A5066482871- Machine Learning in Healthcare
- COVID-19 Clinical Research Studies
- COVID-19 diagnosis using AI
- Asthma and respiratory diseases
- Health Systems, Economic Evaluations, Quality of Life
- Attention Deficit Hyperactivity Disorder
- Chronic Disease Management Strategies
- Artificial Intelligence in Healthcare
- Blood Pressure and Hypertension Studies
- Extraction and Separation Processes
- Marine and fisheries research
- Long-Term Effects of COVID-19
- Bipolar Disorder and Treatment
- Bacterial Identification and Susceptibility Testing
- COVID-19 and Mental Health
- Urinary Tract Infections Management
- Drug-Induced Hepatotoxicity and Protection
- Diabetes Treatment and Management
- COVID-19 and healthcare impacts
- Lipoproteins and Cardiovascular Health
- Magnetic and transport properties of perovskites and related materials
- Respiratory and Cough-Related Research
- Diverse Approaches in Healthcare and Education Studies
- Ferroelectric and Piezoelectric Materials
- Acute Kidney Injury Research
Yale University
2024-2025
Yale New Haven Hospital
2024-2025
Ajou University
2019-2024
Yale New Haven Health System
2024
Korea Institute of Ceramic Engineering and Technology
2020-2021
Government of the Republic of Korea
2020-2021
Prognostic models help aid medical decision-making. Various prognostic are available via websites such as MDCalc, but these typically predict one outcome, for example, stroke risk. Each model requires individual predictors, age, lab results and comorbidities. There is no clinical tool to multiple outcomes from a list of common predictors. Identify constrained set outcome-agnostic We proposed novel technique aggregating the standardised mean difference across hundreds learn predictors that...
Abstract Background We investigated whether we could use influenza data to develop prediction models for COVID-19 increase the speed at which can reliably be developed and validated early in a pandemic. Estimated Risk (COVER) scores that quantify patient’s risk of hospital admission with pneumonia (COVER-H), hospitalization requiring intensive services or death (COVER-I), fatality (COVER-F) 30-days following diagnosis using historical from patients flu-like symptoms tested this patients....
Transparent and FAIR disclosure of meta-information about healthcare data infrastructure is essential but has not been well publicized. In this paper, we provide a transparent the process standardizing common model developing national using claims data. We established an Observational Medical Outcome Partnership (OMOP) database for Health Insurance Review Assessment Service South Korea. To introduce openness policy, built distributed analysis environment released metadata based on principle....
Cause of death is used as an important outcome clinical research; however, access to cause-of-death data limited. This study aimed develop and validate a machine-learning model that predicts the cause from patient's last medical checkup.To classify mortality status each individual death, we stacking ensemble method. The prediction outcomes were all-cause mortality, 8 leading causes in South Korea, other causes. populations extracted national claims (n = 174 747) electronic health records 729...
As a response to the ongoing COVID-19 pandemic, several prediction models in existing literature were rapidly developed, with aim of providing evidence-based guidance. However, none these have been found be reliable. Models are commonly assessed risk bias, often due insufficient reporting, use non-representative data, and lack large-scale external validation. In this paper, we present Observational Health Data Sciences Informatics (OHDSI) analytics pipeline for patient-level modeling as...
Linear mixed models are commonly used in healthcare-based association analyses for analyzing multi-site data with heterogeneous site-specific random effects. Due to regulations protecting patients' privacy, sensitive individual patient (IPD) typically cannot be shared across sites. We propose an algorithm fitting distributed linear (DLMMs) without sharing IPD This achieves results identical those achieved using pooled from multiple sites (i.e., the same effect size and standard error...
ABSTRACT Alpha‐fetoprotein (AFP) level and its changes in chronic hepatitis B (CHB) may influence the risk of future hepatocellular carcinoma (HCC). This study aims to evaluate HCC CHB patients with no overt but elevated AFP explore prognostic role longitudinal liver‐related laboratory values. multicentre cohort included 10,639 without a history from seven medical facilities South Korea. Patients baseline serum test diagnosis on imaging within 3 months were included. categorised into...
Introduction: For stroke survivors, blood pressure (BP) reduction significantly lowers the risk of recurrence; a 10mmHg decrease in systolic BP is associated with 20% reduction. Despite magnitude this benefit, existing data quantifying post-stroke control limited to small cohorts, national surveys relying on self-report stroke, and cross-sectional from closed health systems. We aim determine rates broader population within first year multiple cohorts patients, including large US...
Less frequent adverse drug reactions are usually discovered after a drug's release to the market, making effective and timely communication of regulatory post‐market advisories essential for preventing emerging effects. Time series analysis is key study design assessing impact safety advisories. However, most previous studies have focused on narrow evaluations, limiting systematic assessment how different affect prescribing practices. This aimed investigate changes in practices following...
The objective of this report is to characterize BP control among patients six months post stroke and measure time first visit. Patients were discharged from the Yale New Haven Health System (YNHHS) had visits in EPIC system supported by YNHHS. primary outcome was systolic blood pressure (SBP) values ≥140 mmHg or diastolic (DBP) >90 during visit closest before 6 hospitalization. analysis included 3339 patients. average proportion with SBP ≥DBP 90 31%. ≥130 80 mm Hg 61%. Among who a care...
Background/Objectives: Evidence on the renal benefits and safety of sodium-glucose cotransporter 2 inhibitors (SGLT2i) in Asia region is still lacking. This study aimed to evaluate outcomes SGLT2i compared with dipeptidyl peptidase 4 (DPP4i) using real-world data. Methods: A retrospective cohort was conducted nationwide claims data Republic Korea. We evaluated kidney (any new-onset events, acute injury (AKI), chronic disease (CKD), failure) as primary (infection, hemodynamic adverse...
This study uses data from the US nationwide electronic health record–based Epic Cosmos Dataset to examine prescriptions for semaglutide and tirzepatide, focusing on differences across race, ethnicity, social vulnerability, urbanicity assess need strategies promote equitable access these therapies.
Background As prescribing of newer antihyperglycemic agents expands, there remains limited comparative safety data for older adults a population particularly vulnerable to adverse drug events and underrepresented in clinical trials. We aimed evaluate the real world second-line among with type 2 diabetes. Methods conducted multinational cohort study using nine harmonized electronic health record claims databases from U.S. Europe, applying consistent analytical framework based on LEGEND T2DM...
Background/Objectives: Evidence on the renal benefits and safety of sodium–glucose cotransporter 2 inhibitors (SGLT2i) in Asia region is still lacking. This study aimed to evaluate outcomes SGLT2is compared with dipeptidyl peptidase-4 (DPP4i) using real-world data. Methods: A retrospective cohort was conducted nationwide claims data Republic Korea. We evaluated kidney (any new-onset events, acute injury (AKI), chronic disease (CKD), failure) as primary (infection, hemodynamic adverse...
Objective To develop and externally validate COVID-19 Estimated Risk (COVER) scores that quantify a patient’s risk of hospital admission (COVER-H), requiring intensive services (COVER-I), or fatality (COVER-F) in the 30-days following diagnosis. Methods We analyzed federated network electronic medical records administrative claims data from 14 sources 6 countries. developed validated 3 using 6,869,127 patients with general practice, emergency room, outpatient visit diagnosed influenza...
Abstract Objective Observational studies can impact patient care but must be robust and reproducible. Nonreproducibility is primarily caused by unclear reporting of design choices analytic procedures. This study aimed to: (1) assess how the logic described in an observational could interpreted independent researchers (2) quantify interpretations’ variability on characteristics. Materials Methods Nine teams highly qualified reproduced a cohort from Albogami et al. The were provided clinical...
Aspirin-exacerbated respiratory disease (AERD) is a phenotype of severe asthma, but its course has not been well documented compared with that aspirin-tolerant asthma (ATA).This study aimed to investigate the long-term clinical outcomes between AERD and ATA.AERD patients were identified by diagnostic code positive bronchoprovocation test in real-world database. Longitudinal changes lung function, blood eosinophil/neutrophil counts, annual numbers exacerbations (AEx) ATA groups. Within year...
Journal Article Data Resource Profile: Health Insurance Review and Assessment Service Covid-19 Observational Medical Outcomes Partnership (HIRA OMOP) database in South Korea Get access Chungsoo Kim, Kim Department of Biomedical Sciences, Ajou University Graduate School Medicine, Suwon, Republic https://orcid.org/0000-0003-1802-1777 Search for other works by this author on: Oxford Academic PubMed Google Scholar Dong Han Yu, Yu Big Department, Services, Wonju, Hyeran Baek, Baek Jaehyeong Cho,...
Antibiotic-induced dysbiosis may affect the efficacy of immune checkpoint inhibitors. We investigated impact antibiotics on clinical outcomes nivolumab in patients with non-small cell lung cancer (NSCLC). Patients who received for NSCLC between July 2015 and June 2018 were followed up until 2020 included a retrospective cohort analysis. Of 140 eligible patients, 70 antibiotics. Overall survival (OS) was shorter (ABX) compared to those not (NoABX) (p = 0.014). OS negatively associated...
Background Identifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context often recorded in notes; however, the utilization unstructured data remains limited. This study aimed to develop psychosis-relapse prediction models using various types notes and structured data. Methods Clinical were extracted from electronic health records Ajou University Medical Center South Korea. The population included with psychotic disorders,...