Login
Search
Search
0 Dates
2024
2023
2022
2021
2020
2019
2018
0 Events
CPC 2018
CPC 2019
Curso de Atualização em Medicina Cardiovascular 2019
Reunião Anual Conjunta dos Grupos de Estudo de Cirurgia Cardíaca, Doenças Valvulares e Ecocardiografia da SPC
CPC 2020
CPC 2021
CPC 2022
CPC 2023
CPC 2024
0 Topics
A. Basics
B. Imaging
C. Arrhythmias and Device Therapy
D. Heart Failure
E. Coronary Artery Disease, Acute Coronary Syndromes, Acute Cardiac Care
F. Valvular, Myocardial, Pericardial, Pulmonary, Congenital Heart Disease
G. Aortic Disease, Peripheral Vascular Disease, Stroke
H. Interventional Cardiology and Cardiovascular Surgery
I. Hypertension
J. Preventive Cardiology
K. Cardiovascular Disease In Special Populations
L. Cardiovascular Pharmacology
M. Cardiovascular Nursing
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
O. Basic Science
P. Other
0 Themes
01. History of Cardiology
02. Clinical Skills
03. Imaging
04. Arrhythmias, General
05. Atrial Fibrillation
06. Supraventricular Tachycardia (non-AF)
07. Syncope and Bradycardia
08. Ventricular Arrhythmias and Sudden Cardiac Death (SCD)
09. Device Therapy
10. Chronic Heart Failure
11. Acute Heart Failure
12. Coronary Artery Disease (Chronic)
13. Acute Coronary Syndromes
14. Acute Cardiac Care
15. Valvular Heart Disease
16. Infective Endocarditis
17. Myocardial Disease
18. Pericardial Disease
19. Tumors of the Heart
20. Congenital Heart Disease and Pediatric Cardiology
21. Pulmonary Circulation, Pulmonary Embolism, Right Heart Failure
22. Aortic Disease
23. Peripheral Vascular and Cerebrovascular Disease
24. Stroke
25. Interventional Cardiology
26. Cardiovascular Surgery
27. Hypertension
28. Risk Factors and Prevention
29. Rehabilitation and Sports Cardiology
30. Cardiovascular Disease in Special Populations
31. Pharmacology and Pharmacotherapy
32. Cardiovascular Nursing
33. e-Cardiology / Digital Health
34. Public Health and Health Economics
35. Research Methodology
36. Basic Science
37. Miscellanea
0 Resources
Abstract
Slides
Vídeo
Report
CLEAR FILTERS
Integrating Diverse Real World Data for Enhanced Phenotyping of Cardiovascular Chronic Conditions
Session:
Comunicações Orais - Sessão 06 - Doença coronária
Speaker:
Bernardo Neves
Congress:
CPC 2024
Topic:
H. Interventional Cardiology and Cardiovascular Surgery
Theme:
35. Research Methodology
Subtheme:
35.6 Research Methodology - Other
Session Type:
Comunicações Orais
FP Number:
---
Authors:
Bernardo Neves; Mário J. Silva; Anabela Raimundo; Pedro Sarmento; Jorge Cerejo; Simão Gonçalves; José Maria Moreira; Nuno André da Silva; Frrancisca Leite
Abstract
<p>Introduction: Electronic Health Records (EHR) are increasingly leveraged for secondary observational research, clinical trial recruitment and automatic cardiovascular risk assessment. Traditionally, the identification of conditions in EHRs relies heavily on diagnosis codes such as International Classification of Diseases (ICD), however the accuracy of disease phenotyping can vary significantly. In this study we aim to evaluate the additional contribution of drug prescriptions and laboratory measurements in enhancing the phenotyping of some cardiovascular chronic conditions. </p> <p>Methods: An anonymized dataset from a single hospital's EHR, encompassing 303,807 patients between 2018 and 2022, was analysed. Prevalence of Heart Failure (HF), Diabetes mellitus (DM), Hypertension (HT) and Hypercholesterolemia (HCL) were analyzed trough: 1) ICD9-CM codes assigned by physicians, utilizing the Clinical Classifications Software (CCS) for code aggregation; 2) Drug Prescriptions mapped to conditions trough the previously validatedd Rx-risk model; 3) Laboratory Measurements of NT-pro-BNP > 125 pg/ml for HF, HbA1c ≥6,5% for DM and total cholesterol > 190 mg/dl for HCL. </p> <p>Results: We found drug prescriptions and laboratory measurements as key enhancers in the identification of chronic conditions, always exceeding ICD9-based identification. Drug prescriptions and NT-pro-BNP measurements found 11.9 and 3.7 times more patients with HF than the 1,760 ones found with ICD-9 codes, respectively. Drug prescriptions led to additional 12,819 patients diagnosed with HT, on top of the 13,683 initially found with ICD9 codes. In diabetes, the supplementary methods revealed 2.4 times more patients than the 5,242 initially identified by ICD9. The impact was even more pronounced for HCL, with the combined approach identifying 52,044 additional patients—9.7 times the 5,812 found via ICD9. While 21.2% of patients with HT could be identified by both ICD9 and drug prescriptions, smaller fractions of patients met all three diagnosis criteria: 13.5% for DM, 5.0% for HF, and 2.1% for HCL. </p> <p>Conclusions: This study underscores the effectiveness of multimodal phenotyping in EHRs, significantly amplifying patient identification rates for chronic diseases. Drug prescriptions and laboratory data are confirmed as crucial diagnostic resources for these cardiovascular conditions. The low percentage of patients meeting all criteria suggests underdiagnosis when relying on single real world data sources. Future directions include validation to establish the specificity of each phenotyping approach, mining clinical narratives for additional disease mention, and applying these strategies to other conditions to increase clinical data quality. We believe this is an important step towards automatic diagnosis and cardiovascular risk assessment from existing clinical data. </p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site