Skip to main content

Big Data, Big Impact Grant: Generating Actionable Knowledge from Complex Genomic Data for Personalised Clinical Decisions.

Project Member(s): Kennedy, P., Li, J., Catchpoole, D.

Funding or Partner Organisation: The Children's Hospital at Westmead (The Children's Hospital Westmead)
Cancer Institute NSW

Start year: 2013

Summary: How can we identify patients destined to fail with current treatments? Currently clinicians¿ group patients into symptomatically similar clusters and treat them with the same regimens. Ideally this strategy should reliably identify specific patients who are at greater risk of relapse who would then undergo more stringent therapy. To date investigators explore these groups to identify defects that characterise the group and indicate common biology to explain the group¿s behaviour. However, cancer is complex and characterised by a range of symptoms, pathological results and genetics which defy clinical groupings. Further, the complexity of human biology precludes researchers from simply discovering a single consistent defect for an entire subgroup. Improved patient outcome requires the development of approaches that lead to ¿personalised medicine¿, strategies which are tailored to benefit individual patients. Given the complexity of tumour biology as well as the genetic variations between individuals, managing therapeutic strategies on a patient by patient basis requires approaches capturing all of the important genotypic and/or phenotypic variations among patients, not just a few. By then allowing clinicians to visualise patients based on this information so that distances between patients reflect their biological similarity, a concept we call `similarity space¿, the physician will be able to compare patients which are similar based on common biology, rather than on just clinical presentation. Technologies are now used to gather the genetic variables of an individual and interrogating these large datasets need specialist approaches to make sense this data. Our ¿constructive¿ approach to develop a similarity space that grasps the ¿big picture¿ of biological relationships between patients forms the basis of a patient specific "clinical decision support system". This study specifically addresses the implementation of our proposed application within the clinic.


Garcia, JA, Pisan, Y, Tan, CT & Navarro, KF 1970, 'Assessing the Kinect's Capabilities to Perform a Time-Based Clinical Test for Fall Risk Assessment in Older People', ENTERTAINMENT COMPUTING - ICEC 2014, Springer, pp. 100-107.

Garcia, JA, Pisan, Y, Tan, CT & Navarro, KF 1970, 'Step kinnection: a hybrid clinical test for fall risk assessment in older adults.', CHI Extended Abstracts, International Conference on Human Factors in Computing Systems, ACM, Toronto, Canada, pp. 471-474.
View/Download from: Publisher's site

Tafavogh, S, Navarro, KF, Catchpoole, DR & Kennedy, PJ 2013, 'Non-parametric and integrated framework for segmenting and counting neuroblastic cells within neuroblastoma tumor images', MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, vol. 51, no. 6, pp. 645-655.
View/Download from: Publisher's site

Navarro, KF, Gay, V, Golliard, L, Johnston, B, Leijdekkers, P, Vaughan, E, Wang, X & Williams, M-A 1970, 'SocialCycle What Can a Mobile App Do To Encourage Cycling?', PROCEEDINGS OF THE 2013 38TH ANNUAL IEEE CONFERENCE ON LOCAL COMPUTER NETWORKS WORKSHOPS (LCN WORKSHOPS), IEEE Conference on Local Computer Networks, IEEE Computer Society, Sydney Australia, pp. 24-30.
View/Download from: Publisher's site

Pisan, Y, Marin, JG, Navarro, KF & Machinery, AC 1970, 'Improving Lives: Using Microsoft Kinect to Predict the Loss of Balance for Elderly Users under Cognitive Load', PROCEEDINGS OF THE 9TH AUSTRALASIAN CONFERENCE ON INTERACTIVE ENTERTAINMENT (IE 2013), Interactive Entertainment, ACM Press, Melbourne, Australia, pp. 1-4.
View/Download from: Publisher's site

Tafavogh, S, Navarro, KF, Catchpoole, DR & Kennedy, PJ 1970, 'Segmenting Neuroblastoma Tumor Images and Splitting Overlapping Cells Using Shortest Paths between Cell Contour Convex Regions.', AIME, Artificial Intelligence in Medicine in Europe, Springer, Murcia, Spain, pp. 171-175.
View/Download from: Publisher's site

Mayoh, C, Gifford, AJ, Terry, R, Lau, LMS, Wong, M, Rao, P, Shai-Hee, T, Saletta, F, Khuong-Quang, D-A, Qin, V, Mateos, MK, Meyran, D, Miller, KE, Yuksel, A, Mould, EVA, Bowen-James, R, Govender, D, Senapati, A, Zhukova, N, Omer, N, Dholaria, H, Alvaro, F, Tapp, H, Diamond, Y, Pozza, LD, Moore, AS, Nicholls, W, Gottardo, NG, McCowage, G, Hansford, JR, Khaw, S-L, Wood, PJ, Catchpoole, D, Cottrell, CE, Mardis, ER, Marshall, GM, Tyrrell, V, Haber, M, Ziegler, DS, Vittorio, O, Trapani, JA, Cowley, MJ, Neeson, PJ & Ekert, PG, 'A novel transcriptional signature identifies T-cell infiltration in high-risk paediatric cancer', Genome Medicine, vol. 15, no. 1.
View/Download from: Publisher's site

FOR Codes: Pattern Recognition and Data Mining, Cancer and Related Disorders, Bioinformatics, Bioinformatics and computational biology, Data mining and knowledge discovery, Clinical health