Analyzing Big Data in Heart Failure Patients
Author Information
Author(s): ÇÖLLÜOĞLU Tuğçe, ŞAHİN Anıl, ÇELİK Ahmet, KANIK Emine Arzu
Primary Institution: Karabük University, Sivas Cumhuriyet University, Mersin University
Hypothesis
This article aimed to examine the challenges in accessing and utilizing healthcare big data for heart failure research.
Conclusion
To accurately identify patients with heart failure using big data, it is necessary to establish additional specific criteria and use different statistical programs.
Supporting Evidence
- Big data can reshape healthcare by enabling comprehensive data analysis.
- ICD-10 codes were used to validate heart failure diagnoses.
- The study cohort was created by screening over 85 million healthcare records.
- Statistical analysis was conducted using SPSS, MedCalc, and E-PICOS.
- Propensity score matching was employed to establish similarity among studied groups.
Takeaway
This study looked at a lot of health data to understand heart failure better and found that we need better ways to analyze this data.
Methodology
The study involved a multidisciplinary team that analyzed healthcare records using ICD-10 codes and various statistical programs.
Potential Biases
Potential biases due to missing data and reliance on ICD-10 codes for diagnosis.
Limitations
The study faced challenges with data quality and the sensitivity of ICD-10 codes for heart failure.
Participant Demographics
The study included healthcare records of Turkish citizens diagnosed with heart failure from 2016 to 2022.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website