Metabolite-disease association prediction algorithm combining DeepWalk and random forest

Tie, Jiaojiao; Lei, Xiujuan; Pan, Yi

doi:10.26599/tst.2021.9010003

Cited by 22 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As depicted in Figure 3, RF algorithms are a collection of different classifiers created by mixing decision trees. Its decision tree structures are created from that level of unpredictability, which is a particularly significant feature of certain Ensembles of Classifiers [16], [17]. Depending on this concept, RF is often described as a general rule for randomized decision tree ensembles.…”

Section: ░ 4 Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Nair

Devi

Bhasi

2022

IJEER

View full text Add to dashboard Cite

One of the most serious and deadly diseases in the world is lung cancer. On the other hand, prompt diagnosis, as well as care, could save lives. Probably the most capable imaging method in the medical world, computed tomography (CT) scans are challenging for clinicians to analyze as well as detect cancer. In recent years, there has been an increase in the use of image analysis techniques for the detection of CT scan images matching cancer tissues. Using a Computer-aided detection (CAD) system employing CT scans to aid inside the early lung cancer diagnosis as well as to differentiate among benign/malignant tumors is thus interesting to address. The primary objective of this study would be to assess several computer-aided approaches, analyze the right methodology already in use, and afterward propose a new approach that integrates enhancements to the best system currently in use. This research improves the performance of the existing retrieval system by combining various image feature extraction processes and modifying the internal layer section of the classifier. The segmentation method proposed here to identify cancer is Improved Random Walker segmentation along with Random Forest (RF) classifier and K-Nearest Neighbors (KNN) classifier. Here, the research is accomplished on the Lung Image database consortium (LIDC) datasets which is a collection of CT images and is utilized as the input images to verify the effectiveness of the suggested strategy. The accuracy of the proposed method for the detection of lung cancer with the aid of the RF classifier is 99.6 % as well as the KNN classifier is 96.4% accordingly.

show abstract

Section: ░ 4 Results and Discussionmentioning

confidence: 99%

“…A specific amount of points, as well as edges, may make up the images according to the random walk (RW) theory [16].…”

Section: Image Segmentation Algorithm Based On Random Walkmentioning

confidence: 99%

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Nair

Devi

Bhasi

2022

IJEER

View full text Add to dashboard Cite

show abstract

“…demonstrates the comparative results between the ground-truth density maps and output density maps. Fivefold cross-validation [35,36] is utilized for the RefNet evaluation on our proposed epithelial cell dataset to illustrate the counting performance on the whole dataset. The dataset is divided into five groups according to the serial number of images.…”

Section: Epithelial Cell Datasetmentioning

confidence: 99%

Object Counting Using a Refinement Network

Sun

Jing

2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

To address the scale variance and uneven distribution of objects in scenarios of object-counting tasks, an algorithm called Refinement Network (RefNet) is exploited. The proposed top-down scheme sequentially aggregates multiscale features, which are laterally connected with low-level information. Trained by a multiresolution density regression loss, a set of intermediate-density maps are estimated on each scale in a multiscale feature pyramid, and the detailed information of the density map is gradually added through coarse-to-fine granular refinement progress to predict the final density map. We evaluate our RefNet on three crowd-counting benchmark datasets, namely, ShanghaiTech, UCF CC 50, and UCSD, and our method achieves competitive performances on the mean absolute error and root mean squared error compared to the state-of-the-art approaches. We further extend our RefNet to cell counting, illustrating its effectiveness on relative counting tasks.

show abstract

“…e study of cost prediction tasks is becoming more widespread, and one of the widely used methods for health care cost prediction is the regression-based model [22,23]. To avoid the requirement of general linear models for data to follow a normal distribution, Moran et al performed prediction using generalized linear models [16].…”

Section: Related Workmentioning

confidence: 99%

Explainable and Personalized Medical Cost Prediction Based on Multitask Learning over Mobile Devices

Sun

Wang

Hui

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

Currently, the forecasting of healthcare costs is of significant importance for the finance management of both government and individual citizens. However, the existence of dramatic individual diversity in health status, as well as the extensive complexity of the factors influencing the cost, has made the prediction a challenging task. Thanks to the unprecedented adoption of mobile devices, regular individuals may contribute diverse dimensions of data for the medical cost prediction. Hospitals and healthcare service providers are all setting up their own mobile services and collect user data for analysis. Previous methods usually employed traditional machine learning or simple neural network methods, which are difficult to be applied to the nonlinear medical cost and diverse dimensions of data. Therefore, this paper proposes a multitask learning-based framework for interpretable medical cost interval prediction to address these issues. The framework proposed in this paper first predicts subcost intervals by applying the multidimensional data collected from mobile ends and following the multitask learning paradigm. The total cost interval is then predicted based on this prediction. Simultaneously, the framework derives a decision tree from the parameters of the multitask learning network and calculates the importance of each feature in predicting the cost intervals. This paper demonstrates the method's effectiveness using real-world data experiments.

show abstract

Metabolite-disease association prediction algorithm combining DeepWalk and random forest

Cited by 22 publications

References 24 publications

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Object Counting Using a Refinement Network

Explainable and Personalized Medical Cost Prediction Based on Multitask Learning over Mobile Devices

Contact Info

Product

Resources

About