Sequential Data–Based Patient Similarity Framework for Patient Outcome Prediction: Algorithm Development
Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. We aimed to develop a patient similarity framework for patient outcome predict...
Saved in:
| Published in: | Journal of medical Internet research Vol. 24; no. 1; p. e30720 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Canada
Journal of Medical Internet Research
06.01.2022
Gunther Eysenbach MD MPH, Associate Professor JMIR Publications |
| Subjects: | |
| ISSN: | 1438-8871, 1439-4456, 1438-8871 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity.
We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems.
Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k-nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points-at admission, on Day 7, and at discharge-to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k-nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison.
With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission.
For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. |
|---|---|
| AbstractList | Background: Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. Objective: We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Methods: Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. Results: With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. Conclusions: For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. BackgroundSequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. ObjectiveWe aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. MethodsSequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. ResultsWith all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. ConclusionsFor patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity.BACKGROUNDSequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity.We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems.OBJECTIVEWe aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems.Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k-nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points-at admission, on Day 7, and at discharge-to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k-nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison.METHODSSequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k-nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points-at admission, on Day 7, and at discharge-to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k-nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison.With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission.RESULTSWith all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission.For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.CONCLUSIONSFor patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k-nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points-at admission, on Day 7, and at discharge-to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k-nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance. |
| Audience | Academic |
| Author | Chen, Hui Wang, Ni Zhou, Yang Wang, Muyu Liu, Honglei Fei, Xiaolu Wei, Lan |
| AuthorAffiliation | 1 School of Biomedical Engineering Capital Medical University Beijing China 4 Information Center, Xuanwu Hospital Capital Medical University Beijing China 3 Department of Epidemiology and Biostatistics Institute of Basic Medical Sciences Chinese Academy of Medical Sciences, School of Basic Medicine Peking Union Medical College Beijing China 2 Beijing Advanced Innovation Center for Big Data-based Precision Medicine Capital Medical University Beijing China |
| AuthorAffiliation_xml | – name: 4 Information Center, Xuanwu Hospital Capital Medical University Beijing China – name: 1 School of Biomedical Engineering Capital Medical University Beijing China – name: 3 Department of Epidemiology and Biostatistics Institute of Basic Medical Sciences Chinese Academy of Medical Sciences, School of Basic Medicine Peking Union Medical College Beijing China – name: 2 Beijing Advanced Innovation Center for Big Data-based Precision Medicine Capital Medical University Beijing China |
| Author_xml | – sequence: 1 givenname: Ni orcidid: 0000-0002-8941-0457 surname: Wang fullname: Wang, Ni – sequence: 2 givenname: Muyu orcidid: 0000-0002-1606-5058 surname: Wang fullname: Wang, Muyu – sequence: 3 givenname: Yang orcidid: 0000-0002-8788-0383 surname: Zhou fullname: Zhou, Yang – sequence: 4 givenname: Honglei orcidid: 0000-0001-5518-4749 surname: Liu fullname: Liu, Honglei – sequence: 5 givenname: Lan orcidid: 0000-0002-4458-3215 surname: Wei fullname: Wei, Lan – sequence: 6 givenname: Xiaolu orcidid: 0000-0001-7498-0249 surname: Fei fullname: Fei, Xiaolu – sequence: 7 givenname: Hui orcidid: 0000-0002-0048-0193 surname: Chen fullname: Chen, Hui |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34989682$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkt1uFCEYhiemxv7YWzCTGBON2QrMMIAHJmtrdZPGNlk9Jt8wsGWdGVZg-nPmPXiHXolst62dxnAA-Xi-F3h5d7Ot3vU6y_YxOiBYVO8KxAh6ku3gsuATzhneerDeznZDWCJEUCnws2y7KAUXFSc72XKufw66jxba_Agi_Pn1-yME3eRnEG2q53Pb2Ra8jdf5sYdOXzr_IzfO3wOnQ1Su0_mZ141V0br-fT5tFy61nHf5kb7QrVt1iXyePTXQBr1_O-9l348_fTv8Mjk5_Tw7nJ5MFKU8TjBVDCtOjKCiVlwJUqNalKRuWFUBLrSqS1UTqjQhRKgKa8ZxrcDUBgtqcLGXzTa6jYOlXHnbgb-WDqy8KTi_kOCjVa2WlcICA6UIU1MKykUBDeW6MdA0rEYoaX3YaK2GutONSs_w0I5Exzu9PZcLdyE5Y5xWIgm8vhXwLhkdouxsULptodduCJJUmBEmcEkS-vIRunSD75NViSIlKgQR5T9qAekBtjcunavWonLKKpI-lZdr6uA_VBqN7qxKyTE21UcNb0YNiYn6Ki5gCEHO5l_H7IuHpty7cZeqBLzdAMq7ELw2UtkI62ikW9hWYiTXmZU3mU30q0f0neCY-wtAWukj |
| CitedBy_id | crossref_primary_10_1136_bmjment_2023_300701 crossref_primary_10_2196_49138 crossref_primary_10_1016_j_jbi_2023_104427 crossref_primary_10_1093_jrsssc_qlae070 crossref_primary_10_2196_37486 crossref_primary_10_1016_j_enconman_2025_120043 crossref_primary_10_2196_68830 crossref_primary_10_1007_s12325_024_03060_z crossref_primary_10_1093_jamia_ocaf125 |
| Cites_doi | 10.1089/10665270252935511 10.1371/journal.pone.0127428 10.1109/ichi.2016.16 10.1038/s41597-019-0103-9 10.1136/bmjopen-2020-040291 10.1016/j.jbi.2018.06.001 10.1145/3230734 10.1145/3219819.3219930 10.1016/j.cmpb.2021.106040 10.1109/embc.2016.7591229 10.1016/j.jbi.2020.103518 10.1097/MLR.0b013e3181de9e17 10.1097/MLR.0000000000000315 10.1109/jbhi.2014.2358715 10.1109/tkde.2014.2309131 10.1109/tnb.2018.2837622 10.1186/s12938-019-0718-2 10.1148/radiol.2017170549 10.1007/3-540-48298-9_29 10.1186/1741-7015-11-194 10.3760/cma.j.issn.2095-4352.2018.06.006 10.1038/sdata.2016.35 10.1038/s41746-018-0029-1 10.1186/s12911-021-01432-x 10.18637/jss.v031.i07 10.1109/jbhi.2016.2633963 10.1186/s12911-020-01297-6 10.1126/scitranslmed.aaa9364 10.1016/j.ijcard.2016.11.130 10.1109/icpr.2010.1009 10.1038/s41598-017-16665-y 10.1016/j.eswa.2013.05.066 10.2196/medinform.6730 |
| ContentType | Journal Article |
| Copyright | Ni Wang, Muyu Wang, Yang Zhou, Honglei Liu, Lan Wei, Xiaolu Fei, Hui Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.01.2022. COPYRIGHT 2022 Journal of Medical Internet Research 2022. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Ni Wang, Muyu Wang, Yang Zhou, Honglei Liu, Lan Wei, Xiaolu Fei, Hui Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.01.2022. 2022 |
| Copyright_xml | – notice: Ni Wang, Muyu Wang, Yang Zhou, Honglei Liu, Lan Wei, Xiaolu Fei, Hui Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.01.2022. – notice: COPYRIGHT 2022 Journal of Medical Internet Research – notice: 2022. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Ni Wang, Muyu Wang, Yang Zhou, Honglei Liu, Lan Wei, Xiaolu Fei, Hui Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.01.2022. 2022 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM ISN 3V. 7QJ 7RV 7X7 7XB 8FI 8FJ 8FK ABUWG AFKRA ALSLI AZQEC BENPR CCPQU CNYFK DWQXO E3H F2A FYUFA GHDGH K9. KB0 M0S M1O NAPCQ PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS PRQQA 7X8 5PM DOA |
| DOI | 10.2196/30720 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Canada in Context ProQuest Central (Corporate) Applied Social Sciences Index & Abstracts (ASSIA) Nursing & Allied Health Database (ProQuest) Health & Medical Collection (ProQuest) ProQuest Central (purchase pre-March 2016) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Social Science Premium Collection ProQuest Central Essentials ProQuest Central ProQuest One Community College Library & Information Science Collection ProQuest Central Korea Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Database (Alumni Edition) ProQuest Health & Medical Collection Library Science Database (ProQuest) Nursing & Allied Health Premium ProQuest Central Premium ProQuest One Academic Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest One Social Sciences MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Open Access Full Text |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest One Academic Middle East (New) Library and Information Science Abstracts (LISA) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing Applied Social Sciences Index and Abstracts (ASSIA) ProQuest Central China ProQuest Central ProQuest Library Science ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Library & Information Science Collection ProQuest Central (New) Social Science Premium Collection ProQuest One Social Sciences ProQuest One Academic Eastern Edition ProQuest Nursing & Allied Health Source ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) Nursing & Allied Health Premium ProQuest Health & Medical Complete ProQuest One Academic UKI Edition ProQuest Nursing & Allied Health Source (Alumni) ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | Publicly Available Content Database MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7RV name: Nursing & Allied Health Database url: https://search.proquest.com/nahs sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Library & Information Science |
| EISSN | 1438-8871 |
| ExternalDocumentID | oai_doaj_org_article_6c191a55015f495893ad58edfadd7b00 PMC8778569 A762682844 34989682 10_2196_30720 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- .4I .DC 29L 2WC 36B 53G 5GY 5VS 77I 77K 7RV 7X7 8FI 8FJ AAFWJ AAKPC AAWTL AAYXX ABDBF ABIVO ABUWG ACGFO ADBBV AEGXH AENEX AFFHD AFKRA AFPKN AIAGR ALMA_UNASSIGNED_HOLDINGS ALSLI AOIJS BAWUL BCNDV BENPR CCPQU CITATION CNYFK CS3 DIK DU5 DWQXO E3Z EAP EBD EBS EJD ELW EMB EMOBN ESX F5P FRP FYUFA GROUPED_DOAJ GX1 HMCUK HYE IAO ICO IEA IHR INH ISN ITC KQ8 M1O M48 NAPCQ OK1 OVT P2P PGMZT PHGZM PHGZT PIMPY PPXIY PQQKQ PRQQA RNS RPM SJN SV3 TR2 UKHRP XSB ALIPV CGR CUY CVF ECM EIF NPM 3V. 7QJ 7XB 8FK AZQEC E3H F2A K9. PJZUB PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c558t-15c71c82f959bc8c92b0b942bd766a13ecb4cb25ce2229c61e781bcafbf195f13 |
| IEDL.DBID | 7X7 |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000766777200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1438-8871 1439-4456 |
| IngestDate | Tue Oct 14 19:04:59 EDT 2025 Tue Nov 04 02:00:02 EST 2025 Thu Oct 02 11:11:03 EDT 2025 Sat Nov 08 21:39:50 EST 2025 Tue Nov 11 10:09:57 EST 2025 Tue Nov 04 18:38:59 EST 2025 Thu Nov 13 16:38:07 EST 2025 Thu Jan 02 22:54:41 EST 2025 Tue Nov 18 20:27:43 EST 2025 Sat Nov 29 03:22:39 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | outcome prediction deep learning patient similarity electronic medical records natural language processing health data time series informatics machine learning acute myocardial infarction |
| Language | English |
| License | Ni Wang, Muyu Wang, Yang Zhou, Honglei Liu, Lan Wei, Xiaolu Fei, Hui Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.01.2022. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c558t-15c71c82f959bc8c92b0b942bd766a13ecb4cb25ce2229c61e781bcafbf195f13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-8941-0457 0000-0002-1606-5058 0000-0002-4458-3215 0000-0001-7498-0249 0000-0002-0048-0193 0000-0002-8788-0383 0000-0001-5518-4749 |
| OpenAccessLink | https://www.proquest.com/docview/2624039294?pq-origsite=%requestingapplication% |
| PMID | 34989682 |
| PQID | 2624039294 |
| PQPubID | 2033121 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_6c191a55015f495893ad58edfadd7b00 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8778569 proquest_miscellaneous_2617279142 proquest_journals_2624039294 gale_infotracmisc_A762682844 gale_infotracacademiconefile_A762682844 gale_incontextgauss_ISN_A762682844 pubmed_primary_34989682 crossref_citationtrail_10_2196_30720 crossref_primary_10_2196_30720 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-01-06 |
| PublicationDateYYYYMMDD | 2022-01-06 |
| PublicationDate_xml | – month: 01 year: 2022 text: 2022-01-06 day: 06 |
| PublicationDecade | 2020 |
| PublicationPlace | Canada |
| PublicationPlace_xml | – name: Canada – name: Toronto – name: Toronto, Canada |
| PublicationTitle | Journal of medical Internet research |
| PublicationTitleAlternate | J Med Internet Res |
| PublicationYear | 2022 |
| Publisher | Journal of Medical Internet Research Gunther Eysenbach MD MPH, Associate Professor JMIR Publications |
| Publisher_xml | – name: Journal of Medical Internet Research – name: Gunther Eysenbach MD MPH, Associate Professor – name: JMIR Publications |
| References | ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 Allam, A (ref24) ref1 ref39 ref16 ref38 ref19 ref18 ref23 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 Panahiazar, M (ref26) 2015; 210 ref7 ref9 ref4 ref3 ref6 ref5 Ng, K (ref17) 2015; 2015 |
| References_xml | – volume: 210 start-page: 369 year: 2015 ident: ref26 publication-title: Stud Health Technol Inform – ident: ref24 publication-title: ArXiv – ident: ref34 doi: 10.1089/10665270252935511 – ident: ref16 doi: 10.1371/journal.pone.0127428 – ident: ref8 doi: 10.1109/ichi.2016.16 – ident: ref5 doi: 10.1038/s41597-019-0103-9 – ident: ref36 doi: 10.1136/bmjopen-2020-040291 – ident: ref9 doi: 10.1016/j.jbi.2018.06.001 – ident: ref23 doi: 10.1145/3230734 – ident: ref27 – ident: ref38 doi: 10.1145/3219819.3219930 – ident: ref37 doi: 10.1016/j.cmpb.2021.106040 – ident: ref35 doi: 10.1109/embc.2016.7591229 – ident: ref7 doi: 10.1016/j.jbi.2020.103518 – ident: ref15 doi: 10.1097/MLR.0b013e3181de9e17 – ident: ref29 doi: 10.1097/MLR.0000000000000315 – ident: ref22 doi: 10.1109/jbhi.2014.2358715 – ident: ref33 doi: 10.1109/tkde.2014.2309131 – ident: ref3 doi: 10.1109/tnb.2018.2837622 – ident: ref12 doi: 10.1186/s12938-019-0718-2 – ident: ref2 doi: 10.1148/radiol.2017170549 – ident: ref20 doi: 10.1007/3-540-48298-9_29 – ident: ref32 doi: 10.1186/1741-7015-11-194 – ident: ref39 doi: 10.3760/cma.j.issn.2095-4352.2018.06.006 – ident: ref28 doi: 10.1038/sdata.2016.35 – ident: ref6 doi: 10.1038/s41746-018-0029-1 – ident: ref11 doi: 10.1186/s12911-021-01432-x – ident: ref25 doi: 10.18637/jss.v031.i07 – ident: ref30 doi: 10.1109/jbhi.2016.2633963 – ident: ref4 doi: 10.1186/s12911-020-01297-6 – ident: ref13 doi: 10.1126/scitranslmed.aaa9364 – ident: ref19 doi: 10.1016/j.ijcard.2016.11.130 – ident: ref21 – ident: ref18 doi: 10.1109/icpr.2010.1009 – ident: ref1 doi: 10.1038/s41598-017-16665-y – ident: ref31 doi: 10.1016/j.eswa.2013.05.066 – volume: 2015 start-page: 132 year: 2015 ident: ref17 publication-title: AMIA Jt Summits Transl Sci Proc – ident: ref10 doi: 10.2196/medinform.6730 – ident: ref14 |
| SSID | ssj0020491 |
| Score | 2.4142005 |
| Snippet | Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity... Background Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient... Background: Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient... BackgroundSequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | e30720 |
| SubjectTerms | Algorithms Analysis Cardiac patients Classifiers Clinical outcomes Cluster Analysis Computerized medical records Cross-Sectional Studies Data Decomposition Deep learning Diabetes Disease Dynamic programming Electronic Health Records Heart attack Heart attacks Hospitalization Hospitals Humans Information Information technology Laboratories Measurement Medical records Mortality Multimedia Myocardial infarction Neural networks Neural Networks, Computer Original Paper Patient admissions Patient outcomes Patient Readmission Patients Precision medicine Prediction models Predictions Prognosis Readmission Recurrent Sequences Short term memory Time Time series Trends Type 2 diabetes |
| SummonAdditionalLinks | – databaseName: DOAJ Open Access Full Text dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1fb9MwELfQhCYkhGD8y9gmgyZ4ilYnsR3z1gEVSFAqFaS9WY5jb0Vditp0z3wHviGfhLvEjRJ44IXX3OWS3J19d-35d4ScQlSTsoDqxMpRFmelcrGySRGL1KgiYcKmtoHM_yin0_ziQs16o76wJ6yFB24VdyYsVBQG8mjGPSTzEF5NyXNXeliYEnwGd9-RVLtiKpRakPeyfXIXG53Bxc7AkXGgdy_yNAD9f2_DvTg07JHsBZ3JfXIvZIt03L7lA3LLVQfkOJw1oC9pOEyEyqVhlR6Q_U_h__KH5Nu86ZSGVbykb01tfv34eQ5hq6SzFk6VzhfXC6htIRWnk12bFgWZHcPnbQ0-6ehsjULxQa_peHm5gluurmmv5egR-Tp59-XN-zhMV4gt53kdM24ls3niFVeFza1KilGhsqQopRCGpc4WmS0Sbh2O_LaCOQkprjW-8Exxz9LHZK9aVe4poT43xoEU3sB3ZSMDhi6V5yATRI18RE53mtc2QI_jBIylhhIEDaQbA0XkpGP73mJt_MlwjmbriAiN3VwAh9HBYfS_HCYiL9DoGsEvKuyuuTTbzUZ_mE_1GCKDgBI0yyLyKjD5FbypNeGwAnwv4mUNOI8GnLA67ZC88y0ddoeNTgSiIEJiCuTnHRnvxI63yq22yIOppWJZEpEnrSt2351mKlcgPyJy4KQDxQwp1eKqwQ7Ppcy5UIf_Q5PPyJ0ED4PgD1LiiOzV6607JrftTb3YrE-aBfkbFvk9pQ priority: 102 providerName: Directory of Open Access Journals |
| Title | Sequential Data–Based Patient Similarity Framework for Patient Outcome Prediction: Algorithm Development |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/34989682 https://www.proquest.com/docview/2624039294 https://www.proquest.com/docview/2617279142 https://pubmed.ncbi.nlm.nih.gov/PMC8778569 https://doaj.org/article/6c191a55015f495893ad58edfadd7b00 |
| Volume | 24 |
| WOSCitedRecordID | wos000766777200003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: DOA dateStart: 19990101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Library Science Database customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: M1O dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/libraryscience providerName: ProQuest – providerCode: PRVPQU databaseName: Nursing & Allied Health Database customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: 7RV dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/nahs providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1438-8871 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020491 issn: 1438-8871 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9NAEB5BiyokxKM8amijBVVwsho7Xq-XC0qgEZVIajWA0pO1Xq_TVKlTEocz_4F_yC9hxtmkMUhcuPjgnUzG3tl5rGe_AThEryZEitmJFs3ADTJpXKn91A1bSqa-F-qWriDzP4l-PxoOZWw33Oa2rHJlEytDnU017ZEf-SEhx6EzD95df3OpaxR9XbUtNG7DNrXNJj0Xw5uEC6NfbwfuUbkzKtoRqjO19d7wPxVM_9_GeMMb1SslN1xP98H_Cv0Q7tugk7WXWvIIbpliFw7skQX2mtkzSTRHzC72Xdjp2c_uj-FyUBVcozGYsA-qVL9-_Oyg98tYvERlZYPx1RhTZIzoWXdV7cWQ55rgdFGixIbFM2JKf_SWtScjlLW8uGIblUtP4Ev3-PP7j65t0uBqzqPS9bgWno78XHKZ6khLP22mMvDTTISh8lpGp4FOfa4NdQ7XoWcERspa5WnuSZ57raewVUwLswcsj5QyyIVXKGBBU6G-ZDLnyBNZNXMHDldTl2iLYE6NNCYJZjI0w0k1ww401mTXS8iOPwk6NO_rQULYrm5MZ6PELtgk1JjJKszfPJ5jEolhncp4ZLIcHYJAW-XAK9KahDA0CirSGanFfJ6cDPpJGx1MiJlsEDjwxhLlU5RUK3vmAZ-XYLdqlPs1Slzkuj68UrDEGpl5cqNdDrxcD9MvqXCuMNMF0VCEKr3Ad-DZUpfXz90KZCSRvwOipuW1F1MfKcYXFQR5JETEQ_n832K9gLs-nRahHatwH7bK2cIcwB39vRzPZw1cq2dfG9WKra5RA7Y7x_34rFFtjOC1553ivfikF5__BjnyUpo |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFBUkxKO8DG1ZUIGT1djxa5EQSilRoyYhUopUTma9XqdBqVMSB8SN_8D_4EfxS5ix1yYGiVsPXLOTiT355mXPA2AXvZrvR5idSL_pmE7MlcmlHZleS_DItjzZkvnI_J4_GAQnJ3y4Bj_KXhgqqyxtYm6o45mkZ-R7tkeT49CZO6_OP5m0NYrerpYrNApYHKmvXzBlW7zsHuD_-9S2O2-OXx-aequAKV03yEzLlb4lAzvhLo9kILkdNSPu2FHse56wWkpGjoxsVypadS09S_kY2kmRRInF3cRqId9LsO4Q2BuwPuz2h--rFA_jbWsDrlGBNUJ7DxWIFomveLx8McDf5n_F_9VrM1ecXefG_yamm3Bdh9WsXejBLVhT6SZs66YM9ozpritCIdPmbBM2-rqw4DZ8HOUl5WjupuxAZOLnt-_76N9jNizmzrLR5GwyFbTpj3XKejaGPCuCt8sMJaTYcE5M6YdesPZ0jLLJTs_YSm3WHXh3IZK4C410lqr7wJJACIVc3HzOmdMUqBExT1zkiayaiQG7JVRCqWe006qQaYi5GiEqzBFlwE5Fdl4MJfmTYJ9wVh3SDPH8g9l8HGqTFHoSc3WBGarlJpgmY-AqYjdQcYIuz0drbMATQmlIU0JSKkMai-ViEXZHg7CNLtTDXN1xDHiuiZIZXqkUuqsD75cGi9Uot2qUaMZk_bgEdKjN6CL8jWYDHlfH9E0qDUzVbEk0FINzy7ENuFfoTnXfLYcHHPkb4Ne0qiaY-kk6Oc2HrAe-H7gef_Dvy3oEVw6P-72w1x0cPYSrNvXG0PM5bwsa2XyptuGy_JxNFvMdbSkYfLhorfsFTw-rag |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFEVIiEd5GdqyoAInK_HGr0VCKCVERG2DpRSpnMx6badBqVMSB8SN_8C_4efwS5hx1iYGiVsPXLOTiT355mXPA2APvZrnRZidKK9tm3YsElMoHpluR4qIW67qqGJk_qE3HPonJyLYgB9lLwyVVZY2sTDU8UzRM_IWd2lyHDpzu5Xqsoig1395_smkDVL0prVcp7GCyEHy9Qumb4sXgx7-1084778-fvXG1BsGTOU4fm5ajvIs5fNUOCJSvhI8akfC5lHsua60OomKbBVxRyW09lq5VuJhmKdkGqWWcFKrg3wvwSaG5DZvwGYwOAreV-kext5WE65SsTXCvIXKREvF17xfsSTgb1ew5gvrdZprjq9__X8W2Q24psNt1l3px03YSLIt2NHNGuwp091YhE6mzdwWNI90wcEt-DgqSs3RDE5ZT-by57fv--j3Yxas5tGy0eRsMpW0AZD1yzo3hjwrgrfLHKWVsGBOTOmHnrPudIyyyU_P2FrN1m14dyGSuAONbJYl94ClvpQJcnGK-Wd2W6KmxCJ1kCeyaqcG7JWwCZWe3U4rRKYh5nCErrBAlwG7Fdn5aljJnwT7hLnqkGaLFx_M5uNQm6rQVZjDS8xcLSfF9BkDWhk7fhKn6Ao9tNIGPCbEhjQ9JCNQjeVysQgHo2HYRdfqYg5v2wY800TpDK9USd3tgfdLA8dqlNs1SjRvqn5cgjvU5nUR_ka2AY-qY_omlQxmyWxJNBSbC8vmBtxd6VF13x1b-AL5G-DVNKwmmPpJNjkthq_7nuc7rrj_78t6CE1UtfBwMDx4AFc4tczQYzt3Gxr5fJnswGX1OZ8s5rvaaDD4cNFK9wvmy7Qq |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Sequential+Data%E2%80%93Based+Patient+Similarity+Framework+for+Patient+Outcome+Prediction%3A+Algorithm+Development&rft.jtitle=Journal+of+medical+Internet+research&rft.au=Wang%2C+Ni&rft.au=Wang%2C+Muyu&rft.au=Zhou%2C+Yang&rft.au=Liu%2C+Honglei&rft.date=2022-01-06&rft.pub=Gunther+Eysenbach+MD+MPH%2C+Associate+Professor&rft.eissn=1438-8871&rft.spage=e30720&rft_id=info:doi/10.2196%2F30720&rft.externalDBID=HAS_PDF_LINK |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1438-8871&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1438-8871&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1438-8871&client=summon |