Personalized Mortality Prediction Driven by Electronic Medical Data and a Patient Similarity Metric
Events
Loading … Spinner

Mendeley | Further Information

{"title"=>"Personalized mortality prediction driven by electronic medical data and a patient similarity metric", "type"=>"journal", "authors"=>[{"first_name"=>"Joon", "last_name"=>"Lee", "scopus_author_id"=>"36623108000"}, {"first_name"=>"David M.", "last_name"=>"Maslove", "scopus_author_id"=>"6504503263"}, {"first_name"=>"Joel A.", "last_name"=>"Dubin", "scopus_author_id"=>"7005659450"}], "year"=>2015, "source"=>"PLoS ONE", "identifiers"=>{"scopus"=>"2-s2.0-84929340147", "sgr"=>"84929340147", "issn"=>"19326203", "doi"=>"10.1371/journal.pone.0127428", "pmid"=>"25978419", "isbn"=>"1932-6203", "pui"=>"604392540"}, "id"=>"4520e097-11df-3278-8e3e-2018ab1dc5a6", "abstract"=>"BACKGROUND: Clinical outcome prediction normally employs static, one-size-fits-all models that perform well for the average patient but are sub-optimal for individual patients with unique characteristics. In the era of digital healthcare, it is feasible to dynamically personalize decision support by identifying and analyzing similar past patients, in a way that is analogous to personalized product recommendation in e-commerce. Our objectives were: 1) to prove that analyzing only similar patients leads to better outcome prediction performance than analyzing all available patients, and 2) to characterize the trade-off between training data size and the degree of similarity between the training data and the index patient for whom prediction is to be made.\\n\\nMETHODS AND FINDINGS: We deployed a cosine-similarity-based patient similarity metric (PSM) to an intensive care unit (ICU) database to identify patients that are most similar to each patient and subsequently to custom-build 30-day mortality prediction models. Rich clinical and administrative data from the first day in the ICU from 17,152 adult ICU admissions were analyzed. The results confirmed that using data from only a small subset of most similar patients for training improves predictive performance in comparison with using data from all available patients. The results also showed that when too few similar patients are used for training, predictive performance degrades due to the effects of small sample sizes. Our PSM-based approach outperformed well-known ICU severity of illness scores. Although the improved prediction performance is achieved at the cost of increased computational burden, Big Data technologies can help realize personalized data-driven decision support at the point of care.\\n\\nCONCLUSIONS: The present study provides crucial empirical evidence for the promising potential of personalized data-driven decision support systems. With the increasing adoption of electronic medical record (EMR) systems, our novel medical data analytics contributes to meaningful use of EMR data.", "link"=>"http://www.mendeley.com/research/personalized-mortality-prediction-driven-electronic-medical-data-patient-similarity-metric", "reader_count"=>102, "reader_count_by_academic_status"=>{"Unspecified"=>3, "Professor > Associate Professor"=>2, "Researcher"=>19, "Student > Doctoral Student"=>8, "Student > Ph. D. Student"=>26, "Student > Postgraduate"=>6, "Other"=>7, "Student > Master"=>22, "Student > Bachelor"=>4, "Lecturer"=>1, "Professor"=>4}, "reader_count_by_user_role"=>{"Unspecified"=>3, "Professor > Associate Professor"=>2, "Researcher"=>19, "Student > Doctoral Student"=>8, "Student > Ph. D. Student"=>26, "Student > Postgraduate"=>6, "Other"=>7, "Student > Master"=>22, "Student > Bachelor"=>4, "Lecturer"=>1, "Professor"=>4}, "reader_count_by_subject_area"=>{"Unspecified"=>6, "Agricultural and Biological Sciences"=>2, "Arts and Humanities"=>1, "Business, Management and Accounting"=>3, "Computer Science"=>31, "Decision Sciences"=>1, "Earth and Planetary Sciences"=>1, "Engineering"=>12, "Nursing and Health Professions"=>2, "Mathematics"=>2, "Medicine and Dentistry"=>33, "Pharmacology, Toxicology and Pharmaceutical Science"=>2, "Physics and Astronomy"=>1, "Psychology"=>1, "Social Sciences"=>3, "Immunology and Microbiology"=>1}, "reader_count_by_subdiscipline"=>{"Medicine and Dentistry"=>{"Medicine and Dentistry"=>33}, "Social Sciences"=>{"Social Sciences"=>3}, "Decision Sciences"=>{"Decision Sciences"=>1}, "Physics and Astronomy"=>{"Physics and Astronomy"=>1}, "Psychology"=>{"Psychology"=>1}, "Mathematics"=>{"Mathematics"=>2}, "Unspecified"=>{"Unspecified"=>6}, "Pharmacology, Toxicology and Pharmaceutical Science"=>{"Pharmacology, Toxicology and Pharmaceutical Science"=>2}, "Arts and Humanities"=>{"Arts and Humanities"=>1}, "Engineering"=>{"Engineering"=>12}, "Earth and Planetary Sciences"=>{"Earth and Planetary Sciences"=>1}, "Immunology and Microbiology"=>{"Immunology and Microbiology"=>1}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>2}, "Computer Science"=>{"Computer Science"=>31}, "Business, Management and Accounting"=>{"Business, Management and Accounting"=>3}, "Nursing and Health Professions"=>{"Nursing and Health Professions"=>2}}, "reader_count_by_country"=>{"Canada"=>1, "United States"=>3, "United Kingdom"=>1, "Spain"=>1}, "group_count"=>11}

CrossRef

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84929340147"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84929340147?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84929340147&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84929340147&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/84929340147", "dc:identifier"=>"SCOPUS_ID:84929340147", "eid"=>"2-s2.0-84929340147", "dc:title"=>"Personalized mortality prediction driven by electronic medical data and a patient similarity metric", "dc:creator"=>"Lee J.", "prism:publicationName"=>"PLoS ONE", "prism:eIssn"=>"19326203", "prism:volume"=>"10", "prism:issueIdentifier"=>"5", "prism:pageRange"=>nil, "prism:coverDate"=>"2015-05-15", "prism:coverDisplayDate"=>"15 May 2015", "prism:doi"=>"10.1371/journal.pone.0127428", "citedby-count"=>"59", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"University of Waterloo", "affiliation-city"=>"Waterloo", "affiliation-country"=>"Canada"}], "pubmed-id"=>"25978419", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e0127428", "source-id"=>"10600153309", "openaccess"=>"1", "openaccessFlag"=>true}

Facebook

  • {"url"=>"http%3A%2F%2Fjournals.plos.org%2Fplosone%2Farticle%3Fid%3D10.1371%252Fjournal.pone.0127428", "share_count"=>0, "like_count"=>0, "comment_count"=>0, "click_count"=>0, "total_count"=>0}

Counter

  • {"month"=>"5", "year"=>"2015", "pdf_views"=>"59", "xml_views"=>"4", "html_views"=>"623"}
  • {"month"=>"6", "year"=>"2015", "pdf_views"=>"26", "xml_views"=>"1", "html_views"=>"89"}
  • {"month"=>"7", "year"=>"2015", "pdf_views"=>"30", "xml_views"=>"0", "html_views"=>"140"}
  • {"month"=>"8", "year"=>"2015", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"55"}
  • {"month"=>"9", "year"=>"2015", "pdf_views"=>"14", "xml_views"=>"1", "html_views"=>"62"}
  • {"month"=>"10", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"82"}
  • {"month"=>"11", "year"=>"2015", "pdf_views"=>"25", "xml_views"=>"1", "html_views"=>"58"}
  • {"month"=>"12", "year"=>"2015", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"66"}
  • {"month"=>"1", "year"=>"2016", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"75"}
  • {"month"=>"2", "year"=>"2016", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"69"}
  • {"month"=>"3", "year"=>"2016", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"92"}
  • {"month"=>"4", "year"=>"2016", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"59"}
  • {"month"=>"5", "year"=>"2016", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"49"}
  • {"month"=>"6", "year"=>"2016", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"56"}
  • {"month"=>"7", "year"=>"2016", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"39"}
  • {"month"=>"8", "year"=>"2016", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"64"}
  • {"month"=>"9", "year"=>"2016", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"58"}
  • {"month"=>"10", "year"=>"2016", "pdf_views"=>"29", "xml_views"=>"0", "html_views"=>"83"}
  • {"month"=>"11", "year"=>"2016", "pdf_views"=>"8", "xml_views"=>"0", "html_views"=>"284"}
  • {"month"=>"12", "year"=>"2016", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"404"}
  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"17", "xml_views"=>"1", "html_views"=>"177"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"20", "xml_views"=>"1", "html_views"=>"87"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"37", "xml_views"=>"0", "html_views"=>"137"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"17", "xml_views"=>"1", "html_views"=>"102"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"26", "xml_views"=>"0", "html_views"=>"96"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"29", "xml_views"=>"0", "html_views"=>"112"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"18", "xml_views"=>"1", "html_views"=>"65"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"25", "xml_views"=>"2", "html_views"=>"67"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"24", "xml_views"=>"2", "html_views"=>"72"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"31", "xml_views"=>"0", "html_views"=>"115"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"19", "xml_views"=>"0", "html_views"=>"121"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"29", "xml_views"=>"1", "html_views"=>"129"}
  • {"month"=>"1", "year"=>"2018", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"84"}
  • {"month"=>"2", "year"=>"2018", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"48"}
  • {"month"=>"3", "year"=>"2018", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"58"}
  • {"month"=>"4", "year"=>"2018", "pdf_views"=>"49", "xml_views"=>"0", "html_views"=>"81"}
  • {"month"=>"5", "year"=>"2018", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"61"}
  • {"month"=>"6", "year"=>"2018", "pdf_views"=>"27", "xml_views"=>"1", "html_views"=>"47"}
  • {"month"=>"7", "year"=>"2018", "pdf_views"=>"29", "xml_views"=>"3", "html_views"=>"52"}
  • {"month"=>"8", "year"=>"2018", "pdf_views"=>"21", "xml_views"=>"1", "html_views"=>"62"}
  • {"month"=>"9", "year"=>"2018", "pdf_views"=>"33", "xml_views"=>"0", "html_views"=>"75"}
  • {"month"=>"10", "year"=>"2018", "pdf_views"=>"36", "xml_views"=>"1", "html_views"=>"79"}
  • {"month"=>"11", "year"=>"2018", "pdf_views"=>"34", "xml_views"=>"0", "html_views"=>"46"}
  • {"month"=>"12", "year"=>"2018", "pdf_views"=>"37", "xml_views"=>"0", "html_views"=>"40"}
  • {"month"=>"1", "year"=>"2019", "pdf_views"=>"35", "xml_views"=>"0", "html_views"=>"63"}
  • {"month"=>"2", "year"=>"2019", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"55"}
  • {"month"=>"3", "year"=>"2019", "pdf_views"=>"35", "xml_views"=>"0", "html_views"=>"81"}
  • {"month"=>"4", "year"=>"2019", "pdf_views"=>"27", "xml_views"=>"0", "html_views"=>"56"}
  • {"month"=>"5", "year"=>"2019", "pdf_views"=>"37", "xml_views"=>"0", "html_views"=>"59"}
  • {"month"=>"6", "year"=>"2019", "pdf_views"=>"19", "xml_views"=>"0", "html_views"=>"27"}
  • {"month"=>"7", "year"=>"2019", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"18"}
  • {"month"=>"8", "year"=>"2019", "pdf_views"=>"25", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"9", "year"=>"2019", "pdf_views"=>"32", "xml_views"=>"0", "html_views"=>"55"}
  • {"month"=>"10", "year"=>"2019", "pdf_views"=>"40", "xml_views"=>"1", "html_views"=>"85"}
  • {"month"=>"11", "year"=>"2019", "pdf_views"=>"34", "xml_views"=>"0", "html_views"=>"62"}
  • {"month"=>"12", "year"=>"2019", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"54"}
  • {"month"=>"1", "year"=>"2020", "pdf_views"=>"28", "xml_views"=>"0", "html_views"=>"72"}
  • {"month"=>"2", "year"=>"2020", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"32"}
  • {"month"=>"3", "year"=>"2020", "pdf_views"=>"27", "xml_views"=>"0", "html_views"=>"60"}
  • {"month"=>"4", "year"=>"2020", "pdf_views"=>"40", "xml_views"=>"0", "html_views"=>"31"}
  • {"month"=>"5", "year"=>"2020", "pdf_views"=>"21", "xml_views"=>"1", "html_views"=>"47"}
  • {"month"=>"6", "year"=>"2020", "pdf_views"=>"13", "xml_views"=>"2", "html_views"=>"48"}
  • {"month"=>"7", "year"=>"2020", "pdf_views"=>"27", "xml_views"=>"0", "html_views"=>"54"}
  • {"month"=>"8", "year"=>"2020", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"46"}
  • {"month"=>"9", "year"=>"2020", "pdf_views"=>"29", "xml_views"=>"0", "html_views"=>"51"}
  • {"month"=>"10", "year"=>"2020", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"34"}
  • {"month"=>"11", "year"=>"2020", "pdf_views"=>"36", "xml_views"=>"0", "html_views"=>"43"}

Figshare

  • {"files"=>["https://ndownloader.figshare.com/files/2071104"], "description"=>"<p>The results shown in <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0127428#pone.0127428.g002\" target=\"_blank\">Fig 2</a> are tabulated here. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve; CI: confidence interval.</p><p>Mortality prediction performance of logistic regression as a function of the number of similar patients used in training.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417467, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.t003", "stats"=>{"downloads"=>8, "page_views"=>9, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_logistic_regression_as_a_function_of_the_number_of_similar_patients_used_in_training_/1417467", "title"=>"Mortality prediction performance of logistic regression as a function of the number of similar patients used in training.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071096"], "description"=>"<p>The solid and dashed lines are the mean and 95% confidence intervals, respectively, from 10-fold cross-validation. The maximum number of similar patients corresponds to all available training data. Predictive performance clearly improves as data from fewer but more similar patients are used for training. Identical predictor values in training data prohibited decreasing the number of similar patients further. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417461, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.g002", "stats"=>{"downloads"=>3, "page_views"=>30, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_personalized_logistic_regression_trained_on_similar_patient_data_/1417461", "title"=>"Mortality prediction performance of personalized logistic regression trained on similar patient data.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071101"], "description"=>"<p>The solid and dashed lines are the mean and 95% confidence intervals, respectively, from 10-fold cross-validation. The maximum number of similar patients corresponds to all available training data. Predictive performance clearly improves as data from fewer but more similar patients are used for training. Identical outcome values in training data prohibited decreasing the number of similar patients further. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417464, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.g003", "stats"=>{"downloads"=>3, "page_views"=>10, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_personalized_decision_trees_trained_on_similar_patient_data_/1417464", "title"=>"Mortality prediction performance of personalized decision trees trained on similar patient data.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071102"], "description"=>"<p>Age, SAPS, and SOFA are shown in mean [standard deviation]. SAPS: Simplified Acute Physiology Score; SOFA: Sequential Organ Failure Assessment.</p><p>Patient data characteristics.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417465, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.t001", "stats"=>{"downloads"=>2, "page_views"=>15, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Patient_data_characteristics_/1417465", "title"=>"Patient data characteristics.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071103"], "description"=>"<p>The results shown in <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0127428#pone.0127428.g001\" target=\"_blank\">Fig 1</a> are tabulated here. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve; CI: confidence interval.</p><p>Mortality prediction performance of death counting as a function of the number of similar patients used in training.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417466, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.t002", "stats"=>{"downloads"=>3, "page_views"=>10, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_death_counting_as_a_function_of_the_number_of_similar_patients_used_in_training_/1417466", "title"=>"Mortality prediction performance of death counting as a function of the number of similar patients used in training.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071086"], "description"=>"<p>The solid and dashed lines are the mean and 95% confidence intervals, respectively, from 10-fold cross-validation. A trade-off between training data homogeneity and size is apparent; as the number of similar patients in the training data increases, predictive performance improves initially at a rapid rate thanks to increasing training data size but starts to degrade gradually due to decreasing homogeneity within the training data. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417451, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.g001", "stats"=>{"downloads"=>3, "page_views"=>16, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_death_counting_among_similar_patients_/1417451", "title"=>"Mortality prediction performance of death counting among similar patients.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-05-15 04:16:32"}
  • {"files"=>["https://ndownloader.figshare.com/files/2071105"], "description"=>"<p>The results shown in <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0127428#pone.0127428.g003\" target=\"_blank\">Fig 3</a> are tabulated here. AUROC: area under the receiver operating characteristic curve; AUPRC: area under the precision-recall curve; CI: confidence interval.</p><p>Mortality prediction performance of decision trees as a function of the number of similar patients used in training.</p>", "links"=>[], "tags"=>["illness scores", "sample sizes", "Big Data technologies", "training data size", "performance degrades", "outcome prediction performance", "data analytics", "decision support", "care unit", "psm", "Personalized Mortality Prediction", "EMR data", "Electronic Medical Data", "index patient", "product recommendation", "ICU severity", "training data", "prediction performance", "Patient Similarity Metric BackgroundClinical outcome prediction"], "article_id"=>1417468, "categories"=>["Biological Sciences"], "users"=>["Joon Lee", "David M. Maslove", "Joel A. Dubin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0127428.t004", "stats"=>{"downloads"=>6, "page_views"=>11, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Mortality_prediction_performance_of_decision_trees_as_a_function_of_the_number_of_similar_patients_used_in_training_/1417468", "title"=>"Mortality prediction performance of decision trees as a function of the number of similar patients used in training.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-05-15 04:16:32"}

PMC Usage Stats | Further Information

  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"5"}
  • {"unique-ip"=>"23", "full-text"=>"21", "pdf"=>"16", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"7", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"6"}
  • {"unique-ip"=>"27", "full-text"=>"25", "pdf"=>"20", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"7"}
  • {"unique-ip"=>"20", "full-text"=>"22", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"8"}
  • {"unique-ip"=>"35", "full-text"=>"32", "pdf"=>"15", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"9"}
  • {"unique-ip"=>"36", "full-text"=>"34", "pdf"=>"23", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"10"}
  • {"unique-ip"=>"22", "full-text"=>"23", "pdf"=>"13", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"2"}
  • {"unique-ip"=>"29", "full-text"=>"31", "pdf"=>"15", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"11"}
  • {"unique-ip"=>"27", "full-text"=>"25", "pdf"=>"24", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"6", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"12"}
  • {"unique-ip"=>"22", "full-text"=>"22", "pdf"=>"11", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"1"}
  • {"unique-ip"=>"19", "full-text"=>"19", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"3"}
  • {"unique-ip"=>"22", "full-text"=>"20", "pdf"=>"11", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"4"}
  • {"unique-ip"=>"19", "full-text"=>"23", "pdf"=>"4", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"5"}
  • {"unique-ip"=>"18", "full-text"=>"16", "pdf"=>"11", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"6"}
  • {"unique-ip"=>"13", "full-text"=>"12", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"7"}
  • {"unique-ip"=>"11", "full-text"=>"9", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"8"}
  • {"unique-ip"=>"11", "full-text"=>"9", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"9"}
  • {"unique-ip"=>"15", "full-text"=>"18", "pdf"=>"11", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"10"}
  • {"unique-ip"=>"24", "full-text"=>"26", "pdf"=>"10", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"11"}
  • {"unique-ip"=>"22", "full-text"=>"20", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"12"}
  • {"unique-ip"=>"21", "full-text"=>"16", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"1"}
  • {"unique-ip"=>"15", "full-text"=>"16", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"12", "full-text"=>"11", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"13", "full-text"=>"14", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"13", "full-text"=>"9", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"24", "full-text"=>"29", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"14", "full-text"=>"18", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"17", "full-text"=>"19", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"13", "full-text"=>"15", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"22", "full-text"=>"26", "pdf"=>"8", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
  • {"unique-ip"=>"10", "full-text"=>"10", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"11"}
  • {"unique-ip"=>"10", "full-text"=>"11", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"12"}
  • {"unique-ip"=>"19", "full-text"=>"20", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"1"}
  • {"unique-ip"=>"19", "full-text"=>"18", "pdf"=>"4", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"3"}
  • {"unique-ip"=>"15", "full-text"=>"23", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"1"}
  • {"unique-ip"=>"11", "full-text"=>"6", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"9"}
  • {"unique-ip"=>"9", "full-text"=>"10", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"4"}
  • {"unique-ip"=>"14", "full-text"=>"14", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2018", "month"=>"5"}
  • {"unique-ip"=>"7", "full-text"=>"7", "pdf"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"6"}
  • {"unique-ip"=>"11", "full-text"=>"8", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"7"}
  • {"unique-ip"=>"9", "full-text"=>"13", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2018", "month"=>"10"}
  • {"unique-ip"=>"14", "full-text"=>"12", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"8"}
  • {"unique-ip"=>"19", "full-text"=>"23", "pdf"=>"6", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"11"}
  • {"unique-ip"=>"11", "full-text"=>"11", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"12"}
  • {"unique-ip"=>"14", "full-text"=>"16", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"2"}
  • {"unique-ip"=>"17", "full-text"=>"18", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"3"}
  • {"unique-ip"=>"9", "full-text"=>"14", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"4"}
  • {"unique-ip"=>"10", "full-text"=>"11", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"5"}
  • {"unique-ip"=>"11", "full-text"=>"11", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"8"}
  • {"unique-ip"=>"10", "full-text"=>"9", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"9"}
  • {"unique-ip"=>"9", "full-text"=>"10", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"10"}
  • {"unique-ip"=>"8", "full-text"=>"12", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"12"}
  • {"unique-ip"=>"29", "full-text"=>"31", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"2"}
  • {"unique-ip"=>"23", "full-text"=>"23", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"3"}
  • {"unique-ip"=>"25", "full-text"=>"29", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"4"}
  • {"unique-ip"=>"23", "full-text"=>"27", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"5"}
  • {"unique-ip"=>"15", "full-text"=>"15", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"6"}
  • {"unique-ip"=>"8", "full-text"=>"7", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"7"}
  • {"unique-ip"=>"8", "full-text"=>"5", "pdf"=>"6", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"8"}
  • {"unique-ip"=>"7", "full-text"=>"4", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"9"}
  • {"unique-ip"=>"11", "full-text"=>"11", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"10"}

Relative Metric

{"start_date"=>"2015-01-01T00:00:00Z", "end_date"=>"2015-12-31T00:00:00Z", "subject_areas"=>[]}
Loading … Spinner
There are currently no alerts