{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/143802"},"canonical_url":"https://search.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/143802","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Reducing Length of Stay in Vocational Rehabilitation Through Scheduling Policies and Client Classifications","abstract":"This dissertation explores capacity planning in healthcare-based organizations with changing client mix, competency centered training and highly variable length of stay. The data for analysis is provided by a state residential vocational rehabilitation center in the Eastern U.S. The research uses artificial intelligence (AI) and supervised learning in the forms of CART analysis, logistic regression and neural network analysis to categorically classify jobs, patients, clients or customers into groups to better predict length of stay (LOS). Scheduling policies and capacity planning under changing client mix are examined through simulation modeling. The results of this research will provide a mechanism for effective resource use and capacity planning in organizations with highly variable completion times and changing environmental conditions.","abstract_html":"This dissertation explores capacity planning in healthcare-based organizations with changing client mix, competency centered training and highly variable length of stay. The data for analysis is provided by a state residential vocational rehabilitation center in the Eastern U.S. The research uses artificial intelligence (AI) and supervised learning in the forms of CART analysis, logistic regression and neural network analysis to categorically classify jobs, patients, clients or customers into groups to better predict length of stay (LOS). Scheduling policies and capacity planning under changing client mix are examined through simulation modeling. The results of this research will provide a mechanism for effective resource use and capacity planning in organizations with highly variable completion times and changing environmental conditions.","abstract_has_math":false,"creators":["Warren, Franklin Thomas"],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Business, Business Information Technology","degree_department":"Business, Business Information Technology","school":null,"contributors":[],"advisors":[],"committee_chairs":["Russell, Roberta Snead"],"committee_members":["Zobel, Christopher W.","Nottingham, Quinton J.","Deane, Jason K."],"year":2026,"date_issued":"2026-09-10","date_published":"2026-09-10","updated_at":"2026-11-18T20:18:16Z","subjects":["Keywords: healthcare","vocational rehabilitation","capacity planning","Artificial Intelligence","CART"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:47702"],"render_values":[{"text":"vt_gsexam:47702","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10919/143802","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/10919/143802","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://vtechworks.lib.vt.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Avtechworks.lib.vt.edu%3A10919%2F143802","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Russell, Roberta Snead"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Zobel, Christopher W.","Nottingham, Quinton J.","Deane, Jason K."]},{"key":"dc:contributor.department","label":"Department","values":["Business, Business Information Technology"]},{"key":"dc:creator","label":"Author","values":["Warren, Franklin Thomas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-09-11T08:00:14Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-09-11T08:00:14Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-09-10"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Business, Business Information Technology"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Keywords: healthcare","vocational rehabilitation","capacity planning","Artificial Intelligence","CART"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:47702"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/143802"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation explores capacity planning in healthcare-based organizations with changing client mix, competency centered training and highly variable length of stay. The data for analysis is provided by a state residential vocational rehabilitation center in the Eastern U.S. The research uses artificial intelligence (AI) and supervised learning in the forms of CART analysis, logistic regression and neural network analysis to categorically classify jobs, patients, clients or customers into groups to better predict length of stay (LOS). Scheduling policies and capacity planning under changing client mix are examined through simulation modeling. The results of this research will provide a mechanism for effective resource use and capacity planning in organizations with highly variable completion times and changing environmental conditions."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["This dissertation explores capacity planning in a healthcare-based organization with changing client mix, competency-centered training, and highly variable length of stay. Data for the analysis comes from a case study of a statewide vocational rehabilitation center. Classifying jobs, patients, clients or customers into groups based on characteristics and resource usage provides organizations with better predictive capabilities, facilitates capacity planning, and ultimately increases throughput and resource utilization. The first phase of this research attempts to predict length of stay (LOS) and reduce LOS variability by classifying clients into groups with similar characteristics or resource requirements. This approach is common in healthcare settings (e.g., acute care, ambulatory care and long-term care) where case-mix classifications have been used to group patients, initially for capacity planning, but ultimately for financial reimbursement from insurance companies and federal agencies such as Medicare and Medicaid (Stineman, 1995). While the approach will be similar, this study includes educational factors, vocational training and life-skills development, as well as demographics and medical factors, in the analysis. Initially we evaluated this information through different classification and regression tree analysis (CART) models. Models are developed, tested and summarized with somewhat surprising results. The second stage of research compares the best CART model with logistic regression and neural networks to better predict LOS. We determine the efficacy of each model and summarize when each model is most appropriate. While reducing LOS variability will, in effect, expand capacity, there are several other factors that impact how clients are admitted, scheduled and successfully progress through the center. Some of these factors are environmental, and others are a result of center policies or federal and state policies. The third phase of this research involves a review of the literature on capacity planning in healthcare, describes the capacity problems experienced by the vocational rehabilitation center, and built a simulation model and simulation experiment to test different scheduling policies under changing environmental conditions."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Reducing Length of Stay in Vocational Rehabilitation Through Scheduling Policies and Client Classifications"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Russell, Roberta Snead"],"dc:contributor.committeemember":["Zobel, Christopher W.","Nottingham, Quinton J.","Deane, Jason K."],"dc:contributor.department":["Business, Business Information Technology"],"dc:creator":["Warren, Franklin Thomas"],"dc:date.accessioned":["2026-09-11T08:00:14Z"],"dc:date.available":["2026-09-11T08:00:14Z"],"dc:date.issued":["2026-09-10"],"dc:description.abstract":["This dissertation explores capacity planning in healthcare-based organizations with changing client mix, competency centered training and highly variable length of stay. The data for analysis is provided by a state residential vocational rehabilitation center in the Eastern U.S. The research uses artificial intelligence (AI) and supervised learning in the forms of CART analysis, logistic regression and neural network analysis to categorically classify jobs, patients, clients or customers into groups to better predict length of stay (LOS). Scheduling policies and capacity planning under changing client mix are examined through simulation modeling. The results of this research will provide a mechanism for effective resource use and capacity planning in organizations with highly variable completion times and changing environmental conditions."],"dc:description.abstractgeneral":["This dissertation explores capacity planning in a healthcare-based organization with changing client mix, competency-centered training, and highly variable length of stay. Data for the analysis comes from a case study of a statewide vocational rehabilitation center. Classifying jobs, patients, clients or customers into groups based on characteristics and resource usage provides organizations with better predictive capabilities, facilitates capacity planning, and ultimately increases throughput and resource utilization. The first phase of this research attempts to predict length of stay (LOS) and reduce LOS variability by classifying clients into groups with similar characteristics or resource requirements. This approach is common in healthcare settings (e.g., acute care, ambulatory care and long-term care) where case-mix classifications have been used to group patients, initially for capacity planning, but ultimately for financial reimbursement from insurance companies and federal agencies such as Medicare and Medicaid (Stineman, 1995). While the approach will be similar, this study includes educational factors, vocational training and life-skills development, as well as demographics and medical factors, in the analysis. Initially we evaluated this information through different classification and regression tree analysis (CART) models. Models are developed, tested and summarized with somewhat surprising results. The second stage of research compares the best CART model with logistic regression and neural networks to better predict LOS. We determine the efficacy of each model and summarize when each model is most appropriate. While reducing LOS variability will, in effect, expand capacity, there are several other factors that impact how clients are admitted, scheduled and successfully progress through the center. Some of these factors are environmental, and others are a result of center policies or federal and state policies. The third phase of this research involves a review of the literature on capacity planning in healthcare, describes the capacity problems experienced by the vocational rehabilitation center, and built a simulation model and simulation experiment to test different scheduling policies under changing environmental conditions."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:47702"],"dc:identifier.uri":["https://hdl.handle.net/10919/143802"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Keywords: healthcare","vocational rehabilitation","capacity planning","Artificial Intelligence","CART"],"dc:title":["Reducing Length of Stay in Vocational Rehabilitation Through Scheduling Policies and Client Classifications"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Business, Business Information Technology"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-11-18T20:18:16Z"}