{"id":"https://openalex.org/W7128546829","doi":"https://doi.org/10.1016/j.jbi.2026.104994","title":"Learning dynamic binary treatment policies under treatment selection bias: A Conservative Q-Learning approach with representation balancing","display_name":"Learning dynamic binary treatment policies under treatment selection bias: A Conservative Q-Learning approach with representation balancing","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128546829","doi":"https://doi.org/10.1016/j.jbi.2026.104994","pmid":"https://pubmed.ncbi.nlm.nih.gov/41679676"},"language":"en","primary_location":{"id":"doi:10.1016/j.jbi.2026.104994","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.104994","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.jbi.2026.104994","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066560743","display_name":"Animesh Kumar Paul","orcid":"https://orcid.org/0000-0003-0436-8921"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Animesh Kumar Paul","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada. Electronic address: animeshk@ualberta.ca"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada. Electronic address: animeshk@ualberta.ca","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125540178","display_name":"Russell Greiner","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Russell Greiner","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada. Electronic address: rgreiner@ualberta.ca"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada. Electronic address: rgreiner@ualberta.ca","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066560743"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":{"value":2980,"currency":"USD","value_usd":2980},"apc_paid":{"value":2980,"currency":"USD","value_usd":2980},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3933121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"176","issue":null,"first_page":"104994","last_page":"104994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.6926000118255615,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.6926000118255615,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.07750000059604645,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.03970000147819519,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.7975999712944031},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6021999716758728},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5065000057220459},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47510001063346863},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.7975999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542999982833862},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6021999716758728},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.3626999855041504},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C32252159","wikidata":"https://www.wikidata.org/wiki/Q380037","display_name":"Adverse selection","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.2667999863624573}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.jbi.2026.104994","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.104994","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},{"id":"pmid:41679676","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41679676","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of biomedical informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.1016/j.jbi.2026.104994","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.104994","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1847771980","https://openalex.org/W1979366803","https://openalex.org/W1994884074","https://openalex.org/W2009187570","https://openalex.org/W2011292888","https://openalex.org/W2038146650","https://openalex.org/W2066443416","https://openalex.org/W2165612525","https://openalex.org/W2328111639","https://openalex.org/W2404401223","https://openalex.org/W2505625229","https://openalex.org/W2805002703","https://openalex.org/W2892114828","https://openalex.org/W2911933223","https://openalex.org/W2952818057","https://openalex.org/W2962685611","https://openalex.org/W3015386791","https://openalex.org/W3124658416","https://openalex.org/W3190052902","https://openalex.org/W3210383386","https://openalex.org/W4283067184","https://openalex.org/W4283645503","https://openalex.org/W4327584872","https://openalex.org/W4387249883","https://openalex.org/W4388178633","https://openalex.org/W4403117906","https://openalex.org/W4407445136","https://openalex.org/W4407977713","https://openalex.org/W4409445004","https://openalex.org/W4410765548"],"related_works":[],"abstract_inverted_index":{"Representation":[0],"balancing":[1],"materially":[2],"strengthens":[3],"conservative":[4],"offline":[5],"RL":[6],"for":[7],"DTR":[8],"learning":[9,52],"under":[10],"treatment":[11,48,57],"selection":[12,49],"bias.":[13],"By":[14],"aligning":[15],"patient":[16],"representations":[17],"without":[18],"altering":[19],"CQL's":[20],"safety":[21],"mechanics,":[22],"CQL-RB":[23],"delivers":[24],"policies":[25],"that":[26],"are":[27],"both":[28],"effective":[29],"(higher":[30],"returns)":[31],"and":[32,54],"safer":[33],"(fewer":[34],"adverse":[35],"events)":[36],"in":[37],"realistic":[38],"healthcare":[39],"simulations.":[40],"These":[41],"findings":[42],"underscore":[43],"the":[44],"importance":[45],"of":[46],"addressing":[47],"bias":[50],"when":[51],"robust":[53],"safe":[55],"dynamic":[56],"policies.":[58]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-11T00:00:00"}
