"eHealth Informatics using EHR: A Comparative Analysis of Data Mining Classification Techniques"
Fuente:
Zenodo
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Recurso digital |
| Veröffentlicht: |
Zenodo
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866901250049572864 |
|---|---|
| author | Dr. Vaishali S Parsania |
| author_facet | Dr. Vaishali S Parsania |
| contents | <p>Abstract <br>eHealth informatics has emerged as a transformative domain that integrates healthcare, <br>information technology & data analytics to improve clinical decision-making. With the rapid <br>growth of Electronic Health Records (EHRs), there is an increasing need for intelligent systems <br>capable of extracting meaningful insights from complex and heterogeneous medical data. This <br>paper presents analysis of machine learning classification techniques applied to 5000 EHR <br>datasets to enhance decision support in healthcare systems. <br>The research utilizes a structured EHR dataset comprising 5000 patient records across multiple <br>diseases and healthcare attributes. Various classification algorithms, including Naïve Bayes, <br>BayesNet, Random Forest, JRip, OneR, and PART, are implemented and evaluated using <br>performance metrics. A 10-fold cross-validation approach is employed to ensure reliability and <br>robustness of the results. <br>The findings reveal that probabilistic models, particularly Naïve Bayes and BayesNet, <br>demonstrate comparatively stable and efficient performance across multiple evaluation <br>parameters. The study highlights the importance of selecting appropriate algorithms based on <br>dataset characteristics and healthcare requirements. <br>This research contributes to the eHealth informatics by providing insights into the effectiveness <br>of machine learning approaches in healthcare data analysis. It also reveal the potential of <br>integrating analytics into healthcare systems to achieve improved accuracy, efficiency, and <br>quality of care.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19417060 |
| institution | Zenodo |
| language | |
| publishDate | 2023 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | "eHealth Informatics using EHR: A Comparative Analysis of Data Mining Classification Techniques" Dr. Vaishali S Parsania eHealth Informatics, Electronic Health Records (EHR), Machine Learning, Data Mining, Healthcare Analytics, Classification Algorithms, Naïve Bayes, Random Forest, Predictive Modeling <p>Abstract <br>eHealth informatics has emerged as a transformative domain that integrates healthcare, <br>information technology & data analytics to improve clinical decision-making. With the rapid <br>growth of Electronic Health Records (EHRs), there is an increasing need for intelligent systems <br>capable of extracting meaningful insights from complex and heterogeneous medical data. This <br>paper presents analysis of machine learning classification techniques applied to 5000 EHR <br>datasets to enhance decision support in healthcare systems. <br>The research utilizes a structured EHR dataset comprising 5000 patient records across multiple <br>diseases and healthcare attributes. Various classification algorithms, including Naïve Bayes, <br>BayesNet, Random Forest, JRip, OneR, and PART, are implemented and evaluated using <br>performance metrics. A 10-fold cross-validation approach is employed to ensure reliability and <br>robustness of the results. <br>The findings reveal that probabilistic models, particularly Naïve Bayes and BayesNet, <br>demonstrate comparatively stable and efficient performance across multiple evaluation <br>parameters. The study highlights the importance of selecting appropriate algorithms based on <br>dataset characteristics and healthcare requirements. <br>This research contributes to the eHealth informatics by providing insights into the effectiveness <br>of machine learning approaches in healthcare data analysis. It also reveal the potential of <br>integrating analytics into healthcare systems to achieve improved accuracy, efficiency, and <br>quality of care.</p> |
| title | "eHealth Informatics using EHR: A Comparative Analysis of Data Mining Classification Techniques" |
| topic | eHealth Informatics, Electronic Health Records (EHR), Machine Learning, Data Mining, Healthcare Analytics, Classification Algorithms, Naïve Bayes, Random Forest, Predictive Modeling |
| url | https://doi.org/10.5281/zenodo.19417060 |