Machine Learning with Tunicate Swarm Optimization for Improved Disc Herniation Prediction
A common spinal ailment called disc herniation is the displacement of the spinal discs' inner core as a result of a rupture in their outer covering. The many variables that contribute to disc herniation are examined in this study, including age-related deterioration, genetic predispositions, li...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-06-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_199247_9b5fdad33d29647e7465a31802d476dd.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | A common spinal ailment called disc herniation is the displacement of the spinal discs' inner core as a result of a rupture in their outer covering. The many variables that contribute to disc herniation are examined in this study, including age-related deterioration, genetic predispositions, lifestyle choices, and traumatic experiences. This study highlights the need for accurate prognosis and therapeutic efficacy, and it promotes machine learning (ML) as an essential diagnostic tool. This study employs Extra Tree Classification (ETC), Naïve Bayes Classification (NBC), and Logistic Regression Classification (LRC) to forecast disk herniation. Additionally, Tunicate Swarm Optimization (TSO) is integrated to enhance the accuracy of all three models NBC, ETC, and LRC. To ensure impartiality, unbiased performance assessors are engaged to objectively evaluate the model outcomes. The study's findings showcase the effectiveness of the prediction model for disk herniation. Through hybridization with one optimizer, the three base models yield the following outputs: ETC + TSO (ETTS), NBC + TSO (NBTS), and LRC + TSO (LRTS). In the testing phase, the LRTS model exhibits the utmost performance, attaining an accuracy value of 0.957, while conversely, the NBC model demonstrates the least robust performance, yielding a value of 0.893. These findings unequivocally underscore the superior predictive capability of the LRTS model in forecasting discherniation. |
|---|---|
| ISSN: | 2821-0263 |