Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management
INTRODUCTION:Recurrent cancer is common, costly, and lethal, yet we know little about it in community-based populations. Electronic health records and tumor registries contain vast amounts of data regarding community-based patients, but usually lack recurrence status. Existing algorithms that use st...
Gespeichert in:
| Veröffentlicht in: | Medical care 2017-12, Vol.55 (12), p.e88-e98 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | e98 |
|---|---|
| container_issue | 12 |
| container_start_page | e88 |
| container_title | Medical care |
| container_volume | 55 |
| creator | Hassett, Michael J. Uno, Hajime Cronin, Angel M. Carroll, Nikki M. Hornbrook, Mark C. Ritzwoller, Debra |
| description | INTRODUCTION:Recurrent cancer is common, costly, and lethal, yet we know little about it in community-based populations. Electronic health records and tumor registries contain vast amounts of data regarding community-based patients, but usually lack recurrence status. Existing algorithms that use structured data to detect recurrence have limitations.
METHODS:We developed algorithms to detect the presence and timing of recurrence after definitive therapy for stages I–III lung and colorectal cancer using 2 data sources that contain a widely available type of structured data (claims or electronic health record encounters) linked to gold-standard recurrence statusMedicare claims linked to the Cancer Care Outcomes Research and Surveillance study, and the Cancer Research Network Virtual Data Warehouse linked to registry data. Twelve potential indicators of recurrence were used to develop separate models for each cancer in each data source. Detection models maximized area under the ROC curve (AUC); timing models minimized average absolute error. Algorithms were compared by cancer type/data source, and contrasted with an existing binary detection rule.
RESULTS:Detection model AUCs (>0.92) exceeded existing prediction rules. Timing models yielded absolute prediction errors that were small relative to follow-up time ( |
| doi_str_mv | 10.1097/MLR.0000000000000404 |
| format | Article |
| fullrecord | <record><control><sourceid>jstor_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_4732933</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>26418501</jstor_id><sourcerecordid>26418501</sourcerecordid><originalsourceid>FETCH-LOGICAL-c5035-a47fe52736e3a7399dd549459046e4c8f83242a72394ff265e3b3f26e32544ef3</originalsourceid><addsrcrecordid>eNpdUttuEzEQtRCIhsAfAFqJF1629XW9fkGq0kKRUhUV-mw5zmyywbsOvrTiV_ha3KS0pZbsGdtnzsz4GKG3BB8SrOTR-fzyED8eHPNnaEIEkzVRvH2OJhhTUUss1QF6FeMGYyKZoC_RAVWECSnJBP05gQQ29eOqmueymHFZzbzzoRwaV83MaCFUl2BzCFD86ireYr-nkG3KAQra9WNvjTs6Xg7FiymY1F9DdWKSqZKvTkezcFBd5GT9ALFwRTDBrnepvvltdgXvx-oMjEvr6tyMZgUDjOk1etEZF-HNnZ2iq8-nP2Zn9fziy9fZ8by2AjNRGy47EFSyBpiRTKnlUnDFhcK8AW7brmWUUyMpU7zraCOALVixwKjgHDo2RZ_2vNu8GGBpS-pgnN6GfjDht_am1__fjP1ar_y15pJRxVgh-HhHEPyvDDHpoY8WnDMj-Bw1UQ2XGMtSwhR9eALd-BzG0l5BtVgpzlRbUHyPssHHGKC7L4ZgfSu-LuLrp-KXsPePG7kP-qf2A--NdwlC_OnyDQS93r38jk80Ate0_BNCy64us_ynKXq3D9vE5MMDbcNJKzBhfwFY4MVY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1980994398</pqid></control><display><type>article</type><title>Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management</title><source>Jstor Complete Legacy</source><source>MEDLINE</source><source>Journals@Ovid Complete</source><creator>Hassett, Michael J. ; Uno, Hajime ; Cronin, Angel M. ; Carroll, Nikki M. ; Hornbrook, Mark C. ; Ritzwoller, Debra</creator><creatorcontrib>Hassett, Michael J. ; Uno, Hajime ; Cronin, Angel M. ; Carroll, Nikki M. ; Hornbrook, Mark C. ; Ritzwoller, Debra</creatorcontrib><description>INTRODUCTION:Recurrent cancer is common, costly, and lethal, yet we know little about it in community-based populations. Electronic health records and tumor registries contain vast amounts of data regarding community-based patients, but usually lack recurrence status. Existing algorithms that use structured data to detect recurrence have limitations.
METHODS:We developed algorithms to detect the presence and timing of recurrence after definitive therapy for stages I–III lung and colorectal cancer using 2 data sources that contain a widely available type of structured data (claims or electronic health record encounters) linked to gold-standard recurrence statusMedicare claims linked to the Cancer Care Outcomes Research and Surveillance study, and the Cancer Research Network Virtual Data Warehouse linked to registry data. Twelve potential indicators of recurrence were used to develop separate models for each cancer in each data source. Detection models maximized area under the ROC curve (AUC); timing models minimized average absolute error. Algorithms were compared by cancer type/data source, and contrasted with an existing binary detection rule.
RESULTS:Detection model AUCs (>0.92) exceeded existing prediction rules. Timing models yielded absolute prediction errors that were small relative to follow-up time (<15%). Similar covariates were included in all detection and timing algorithms, though differences by cancer type and dataset challenged efforts to create 1 common algorithm for all scenarios.
CONCLUSIONS:Valid and reliable detection of recurrence using big data is feasible. These tools will enable extensive, novel research on quality, effectiveness, and outcomes for lung and colorectal cancer patients and those who develop recurrence.</description><identifier>ISSN: 0025-7079</identifier><identifier>EISSN: 1537-1948</identifier><identifier>DOI: 10.1097/MLR.0000000000000404</identifier><identifier>PMID: 29135771</identifier><language>eng</language><publisher>United States: Wolters Kluwer Health, Inc</publisher><subject>Adult ; Aged ; Algorithms ; Applied Methods ; Cancer ; Clinical Coding ; Colorectal cancer ; Colorectal carcinoma ; Colorectal Neoplasms - diagnosis ; Colorectal Neoplasms - epidemiology ; Communities ; Data management ; Data warehouses ; Electronic health records ; Electronic medical records ; Female ; Government programs ; Health care ; Health Status Indicators ; Humans ; Lung cancer ; Lung Neoplasms - diagnosis ; Lung Neoplasms - epidemiology ; Male ; Mathematical models ; Middle Aged ; Neoplasm Recurrence, Local - diagnosis ; Neoplasm Recurrence, Local - epidemiology ; Neoplasm Staging ; Outcome Assessment, Health Care ; Patient Care Management - organization & administration ; Patients ; Reproducibility of Results ; United States</subject><ispartof>Medical care, 2017-12, Vol.55 (12), p.e88-e98</ispartof><rights>Copyright © 2015 Wolters Kluwer Health, Inc.</rights><rights>Copyright © 2017 Wolters Kluwer Health, Inc. All rights reserved.</rights><rights>Copyright Lippincott Williams & Wilkins Ovid Technologies Dec 2017</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c5035-a47fe52736e3a7399dd549459046e4c8f83242a72394ff265e3b3f26e32544ef3</citedby><cites>FETCH-LOGICAL-c5035-a47fe52736e3a7399dd549459046e4c8f83242a72394ff265e3b3f26e32544ef3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/26418501$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/26418501$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>230,314,776,780,799,881,27901,27902,57992,58225</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29135771$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Hassett, Michael J.</creatorcontrib><creatorcontrib>Uno, Hajime</creatorcontrib><creatorcontrib>Cronin, Angel M.</creatorcontrib><creatorcontrib>Carroll, Nikki M.</creatorcontrib><creatorcontrib>Hornbrook, Mark C.</creatorcontrib><creatorcontrib>Ritzwoller, Debra</creatorcontrib><title>Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management</title><title>Medical care</title><addtitle>Med Care</addtitle><description>INTRODUCTION:Recurrent cancer is common, costly, and lethal, yet we know little about it in community-based populations. Electronic health records and tumor registries contain vast amounts of data regarding community-based patients, but usually lack recurrence status. Existing algorithms that use structured data to detect recurrence have limitations.
METHODS:We developed algorithms to detect the presence and timing of recurrence after definitive therapy for stages I–III lung and colorectal cancer using 2 data sources that contain a widely available type of structured data (claims or electronic health record encounters) linked to gold-standard recurrence statusMedicare claims linked to the Cancer Care Outcomes Research and Surveillance study, and the Cancer Research Network Virtual Data Warehouse linked to registry data. Twelve potential indicators of recurrence were used to develop separate models for each cancer in each data source. Detection models maximized area under the ROC curve (AUC); timing models minimized average absolute error. Algorithms were compared by cancer type/data source, and contrasted with an existing binary detection rule.
RESULTS:Detection model AUCs (>0.92) exceeded existing prediction rules. Timing models yielded absolute prediction errors that were small relative to follow-up time (<15%). Similar covariates were included in all detection and timing algorithms, though differences by cancer type and dataset challenged efforts to create 1 common algorithm for all scenarios.
CONCLUSIONS:Valid and reliable detection of recurrence using big data is feasible. These tools will enable extensive, novel research on quality, effectiveness, and outcomes for lung and colorectal cancer patients and those who develop recurrence.</description><subject>Adult</subject><subject>Aged</subject><subject>Algorithms</subject><subject>Applied Methods</subject><subject>Cancer</subject><subject>Clinical Coding</subject><subject>Colorectal cancer</subject><subject>Colorectal carcinoma</subject><subject>Colorectal Neoplasms - diagnosis</subject><subject>Colorectal Neoplasms - epidemiology</subject><subject>Communities</subject><subject>Data management</subject><subject>Data warehouses</subject><subject>Electronic health records</subject><subject>Electronic medical records</subject><subject>Female</subject><subject>Government programs</subject><subject>Health care</subject><subject>Health Status Indicators</subject><subject>Humans</subject><subject>Lung cancer</subject><subject>Lung Neoplasms - diagnosis</subject><subject>Lung Neoplasms - epidemiology</subject><subject>Male</subject><subject>Mathematical models</subject><subject>Middle Aged</subject><subject>Neoplasm Recurrence, Local - diagnosis</subject><subject>Neoplasm Recurrence, Local - epidemiology</subject><subject>Neoplasm Staging</subject><subject>Outcome Assessment, Health Care</subject><subject>Patient Care Management - organization & administration</subject><subject>Patients</subject><subject>Reproducibility of Results</subject><subject>United States</subject><issn>0025-7079</issn><issn>1537-1948</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpdUttuEzEQtRCIhsAfAFqJF1629XW9fkGq0kKRUhUV-mw5zmyywbsOvrTiV_ha3KS0pZbsGdtnzsz4GKG3BB8SrOTR-fzyED8eHPNnaEIEkzVRvH2OJhhTUUss1QF6FeMGYyKZoC_RAVWECSnJBP05gQQ29eOqmueymHFZzbzzoRwaV83MaCFUl2BzCFD86ireYr-nkG3KAQra9WNvjTs6Xg7FiymY1F9DdWKSqZKvTkezcFBd5GT9ALFwRTDBrnepvvltdgXvx-oMjEvr6tyMZgUDjOk1etEZF-HNnZ2iq8-nP2Zn9fziy9fZ8by2AjNRGy47EFSyBpiRTKnlUnDFhcK8AW7brmWUUyMpU7zraCOALVixwKjgHDo2RZ_2vNu8GGBpS-pgnN6GfjDht_am1__fjP1ar_y15pJRxVgh-HhHEPyvDDHpoY8WnDMj-Bw1UQ2XGMtSwhR9eALd-BzG0l5BtVgpzlRbUHyPssHHGKC7L4ZgfSu-LuLrp-KXsPePG7kP-qf2A--NdwlC_OnyDQS93r38jk80Ate0_BNCy64us_ynKXq3D9vE5MMDbcNJKzBhfwFY4MVY</recordid><startdate>201712</startdate><enddate>201712</enddate><creator>Hassett, Michael J.</creator><creator>Uno, Hajime</creator><creator>Cronin, Angel M.</creator><creator>Carroll, Nikki M.</creator><creator>Hornbrook, Mark C.</creator><creator>Ritzwoller, Debra</creator><general>Wolters Kluwer Health, Inc</general><general>Copyright Wolters Kluwer Health, Inc. All rights reserved</general><general>Lippincott Williams & Wilkins Ovid Technologies</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>K9.</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>201712</creationdate><title>Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management</title><author>Hassett, Michael J. ; Uno, Hajime ; Cronin, Angel M. ; Carroll, Nikki M. ; Hornbrook, Mark C. ; Ritzwoller, Debra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c5035-a47fe52736e3a7399dd549459046e4c8f83242a72394ff265e3b3f26e32544ef3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Algorithms</topic><topic>Applied Methods</topic><topic>Cancer</topic><topic>Clinical Coding</topic><topic>Colorectal cancer</topic><topic>Colorectal carcinoma</topic><topic>Colorectal Neoplasms - diagnosis</topic><topic>Colorectal Neoplasms - epidemiology</topic><topic>Communities</topic><topic>Data management</topic><topic>Data warehouses</topic><topic>Electronic health records</topic><topic>Electronic medical records</topic><topic>Female</topic><topic>Government programs</topic><topic>Health care</topic><topic>Health Status Indicators</topic><topic>Humans</topic><topic>Lung cancer</topic><topic>Lung Neoplasms - diagnosis</topic><topic>Lung Neoplasms - epidemiology</topic><topic>Male</topic><topic>Mathematical models</topic><topic>Middle Aged</topic><topic>Neoplasm Recurrence, Local - diagnosis</topic><topic>Neoplasm Recurrence, Local - epidemiology</topic><topic>Neoplasm Staging</topic><topic>Outcome Assessment, Health Care</topic><topic>Patient Care Management - organization & administration</topic><topic>Patients</topic><topic>Reproducibility of Results</topic><topic>United States</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hassett, Michael J.</creatorcontrib><creatorcontrib>Uno, Hajime</creatorcontrib><creatorcontrib>Cronin, Angel M.</creatorcontrib><creatorcontrib>Carroll, Nikki M.</creatorcontrib><creatorcontrib>Hornbrook, Mark C.</creatorcontrib><creatorcontrib>Ritzwoller, Debra</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Medical care</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hassett, Michael J.</au><au>Uno, Hajime</au><au>Cronin, Angel M.</au><au>Carroll, Nikki M.</au><au>Hornbrook, Mark C.</au><au>Ritzwoller, Debra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management</atitle><jtitle>Medical care</jtitle><addtitle>Med Care</addtitle><date>2017-12</date><risdate>2017</risdate><volume>55</volume><issue>12</issue><spage>e88</spage><epage>e98</epage><pages>e88-e98</pages><issn>0025-7079</issn><eissn>1537-1948</eissn><abstract>INTRODUCTION:Recurrent cancer is common, costly, and lethal, yet we know little about it in community-based populations. Electronic health records and tumor registries contain vast amounts of data regarding community-based patients, but usually lack recurrence status. Existing algorithms that use structured data to detect recurrence have limitations.
METHODS:We developed algorithms to detect the presence and timing of recurrence after definitive therapy for stages I–III lung and colorectal cancer using 2 data sources that contain a widely available type of structured data (claims or electronic health record encounters) linked to gold-standard recurrence statusMedicare claims linked to the Cancer Care Outcomes Research and Surveillance study, and the Cancer Research Network Virtual Data Warehouse linked to registry data. Twelve potential indicators of recurrence were used to develop separate models for each cancer in each data source. Detection models maximized area under the ROC curve (AUC); timing models minimized average absolute error. Algorithms were compared by cancer type/data source, and contrasted with an existing binary detection rule.
RESULTS:Detection model AUCs (>0.92) exceeded existing prediction rules. Timing models yielded absolute prediction errors that were small relative to follow-up time (<15%). Similar covariates were included in all detection and timing algorithms, though differences by cancer type and dataset challenged efforts to create 1 common algorithm for all scenarios.
CONCLUSIONS:Valid and reliable detection of recurrence using big data is feasible. These tools will enable extensive, novel research on quality, effectiveness, and outcomes for lung and colorectal cancer patients and those who develop recurrence.</abstract><cop>United States</cop><pub>Wolters Kluwer Health, Inc</pub><pmid>29135771</pmid><doi>10.1097/MLR.0000000000000404</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0025-7079 |
| ispartof | Medical care, 2017-12, Vol.55 (12), p.e88-e98 |
| issn | 0025-7079 1537-1948 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_4732933 |
| source | Jstor Complete Legacy; MEDLINE; Journals@Ovid Complete |
| subjects | Adult Aged Algorithms Applied Methods Cancer Clinical Coding Colorectal cancer Colorectal carcinoma Colorectal Neoplasms - diagnosis Colorectal Neoplasms - epidemiology Communities Data management Data warehouses Electronic health records Electronic medical records Female Government programs Health care Health Status Indicators Humans Lung cancer Lung Neoplasms - diagnosis Lung Neoplasms - epidemiology Male Mathematical models Middle Aged Neoplasm Recurrence, Local - diagnosis Neoplasm Recurrence, Local - epidemiology Neoplasm Staging Outcome Assessment, Health Care Patient Care Management - organization & administration Patients Reproducibility of Results United States |
| title | Detecting Lung and Colorectal Cancer Recurrence Using Structured Clinical/Administrative Data to Enable Outcomes Research and Population Health Management |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T04%3A22%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Detecting%20Lung%20and%20Colorectal%20Cancer%20Recurrence%20Using%20Structured%20Clinical/Administrative%20Data%20to%20Enable%20Outcomes%20Research%20and%20Population%20Health%20Management&rft.jtitle=Medical%20care&rft.au=Hassett,%20Michael%20J.&rft.date=2017-12&rft.volume=55&rft.issue=12&rft.spage=e88&rft.epage=e98&rft.pages=e88-e98&rft.issn=0025-7079&rft.eissn=1537-1948&rft_id=info:doi/10.1097/MLR.0000000000000404&rft_dat=%3Cjstor_pubme%3E26418501%3C/jstor_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1980994398&rft_id=info:pmid/29135771&rft_jstor_id=26418501&rfr_iscdi=true |