{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/9740"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/9740","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Improved access to large medical databases for clinical research and quality improvement","abstract":"Computerized medical databases are now commonplace in healthcare environments. Information is routinely stored for each clinical encounter, be it an inpatient, outpatient, telephone, or even computer-based interaction. In the past, the vast majority of this data concerned the demographic and financial details of the encounter; however, more and more clinically relevant content is now being collected. Along with this increased amount of available data has come promises of improve patient care, easier clinical research studies, and enhanced efficiency and quality of healthcare institutions. In part, these promises have been kept; there are examples in the literature and in real-world medical environments in which care has improved through the use of data stores. The ease by which this information is accessed, displayed, and interpreted remains a significant problem, however. In addition, current data retrieval methods do not foster user \"exploration\" of the data, and thus limit its potential. The specific aim of this thesis has been the development of a new computer application (\"Goldminer\"), which provides for enhanced data retrieval, interpretation, and analysis by authorized personnel at large medical institutions. This application also provides for patient data privacy; unique patient identifiers are not disclosed in information requests, and routine logs of Goldminer's usage are kept for analysis by hospital administrative staff. The methods used in this work included the integration and mapping of disparate data sources to one central database, followed by the implementation of a group of simple \"atomic\" queries, which insulate users from the underlying database complexity. These queries include both population-based and temporal predicates, and are combinable to allow for arbitrarily complex data retrieval. All data have personal identifiers removed before presentation to the user. Goldminer will be deployed within the hospital Intranet as a web-based \"point and click\" tool, allowing for efficient data analysis and exploration by non-programming healthcare personnel.","abstract_html":"Computerized medical databases are now commonplace in healthcare environments. Information is routinely stored for each clinical encounter, be it an inpatient, outpatient, telephone, or even computer-based interaction. In the past, the vast majority of this data concerned the demographic and financial details of the encounter; however, more and more clinically relevant content is now being collected. Along with this increased amount of available data has come promises of improve patient care, easier clinical research studies, and enhanced efficiency and quality of healthcare institutions. In part, these promises have been kept; there are examples in the literature and in real-world medical environments in which care has improved through the use of data stores. The ease by which this information is accessed, displayed, and interpreted remains a significant problem, however. In addition, current data retrieval methods do not foster user "exploration" of the data, and thus limit its potential. The specific aim of this thesis has been the development of a new computer application ("Goldminer"), which provides for enhanced data retrieval, interpretation, and analysis by authorized personnel at large medical institutions. This application also provides for patient data privacy; unique patient identifiers are not disclosed in information requests, and routine logs of Goldminer's usage are kept for analysis by hospital administrative staff. The methods used in this work included the integration and mapping of disparate data sources to one central database, followed by the implementation of a group of simple "atomic" queries, which insulate users from the underlying database complexity. These queries include both population-based and temporal predicates, and are combinable to allow for arbitrarily complex data retrieval. All data have personal identifiers removed before presentation to the user. Goldminer will be deployed within the hospital Intranet as a web-based "point and click" tool, allowing for efficient data analysis and exploration by non-programming healthcare personnel.","abstract_has_math":false,"creators":["Nigrin, Daniel J. (Daniel Joseph), 1965-"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Whitaker College of Health Sciences and Technology","school":null,"contributors":[],"advisors":["Isaac S. Kohane and Peter Szolovits."],"committee_chairs":[],"committee_members":[],"year":1999,"date_issued":"1999","date_published":"1999","updated_at":"2026-07-22T22:21:09Z","subjects":["Whitaker College of Health Sciences and Technology"],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/9740","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Isaac S. Kohane and Peter Szolovits."]},{"key":"dc:contributor.department","label":"Department","values":["Whitaker College of Health Sciences and Technology"]},{"key":"dc:creator","label":"Author","values":["Nigrin, Daniel J. (Daniel Joseph), 1965-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2005-08-19T19:50:52Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2005-08-19T19:50:52Z"]},{"key":"dc:date.issued","label":"Date","values":["1999"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Whitaker College of Health Sciences and Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/9740"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (S.M.)--Massachusetts Institute of Technology, Whitaker College of Health Sciences and Technology, 1999.","Includes bibliographical references (leaves 39-40)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Computerized medical databases are now commonplace in healthcare environments. Information is routinely stored for each clinical encounter, be it an inpatient, outpatient, telephone, or even computer-based interaction. In the past, the vast majority of this data concerned the demographic and financial details of the encounter; however, more and more clinically relevant content is now being collected. Along with this increased amount of available data has come promises of improve patient care, easier clinical research studies, and enhanced efficiency and quality of healthcare institutions. In part, these promises have been kept; there are examples in the literature and in real-world medical environments in which care has improved through the use of data stores. The ease by which this information is accessed, displayed, and interpreted remains a significant problem, however. In addition, current data retrieval methods do not foster user \"exploration\" of the data, and thus limit its potential. The specific aim of this thesis has been the development of a new computer application (\"Goldminer\"), which provides for enhanced data retrieval, interpretation, and analysis by authorized personnel at large medical institutions. This application also provides for patient data privacy; unique patient identifiers are not disclosed in information requests, and routine logs of Goldminer's usage are kept for analysis by hospital administrative staff. The methods used in this work included the integration and mapping of disparate data sources to one central database, followed by the implementation of a group of simple \"atomic\" queries, which insulate users from the underlying database complexity. These queries include both population-based and temporal predicates, and are combinable to allow for arbitrarily complex data retrieval. All data have personal identifiers removed before presentation to the user. Goldminer will be deployed within the hospital Intranet as a web-based \"point and click\" tool, allowing for efficient data analysis and exploration by non-programming healthcare personnel."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Improved access to large medical databases for clinical research and quality improvement"]}]}],"canonical_facts":{"dc:contributor.advisor":["Isaac S. Kohane and Peter Szolovits."],"dc:contributor.department":["Whitaker College of Health Sciences and Technology"],"dc:creator":["Nigrin, Daniel J. (Daniel Joseph), 1965-"],"dc:date.accessioned":["2005-08-19T19:50:52Z"],"dc:date.available":["2005-08-19T19:50:52Z"],"dc:date.issued":["1999"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Whitaker College of Health Sciences and Technology, 1999.","Includes bibliographical references (leaves 39-40)."],"dc:description.abstract":["Computerized medical databases are now commonplace in healthcare environments. Information is routinely stored for each clinical encounter, be it an inpatient, outpatient, telephone, or even computer-based interaction. In the past, the vast majority of this data concerned the demographic and financial details of the encounter; however, more and more clinically relevant content is now being collected. Along with this increased amount of available data has come promises of improve patient care, easier clinical research studies, and enhanced efficiency and quality of healthcare institutions. In part, these promises have been kept; there are examples in the literature and in real-world medical environments in which care has improved through the use of data stores. The ease by which this information is accessed, displayed, and interpreted remains a significant problem, however. In addition, current data retrieval methods do not foster user \"exploration\" of the data, and thus limit its potential. The specific aim of this thesis has been the development of a new computer application (\"Goldminer\"), which provides for enhanced data retrieval, interpretation, and analysis by authorized personnel at large medical institutions. This application also provides for patient data privacy; unique patient identifiers are not disclosed in information requests, and routine logs of Goldminer's usage are kept for analysis by hospital administrative staff. The methods used in this work included the integration and mapping of disparate data sources to one central database, followed by the implementation of a group of simple \"atomic\" queries, which insulate users from the underlying database complexity. These queries include both population-based and temporal predicates, and are combinable to allow for arbitrarily complex data retrieval. All data have personal identifiers removed before presentation to the user. Goldminer will be deployed within the hospital Intranet as a web-based \"point and click\" tool, allowing for efficient data analysis and exploration by non-programming healthcare personnel."],"dc:description.degree":["S.M."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["http://hdl.handle.net/1721.1/9740"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Whitaker College of Health Sciences and Technology"],"dc:title":["Improved access to large medical databases for clinical research and quality improvement"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:09Z"}