{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-3735"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-3735","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Data Mining in Large-Scale Clinical Visit Data for Rett Syndrome Patients","abstract":"Rett syndrome (RTT) is a rare neurological disorder that predominantly affects girls. Research on RTT has mostly centered around gene mutations and possibility of cure using gene therapy. In this thesis we perform the first large scale systematic study of RTT patient records. The thesis has two major goals. One is to identify behavioral groups and the other is to study the association of medications and behavior or conditions. To achieve the first goal we apply standard clustering techniques like non-negative matrix factorization and k-means. We identify behavioral groups which could be used by clinicians for formulating better treatments. For the second goal we start with the most popular existing technique, disproportionality analysis, and make necessary adaptations for our data set. We then generalize this method and suggest an alternate approach which efficiently answers which medication caused the most change in a behavior. We test both approaches and show that the medications shown to decrease seizures the most are indeed those prescribed for the same. Using this as a tool, clinicians can identify possible side effects of medications.","abstract_html":"Rett syndrome (RTT) is a rare neurological disorder that predominantly affects girls. Research on RTT has mostly centered around gene mutations and possibility of cure using gene therapy. In this thesis we perform the first large scale systematic study of RTT patient records. The thesis has two major goals. One is to identify behavioral groups and the other is to study the association of medications and behavior or conditions. To achieve the first goal we apply standard clustering techniques like non-negative matrix factorization and k-means. We identify behavioral groups which could be used by clinicians for formulating better treatments. For the second goal we start with the most popular existing technique, disproportionality analysis, and make necessary adaptations for our data set. We then generalize this method and suggest an alternate approach which efficiently answers which medication caused the most change in a behavior. We test both approaches and show that the medications shown to decrease seizures the most are indeed those prescribed for the same. Using this as a tool, clinicians can identify possible side effects of medications.","abstract_has_math":false,"creators":["Avudaiappan, Neela Saranya"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"School of Computing","degree_department":null,"school":null,"contributors":["Dr. Brian Dean, Committee Chair","Dr. Ilya Safro","Dr. Alexander Herzog"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:16:07Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/2728","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/2728","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-3735","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Brian Dean, Committee Chair","Dr. Ilya Safro","Dr. Alexander Herzog"]},{"key":"dc:creator","label":"Author","values":["Avudaiappan, Neela Saranya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2017-08-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Computing"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/2728"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Rett syndrome (RTT) is a rare neurological disorder that predominantly affects girls. Research on RTT has mostly centered around gene mutations and possibility of cure using gene therapy. In this thesis we perform the first large scale systematic study of RTT patient records. The thesis has two major goals. One is to identify behavioral groups and the other is to study the association of medications and behavior or conditions. To achieve the first goal we apply standard clustering techniques like non-negative matrix factorization and k-means. We identify behavioral groups which could be used by clinicians for formulating better treatments. For the second goal we start with the most popular existing technique, disproportionality analysis, and make necessary adaptations for our data set. We then generalize this method and suggest an alternate approach which efficiently answers which medication caused the most change in a behavior. We test both approaches and show that the medications shown to decrease seizures the most are indeed those prescribed for the same. Using this as a tool, clinicians can identify possible side effects of medications."]},{"key":"dc:title","label":"Title","values":["Data Mining in Large-Scale Clinical Visit Data for Rett Syndrome Patients"]}]}],"canonical_facts":{"dc:contributor":["Dr. Brian Dean, Committee Chair","Dr. Ilya Safro","Dr. Alexander Herzog"],"dc:creator":["Avudaiappan, Neela Saranya"],"dc:date.created":["2017-08-01T07:00:00Z"],"dc:description.abstract":["Rett syndrome (RTT) is a rare neurological disorder that predominantly affects girls. Research on RTT has mostly centered around gene mutations and possibility of cure using gene therapy. In this thesis we perform the first large scale systematic study of RTT patient records. The thesis has two major goals. One is to identify behavioral groups and the other is to study the association of medications and behavior or conditions. To achieve the first goal we apply standard clustering techniques like non-negative matrix factorization and k-means. We identify behavioral groups which could be used by clinicians for formulating better treatments. For the second goal we start with the most popular existing technique, disproportionality analysis, and make necessary adaptations for our data set. We then generalize this method and suggest an alternate approach which efficiently answers which medication caused the most change in a behavior. We test both approaches and show that the medications shown to decrease seizures the most are indeed those prescribed for the same. Using this as a tool, clinicians can identify possible side effects of medications."],"dc:identifier":["https://open.clemson.edu/all_theses/2728"],"dc:title":["Data Mining in Large-Scale Clinical Visit Data for Rett Syndrome Patients"],"thesis:degree_discipline":["School of Computing"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:16:07Z"}