{"doi":"10.1145/3748636.3764184","title":"Leveraging Reinforcement Learning for Maternity Care Resource Reallocation: A Case Study in Florida","abstract":"Persistent disparities in access to maternal healthcare across the United States, particularly in rural and underserved communities, have resulted in poor maternal outcomes. Traditional statistical methods, such as Quadratic Programming (QP), have been utilized for healthcare resource reallocation, but they struggle with dynamic, multi-objective geographic optimization problems. This study presents a Reinforcement Learning (RL)-based framework to optimize maternity care resource distribution. We follow the Maximal Accessible Equality Problem (MAEP), aiming to enhance spatial equality by reducing the weighted accessibility variance. We integrate the Two-Step Floating Catchment Area (2SFCA) method for measuring maternity care accessibility and leverage Proximal Policy Optimization (PPO) to dynamically reallocate obstetric facilities across counties in Florida. To account for real-world complexities, we tested our RL framework under three scenario objectives: minimizing distance, obstetric bed supply preservation, and prioritizing underserved counties. Results show the proposed framework effectively reduces accessibility variance by 31.7–49.3%. These findings highlight the potential of RL in offering scalable, data-driven solutions to support equitable maternity health care, benefiting practical applications for implementing actionable health policy decision making.","journal":null,"year":2025,"id":586308,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9468,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1326633,"name":"Yuhao Kang","orcid":"0000-0003-3810-9450","position":1,"is_corresponding":false},{"id":1500303,"name":"Hanqi Li","orcid":"0000-0002-9208-8470","position":2,"is_corresponding":false},{"id":1500304,"name":"Shiqi Wang","orcid":"0009-0001-4333-5463","position":3,"is_corresponding":false},{"id":1500305,"name":"Bing Zhou","orcid":"0000-0003-1106-1370","position":4,"is_corresponding":false},{"id":393072,"name":"Fahui Wang","orcid":"0000-0001-7765-3024","position":5,"is_corresponding":false},{"id":353056,"name":"Peiyin Hung","orcid":"0000-0002-1529-0819","position":6,"is_corresponding":false},{"id":1500302,"name":"Andy Qin","orcid":"0009-0007-7759-8310","position":0,"is_corresponding":true}],"reference_count":4,"raw_metadata":null,"created_at":"2026-07-19T02:59:28.666390Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}