Heart Failure Awareness Days
This year, the Heart Failure Awareness Days are taking place from 1 to 7 May.
Download our heart failure use cases, and discover how big data and technology can
- contribute to better and more effective screening for (rare) cardiac diseases, and
- provide further insights into the effectiveness of heart failure treatments in a real-world patient population.
Scroll down to read more.
As we begin 2023’s Heart Failure Awareness Week, it is important to reflect on how we can better detect and treat this condition. This year's theme, "Detect the Undetected" highlights the need for early detection and intervention to improve patient outcomes.
Real-world evidence (RWE) and data (RWD) play a crucial role in achieving this goal. While structured clinical data provides a standardized and organized view of a patient's medical history, much of the valuable information about comorbidities and clinical manifestations of cardiovascular disease, including the risk of HF is recorded in narrative text within electronic health records (EHRs).
This is where unstructured data becomes crucial. By leveraging natural language processing (NLP) and machine learning (ML) technologies, we can analyze unstructured data within EHRs to extract valuable information that is not available in structured data alone. This can help clinicians identify patients who are at risk of developing heart failure, track the progression of the disease, and evaluate the effectiveness of different treatment options.
Discover some examples by clicking the download button at the top of the page:
- AI and Natural Language Processing (NLP) was used to extract insights from anonymized EHRs to investigate the effectiveness of Dapaglifozin in HF patients in the real world.
- An NLP-algorithm was used to detect unique combinations of cardiac and non-cardiac phenotypes in EHRs to enhance the diagnosis of aTTR-CM in a real-world heart failure population.
But also in many independent publications, such as this article published in the American Journal of Preventive Cardiology where the authors found that using NLP to extract unstructured data significantly improved the sensitivity, negative predictive value, and area under the curve compared to structured data alone in identifying reasons for patients not being on HIST (high-intensity statin therapy).
Having access to granular RWD by leveraging both structured and unstructured clinical data, will be essential to enable early detection and treatment of at-risk patients. NLP and ML technologies are key components of this approach, enabling clinicians to extract valuable insights from unstructured data and make more informed decisions.
As we begin 2023’s Heart Failure Awareness Week, it is important to reflect on how we can better detect and treat this condition. This year's theme, "Detect the Undetected" highlights the need for early detection and intervention to improve patient outcomes.
Real-world evidence (RWE) and data (RWD) play a crucial role in achieving this goal. While structured clinical data provides a standardized and organized view of a patient's medical history, much of the valuable information about comorbidities and clinical manifestations of cardiovascular disease, including the risk of HF is recorded in narrative text within electronic health records (EHRs).
This is where unstructured data becomes crucial. By leveraging natural language processing (NLP) and machine learning (ML) technologies, we can analyze unstructured data within EHRs to extract valuable information that is not available in structured data alone. This can help clinicians identify patients who are at risk of developing heart failure, track the progression of the disease, and evaluate the effectiveness of different treatment options.
Discover some examples by clicking the download button at the top of the page:
- AI and Natural Language Processing (NLP) was used to extract insights from anonymized EHRs to investigate the effectiveness of Dapaglifozin in HF patients in the real world.
- An NLP-algorithm was used to detect unique combinations of cardiac and non-cardiac phenotypes in EHRs to enhance the diagnosis of aTTR-CM in a real-world heart failure population.
But also in many independent publications, such as this article published in the American Journal of Preventive Cardiology where the authors found that using NLP to extract unstructured data significantly improved the sensitivity, negative predictive value, and area under the curve compared to structured data alone in identifying reasons for patients not being on HIST (high-intensity statin therapy).
Having access to granular RWD by leveraging both structured and unstructured clinical data, will be essential to enable early detection and treatment of at-risk patients. NLP and ML technologies are key components of this approach, enabling clinicians to extract valuable insights from unstructured data and make more informed decisions.
