Conectar
by Ikgyu Shin, Nilay Bhatt, Alaa Alashi, Keervani Kandala, Karthik Murugiah
ObjectivesTo develop and compare prediction models for 30-day and 1-year mortality in Heart failure with preserved ejection fraction (HFpEF) using EHR data, utilizing both traditional and machine learning (ML) techniques.
BackgroundHFpEF represents 1 in 2 heart failure patients. Predictive models in HFpEF, specifically those derived from electronic health record (EHR) data, are less established.
MethodsUsing MIMIC-IV EHR data from 2008−2019, patients aged ≥ 18 years admitted with a primary diagnosis of HFpEF were identified using ICD-9 and 10 codes. Demographics, vital signs, prior diagnoses, and lab data were extracted. Data was partitioned into 80% training, 20% test sets. Prediction models from seven model classes (Support Vector Classifier (SVC), Logistic Regression, Lasso Regression, Elastic Net, Random Forest, Histogram-based Gradient Boosting Classifier (HGBC), and eXtreme Gradient Boosting (XGBoost)) were developed using various imputation and oversampling techniques with 5-fold cross-validation. Model performance was compared using several metrics, and individual feature importance assessed using SHapley Additive exPlanations (SHAP) analysis.
ResultsAmong 3,235 hospitalizations for HFpEF, 30-day mortality was 6.3%, and 1- year mortality was 29.2%. Logistic regression performed well for 30-day mortality (Area Under the Receiver operating characteristic curve (AUC) 0.83), whereas Random Forest (AUC 0.79) and HGBC (AUC 0.78) for 1-year mortality. Age and NT-proBNP were the strongest predictors in SHAP analyses for both outcomes.
ConclusionModels derived from EHR data can predict mortality after HFpEF hospitalization with comparable performance to models derived from registry or trial data, highlighting the potential for clinical implementation.
To investigate the relationship between a quality of life (QOL) score and clinical parameters in patients with hypertrophic cardiomyopathy (HCM).
A multicentre cross-sectional study.
We analysed data from the Searching for Atrial Fibrillation and Early Recruitment of Heart Failure in HCM registry, collected between 2018 and 2023.
Patients with HCM (n=499) aged ≥18 years from 12 institutions (Shizuoka Prefecture, Japan) were consecutively enrolled.
Clinical parameters, along with data from a short form of the Kansas City Cardiomyopathy Questionnaire (KCCQ-12), were collected. The association between each clinical parameter and the KCCQ-12 score was analysed. Clinical parameters with a significant univariable association (p
In the univariable analysis, KCCQ-12 scores exhibited significant associations with 21 clinical parameters, including sex, left ventricular morphology and the Pittsburgh Sleep Quality Index (PSQI). The multiple regression model with 12 parameters that had a significant univariable association exhibited an adjusted R2 of 0.48. In this model, the PSQI (standardised coefficient –0.39; p
In patients with HCM, we investigated the association between the KCCQ-12 score and various clinical parameters. PSQI, as well as known heart failure-related clinical parameters, was significantly associated with the KCCQ-12 score. Visualising the associations of various clinical parameters with the KCCQ-12 score will help physicians to consider factors linked to the decline in QOL in patients with HCM.
To assess the capability of a convolutional neural network trained by transfer learning on anterior segment optical coherence tomography (AS-OCT) images, Placido-disk corneal topography images and external photographs to predict age and biological sex.
Development of a deep learning model trained on retrospectively collected data using transfer learning.
A multicentre secondary care public health trust based in London.
We included 557,468 scans from 40,592 eyes of 20,542 patients. Data were extracted from all patients who underwent MS-39 imaging within our trust from October 2020 to March 2023.
Primary outcome measures for biological sex classification included accuracy, precision, recall, F1-score and area under the receiver operating curve (ROC-AUC). Primary outcome measures for age prediction were Pearson correlation coefficients (r), coefficients of determination (R²) and the mean absolute error (MAE) to evaluate the predictive performance. The secondary outcome was to visualise and interpret the model’s decision-making process through the construction of saliency maps.
For age prediction, the MAEs for the Placido, AS-OCT and external photograph models were 5.2, 5.1 and 6.2 years, respectively. For gender classification, the same models achieved ROC-AUCs of 0.88, 0.73 and 0.81, respectively. No difference in performance was found in the analysis of corneas with pathological topography. The saliency maps highlighted the peri-limbal cornea for age prediction and the central cornea for gender discrimination.
Our study demonstrates that deep learning models can extract age and gender information from anterior segment images. These findings support the concept that the anterior segment, like the retina, encodes important biological information. Future research should explore whether these models can predict specific systemic conditions.
(1) Explore prelicensure baccalaureate nursing students' perceptions about applying any health equity knowledge gained in school for their future nursing practice. (2) Evaluate whether student perspectives of health equity learning in their programs align with explicit health equity content within curricular documents.
Mixed methods explanatory sequential design.
Curricular documents from nursing programs were analysed for health equity content and quantitised. Nursing students then participated in focus group interviews. Findings were analysed separately then integrated and interpreted.
Three nursing programs participated, including 197 curricular documents from 60 courses. Six students participated in focus group interviews. Most nursing courses contained at least one occurrence of explicit health equity content, but certain topic areas were lacking or absent. Focus group interview themes included the value of experiential learning, the process of learning through the unknown and student conscientisation but not yet fully engaging in praxis. Integration provided contextualisation of results and revealed areas of convergence and divergence.
This mixed method study highlighted areas of alignment and conflict between student perspectives of their learning and explicit content in curricular documents. The study underscored students' perceived value of experiential learning and identified potential content gaps, including historic context and policy, aligning with calls for nurse activism.
To make strides toward health equity in practice, additional focus on health equity-related competencies in nursing education and educational research may be warranted.
Nurses, both globally and in the United States, due to the size of the workforce and their unique role, are positioned to progress communities toward health equity. Nursing education is an important systemic aspect of equipping the nursing workforce to meet complex health and wellness and societal needs.
Journal Article Reporting Standards–Mixed Methods Article Reporting Standards guidelines.
No patient or public involvement.
This study aims to assess how implementing a checklist for managing extremely preterm or extremely low birth weight infants can reduce mortality rates and morbidities.
A quasi-experimental, before-and-after study.
Neonatal intensive care unit at Dr. Cipto Mangunkusumo National General Hospital, a national referral hospital in Indonesia.
86 infants were born at
Implementation of a modified Canberra Health Services extremely preterm-early management checklist during the initial management of extremely preterm or low birth weight infants, including humidified gas resuscitation, thermal management, early surfactant administration and standardised first-hour care protocols.
The primary outcome was the mortality rate. Secondary outcomes included comorbidities such as hypothermia, hypoglycaemia, acidosis, intraventricular haemorrhage (IVH), periventricular leukomalacia (PVL) and retinopathy of prematurity (ROP).
A total of 86 extremely premature and/or extremely low birth weight infants were enrolled, 48 neonates prior to and 38 neonates after the use of the checklist. Baseline characteristics were comparable between groups (median gestational age 27 weeks in both groups, median birth weight 795 g vs 868.5 g, p=0.09). Mortality at discharge showed a non-significant reduction from 52.1% to 47.4% (p=0.664, 0.91, 95% CI 0.64 to 1.30). Significant reductions were observed in IVH (79.2% to 28.9%, p
Implementation of a systematic checklist was associated with significant reductions in IVH and ROP, though mortality reduction was not statistically significant. These findings suggest potential benefits of structured early care protocols, but the observational design limits causal inference.
To increase the sustainability of healthcare, clinical trials must assess the environmental impact of interventions alongside clinical outcomes. This should be guided by Standard Protocol Items: Recommendations for Interventional Trials (SPIRIT) and Consolidated Standards of Reporting Trials (CONSORT) extensions, which will be developed by The Implementing Climate and Environmental Outcomes in Trials Group. The objective of the scoping review is to describe the existing methods for reporting and measuring environmental outcomes in randomised trials. The results will be used to inform the future development of the SPIRIT and CONSORT extensions on environmental outcomes (SPIRIT-ICE and CONSORT-ICE).
This protocol outlines the methodology for a scoping review, which will be conducted in two distinct sections: (1) identifying any existing guidelines, reviews or methodological studies describing environmental impacts of interventions and (2) identifying how environmental outcomes are reported in randomised trial protocols and trial results. A search specialist will search major medical databases, reference lists of trial publications and clinical trial registries to identify relevant publications. Data from the included studies will be extracted independently by two review authors. Based on the results, a preliminary list of items for the SPIRIT and CONSORT extensions will be developed.
This study does not include any human participants, and ethics approval is not required according to the Declaration of Helsinki. The findings from the scoping review will be published in international peer-reviewed journals, and the findings will be used to inform the design of a Delphi survey of relevant stakeholders.
Registered with Open Science 28 of February 2025.
The WHO has declared climate change the defining public health challenge of the 21st century. Incorporating climate and environmental outcomes in randomised trials is essential for enhancing healthcare treatments’ sustainability and safeguarding global health. To implement such outcomes, it is necessary to establish a framework for unbiased and transparent planning and reporting. We aim to develop extensions to the Standard Protocol Items: Recommendations for Interventional Trials (SPIRIT 2025) and Consolidated Standards of Reporting Trials (CONSORT 2025) statements by introducing guidelines for reporting climate and environmental outcomes.
This is a protocol for SPIRIT and CONSORT extensions on reporting climate and environmental outcomes in randomised trials termed SPIRIT-Implementing Climate and Environmental (ICE) and CONSORT-ICE. The development of the extensions will consist of five phases: phase 1—project launch, phase 2—review of the literature, phase 3—Delphi survey, phase 4—consensus meeting and phase 5—dissemination and implementation. The phases are expected to overlap. The SPIRIT-ICE and CONSORT-ICE extensions will be developed in parallel. The extensions will guide researchers on how and what to report when assessing climate and environmental outcomes.
The protocol was submitted to the Danish Research Ethics Committees, Denmark in June 2025. Ethics approval is expected in September 2025. The SPIRIT and CONSORT extensions will be published in international peer-reviewed journals.
As the HIV epidemic stabilises in Sub-Saharan Africa with effective antiretroviral therapy, cardiometabolic disorders (CMDs) remain the next major challenge for people living with HIV. Relationship dynamics and spousal support are important for the medical management of single diseases such as HIV, yet little is known about how couples manage the complexity of multiple competing health conditions and their synergistic effects on health. The Healthy Hearts study aimed to develop a conceptual model of dyadic management of HIV and CMDs, inform interventions for couples in Sub-Saharan Africa, and ultimately improve clinical practice and disease management for HIV and CMD comorbidities.
This study will enrol 250 couples who have at least one partner living with HIV and CMD (either hypertension or diabetes) for a prospective observational cohort study. Patients will be recruited from HIV and CMD clinics in Zomba and Blantyre, Malawi. Couples will attend four study visits at quarterly intervals over 12 months. Both partners are given interviewer-administered surveys and complete a clinical assessment. Regression techniques will be used to test associations between key constructs in our conceptual model, including communal coping, multimorbidity illness perceptions, relationship quality, psychosocial health, disease management (eg, adherence to lifestyle advice and medications) and disease outcomes (eg, viral suppression and CMD control). Findings will be used to identify elements to target in a couple-based intervention for CMD and HIV.
This study was approved by the University of California, San Francisco (HRPP (Human Research Protection Program); Protocol number 20–32126), and the National Health Sciences Research Committee of Malawi (Protocol number 21/04/2677). The results will be disseminated at local community meetings and conferences focused on relationships, CMDs and HIV and published in scientific journals.
Single studies support the presence of several post-COVID-19 symptoms; however, there is no evidence for the synthesis of symptoms.
We attempt to provide an overview of the persistent symptoms that post-COVID-19 patients encounter, as well as the duration of these symptoms to help them plan their rehabilitation.
Systematic review and meta-analysis.
A total of 16 studies involving 8756 patients post-COVID-19 were included.
The CINAHL, PubMed, EMBASE, Scopus, and Web of Science databases were searched from 2019 to August 2021. Observational studies that reported data on post-COVID-19 symptoms were included. The methodological quality of the studies was assessed using the Joanna Briggs Institute Critical Appraisal for Observational Studies. We included medium- to high-quality studies. We used a random-effects model for the meta-analytical pooled prevalence of each post-COVID-19 symptom, and I 2 statistics for heterogeneity.
From the 2481 studies identified, 16 met the inclusion criteria. The sample included 7623 hospitalised and 1133 non-hospitalised patients. We found the most prevalent symptoms were fatigue and dyspnea with a pooled prevalence ranging from 42% (27%–58%). Other post-COVID-19 symptoms included sleep disturbance 28% (14%–45%), cough 25% (10%–44%), anosmia/ageusia 24% (7%–47%), fever 21% (4%–47%), myalgia 17% (2%–41%), chest pain 11% (5%–20%), and headache 9% (2%–20%). In addition to physical symptoms, anxiety/depression was also prevalent 27% (8%–53%).
Fatigue and dyspnea were the most prevalent post-COVID-19 symptoms and experienced up to 12 months.
Multiple persistent symptoms are still experienced until 12 months of post-Covid 19. This meta-analysis should provide some awareness to nurses to highlights the unmet healthcare needs of post-COVID-19 patients. Long-term monitoring for the evaluation and treatment of symptoms and conditions and rehabilitation programs should be conducted.
FreshRSS 