Developing lung cancer post-diagnosis system using pervasive data analytic framework
The data from lung cancer patients using wearable sensors and clinical assessments after observation is available to predict the disease’s recurrence. In recurrence prediction, pervasive data analysis is required to prevent flaws in clinical correlations and data observations. This article proposes...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier Ltd.
2023
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/27371/2/0102922062023.PDF http://eprints.utem.edu.my/id/eprint/27371/ https://www.sciencedirect.com/science/article/pii/S0045790622007431 https://www.sciencedirect.com/science/article/pii/S0045790622007431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The data from lung cancer patients using wearable sensors and clinical assessments after observation is available to predict the disease’s recurrence. In recurrence prediction, pervasive data analysis is required to prevent flaws in clinical correlations and data observations. This article proposes a Pervasive Data Analytical Framework (PDAF) for recurrence prediction. The proposed framework incorporates three processes: data segregation using Butterfly Optimisation, feature correlation using Jaya Optimisation, and autoencoder prediction. First, the data from the wearable sensor is segregated using observation count for its availability and discreteness. It prevents missing errors under different observation sequences for which the correlation rate is determined using the next optimization. In the Jaya optimization process, the features correlate with the
clinical assessments to improve precision. The autoencoder predicts the occurrence of previous missing and non-correlated inputs for maximizing the detection rate. Using the proposed framework, the maximum gains of 9.22% in accuracy, 9.29% in detection, and 7.96% in recommendations. |
|---|