{"id":{"repo_id":"toronto-retro","oai_identifier":"oai:utoronto.scholaris.ca:1807/91844"},"canonical_url":"https://search.dev.ndltd.org/etd/toronto-retro/oai:utoronto.scholaris.ca:1807/91844","repository":{"repo_id":"toronto-retro","name":"University of Toronto","base_url":"https://utoronto.scholaris.ca/server/oai/request"},"display":{"title":"Supporting Transfer Time Predictions in Medical Dispatch using Visualizations of Historical Data","abstract":"Decision making in emergency medical dispatch is difficult due to the high time pressure and uncertainty faced by dispatchers. This is especially true in large-scale medical transport systems, such as Ornge in Ontario, because of the large geographical area serviced and the limited air and land ambulance resources available. Oversight agencies have highlighted the need to support patient transport time prediction for different transport options to facilitate better dispatch decisions. This dissertation proposes the use of visualizations of historical transport time data as a decision-aid to support predictions of patient transport time. Specifically, this dissertation examines whether visualizing the variability of historical data, which can help decision makers understand the uncertainty of the process, may improve transport time predictions. Historical time predictions recorded by Ornge were statistically analyzed and two field studies were conducted at Ornge. Transport time predictions were found to be an important part of the dispatch process, but they are often underestimated, and that dispatchers do not explicitly incorporate uncertainty information in their predictions, possibly due to time constraints. Based on these results, an interface and workflow for a decision-aid visualizing historical data was proposed. In order to support the design of this decision-aid, two experimental studies were conducted to examine the influence of display format and context information on prediction behavior. The experiments were based on a proposed framework, informed by the literature, for how individuals use historical data visualizations to predict values of a variable. The experimental results provided evidence that both display format and context information impact prediction behavior, however the underlying process used by the participants appeared to differ from that suggested in the proposed framework. Thus, further research is needed to improve this framework. Overall, this dissertation adds to the very limited literature on supporting medical dispatch decisions through the design of a decision-aid for transport time prediction. In addition, this dissertation provides preliminary evidence for how individuals use visualizations of historical data to generate predictions of variables and what factors may influence these predictions.","abstract_html":"Decision making in emergency medical dispatch is difficult due to the high time pressure and uncertainty faced by dispatchers. This is especially true in large-scale medical transport systems, such as Ornge in Ontario, because of the large geographical area serviced and the limited air and land ambulance resources available. Oversight agencies have highlighted the need to support patient transport time prediction for different transport options to facilitate better dispatch decisions. This dissertation proposes the use of visualizations of historical transport time data as a decision-aid to support predictions of patient transport time. Specifically, this dissertation examines whether visualizing the variability of historical data, which can help decision makers understand the uncertainty of the process, may improve transport time predictions. Historical time predictions recorded by Ornge were statistically analyzed and two field studies were conducted at Ornge. Transport time predictions were found to be an important part of the dispatch process, but they are often underestimated, and that dispatchers do not explicitly incorporate uncertainty information in their predictions, possibly due to time constraints. Based on these results, an interface and workflow for a decision-aid visualizing historical data was proposed. In order to support the design of this decision-aid, two experimental studies were conducted to examine the influence of display format and context information on prediction behavior. The experiments were based on a proposed framework, informed by the literature, for how individuals use historical data visualizations to predict values of a variable. The experimental results provided evidence that both display format and context information impact prediction behavior, however the underlying process used by the participants appeared to differ from that suggested in the proposed framework. Thus, further research is needed to improve this framework. Overall, this dissertation adds to the very limited literature on supporting medical dispatch decisions through the design of a decision-aid for transport time prediction. In addition, this dissertation provides preliminary evidence for how individuals use visualizations of historical data to generate predictions of variables and what factors may influence these predictions.","abstract_has_math":false,"creators":["Giang, Wayne Chi Wei"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Mechanical and Industrial Engineering","school":null,"contributors":[],"advisors":["Donmez, Birsen","MacDonald, Russell D"],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-11","date_published":"2018-11","updated_at":"2026-07-27T21:28:20Z","subjects":["Decision making","Decision support","Medical dispatch","Prehospital emergency care","Time prediction","Uncertainty visualizations"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1807/91844","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Donmez, Birsen","MacDonald, Russell D"]},{"key":"dc:contributor.department","label":"Department","values":["Mechanical and Industrial Engineering"]},{"key":"dc:creator","label":"Author","values":["Giang, Wayne Chi Wei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-11"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-11-17T00:01:16Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-11-17T00:01:16Z"]},{"key":"dc:date.issued","label":"Date","values":["2018-11"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Decision making","Decision support","Medical dispatch","Prehospital emergency care","Time prediction","Uncertainty visualizations"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1807/91844"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Decision making in emergency medical dispatch is difficult due to the high time pressure and uncertainty faced by dispatchers. This is especially true in large-scale medical transport systems, such as Ornge in Ontario, because of the large geographical area serviced and the limited air and land ambulance resources available. Oversight agencies have highlighted the need to support patient transport time prediction for different transport options to facilitate better dispatch decisions. This dissertation proposes the use of visualizations of historical transport time data as a decision-aid to support predictions of patient transport time. Specifically, this dissertation examines whether visualizing the variability of historical data, which can help decision makers understand the uncertainty of the process, may improve transport time predictions. Historical time predictions recorded by Ornge were statistically analyzed and two field studies were conducted at Ornge. Transport time predictions were found to be an important part of the dispatch process, but they are often underestimated, and that dispatchers do not explicitly incorporate uncertainty information in their predictions, possibly due to time constraints. Based on these results, an interface and workflow for a decision-aid visualizing historical data was proposed. In order to support the design of this decision-aid, two experimental studies were conducted to examine the influence of display format and context information on prediction behavior. The experiments were based on a proposed framework, informed by the literature, for how individuals use historical data visualizations to predict values of a variable. The experimental results provided evidence that both display format and context information impact prediction behavior, however the underlying process used by the participants appeared to differ from that suggested in the proposed framework. Thus, further research is needed to improve this framework. Overall, this dissertation adds to the very limited literature on supporting medical dispatch decisions through the design of a decision-aid for transport time prediction. In addition, this dissertation provides preliminary evidence for how individuals use visualizations of historical data to generate predictions of variables and what factors may influence these predictions."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Supporting Transfer Time Predictions in Medical Dispatch using Visualizations of Historical Data"]}]}],"canonical_facts":{"dc:contributor.advisor":["Donmez, Birsen","MacDonald, Russell D"],"dc:contributor.department":["Mechanical and Industrial Engineering"],"dc:creator":["Giang, Wayne Chi Wei"],"dc:date":["2018-11"],"dc:date.accessioned":["2018-11-17T00:01:16Z"],"dc:date.available":["2018-11-17T00:01:16Z"],"dc:date.issued":["2018-11"],"dc:description.abstract":["Decision making in emergency medical dispatch is difficult due to the high time pressure and uncertainty faced by dispatchers. This is especially true in large-scale medical transport systems, such as Ornge in Ontario, because of the large geographical area serviced and the limited air and land ambulance resources available. Oversight agencies have highlighted the need to support patient transport time prediction for different transport options to facilitate better dispatch decisions. This dissertation proposes the use of visualizations of historical transport time data as a decision-aid to support predictions of patient transport time. Specifically, this dissertation examines whether visualizing the variability of historical data, which can help decision makers understand the uncertainty of the process, may improve transport time predictions. Historical time predictions recorded by Ornge were statistically analyzed and two field studies were conducted at Ornge. Transport time predictions were found to be an important part of the dispatch process, but they are often underestimated, and that dispatchers do not explicitly incorporate uncertainty information in their predictions, possibly due to time constraints. Based on these results, an interface and workflow for a decision-aid visualizing historical data was proposed. In order to support the design of this decision-aid, two experimental studies were conducted to examine the influence of display format and context information on prediction behavior. The experiments were based on a proposed framework, informed by the literature, for how individuals use historical data visualizations to predict values of a variable. The experimental results provided evidence that both display format and context information impact prediction behavior, however the underlying process used by the participants appeared to differ from that suggested in the proposed framework. Thus, further research is needed to improve this framework. Overall, this dissertation adds to the very limited literature on supporting medical dispatch decisions through the design of a decision-aid for transport time prediction. In addition, this dissertation provides preliminary evidence for how individuals use visualizations of historical data to generate predictions of variables and what factors may influence these predictions."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1807/91844"],"dc:subject":["Decision making","Decision support","Medical dispatch","Prehospital emergency care","Time prediction","Uncertainty visualizations"],"dc:title":["Supporting Transfer Time Predictions in Medical Dispatch using Visualizations of Historical Data"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T21:28:20Z"}