (Κ). Results: The sample consisted of 26,980 LoFT and in 56.3% no code could be assigned because it was not a specific diagnosis. The most common diagnostic codes were, 'dorsopathies' (3.9%, a code covering all types of back problems, including non-specific lower back pain, scoliosis, and others) and 'other diseases of the circulatory system' (3.1%). Raters were in almost perfect agreement (Κ ≥ 0.81) for 69 of the 105 diagnostic codes, and 28 codes showed a substantial agreement (K between 0.61 and 0.80). Both high coding frequency and almost perfect agreement were found in 37 codes, including codes that are particularly difficult to identify from components of the electronic medical record, such as musculoskeletal conditions, cancer or tobacco use. Conclusion: The coding framework was characterised by a subset of very frequent and highly reliable diagnostic codes, which will be the most valuable targets for training NLP models for automated disease classification based on free-text diagnoses from Swiss general practice. [ABSTRACT FROM AUTHOR]

Background: As global aging intensifies, the prevalence of ocular fundus diseases continues to rise. In China, the tense doctor-patient ratio poses numerous challenges for the early diagnosis and treatment of ocular fundus diseases. To reduce the high risk of missed or misdiagnosed cases, avoid irreversible visual impairment for patients, and ensure good visual prognosis for patients with ocular fundus diseases, it is particularly important to enhance the growth and diagnostic capabilities of junior doctors. This study aims to leverage the value of electronic medical record data to developing a diagnostic intelligent decision support platform. This platform aims to assist junior doctors in diagnosing ocular fundus diseases quickly and accurately, expedite their professional growth, and prevent delays in patient treatment. An empirical evaluation will assess the platform's effectiveness in enhancing doctors' diagnostic efficiency and accuracy. Methods: In this study, eight Chinese Named Entity Recognition (NER) models were compared, and the SoftLexicon-Glove-Word2vec model, achieving a high F1 score of 93.02%, was selected as the optimal recognition tool. This model was then used to extract key information from electronic medical records (EMRs) and generate feature variables based on diagnostic rule templates. Subsequently, an XGBoost algorithm was employed to construct an intelligent decision support platform for diagnosing ocular fundus diseases. The effectiveness of the platform in improving diagnostic efficiency and accuracy was evaluated through a controlled experiment comparing experienced and junior doctors. Results: The use of the diagnostic intelligent decision support platform resulted in significant improvements in both diagnostic efficiency and accuracy for both experienced and junior doctors (P < 0.05). Notably, the gap in diagnostic speed and precision between junior doctors and experienced doctors narrowed considerably when the platform was used. Although the platform also provided some benefits to experienced doctors, the improvement was less pronounced compared to junior doctors. Conclusion: The diagnostic intelligent decision support platform established in this study, based on the XGBoost algorithm and NER, effectively enhances the diagnostic efficiency and accuracy of junior doctors in ocular fundus diseases. This has significant implications for optimizing clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Background: The Tanzania healthcare system is beset by prolonged waiting time in its hospitals particularly in the outpatient departments (OPD). Previous studies conducted at Kilimanjaro Christian Medical Centre (KCMC) revealed that patients typically waited an average of six hours before receiving the services at the OPD making KCMC have the longest waiting time of all the Zonal and National Referral Hospitals. KCMC implemented various interventions from 2016 to 2021 to reduce the waiting time. This study evaluates the outcome of the interventions on waiting time at the OPD. Methods: This is an analytical cross-sectional mixed method using an explanatory sequential design. The study enrolled 412 patients who completed a structured questionnaire and in-depth interviews (IDI) were conducted among 24 participants (i.e., 12 healthcare providers and 12 patients) from 3rd to 14th July, 2023. Also, a documentary review was conducted to review benchmarks with regards to waiting time. Quantitative data analysis included descriptive statistics, bivariable and multivariable. All statistical tests were conducted at 5% significance level. Thematic analysis was used to analyse qualitative data. Results: The findings suggest that post-intervention of technical strategies, the overall median OPD waiting time significantly decreased to 3 h 30 min IQR (2.51–4.08), marking a 45% reduction from the previous six-hour wait. Substantial improvements were observed in the waiting time for registration (9 min), payment (10 min), triage (14 min for insured patients), and pharmacy (4 min). Among the implemented strategies, electronic medical records emerged as a significant predictor to reduced waiting time (AOR = 2.08, 95% CI, 1.10–3.94, p-value = 0.025). IDI findings suggested a positive shift in patients' perceptions of OPD waiting time. Problems identified that still need addressing include, ineffective implementation of block appointment and extension of clinic days was linked to issues of ownership, organizational culture, insufficient training, and ineffective follow-up. The shared use of central modern diagnostic equipment between inpatient and outpatient services at the radiology department resulted in delays. Conclusion: The established technical strategies have been effective in reducing waiting time, although further action is needed to attain the global standard of 30 min to 2 h OPD waiting time. [ABSTRACT FROM AUTHOR]

Background: Hypersensitivity to beta-lactam (BL) antibiotics is one of the most frequent reported drug allergies. In our population, it is common to find labels of BL allergy in electronic medical records (EMRs) that have not been assessed. The objective of our study was to detect patients with beta-lactam allergy labels in their EMRs and to assess how many of them are false after a correct diagnostic evaluation. Methods: A multicentre prospective study was performed with patients labelled as allergic to BLs in their EMRs in the previous 5 years. Demographical and clinical data, as well as variables regarding the BL allergy label and the characteristics of the index reaction from clinical history and EMRs, were recorded. Then, diagnostic assessments including clinical history, skin tests (STs), and drug provocation tests (DPTs) were conducted in order to confirm or exclude the diagnosis of BL allergy. Results: A total of 249 patients completed the study, of which 160 (64.3%) were women with a median age of 57 years (interquartile range [IQR], 45-68). The most frequent BL allergy labels detected were for penicillin (124), amoxicillin/clavulanic acid (61), and amoxicillin (54). Of the 204 patients who underwent STs, 20.1% were positive. DPTs were performed in 224 patients, showing good tolerance in 87.1% of cases. After the allergy diagnosis work-up, 186 patients (74.7%) were diagnosed as non-allergic to BL antibiotics. Conclusion: In our study population, the number of patients labelled as allergic to BLs in their EMRs was similar to that in previously published studies, with proportions near to 75%-80% being falsely labelled as allergic to BLs. [ABSTRACT FROM AUTHOR]

Purpose: To describe the clinical and demographic profile of herpes zoster ophthalmicus (HZO) in patients presenting to a multitier ophthalmology hospital network in India. Methods: Cross-sectional hospital-based study included 3,004,470 new patients between August 2010 and October 2021. Patients with a clinical diagnosis of HZO in at least one eye were included. Data were collected using an electronic medical record system. Results: In total, 1,752 (0.058%) patients were diagnosed with HZO. Nearly two-thirds were male (63.76%) in the seventh decade of life (339;19.35% patients) with unilateral (98.34%) affliction. Higher prevalence was seen in patients from higher socioeconomic status (0.059%) and metropolitan geography (0.062%). Most common ocular signs included eyelid edema (44.19%), conjunctival congestion (65.69%), punctate keratopathy (23.36%), and anterior uveitis (21.22%). Of the 1,781 eyes, mild/ no visual impairment was seen in 952 (53.45%) eyes, moderate in 258 (14.49%) eyes, and severe to blindness in 363 (20.39%) eyes. Oral antivirals were started within 72 h (Group A) in 361 (20.61%) patients and after 72 h in 1391 (79.39%) patients (Group B). Significantly lesser severity of ocular involvement was noted in Group A (P < 0.00001). Surgical intervention was required in 211 (11.85%) eyes. Conclusion: HZO more commonly affects males in the seventh decade of life and is predominantly unilateral. It more commonly affects those from higher socioeconomic strata and metropolitan regions. Half of the eyes have mild or no visual impairment, while others have moderate to severe impairment. Institution of antivirals within 72 h is associated with less severe involvement. Surgical intervention is warranted in a tenth of the eyes. [ABSTRACT FROM AUTHOR]

To describe the clinical profile of patients presented with Acanthamoeba keratitis (AK) to a multi-tier ophthalmology hospital network in India. This cross-sectional hospital-based study included 1945339 new patients registering between September 2016 and May 2022. Patients with clinically confirmed diagnosis of AK in one or both eyes were included in the study. All the relevant data were documented using an electronic medical record (EMR) system. A total of 245 (0.013%) patients were diagnosed with AK and majority were male (62.86%) with unilateral (99.59%) affliction. The most common age group was during the fourth decade of life, 65 (26.53%) patients and predominantly were adults (95.51%). The prevalence of the infection was higher in patients from a lower socioeconomic status (43.27%) from rural geography (52.24%) and in agriculture-related work (28.16%). The most common inciting factor was injury with vegetative matter (8.98%), dust (7.76%) and contact lens wear (4.49%). The majority of the eyes had blindness (20/400 to 20/1200) in 116 (47.15%) eyes with a presenting visual acuity (logMAR) of 2.14 ± 1.04. Among the surgical interventions, therapeutic keratoplasty was performed in 41 (16.67%) eyes, penetrating keratoplasty in 22 (8.94%) eyes, and evisceration in 2 (0.81%) eyes. AK more commonly affects males presenting during the fourth decade of life from lower socio-economic status and is predominantly unilateral. A fourth of the affected eyes underwent keratoplasty and the majority had significant visual impairment at presentation. [ABSTRACT FROM AUTHOR]

Background/Aim: The risk of new-onset fibromyalgia after total knee replacement (TKR) in osteoarthritis patients is not well-established. This study aimed to assess the risk of developing fibromyalgia post-TKR, considering potential variations across age and sex. Patients and Methods: Utilizing a multicenter retrospective cohort design and data from the TriNetX research network, electronic health records of osteoarthritis patients who underwent TKR and the same number of matched controls were analyzed. Propensity-score matching was performed by matching critical confounders. Hazard ratios were evaluated to assess fibromyalgia risk in the TKR cohort compared to non-TKR controls. Results: The hazard ratio of future fibromyalgia for the TKR cohort was 2.08 (95% confidence interval=1.74-2.49) for 1 year after the index date, 1.81 (95% confidence interval=1.62-2.02) for 3 years, and 1.69 (95% confidence interval=1.54-1.86) for 5 years compared with non-TKR controls. The significant association remained in sensitivity models and stratification analyses in different age and sex subgroups. Conclusion: Clinicians should be vigilant about the potential for fibromyalgia development post-TKR and consider tailored interventions; our findings emphasize the need for further research to elucidate underlying mechanisms and identify modifiable risk factors. [ABSTRACT FROM AUTHOR]

Despite the acknowledged importance of Human Papillomavirus (HPV) vaccination in reducing HPV-related diseases, the influence of electronic medical records (EMR) on HPV vaccination uptake (HVU) remains underexplored. This study aimed to evaluate the efficacy of EMR-based interventions on HVU. A systematic review and meta-analysis of randomized controlled trials were performed, focusing on studies that primarily used EMR-based interventions to measure initiation rates, completion rates, and receipt of the next required vaccine dose. Subgroup analyses were conducted to assess the differential effects of supplementary strategies, provider feedback, and parental education or reminders on these outcomes. The results of the comprehensive analysis provided robust evidence for the significant role of EMR interventions, demonstrating an average increase of 4.7% in vaccine initiation, 6.6% in vaccine completion, and 7.2% in receipt of the next HPV vaccine dose. Additionally, the subgroup analyses indicated that provider feedback and parental education could further enhance the effectiveness of EMR-based interventions. These findings support the broader adoption of digital health technologies in vaccination programs, offering vital insights for healthcare providers, policymakers, and researchers, and emphasizing the need for continued technological innovation to improve public health outcomes. [ABSTRACT FROM AUTHOR]

Abstract Background The integrity of clinical research and machine learning models in healthcare heavily relies on the quality of underlying clinical laboratory data. However, the preprocessing of this data to ensure its reliability and accuracy remains a significant challenge due to variations in data recording and reporting standards. Methods We developed lab2clean, a novel algorithm aimed at automating and standardizing the cleaning of retrospective clinical laboratory results data. lab2clean was implemented as two R functions specifically designed to enhance data conformance and plausibility by standardizing result formats and validating result values. The functionality and performance of the algorithm were evaluated using two extensive electronic medical record (EMR) databases, encompassing various clinical settings. Results lab2clean effectively reduced the variability of laboratory results and identified potentially erroneous records. Upon deployment, it demonstrated effective and fast standardization and validation of substantial laboratory data records. The evaluation highlighted significant improvements in the conformance and plausibility of lab results, confirming the algorithm’s efficacy in handling large-scale data sets. Conclusions lab2clean addresses the challenge of preprocessing and cleaning clinical laboratory data, a critical step in ensuring high-quality data for research outcomes. It offers a straightforward, efficient tool for researchers, improving the quality of clinical laboratory data, a major portion of healthcare data. Thereby, enhancing the reliability and reproducibility of clinical research outcomes and clinical machine learning models. Future developments aim to broaden its functionality and accessibility, solidifying its vital role in healthcare data management. Graphical Abstract

Abstract Aims This study aimed to examine the diagnostic pathways and outcomes of patients with heart failure (HF), stratified by left ventricular ejection fraction (EF), and to highlight deficiencies in real‐world HF diagnosis and management. Methods and results We conducted a retrospective cohort study in Salford, United Kingdom, utilizing linked primary and secondary care data for HF patients diagnosed between January 2010 and November 2019. We evaluated characteristics, diagnostic patterns, healthcare resource utilization, and outcomes. Patients were categorized according to baseline (the latest measure prior to or within 90 days post‐diagnosis) as having HF with reduced EF (HFrEF), mildly reduced EF (HFmrEF), or preserved EF (HFpEF). The data encompassed a 2 year period before diagnosis and up to 5 years post‐diagnosis. A total of 3227 patients were diagnosed with HF between January 2010 and November 2019. The mean follow‐up time was 2.6 [±1.9 standard deviation (SD)] years. The mean age at diagnosis was 74.8 (±12.7 SD) years, and 1469 (45.5%) were female. HFpEF was the largest cohort (46.6%, npEF = 1505), HFmrEF constituted 16.1% (nmrEF = 520), and HFrEF 18.5% (nrEF = 596) of the population, while 18.8% (nu = 606) of patients remained unassigned due to insufficient evidence to support categorization. At baseline, measurement of natriuretic peptide (NP; brain NP and N‐terminal pro‐B‐type NP) and echocardiographic report data were available for 592 (18.3%) and 2621 (81.2%) patients, respectively. A total of 2099 (65.0%) of the HF cohort had access to a cardiology‐led outpatient clinic prior to the HF diagnosis, and 602 (18.7%) attended cardiac rehabilitation post‐diagnosis. The 5 year crude survival rate was 37.8% [95% confidence interval (CI) (35.2–40.7%)], 42.3% [95% CI (38.0–47.2%)], and 45.5% [95% CI (41.0–50.4%)] for HFpEF, HFrEF, and HFmrEF, respectively. Conclusions Low survival rates were observed across all HF groups, along with suboptimal rates of NP testing and specialist assessments. These findings suggest missed opportunities for timely and accurate HF diagnosis, a pivotal first step in improving outcomes for HF patients. Addressing these gaps in diagnosis and management is urgently needed.

Abstract Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients.

Abstract Background Diagnoses entered by general practitioners into electronic medical records have great potential for research and practice, but unfortunately, diagnoses are often in uncoded format, making them of little use. Natural language processing (NLP) could assist in coding free-text diagnoses, but NLP models require local training data to unlock their potential. The aim of this study was to develop a framework of research-relevant diagnostic codes, to test the framework using free-text diagnoses from a Swiss primary care database and to generate training data for NLP modelling. Methods The framework of diagnostic codes was developed based on input from local stakeholders and consideration of epidemiological data. After pre-testing, the framework contained 105 diagnostic codes, which were then applied by two raters who independently coded randomly drawn lines of free text (LoFT) from diagnosis lists extracted from the electronic medical records of 3000 patients of 27 general practitioners. Coding frequency and mean occurrence rates (n and %) and inter-rater reliability (IRR) of coding were calculated using Cohen’s kappa (Κ). Results The sample consisted of 26,980 LoFT and in 56.3% no code could be assigned because it was not a specific diagnosis. The most common diagnostic codes were, ‘dorsopathies’ (3.9%, a code covering all types of back problems, including non-specific lower back pain, scoliosis, and others) and ‘other diseases of the circulatory system’ (3.1%). Raters were in almost perfect agreement (Κ ≥ 0.81) for 69 of the 105 diagnostic codes, and 28 codes showed a substantial agreement (K between 0.61 and 0.80). Both high coding frequency and almost perfect agreement were found in 37 codes, including codes that are particularly difficult to identify from components of the electronic medical record, such as musculoskeletal conditions, cancer or tobacco use. Conclusion The coding framework was characterised by a subset of very frequent and highly reliable diagnostic codes, which will be the most valuable targets for training NLP models for automated disease classification based on free-text diagnoses from Swiss general practice.

Abstract Background The Tanzania healthcare system is beset by prolonged waiting time in its hospitals particularly in the outpatient departments (OPD). Previous studies conducted at Kilimanjaro Christian Medical Centre (KCMC) revealed that patients typically waited an average of six hours before receiving the services at the OPD making KCMC have the longest waiting time of all the Zonal and National Referral Hospitals. KCMC implemented various interventions from 2016 to 2021 to reduce the waiting time. This study evaluates the outcome of the interventions on waiting time at the OPD. Methods This is an analytical cross-sectional mixed method using an explanatory sequential design. The study enrolled 412 patients who completed a structured questionnaire and in-depth interviews (IDI) were conducted among 24 participants (i.e., 12 healthcare providers and 12 patients) from 3rd to 14th July, 2023. Also, a documentary review was conducted to review benchmarks with regards to waiting time. Quantitative data analysis included descriptive statistics, bivariable and multivariable. All statistical tests were conducted at 5% significance level. Thematic analysis was used to analyse qualitative data. Results The findings suggest that post-intervention of technical strategies, the overall median OPD waiting time significantly decreased to 3 h 30 min IQR (2.51–4.08), marking a 45% reduction from the previous six-hour wait. Substantial improvements were observed in the waiting time for registration (9 min), payment (10 min), triage (14 min for insured patients), and pharmacy (4 min). Among the implemented strategies, electronic medical records emerged as a significant predictor to reduced waiting time (AOR = 2.08, 95% CI, 1.10–3.94, p-value = 0.025). IDI findings suggested a positive shift in patients' perceptions of OPD waiting time. Problems identified that still need addressing include, ineffective implementation of block appointment and extension of clinic days was linked to issues of ownership, organizational culture, insufficient training, and ineffective follow-up. The shared use of central modern diagnostic equipment between inpatient and outpatient services at the radiology department resulted in delays. Conclusion The established technical strategies have been effective in reducing waiting time, although further action is needed to attain the global standard of 30 min to 2 h OPD waiting time.

Abstract Background As global aging intensifies, the prevalence of ocular fundus diseases continues to rise. In China, the tense doctor-patient ratio poses numerous challenges for the early diagnosis and treatment of ocular fundus diseases. To reduce the high risk of missed or misdiagnosed cases, avoid irreversible visual impairment for patients, and ensure good visual prognosis for patients with ocular fundus diseases, it is particularly important to enhance the growth and diagnostic capabilities of junior doctors. This study aims to leverage the value of electronic medical record data to developing a diagnostic intelligent decision support platform. This platform aims to assist junior doctors in diagnosing ocular fundus diseases quickly and accurately, expedite their professional growth, and prevent delays in patient treatment. An empirical evaluation will assess the platform’s effectiveness in enhancing doctors’ diagnostic efficiency and accuracy. Methods In this study, eight Chinese Named Entity Recognition (NER) models were compared, and the SoftLexicon-Glove-Word2vec model, achieving a high F1 score of 93.02%, was selected as the optimal recognition tool. This model was then used to extract key information from electronic medical records (EMRs) and generate feature variables based on diagnostic rule templates. Subsequently, an XGBoost algorithm was employed to construct an intelligent decision support platform for diagnosing ocular fundus diseases. The effectiveness of the platform in improving diagnostic efficiency and accuracy was evaluated through a controlled experiment comparing experienced and junior doctors. Results The use of the diagnostic intelligent decision support platform resulted in significant improvements in both diagnostic efficiency and accuracy for both experienced and junior doctors (P

Abstract Background Hypertensive disorders of pregnancy (HDP) pose significant risks to both maternal and fetal health, contributing to global morbidity and mortality. Management of HDP is complex, particularly because of concerns regarding potential negative effects on utero-placental circulation and limited therapeutic options due to fetal safety. Our study investigates whether blood pressure monitoring through a mobile health (mHealth) application can aid in addressing the challenges of blood pressure management in pregnant individuals with HDP. Additionally, we aim to assess whether this intervention can improve short-term maternal and fetal outcomes and potentially mitigate long-term cardiovascular consequences. Methods This prospective, randomized, single-center trial will include 580 pregnant participants who meet the HDP criteria or who have a heightened risk of pregnancy-related hypertension due to factors such as multiple pregnancies, obesity, diabetes, or a history of HDP in prior pregnancies leading to preterm birth. Participants will be randomized to either the mHealth intervention group or the standard care group. The primary endpoint is the difference in systolic blood pressure from enrollment to 1 month after childbirth. The secondary endpoints include various blood pressure parameters, obstetric outcomes, body mass index trajectory, step counts, mood assessment, and drug adherence. Conclusions This study emphasizes the potential of mHealth interventions, such as the Heart4U application, to improve blood pressure management in pregnant individuals with HDP. By leveraging technology to enhance engagement, communication, and monitoring, this study aims to positively impact maternal, fetal, and postpartum outcomes associated with HDP. This innovative approach demonstrates the potential of personalized technology-driven solutions for managing complex health conditions. Trial registration ClinicalTrials.gov NCT05995106. Registered on 16 August 2023.

Without proper security mechanisms, medical records stored electronically can be accessed more easily than physical files. Patient health information is scattered throughout the hospital environment, including laboratories, pharmacies, and daily medical status reports. The electronic format of medical reports ensures that all information is available in a single place. However, it is difficult to store and manage large amounts of data. Dedicated servers and a data center are needed to store and manage patient data. However, self-managed data centers are expensive for hospitals. Storing data in a cloud is a cheaper alternative. The advantage of storing data in a cloud is that it can be retrieved anywhere and anytime using any device connected to the Internet. Therefore, doctors can easily access the medical history of a patient and diagnose diseases according to the context. It also helps prescribe the correct medicine to a patient in an appropriate way. The systematic storage of medical records could help reduce medical errors in hospitals. The challenge is to store medical records on a third-party cloud server while addressing privacy and security concerns. These servers are often semi-trusted. Thus, sensitive medical information must be protected. Open access to records and modifications performed on the information in those records may even cause patient fatalities. Patient-centric health-record security is a major concern. End-to-end file encryption before outsourcing data to a third-party cloud server ensures security. This paper presents a method that is a combination of the advanced encryption standard and the elliptical curve Diffie-Hellman method designed to increase the efficiency of medical record security for users. Comparisons of existing and proposed techniques are presented at the end of the article, with a focus on the analyzing the security approaches between the elliptic curve and secret-sharing methods. This study aims to provide a high level of security for patient health records.

Abstract Background For many countries, especially those outside the USA without incentive payments, implementing and maintaining electronic medical records (EMR) is expensive and can be controversial given the large amounts of investment. Evaluating the value of EMR implementation is necessary to understand whether or not, such investment, especially when it comes from the public source, is an efficient allocation of healthcare resources. Nonetheless, most countries have struggled to measure the return on EMR investment due to the lack of appropriate evaluation frameworks. Methods This paper outlines the development of an evidence-based digital health cost-benefit analysis (eHealth-CBA) framework to calculate the total economic value of the EMR implementation over time. A net positive benefit indicates such investment represents improved efficiency, and a net negative is considered a wasteful use of public resources. Results We developed a three-stage process that takes into account the complexity of the healthcare system and its stakeholders, the investment appraisal and evaluation practice, and the existing knowledge of EMR implementation. The three stages include (1) literature review, (2) stakeholder consultation, and (3) CBA framework development. The framework maps the impacts of the EMR to the quadruple aim of healthcare and clearly creates a method for value assessment. Conclusions The proposed framework is the first step toward developing a comprehensive evaluation framework for EMRs to inform health decision-makers about the economic value of digital investments rather than just the financial value.

Abstract Background Medical records are a valuable source for understanding patient health conditions. Doctors often use these records to assess health without solely depending on time-consuming and complex examinations. However, these records may not always be directly relevant to a patient’s current health issue. For instance, information about common colds may not be relevant to a more specific health condition. While experienced doctors can effectively navigate through unnecessary details in medical records, this excess information presents a challenge for machine learning models in predicting diseases electronically. To address this, we have developed ‘al-BERT’, a new disease prediction model that leverages the BERT framework. This model is designed to identify crucial information from medical records and use it to predict diseases. ‘al-BERT’ operates on the principle that the structure of sentences in diagnostic records is similar to regular linguistic patterns. However, just as stuttering in speech can introduce ‘noise’ or irrelevant information, similar issues can arise in written records, complicating model training. To overcome this, ‘al-BERT’ incorporates a semi-supervised layer that filters out irrelevant data from patient visitation records. This process aims to refine the data, resulting in more reliable indicators for disease correlations and enhancing the model’s predictive accuracy and utility in medical diagnostics. Method To discern noise diseases within patient records, especially those resembling influenza-like illnesses, our approach employs a customized semi-supervised learning algorithm equipped with a focused attention mechanism. This mechanism is specifically calibrated to enhance the model’s sensitivity to chronic conditions while concurrently distilling salient features from patient records, thereby augmenting the predictive accuracy and utility of the model in clinical settings. We evaluate the performance of al-BERT using real-world health insurance data provided by Taiwan’s National Health Insurance. Result In our study, we evaluated our model against two others: one based on BERT that uses complete disease records, and another variant that includes extra filtering techniques. Our findings show that models incorporating filtering mechanisms typically perform better than those using the entire, unfiltered dataset. Our approach resulted in improved outcomes across several key measures: AUC-ROC (an indicator of a model’s ability to distinguish between classes), precision (the accuracy of positive predictions), recall (the model’s ability to find all relevant cases), and overall accuracy. Most notably, our model showed a 15% improvement in recall compared to the current best-performing method in the field of disease prediction. Conclusion The conducted ablation study affirms the advantages of our attention mechanism and underscores the crucial role of the selection module within al-BERT.

Objectives This paper aimed to assess the adoption of electronic medical records (EMRs) in healthcare facilities in Dubai, the largest city in the United Arab Emirates (UAE) and a location where extensive healthcare services are provided. It explored the challenges, milestones, and accomplishments associated with this process. Methods A situation analysis was conducted by contacting 2,089 healthcare facilities in Dubai to determine whether they had implemented EMR in their medical practices and to identify the challenges they faced during this process. Additionally, the Electronic Medical Record Adoption Model (EMRAM) was utilized to measure the maturity level of hospitals in terms of EMR adoption. The EMRAM stages were rated on a scale from 0 to 7, with 0 representing the least mature stage and 7 the most mature. Results By September 2023, all hospitals (100%, n = 54) and 75% of private clinics (n = 1,460) in Dubai had implemented EMRs. Several challenges were identified, including the absence of EMRs within the healthcare facility, having an EMR with a low EMRAM score, or the lack of a unified interoperability standard. Additionally, the absence of a clear licensing program for EMR vendors, whether standalone or cloud-based, was among the other challenges noted. Conclusions EMR implementation in healthcare facilities in Dubai is at a mature stage. However, further efforts are required at both the decision-making and technical levels. We believe that our experience can benefit other countries in the region in implementing EMRs and using EMRAM to assess their health information systems.

Background: Chronic cough (CC) affects about 10% of adults, but opioid use in CC is not well understood. Objectives: To determine the use of opioid-containing cough suppressant (OCCS) prescriptions in patients with CC using electronic health records. Design: Retrospective cohort study. Methods: Through retrospective analysis of Midwestern U.S. electronic health records, diagnoses, prescriptions, and natural language processing identified CC – at least three medical encounters with cough, with 56–120 days between first and last encounter – and a 'non-chronic cohort'. Student's t -test, Pearson's chi-square, and zero-inflated Poisson models were used. Results: About 20% of 23,210 patients with CC were prescribed OCCS; odds of an OCCS prescription were twice as great in CC. In CC, OCCS drugs were ordered in 38% with Medicaid insurance and 15% with commercial insurance. Conclusion: Findings identify an important role for opioids in CC, and opportunity to learn more about the drugs' effectiveness. [ABSTRACT FROM AUTHOR]

Methods: Electronic medical records from patients with CKD at a single center from 2015 to 2020 were used to develop machine learning models for the prediction of CVD. Least absolute shrinkage and selection operator (LASSO) regression was used to select important features predicting the risk of developing CVD. Seven machine learning classification algorithms were used to build models, which were evaluated by receiver operating characteristic curves, accuracy, sensitivity, specificity, and F1-score, and Shapley Additive explanations was used to interpret the model results. CVD was defined as composite cardiovascular events including coronary heart disease (coronary artery disease, myocardial infarction, angina pectoris, and coronary artery revascularization), cerebrovascular disease (hemorrhagic stroke and ischemic stroke), deaths from all causes (cardiovascular deaths, non-cardiovascular deaths, unknown cause of death), congestive heart failure, and peripheral artery disease (aortic aneurysm, aortic or other peripheral arterial revascularization). A cardiovascular event was a composite outcome of multiple cardiovascular events, as determined by reviewing medical records. Results: This study included 8,894 patients with CKD, with a composite CVD event incidence of 25.9%; a total of 2,304 patients reached this outcome. LASSO regression identified eight important features for predicting the risk of CKD developing into CVD: age, history of hypertension, sex, antiplatelet drugs, high-density lipoprotein, sodium ions, 24-h urinary protein, and estimated glomerular filtration rate. The model developed using Extreme Gradient Boosting in the test set had an area under the curve of 0.89, outperforming the other models, indicating that it had the best CVD predictive performance. Conclusion: This study established a CVD risk prediction model for patients with CKD, based on routine clinical diagnostic and treatment data, with good predictive accuracy. This model is expected to provide a scientific basis for the management and treatment of patients with CKD. [ABSTRACT FROM AUTHOR]

Background: Previous research has indicated a potential correlation between hidradenitis suppurativa (HS) and psoriasis (PSO), two chronic inflammatory dermatological diseases. However, there is a lack of comprehensive evaluations that consider a variety of clinical and demographic factors, and the risk of developing HS in PSO patients remains unclear. Our study aims to examine HS risk over time among PSO patients versus matched controls while considering the influence of confounders to provide insights into the potential link between these two diseases. Method: In this multi-institutional cohort study using the TriNetX database, we matched 202,318 patients with PSO with an equivalent number of individuals without PSO, using propensity score matching. The study period extended from 1 January 2005 to 31 December 2018. We computed hazard ratios and their respective 95% confidence intervals (CIs) to evaluate the probability of HS manifestation over a period of 5 years in patients with PSO in comparison to those without PSO. Results: PSO patients demonstrated a consistently higher risk of developing HS than matched controls across all analytic models with the hazard ratios (HR) ranging from 1.43 (95% CI 1.30–1.56) to 5.91 (95% CI 2.49–14.04). Stratified analyses showed the increased HS risk was observed in both genders but only significant in those aged 18–64 years. Kaplan–Meier analysis indicated PSO patients had a higher cumulative probability of developing HS over time (HR 1.77, 95% CI 1.49–1.89). Conclusions: PSO was associated with increased HS risk, highlighting the importance of considering HS as a potential comorbidity in PSO patients and may have implications for early detection, prevention, and management strategies for both conditions. Shared inflammatory pathways, genetic components, and skin dysbiosis may contribute. Further research should elucidate underlying mechanisms. [ABSTRACT FROM AUTHOR]

The development of artificial intelligence in the field of health encourages the use of electronic medical records in all health facilities to record health services provided to patients. For hospitals, extracting information from electronic medical records can make it easier for management to make clinical decisions and for researchers to obtain data for research in the medical and nursing fields. Information extraction is part of natural language processing, which requires a deep learning model in the medical and nursing fields. Information extraction is from electronic medical records. The research builds a model of named entity recognition in electronic medical records based on hybrid neural networks, bidirectional encoder representations from transformers, and setting hyperparameters to get the highest accuracy. The research data set is processed from an initial examination form of an adult patient in a hospital onto an electronic medical record in 2022, and the data is pre-processed. Next, perform the entity-tagging phase on the text and divide 70% of the training datasets by 30% of the testing datasets. Training and evaluation of models built using the confusion matrix method. The results of this study show that the entity identification model called bidirectional encoder representations from transformers consistently outperforms the neural network-based entity recognition model in any evaluation metric. The abbreviation of the bi-directional encoder representation of transformer has very high precision, recall, and f1-score values, demonstrating its ability to recognise entities very well. In this study, although the model named Entity Recognition based on neural networks also has high accuracy, the low precision and recall values indicate that this model may have difficulty recognising entities accurately. [ABSTRACT FROM AUTHOR]

Electronic medical records have the advantages of large storage capacity, convenience, improved efficiency, etc. However, since electronic medical records contain a large amount of patient's private information, if they are stored directly in the cloud server, patients may face the risk of privacy data leakage and electronic medical record data tampering. To solve the above problems, this paper proposes a secure sharing scheme of electronic medical records combining quantum key and blockchain. Based on the true randomness of quantum keys, the multi-user secure forwarding mechanism of quantum keys is designed using proxy re-encryption technology and blockchain. A fine-grained access control scheme for electronic medical records by users with different roles was proposed using data desensitization technology. To facilitate secure retrieval from the cloud server, searchable encryption technology is used. This paper analyzes the comprehensive performance level of the proposed scheme through blockchain performance testing and system efficiency testing. [ABSTRACT FROM AUTHOR]

Aims and Objectives: To investigate whether a low Braden Skin Score (BSS), reflecting an increased risk of pressure injury, could predict the risk of delirium in older patients in the intensive care unit (ICU). Background: Delirium, a common acute encephalopathy syndrome in older ICU patients, is associated with prolonged hospital stay, long‐term cognitive impairment and increased mortality. However, few studies have explored the relationship between BSS and delirium. Design: Multicenter cohort study. Methods: The study included 24,123 older adults from the Medical Information Mart for Intensive Care IV (MIMIC‐IV) database and 1090 older adults from the eICU Collaborative Research Database (eICU‐CRD), all of whom had a record of BSS on admission to the ICU. We used structured query language to extract relevant data from the electronic health records. Delirium, the primary outcome, was primarily diagnosed by the Confusion Assessment Method for the ICU or the Intensive Care Delirium Screening Checklist. Logistic regression models were used to validate the association between BSS and outcome. A STROBE checklist was the reporting guide for this study. Results: The median age within the MIMIC‐IV and eICU‐CRD databases was approximately 77 and 75 years, respectively, with 11,195 (46.4%) and 524 (48.1%) being female. The median BSS at enrollment in both databases was 15 (interquartile range: 13, 17). Multivariate logistic regression showed a negative association between BSS on ICU admission and the prevalence of delirium. Similar patterns were found in the eICU‐CRD database. Conclusions: This study found a significant negative relationship between ICU admission BSS and the prevalence of delirium in older patients. Relevance to Clinical Practice: The BSS, which is simple and accessible, may reflect the health and frailty of older patients. It is recommended that BSS assessment be included as an essential component of delirium management strategies for older patients in the ICU. No Patient or Public Contribution: This is a retrospective cohort study, and no patients or the public were involved in the design and conduct of the study. [ABSTRACT FROM AUTHOR]