Limits...
Dimensionality Reduction in Complex Medical Data: Improved Self-Adaptive Niche Genetic Algorithm.

Zhu M, Xia J, Yan M, Cai G, Yan J, Ning G - Comput Math Methods Med (2015)

Bottom Line: High-dimensional clinical data will increase the complexity of classification, which is often utilized in the models, and thus reduce efficiency.The INGA was verified in a stratification model for sepsis patients.The results show that, by applying INGA, the feature dimensionality of datasets was reduced from 77 to 10 and that the model achieved an accuracy of 92% in predicting 28-day death in sepsis patients, which is significantly higher than other methods.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Zhejiang University, 38 Zheda Road, Hangzhou, Zhejiang 310027, China ; Guizhou Key Laboratory of Agricultural Bioengineering, Guizhou University, Guiyang, Guizhou 550025, China.

ABSTRACT
With the development of medical technology, more and more parameters are produced to describe the human physiological condition, forming high-dimensional clinical datasets. In clinical analysis, data are commonly utilized to establish mathematical models and carry out classification. High-dimensional clinical data will increase the complexity of classification, which is often utilized in the models, and thus reduce efficiency. The Niche Genetic Algorithm (NGA) is an excellent algorithm for dimensionality reduction. However, in the conventional NGA, the niche distance parameter is set in advance, which prevents it from adjusting to the environment. In this paper, an Improved Niche Genetic Algorithm (INGA) is introduced. It employs a self-adaptive niche-culling operation in the construction of the niche environment to improve the population diversity and prevent local optimal solutions. The INGA was verified in a stratification model for sepsis patients. The results show that, by applying INGA, the feature dimensionality of datasets was reduced from 77 to 10 and that the model achieved an accuracy of 92% in predicting 28-day death in sepsis patients, which is significantly higher than other methods.

No MeSH data available.


Related in: MedlinePlus

Classification accuracy (%). (a) is the result before dimensionality reduction and (b)–(e) are the result after dimensionality reduction.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4663319&req=5

fig6: Classification accuracy (%). (a) is the result before dimensionality reduction and (b)–(e) are the result after dimensionality reduction.

Mentions: (a) Accuracy of Classification. The number of feature subsets before and after dimensionality reduction is shown in Table 3. It is shown that INGA has better control over the number of feature subsets than other dimensionality reduction methods, as a smaller number of feature subsets were obtained by INGA. However, considering the number of feature subsets alone is not enough, as the classification accuracy should be combined. The classification accuracies before and after dimensionality reduction are shown in Figure 6. It is noticed that the accuracy increased obviously after the dimensionality reduction; the highest accuracy was obtained by RF-INGA.


Dimensionality Reduction in Complex Medical Data: Improved Self-Adaptive Niche Genetic Algorithm.

Zhu M, Xia J, Yan M, Cai G, Yan J, Ning G - Comput Math Methods Med (2015)

Classification accuracy (%). (a) is the result before dimensionality reduction and (b)–(e) are the result after dimensionality reduction.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4663319&req=5

fig6: Classification accuracy (%). (a) is the result before dimensionality reduction and (b)–(e) are the result after dimensionality reduction.
Mentions: (a) Accuracy of Classification. The number of feature subsets before and after dimensionality reduction is shown in Table 3. It is shown that INGA has better control over the number of feature subsets than other dimensionality reduction methods, as a smaller number of feature subsets were obtained by INGA. However, considering the number of feature subsets alone is not enough, as the classification accuracy should be combined. The classification accuracies before and after dimensionality reduction are shown in Figure 6. It is noticed that the accuracy increased obviously after the dimensionality reduction; the highest accuracy was obtained by RF-INGA.

Bottom Line: High-dimensional clinical data will increase the complexity of classification, which is often utilized in the models, and thus reduce efficiency.The INGA was verified in a stratification model for sepsis patients.The results show that, by applying INGA, the feature dimensionality of datasets was reduced from 77 to 10 and that the model achieved an accuracy of 92% in predicting 28-day death in sepsis patients, which is significantly higher than other methods.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Zhejiang University, 38 Zheda Road, Hangzhou, Zhejiang 310027, China ; Guizhou Key Laboratory of Agricultural Bioengineering, Guizhou University, Guiyang, Guizhou 550025, China.

ABSTRACT
With the development of medical technology, more and more parameters are produced to describe the human physiological condition, forming high-dimensional clinical datasets. In clinical analysis, data are commonly utilized to establish mathematical models and carry out classification. High-dimensional clinical data will increase the complexity of classification, which is often utilized in the models, and thus reduce efficiency. The Niche Genetic Algorithm (NGA) is an excellent algorithm for dimensionality reduction. However, in the conventional NGA, the niche distance parameter is set in advance, which prevents it from adjusting to the environment. In this paper, an Improved Niche Genetic Algorithm (INGA) is introduced. It employs a self-adaptive niche-culling operation in the construction of the niche environment to improve the population diversity and prevent local optimal solutions. The INGA was verified in a stratification model for sepsis patients. The results show that, by applying INGA, the feature dimensionality of datasets was reduced from 77 to 10 and that the model achieved an accuracy of 92% in predicting 28-day death in sepsis patients, which is significantly higher than other methods.

No MeSH data available.


Related in: MedlinePlus