Publications by authors named "Arjuna Scagnetto"
Article Synopsis
- LDL cholesterol is a major focus for preventing cardiovascular events, and Proprotein Convertase Subtilisin-Kexin type 9 inhibitors (PCSK9-i) have become an important treatment to lower LDL levels.
- A recent study aimed to understand how many people qualify for PCSK9-i treatment and how effective it is by analyzing electronic health records from 2017 to 2020.
- Results showed that only 8% of eligible individuals received PCSK9-i, but those treated experienced a significant reduction in the risk of death and hospitalizations compared to those who didn't receive the treatment.
Article Synopsis
- Heart failure with preserved ejection fraction (HFpEF) has been challenging to treat over the years, but recent therapies, including sodium-glucose cotransporter 2 inhibitors (SGLT2i), show promise in improving patient outcomes.
- HFpEF is increasingly prevalent, influenced by longer life expectancies and rising health issues like diabetes and obesity, suggesting it's part of a wider cardio-nephro-metabolic syndrome.
- The Cardiovascular Observatory of Friuli-Venezia Giulia plays a crucial role in identifying and managing HFpEF patients, highlighting the need for tailored therapeutic approaches, particularly with the emerging role of SGLT2i in treatment guidelines.
Objectives: This study aims to show the application of flexible statistical methods in real-world cost-effectiveness analyses applied in the cardiovascular field, focusing specifically on the use of proprotein convertase subtilisin-kexin type 9 inhibitors for hyperlipidemia.
Methods: The proposed method allowed us to use an electronic health database to emulate a target trial for cost-effectiveness analysis using multistate modeling and microsimulation. We formally established the study design and provided precise definitions of the causal measures of interest while also outlining the assumptions necessary for accurately estimating these measures using the available data.
Background: Machine learning (ML) methods to build prediction models starting from electrocardiogram (ECG) signals are an emerging research field. The aim of the present study is to investigate the performances of two ML approaches based on ECGs for the prediction of new-onset atrial fibrillation (AF), in terms of discrimination, calibration and sample size dependence.
Methods: We trained two models to predict new-onset AF: a convolutional neural network (CNN), that takes as input the raw ECG signals, and an eXtreme Gradient Boosting model (XGB), that uses the signal's extracted features.
Article Synopsis
- * The study analyzed electronic health records from over 10,600 patients who were evaluated for heart conditions but had no prior heart failure diagnosis, tracking developments over an average of 65 months.
- * Two AI models were developed, with a deep neural network model (PHNN) proving more effective than a traditional Cox model in predicting heart failure risks, identifying 20 key predictors relevant to clinical practice.
Article Synopsis
- Interpretability in healthcare is crucial, but deep learning models often lack it, hindering their use; this study introduces an attention layer in an LSTM neural network to improve model transparency in predicting patient outcomes.
- Using data from 10,616 cardiovascular patients in the MIMIC III dataset, the model analyzes 48 clinical parameters over 10-hour sequences to predict death within a week, achieving an AUC of 0.790.
- The study finds that attention weights align well with known risk factors, demonstrating the effectiveness of attention mechanisms in enhancing deep learning interpretability for electronic health records analysis.
Sex-related differences in chronic heart failure: a community-based study.
J Cardiovasc Med (Hagerstown)
January 2021
Article Synopsis
- The study aimed to assess sex-related differences in chronic heart failure patients and how these differences affect treatment and outcomes.
- Among 2528 patients examined, females were more likely to have heart failure with preserved ejection fraction (HFpEF) and showed distinct health profiles compared to males.
- Although overall mortality rates were similar between sexes, adjusted findings indicated that females had a lower risk of mortality in HFpEF and mid-range ejection fraction (HFmrEF) groups, largely due to non-cardiac comorbidities affecting their prognosis.
Article Synopsis
- The study focuses on adult patients with simple congenital heart disease (sACHD), who are at risk for atrial arrhythmias (AA), and investigates how the CHADS-VASc score predicts thromboembolic risk in this group.
- Researchers evaluated 427 sACHD patients over a mean follow-up of 70 months, finding that those with a higher CHADS-VASc score (group B) had significantly worse outcomes, including higher rates of hospitalization and death compared to those with lower scores (group A).
- The findings indicate that the CHADS-VASc score can effectively classify sACHD patients' risk levels for serious clinical events in the long term, independent of their cardiac rhythm.
Background: Much data about prescription adherence in patients with heart failure (HF) are available, but few exist about the evaluation of true patient adherence. Further, methods for analyzing this issue are poorly known.
Objectives: Our objective was to evaluate the impact of patient adherence to disease-modifying drugs after HF hospitalization in a community-based cohort.
Article Synopsis
- The study analyzed heart failure (HF) progression and its impact on patient prognosis, focusing on data from 2009 to 2015 involving 2528 HF patients with a median age of 76.
- HF progression was defined by changes in NYHA class, left ventricular ejection fraction (LVEF), diuretic use, or hospitalizations, revealing a 39% incidence of progression over four years, with a higher risk in patients with LVEF ≤ 35%.
- The findings highlight that nearly 39% of patients experienced HF progression, while 18% died without signs of it, particularly emphasizing the need for better healthcare strategies for at-risk populations.
Background: How different risk profiles of heart failure (HF) patients can influence multiple readmissions and outpatient management is largely unknown. We propose the application of two multi-state models in real world setting to jointly evaluate the impact of different risk factors on multiple hospital admissions, Integrated Home Care (IHC) activations, Intermediate Care Unit (ICU) admissions and death.
Methods And Findings: The first model (model 1) concerns only hospitalizations as possible events and aims at detecting the determinants of repeated hospitalizations.