Date

2017

Author

Açıkel, Cengizhan

Metadata

Show full item record

Item Usage Stats

347
views

181
downloads

Cite This

This study proposes an infrastructure with a global workflow management algorithm in order to interconnect facilities, reporting units and radiologists on a single access interface. This infrastructure is enhanced by a reporting workflow optimization algorithm (RWOA) to determine the optimum match between the inspection and radiologist in terms of experience, subspeciality, response time and workload parameters. RWOA increases the efficiency of the reporting process by decreasing access time to medical images and turnaround time of medical reports and increases the quality of medical reports. In RWOA implementation, inspection and radiologist attributes are modelled using a hierarchical ontology structure based on Digital Imaging and Communications in Medicine (DICOM) Conformance, DICOM Content Mapping Resource and World Health Organization (WHO) definitions. Attribute preferences rated by radiologists and technical experts are formed into reciprocal matrixes and weights for entities are calculated utilizing Analytic Hierarchy Process (AHP). The assignment alternatives are processed by relation-based semantic matching (RBSM) and Integer Linear Programming (ILP). The results are evaluated based on both real case applications and simulated process data in terms of subspecialty, response time and workload success rates. Results obtained using simulated data are compared with the outcomes obtained by applying Round Robin, Shortest Queue and Random distribution policies. It was concluded that RBSM gives the highest subspecialty ratings, but integrating ILP with RBSM ratings provides a better response time and workload success rate. RBSM and ILP based image delivery also prevents bandwidth, storage or hardware related stuck and latencies. When compared with a real case teleradiology application where inspection assignments were performed manually, the proposed solution was found to increase the subspecialty success rate by 13.25 %, increase the workload success rate by 34.92% and increase the response time success rate by 120%. The total response time in the real case application data was improved by 22.39%. The proposed architecture has been tested in a total of 35 hospitals, 13 primary care clinics, 3 mobile clinics, 1 reporting unit. 3.35 million inspections were archived and 14216 inspections were reported by the reporting unit. However, an organized reporting process was executed only for 6202 reports which were utilized for RWOA evaluation. The proposed architecture with RWOA is piloted to provide reporting service for 8 primary care and 3 cancer screening medical imaging centers. The piloted application is currently available at http://eradyoloji.saglik.gov.tr supported by the Governship of Public Health, Ankara, Turkey. The insfrastructure and techiniques suggested in this study can be used for or applied to teleradiology applications where the reporting service is outsourced by multiple medical centers to multiple radiology groups or individual radiologists. It is considered that the advantage of the infrastructure will be maximized in large scale applications. Financial models can also be integrated with this architecture where shorter turnaround time and high quality reports can be promoted. The cost of the reporting service per inspection is decreased while the quality of service is increased. Performance assessment, quality control and workload distribution statistics modules can be integrated on this architecture for administrative purposes.

Subject Keywords

Genomics., Data mining., Bioinformatics., Manic-depressive illness.

URI

http://etd.lib.metu.edu.tr/upload/12620901/index.pdf
https://hdl.handle.net/11511/26393

Collections

Graduate School of Informatics, Thesis