TY - GEN
T1 - δ-TRIMAX Method with Silhouette Coefficient on Microarray Gene Expression Data for Early Detection of Heart Failure
AU - Daeng, Wilhelmina A.N.
AU - Siswantining, Titin
AU - Bustamam, Alhadi
AU - Anki, Prasnurzaki
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Heart failure, often called congestive heart failure (CHF), is a condition where the heart cannot pump blood to meet the needs of metabolic tissues. To date, there has been a lot of research on methods of gene expression analysis to produce the information needed regarding the diagnosis and prognosis of various diseases, including heart failure. The 3-dimensional data analysis was finally brought to the context of computational biologies, such as gene-sample-time, patient-record-time, druggene-dose expression data, and so on. This 3-dimensional data is essential to help understand the complex biology and physical processes related to a disease's progress and response to stimulus/drug/therapy. δ-Trimax is a triclustering algorithm used to find a tricluster with an MSR smaller than the predetermined threshold. For determing the threshold, we use the K-means clustering algorithm with the Silhouette Method to find a threshold that can maximize the quality of the tricluster (minimum MSR accompanied by maximum tricluster volume). In this study, δ-Trimax was implemented with several scenarios in gene expression data of patients with and without PAH (Pulmonary Arterial Hypertension). PAH is a kind of symptom of heart failure disease. The low value of the Tricluster Quality Index (TQI) indicate best triclustering result. In this case, we found that the scenario with a threshold δ of 0.08156218 and produced a higher quality tricluster than the other scenarios.
AB - Heart failure, often called congestive heart failure (CHF), is a condition where the heart cannot pump blood to meet the needs of metabolic tissues. To date, there has been a lot of research on methods of gene expression analysis to produce the information needed regarding the diagnosis and prognosis of various diseases, including heart failure. The 3-dimensional data analysis was finally brought to the context of computational biologies, such as gene-sample-time, patient-record-time, druggene-dose expression data, and so on. This 3-dimensional data is essential to help understand the complex biology and physical processes related to a disease's progress and response to stimulus/drug/therapy. δ-Trimax is a triclustering algorithm used to find a tricluster with an MSR smaller than the predetermined threshold. For determing the threshold, we use the K-means clustering algorithm with the Silhouette Method to find a threshold that can maximize the quality of the tricluster (minimum MSR accompanied by maximum tricluster volume). In this study, δ-Trimax was implemented with several scenarios in gene expression data of patients with and without PAH (Pulmonary Arterial Hypertension). PAH is a kind of symptom of heart failure disease. The low value of the Tricluster Quality Index (TQI) indicate best triclustering result. In this case, we found that the scenario with a threshold δ of 0.08156218 and produced a higher quality tricluster than the other scenarios.
KW - 3D gene expression data
KW - gene-sample-time
KW - Heart failure
KW - TQI
KW - triclustering
KW - δ-trimax
UR - http://www.scopus.com/inward/record.url?scp=85145354842&partnerID=8YFLogxK
U2 - 10.1109/ICOIACT55506.2022.9971865
DO - 10.1109/ICOIACT55506.2022.9971865
M3 - Conference contribution
AN - SCOPUS:85145354842
T3 - ICOIACT 2022 - 5th International Conference on Information and Communications Technology: A New Way to Make AI Useful for Everyone in the New Normal Era, Proceeding
SP - 412
EP - 416
BT - ICOIACT 2022 - 5th International Conference on Information and Communications Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Conference on Information and Communications Technology, ICOIACT 2022
Y2 - 24 August 2022 through 25 August 2022
ER -