{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/53424"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/53424","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Active Feature Acquisition for efficient & transparent medical diagnoses","abstract":"In many real-world machine learning scenarios, such as clinical diagnostics, input features are acquired sequentially and selectively, due to practical constraints like cost and time. This necessitates accurate predictions from partially observed data and the strategic selection of informative features. Active Feature Acquisition (AFA), also referred to as Dynamic Feature Selection (DFS), addresses this challenge by dynamically determining which features to acquire at each step. We propose three novel methodologies to enhance the performance and robustness of Active Feature Acquisition (AFA) frameworks. First, we introduce a feature imputation strategy that supplies imputed values for unobserved features during the estimation of conditional mutual information (CMI), serving as a heuristic to support more informed acquisition decisions by approximating missing feature values. Second, we develop a non-greedy acquisition mechanism that leverages the predicted discounted cumulative CMI to forecast the value of future acquisitions, allowing for more strategic and forward-looking feature selection. Finally, we present an ensemble acquisition policy that trains multiple policies and averages their outputs, thereby improving the robustness, stability, and generalization of the feature selection process across different datasets and tasks. Empirical evaluations show that these strategies significantly enhance both acquisition efficiency and predictive accuracy.","abstract_html":"In many real-world machine learning scenarios, such as clinical diagnostics, input features are acquired sequentially and selectively, due to practical constraints like cost and time. This necessitates accurate predictions from partially observed data and the strategic selection of informative features. Active Feature Acquisition (AFA), also referred to as Dynamic Feature Selection (DFS), addresses this challenge by dynamically determining which features to acquire at each step. We propose three novel methodologies to enhance the performance and robustness of Active Feature Acquisition (AFA) frameworks. First, we introduce a feature imputation strategy that supplies imputed values for unobserved features during the estimation of conditional mutual information (CMI), serving as a heuristic to support more informed acquisition decisions by approximating missing feature values. Second, we develop a non-greedy acquisition mechanism that leverages the predicted discounted cumulative CMI to forecast the value of future acquisitions, allowing for more strategic and forward-looking feature selection. Finally, we present an ensemble acquisition policy that trains multiple policies and averages their outputs, thereby improving the robustness, stability, and generalization of the feature selection process across different datasets and tasks. Empirical evaluations show that these strategies significantly enhance both acquisition efficiency and predictive accuracy.","abstract_has_math":false,"creators":["Saichandran, Ketan Suhaas"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Kolachalama, Vijaya B."],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-19T02:42:12Z","subjects":["Artificial intelligence","Computer science","Active Feature Acquisition","Active learning","Information theory","Online Learning","Reinforcement learning","Sequential decision making"],"languages":["en_US"],"rights":["Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[],"person_identifier_entries":[{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0000-3319-9974"],"render_values":[{"text":"0009-0000-3319-9974","href":"https://orcid.org/0009-0000-3319-9974","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2144/53424","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/53424","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://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F53424","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kolachalama, Vijaya B."]},{"key":"dc:creator","label":"Author","values":["Saichandran, Ketan Suhaas"]},{"key":"dc:identifier.orcid","label":"ORCID","values":["0009-0000-3319-9974"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-07-31T17:50:51Z"]},{"key":"dc:date.embargo","label":"Dc Date Embargo","values":["2027-07-22T00:00:00Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2026-07-22T22:15:35Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence","Computer science","Active Feature Acquisition","Active learning","Information theory","Online Learning","Reinforcement learning","Sequential decision making"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/53424"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["In many real-world machine learning scenarios, such as clinical diagnostics, input features are acquired sequentially and selectively, due to practical constraints like cost and time. This necessitates accurate predictions from partially observed data and the strategic selection of informative features. Active Feature Acquisition (AFA), also referred to as Dynamic Feature Selection (DFS), addresses this challenge by dynamically determining which features to acquire at each step. We propose three novel methodologies to enhance the performance and robustness of Active Feature Acquisition (AFA) frameworks. First, we introduce a feature imputation strategy that supplies imputed values for unobserved features during the estimation of conditional mutual information (CMI), serving as a heuristic to support more informed acquisition decisions by approximating missing feature values. Second, we develop a non-greedy acquisition mechanism that leverages the predicted discounted cumulative CMI to forecast the value of future acquisitions, allowing for more strategic and forward-looking feature selection. Finally, we present an ensemble acquisition policy that trains multiple policies and averages their outputs, thereby improving the robustness, stability, and generalization of the feature selection process across different datasets and tasks. Empirical evaluations show that these strategies significantly enhance both acquisition efficiency and predictive accuracy."]},{"key":"dc:title","label":"Title","values":["Active Feature Acquisition for efficient & transparent medical diagnoses"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kolachalama, Vijaya B."],"dc:creator":["Saichandran, Ketan Suhaas"],"dc:date.accessioned":["2026-07-31T17:50:51Z"],"dc:date.embargo":["2027-07-22T00:00:00Z"],"dc:date.issued":["2025"],"dc:date.updated":["2026-07-22T22:15:35Z"],"dc:description":["2025"],"dc:description.abstract":["In many real-world machine learning scenarios, such as clinical diagnostics, input features are acquired sequentially and selectively, due to practical constraints like cost and time. This necessitates accurate predictions from partially observed data and the strategic selection of informative features. Active Feature Acquisition (AFA), also referred to as Dynamic Feature Selection (DFS), addresses this challenge by dynamically determining which features to acquire at each step. We propose three novel methodologies to enhance the performance and robustness of Active Feature Acquisition (AFA) frameworks. First, we introduce a feature imputation strategy that supplies imputed values for unobserved features during the estimation of conditional mutual information (CMI), serving as a heuristic to support more informed acquisition decisions by approximating missing feature values. Second, we develop a non-greedy acquisition mechanism that leverages the predicted discounted cumulative CMI to forecast the value of future acquisitions, allowing for more strategic and forward-looking feature selection. Finally, we present an ensemble acquisition policy that trains multiple policies and averages their outputs, thereby improving the robustness, stability, and generalization of the feature selection process across different datasets and tasks. Empirical evaluations show that these strategies significantly enhance both acquisition efficiency and predictive accuracy."],"dc:identifier.orcid":["0009-0000-3319-9974"],"dc:identifier.uri":["https://hdl.handle.net/2144/53424"],"dc:language.iso":["en_US"],"dc:rights":["Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Artificial intelligence","Computer science","Active Feature Acquisition","Active learning","Information theory","Online Learning","Reinforcement learning","Sequential decision making"],"dc:title":["Active Feature Acquisition for efficient & transparent medical diagnoses"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-19T02:42:12Z"}