A5015405593- Blood Pressure and Hypertension Studies
- Sparse and Compressive Sensing Techniques
- Cardiovascular Health and Risk Factors
- Health Systems, Economic Evaluations, Quality of Life
- Acute Myocardial Infarction Research
- Machine Learning in Healthcare
- COVID-19 epidemiological studies
- Misinformation and Its Impacts
- Long-Term Effects of COVID-19
- Sepsis Diagnosis and Treatment
- Acute Kidney Injury Research
- Cardiac, Anesthesia and Surgical Outcomes
- Microwave Imaging and Scattering Analysis
- Antiplatelet Therapy and Cardiovascular Diseases
- Hemodynamic Monitoring and Therapy
- Cardiac Imaging and Diagnostics
- Hormonal Regulation and Hypertension
- Sodium Intake and Health
- Chronic Kidney Disease and Diabetes
- Cardiac Health and Mental Health
- Image and Signal Denoising Methods
- SARS-CoV-2 and COVID-19 Research
- Intensive Care Unit Cognitive Disorders
- Photoacoustic and Ultrasonic Imaging
- Medication Adherence and Compliance
Yale New Haven Hospital
2017-2025
Yale University
2015-2025
Sichuan University
2025
Krirk University
2024
Medtronic (United States)
2024
Shaanxi Normal University
2023
University of Illinois Urbana-Champaign
2022
Chongqing University of Posts and Telecommunications
2021
Yale New Haven Health System
2021
Purdue University West Lafayette
2021
Accurate prediction of adverse outcomes after acute myocardial infarction (AMI) can guide the triage care services and shared decision-making, novel methods hold promise for using existing data to generate additional insights.To evaluate whether contemporary machine learning facilitate risk by including a larger number variables identifying complex relationships between predictors outcomes.This cohort study used American College Cardiology Chest Pain-MI Registry identify all AMI...
The current acute kidney injury (AKI) risk prediction model for patients undergoing percutaneous coronary intervention (PCI) from the American College of Cardiology (ACC) National Cardiovascular Data Registry (NCDR) employed regression techniques. This study aimed to evaluate whether models using machine learning techniques could significantly improve AKI after PCI.We used same cohort and candidate variables develop NCDR CathPCI model, including 947,091 who underwent PCI procedures between...
Importance Early warning decision support tools to identify clinical deterioration in the hospital are widely used, but there is little information on their comparative performance. Objective To compare 3 proprietary artificial intelligence (AI) early scores and publicly available simple aggregated weighted scores. Design, Setting, Participants This retrospective cohort study was performed at 7 hospitals Yale New Haven Health System. All consecutive adult medical-surgical ward encounters...
<h3>Importance</h3> Better prediction of major bleeding after percutaneous coronary intervention (PCI) may improve clinical decisions aimed to reduce risk. Machine learning techniques, bolstered by better selection variables, hold promise for enhancing prediction. <h3>Objective</h3> To determine whether machine techniques predict post-PCI compared with the existing National Cardiovascular Data Registry (NCDR) models. <h3>Design, Setting, and Participants</h3> This comparative effectiveness...
New methods such as machine learning techniques have been increasingly used to enhance the performance of risk predictions for clinical decision-making. However, commonly reported metrics may not be sufficient capture advantages these newly proposed models their adoption by health care professionals improve care. Machine often estimation certain subpopulations that missed metrics.This article addresses limitations comparison and proposes additional metrics. Our discussions cover related...
Background Characterizing and assessing the prevalence, awareness, treatment patterns of patients with isolated diastolic hypertension ( IDH ) can generate new knowledge highlight opportunities to improve their care. Methods Results We used data from China PEACE (Patient‐centered Evaluative Assessment Cardiac Events) Million Persons Project, which screened 2 351 035 participants aged 35 75 years between 2014 2018. was defined as systolic blood pressure <140 ≥90 mm Hg; awareness...
Visit-to-visit variability (VVV) in blood pressure values has been reported clinical studies. However, little is known about VVV practice and whether it associated with patient characteristics real-world setting.
ABSTRACT Introduction A chronic post-vaccination syndrome (PVS) after covid-19 vaccination has been reported but yet to be well characterized. Methods We included 241 individuals aged 18 and older who self-reported PVS joined the online Yale Listen Immune, Symptom Treatment Experiences Now (LISTEN) Study from May 2022 July 2023. summarized their demographics, health status, symptoms, treatments tried, overall experience. Results The median age of participants was 46 years (interquartile...
Internal tremors and vibrations are symptoms previously described as part of neurologic disorders but not fully a long COVID. This study compared pre-pandemic comorbidities, new-onset conditions, COVID between people with internal their without these symptoms.
Determining the association of contrast volume during percutaneous coronary intervention (PCI) with risk acute kidney injury (AKI) is important for optimizing PCI safety.To quantify how AKI associated volume, accounting possibility nonlinearity and heterogeneity among different baseline risks.This prognostic study used data from American College Cardiology National Cardiovascular Data Registry CathPCI 1694 US hospitals. Derivation analysis included 2 076 694 individuals who underwent July 1,...
Background The digital transformation of medical data provides opportunities to perform population health surveillance and identify people inadequately managed in usual care. We leveraged the electronic records a large system patients with markedly elevated blood pressure characterize their follow‐up care pattern. Methods Results included 373 861 aged 18 85 years, who had at least 1 outpatient encounter Yale New Haven Health System between January 2013 December 2017. described prevalence...
Background: Intraoperative data may improve models predicting postoperative events. We evaluated the effect of incorporating intraoperative variables to existing preoperative model on predictive performance for coronary artery bypass graft. Methods: analyzed 378 572 isolated graft cases performed across 1083 centers, using national Society Thoracic Surgeons Adult Cardiac Surgery Database between 2014 and 2016. Outcomes were operative mortality, 5 complications, composite representation all...
Objective To describe the experience of people with long COVID symptomatology and characterize psychological, social, financial challenges they experience. Background The needs further amplification, especially a comprehensive focus on symptomatology, treatments, impact daily life finances. Methods We collected data from individuals aged 18 older reporting as participants in Yale Listen to Immune, Symptom Treatment Experiences Now (LISTEN) Study. sample population included 441 surveyed...
Background Harnessing health-related data posted on social media in real time can offer insights into how the pandemic impacts mental health and general well-being of individuals populations over time. Objective This study aimed to obtain information symptoms medical conditions self-reported by non-Twitter users during COVID-19 pandemic, determine discussion these changed time, identify correlations between frequency top 5 commonly mentioned post daily statistics (new cases, new deaths,...
Background SPRINT (Systolic Blood Pressure Intervention Trial) and the ACCORD (Action to Control Cardiovascular Risk in Diabetes) blood pressure trial used similar interventions but produced discordant results. We investigated whether differences systolic ( SBP ) response contributed Methods Results evaluated distributions of during first year for intensive standard treatment groups using growth mixture models. assessed significant existed between trials achieved at 1 treatment‐independent...
Machine learning (ML) techniques have become ubiquitous and indispensable for solving intricate problems in most disciplines. To determine the extent of funding clinical research projects applying ML by National Institutes Health (NIH) 2017, we searched NIH Research Portfolio Online Reporting Tools Expenditures Results (RePORTER) system using relevant keywords. We identified 535 projects, which together received a total $264 million, accounting 2% extramural budget research.
Randomized trials of hypertension have seldom examined heterogeneity in response to treatments over time and the implications for cardiovascular outcomes. Understanding this heterogeneity, however, is a necessary step toward personalizing antihypertensive therapy. We applied trajectory-based modeling data on 39 763 study participants ALLHAT (Antihypertensive Lipid-Lowering Treatment Prevent Heart Attack Trial) identify distinct patterns systolic blood pressure (SBP) randomized medications...
ABSTRACT Importance Internal tremors and vibrations symptoms have been described as part of neurologic disorders but not fully a long COVID. Objective To compare demographics, socioeconomic characteristics, pre-pandemic comorbidities, new-onset conditions, COVID between people with internal their without these symptoms. Design A cross-sectional study, Listen to Immune, Symptom Treatment Experiences Now (LISTEN), adults post-vaccination syndrome, defined by self-report. Setting Hugo Health...
Abstract Background The continuous emergence of novel SARS-CoV-2 variants with markedly increased transmissibility presents major challenges to the zero-COVID policy in China. It is critical adjust aspects about non-pharmaceutical interventions (NPIs) by searching for and implementing more effective ways. We use a mathematical model mimic epidemic pattern Omicron variant Shanghai quantitatively show control investigate feasibility different patterns avoiding other waves. Methods initially...