The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets
Events
Loading … Spinner

Mendeley | Further Information

{"title"=>"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets", "type"=>"journal", "authors"=>[{"first_name"=>"Takaya", "last_name"=>"Saito", "scopus_author_id"=>"56621758300"}, {"first_name"=>"Marc", "last_name"=>"Rehmsmeier", "scopus_author_id"=>"6603646396"}], "year"=>2015, "source"=>"PLoS ONE", "identifiers"=>{"doi"=>"10.1371/journal.pone.0118432", "sgr"=>"84928911070", "isbn"=>"1932-6203", "pmid"=>"25738806", "issn"=>"19326203", "scopus"=>"2-s2.0-84928911070", "pui"=>"604166232"}, "id"=>"5fb254e5-9c9c-3970-98ec-b3edf373e3c1", "abstract"=>"Binary classifiers are routinely evaluated with performance measures such as sensitivity and specificity, and performance is frequently illustrated with Receiver Operating Characteristics (ROC) plots. Alternative measures such as positive predictive value (PPV) and the associated Precision/Recall (PRC) plots are used less frequently. Many bioinformatics studies develop and evaluate classifiers that are to be applied to strongly imbalanced datasets in which the number of negatives outweighs the number of positives significantly. While ROC plots are visually appealing and provide an overview of a classifier's performance across a wide range of specificities, one can ask whether ROC plots could be misleading when applied in imbalanced classification scenarios. We show here that the visual interpretability of ROC plots in the context of imbalanced datasets can be deceptive with respect to conclusions about the reliability of classification performance, owing to an intuitive but wrong interpretation of specificity. PRC plots, on the other hand, can provide the viewer with an accurate prediction of future classification performance due to the fact that they evaluate the fraction of true positives among positive predictions. Our findings have potential implications for the interpretation of a large number of studies that use ROC plots on imbalanced datasets.", "link"=>"http://www.mendeley.com/research/precisionrecall-plot-more-informative-roc-plot-evaluating-binary-classifiers-imbalanced-datasets", "reader_count"=>277, "reader_count_by_academic_status"=>{"Unspecified"=>11, "Professor > Associate Professor"=>7, "Researcher"=>58, "Student > Doctoral Student"=>16, "Student > Ph. D. Student"=>77, "Student > Postgraduate"=>11, "Other"=>14, "Student > Master"=>50, "Student > Bachelor"=>23, "Lecturer"=>1, "Lecturer > Senior Lecturer"=>2, "Professor"=>7}, "reader_count_by_user_role"=>{"Unspecified"=>11, "Professor > Associate Professor"=>7, "Researcher"=>58, "Student > Doctoral Student"=>16, "Student > Ph. D. Student"=>77, "Student > Postgraduate"=>11, "Other"=>14, "Student > Master"=>50, "Student > Bachelor"=>23, "Lecturer"=>1, "Lecturer > Senior Lecturer"=>2, "Professor"=>7}, "reader_count_by_subject_area"=>{"Unspecified"=>25, "Agricultural and Biological Sciences"=>38, "Philosophy"=>1, "Business, Management and Accounting"=>1, "Veterinary Science and Veterinary Medicine"=>1, "Chemistry"=>7, "Computer Science"=>104, "Earth and Planetary Sciences"=>2, "Economics, Econometrics and Finance"=>5, "Engineering"=>35, "Environmental Science"=>4, "Biochemistry, Genetics and Molecular Biology"=>17, "Nursing and Health Professions"=>1, "Materials Science"=>1, "Mathematics"=>9, "Medicine and Dentistry"=>14, "Neuroscience"=>2, "Pharmacology, Toxicology and Pharmaceutical Science"=>1, "Sports and Recreations"=>1, "Physics and Astronomy"=>3, "Psychology"=>4, "Social Sciences"=>1}, "reader_count_by_subdiscipline"=>{"Materials Science"=>{"Materials Science"=>1}, "Medicine and Dentistry"=>{"Medicine and Dentistry"=>14}, "Social Sciences"=>{"Social Sciences"=>1}, "Sports and Recreations"=>{"Sports and Recreations"=>1}, "Physics and Astronomy"=>{"Physics and Astronomy"=>3}, "Psychology"=>{"Psychology"=>4}, "Mathematics"=>{"Mathematics"=>9}, "Unspecified"=>{"Unspecified"=>25}, "Environmental Science"=>{"Environmental Science"=>4}, "Pharmacology, Toxicology and Pharmaceutical Science"=>{"Pharmacology, Toxicology and Pharmaceutical Science"=>1}, "Engineering"=>{"Engineering"=>35}, "Chemistry"=>{"Chemistry"=>7}, "Neuroscience"=>{"Neuroscience"=>2}, "Earth and Planetary Sciences"=>{"Earth and Planetary Sciences"=>2}, "Economics, Econometrics and Finance"=>{"Economics, Econometrics and Finance"=>5}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>38}, "Computer Science"=>{"Computer Science"=>104}, "Business, Management and Accounting"=>{"Business, Management and Accounting"=>1}, "Nursing and Health Professions"=>{"Nursing and Health Professions"=>1}, "Biochemistry, Genetics and Molecular Biology"=>{"Biochemistry, Genetics and Molecular Biology"=>17}, "Philosophy"=>{"Philosophy"=>1}, "Veterinary Science and Veterinary Medicine"=>{"Veterinary Science and Veterinary Medicine"=>1}}, "reader_count_by_country"=>{"United States"=>2, "Japan"=>1, "Ukraine"=>1, "United Kingdom"=>1, "Switzerland"=>1, "Spain"=>1, "New Zealand"=>1, "Canada"=>1, "Belgium"=>1, "Norway"=>1, "Poland"=>1, "Brazil"=>2, "Denmark"=>1, "South Africa"=>1, "Chile"=>1, "Germany"=>5}, "group_count"=>15}

CrossRef

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84928911070"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84928911070?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84928911070&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84928911070&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/84928911070", "dc:identifier"=>"SCOPUS_ID:84928911070", "eid"=>"2-s2.0-84928911070", "dc:title"=>"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets", "dc:creator"=>"Saito T.", "prism:publicationName"=>"PLoS ONE", "prism:eIssn"=>"19326203", "prism:volume"=>"10", "prism:issueIdentifier"=>"3", "prism:pageRange"=>nil, "prism:coverDate"=>"2015-03-04", "prism:coverDisplayDate"=>"4 March 2015", "prism:doi"=>"10.1371/journal.pone.0118432", "citedby-count"=>"593", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"Universitetet i Bergen", "affiliation-city"=>"Bergen", "affiliation-country"=>"Norway"}], "pubmed-id"=>"25738806", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e0118432", "source-id"=>"10600153309", "openaccess"=>"1", "openaccessFlag"=>true}

Facebook

  • {"url"=>"http%3A%2F%2Fjournals.plos.org%2Fplosone%2Farticle%3Fid%3D10.1371%252Fjournal.pone.0118432", "share_count"=>0, "like_count"=>0, "comment_count"=>0, "click_count"=>0, "total_count"=>0}

Twitter

Counter

  • {"month"=>"3", "year"=>"2015", "pdf_views"=>"65", "xml_views"=>"11", "html_views"=>"496"}
  • {"month"=>"4", "year"=>"2015", "pdf_views"=>"28", "xml_views"=>"1", "html_views"=>"127"}
  • {"month"=>"5", "year"=>"2015", "pdf_views"=>"22", "xml_views"=>"1", "html_views"=>"138"}
  • {"month"=>"6", "year"=>"2015", "pdf_views"=>"12", "xml_views"=>"0", "html_views"=>"77"}
  • {"month"=>"7", "year"=>"2015", "pdf_views"=>"12", "xml_views"=>"0", "html_views"=>"79"}
  • {"month"=>"8", "year"=>"2015", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"85"}
  • {"month"=>"9", "year"=>"2015", "pdf_views"=>"12", "xml_views"=>"1", "html_views"=>"92"}
  • {"month"=>"10", "year"=>"2015", "pdf_views"=>"17", "xml_views"=>"1", "html_views"=>"108"}
  • {"month"=>"11", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"1", "html_views"=>"135"}
  • {"month"=>"12", "year"=>"2015", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"91"}
  • {"month"=>"1", "year"=>"2016", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"96"}
  • {"month"=>"2", "year"=>"2016", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"102"}
  • {"month"=>"3", "year"=>"2016", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"75"}
  • {"month"=>"4", "year"=>"2016", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"100"}
  • {"month"=>"5", "year"=>"2016", "pdf_views"=>"19", "xml_views"=>"0", "html_views"=>"102"}
  • {"month"=>"6", "year"=>"2016", "pdf_views"=>"22", "xml_views"=>"0", "html_views"=>"102"}
  • {"month"=>"7", "year"=>"2016", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"92"}
  • {"month"=>"8", "year"=>"2016", "pdf_views"=>"29", "xml_views"=>"0", "html_views"=>"86"}
  • {"month"=>"9", "year"=>"2016", "pdf_views"=>"29", "xml_views"=>"0", "html_views"=>"134"}
  • {"month"=>"10", "year"=>"2016", "pdf_views"=>"23", "xml_views"=>"0", "html_views"=>"129"}
  • {"month"=>"11", "year"=>"2016", "pdf_views"=>"23", "xml_views"=>"0", "html_views"=>"151"}
  • {"month"=>"12", "year"=>"2016", "pdf_views"=>"39", "xml_views"=>"0", "html_views"=>"115"}
  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"99", "xml_views"=>"4", "html_views"=>"263"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"45", "xml_views"=>"0", "html_views"=>"279"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"87", "xml_views"=>"0", "html_views"=>"370"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"59", "xml_views"=>"1", "html_views"=>"327"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"75", "xml_views"=>"1", "html_views"=>"398"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"85", "xml_views"=>"0", "html_views"=>"352"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"75", "xml_views"=>"1", "html_views"=>"259"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"87", "xml_views"=>"0", "html_views"=>"478"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"82", "xml_views"=>"2", "html_views"=>"513"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"69", "xml_views"=>"1", "html_views"=>"520"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"100", "xml_views"=>"0", "html_views"=>"454"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"70", "xml_views"=>"2", "html_views"=>"335"}
  • {"month"=>"1", "year"=>"2018", "pdf_views"=>"118", "xml_views"=>"2", "html_views"=>"387"}
  • {"month"=>"2", "year"=>"2018", "pdf_views"=>"116", "xml_views"=>"0", "html_views"=>"241"}
  • {"month"=>"3", "year"=>"2018", "pdf_views"=>"125", "xml_views"=>"1", "html_views"=>"292"}
  • {"month"=>"4", "year"=>"2018", "pdf_views"=>"325", "xml_views"=>"4", "html_views"=>"1211"}
  • {"month"=>"5", "year"=>"2018", "pdf_views"=>"200", "xml_views"=>"2", "html_views"=>"380"}
  • {"month"=>"6", "year"=>"2018", "pdf_views"=>"178", "xml_views"=>"1", "html_views"=>"385"}
  • {"month"=>"7", "year"=>"2018", "pdf_views"=>"179", "xml_views"=>"3", "html_views"=>"402"}
  • {"month"=>"8", "year"=>"2018", "pdf_views"=>"272", "xml_views"=>"2", "html_views"=>"528"}
  • {"month"=>"9", "year"=>"2018", "pdf_views"=>"155", "xml_views"=>"3", "html_views"=>"409"}
  • {"month"=>"10", "year"=>"2018", "pdf_views"=>"179", "xml_views"=>"2", "html_views"=>"423"}
  • {"month"=>"11", "year"=>"2018", "pdf_views"=>"159", "xml_views"=>"1", "html_views"=>"406"}
  • {"month"=>"12", "year"=>"2018", "pdf_views"=>"166", "xml_views"=>"2", "html_views"=>"449"}
  • {"month"=>"1", "year"=>"2019", "pdf_views"=>"210", "xml_views"=>"2", "html_views"=>"425"}
  • {"month"=>"2", "year"=>"2019", "pdf_views"=>"211", "xml_views"=>"0", "html_views"=>"487"}
  • {"month"=>"3", "year"=>"2019", "pdf_views"=>"227", "xml_views"=>"0", "html_views"=>"532"}
  • {"month"=>"4", "year"=>"2019", "pdf_views"=>"231", "xml_views"=>"4", "html_views"=>"566"}
  • {"month"=>"5", "year"=>"2019", "pdf_views"=>"355", "xml_views"=>"2", "html_views"=>"1189"}
  • {"month"=>"6", "year"=>"2019", "pdf_views"=>"272", "xml_views"=>"1", "html_views"=>"631"}
  • {"month"=>"7", "year"=>"2019", "pdf_views"=>"306", "xml_views"=>"1", "html_views"=>"597"}
  • {"month"=>"8", "year"=>"2019", "pdf_views"=>"300", "xml_views"=>"1", "html_views"=>"625"}
  • {"month"=>"9", "year"=>"2019", "pdf_views"=>"273", "xml_views"=>"2", "html_views"=>"596"}
  • {"month"=>"10", "year"=>"2019", "pdf_views"=>"317", "xml_views"=>"2", "html_views"=>"788"}
  • {"month"=>"11", "year"=>"2019", "pdf_views"=>"266", "xml_views"=>"1", "html_views"=>"781"}
  • {"month"=>"12", "year"=>"2019", "pdf_views"=>"353", "xml_views"=>"2", "html_views"=>"821"}
  • {"month"=>"1", "year"=>"2020", "pdf_views"=>"378", "xml_views"=>"1", "html_views"=>"796"}
  • {"month"=>"2", "year"=>"2020", "pdf_views"=>"350", "xml_views"=>"4", "html_views"=>"809"}
  • {"month"=>"3", "year"=>"2020", "pdf_views"=>"349", "xml_views"=>"1", "html_views"=>"777"}
  • {"month"=>"4", "year"=>"2020", "pdf_views"=>"2149", "xml_views"=>"1", "html_views"=>"864"}
  • {"month"=>"5", "year"=>"2020", "pdf_views"=>"2349", "xml_views"=>"2", "html_views"=>"939"}
  • {"month"=>"6", "year"=>"2020", "pdf_views"=>"400", "xml_views"=>"3", "html_views"=>"921"}
  • {"month"=>"7", "year"=>"2020", "pdf_views"=>"354", "xml_views"=>"1", "html_views"=>"852"}
  • {"month"=>"8", "year"=>"2020", "pdf_views"=>"410", "xml_views"=>"1", "html_views"=>"729"}
  • {"month"=>"9", "year"=>"2020", "pdf_views"=>"434", "xml_views"=>"0", "html_views"=>"750"}
  • {"month"=>"10", "year"=>"2020", "pdf_views"=>"538", "xml_views"=>"2", "html_views"=>"824"}
  • {"month"=>"11", "year"=>"2020", "pdf_views"=>"447", "xml_views"=>"1", "html_views"=>"781"}

Figshare

  • {"files"=>["https://ndownloader.figshare.com/files/1935521"], "description"=>"<p>The upper barplot shows the number of papers found by the term “ROC”, whereas the lower plot shows the number found by the term “((Support Vector Machine) AND Genome-wide) NOT Association”.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325824, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g006", "stats"=>{"downloads"=>1, "page_views"=>38, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Two_PubMed_search_results_show_the_annual_number_of_papers_found_between_2002_and_2012_/1325824", "title"=>"Two PubMed search results show the annual number of papers found between 2002 and 2012.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935524"], "description"=>"<p>ROC and PRC plots show the performances of six different tools, MiRFinder (red), miPred (blue), RNAmicro (green), ProMiR (purple), and RNAfold (orange). A gray solid line represents a baseline. The re-analysis used two independent test sets, T1 and T2. The four plots are for (A) ROC on T1, (B) PRC on T1, (C) ROC on T2, and (D) PRC on T2.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325827, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g007", "stats"=>{"downloads"=>1, "page_views"=>32, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_A_re_analysis_of_the_MiRFinder_study_reveals_that_PRC_is_stronger_than_ROC_on_imbalanced_data_/1325827", "title"=>"A re-analysis of the MiRFinder study reveals that PRC is stronger than ROC on imbalanced data.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935525"], "description"=>"<p>ACC: accuracy; ERR: error rate; SN: sensitivity; TPR: true positive rate; REC: recall; SP: specificity; FPR: false positive rate; PREC: precision; PPV: positive predictive value; MCC: Matthews correlation coefficient; F: F score; TP: true positives; TN: true negatives; FP: false positives; FN: false negatives</p><p>Basic evaluation measures from the confusion matrix.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325828, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.t001", "stats"=>{"downloads"=>6, "page_views"=>37, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Basic_evaluation_measures_from_the_confusion_matrix_/1325828", "title"=>"Basic evaluation measures from the confusion matrix.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935526"], "description"=>"<p>For the numbers of true and false positives and negatives in the two datasets, see <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0118432#pone.0118432.g001\" target=\"_blank\">Fig. 1C</a>.</p><p>Example of basic evaluation measures on a balanced and on an imbalanced dataset.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325829, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.t002", "stats"=>{"downloads"=>8, "page_views"=>25, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Example_of_basic_evaluation_measures_on_a_balanced_and_on_an_imbalanced_dataset_/1325829", "title"=>"Example of basic evaluation measures on a balanced and on an imbalanced dataset.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935527"], "description"=>"<p>N: normal distribution with mean and variance; Beta: Beta distribution with shape parameters. For performance level Perfect, fixed values 1 and 0 were used</p><p>Score distributions of positives and negatives for the performance simulations.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325830, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.t003", "stats"=>{"downloads"=>9, "page_views"=>13, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Score_distributions_of_positives_and_negatives_for_the_performance_simulations_/1325830", "title"=>"Score distributions of positives and negatives for the performance simulations.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935528"], "description"=>"<p><sup>a</sup>SVM: type of SVM, Data: data type, Eval: evaluation method.</p><p><sup>b</sup>The total number of articles is 58.</p><p><sup>c</sup>Filtered by SVM binary (BS) AND Imbalanced (IB1 or IB2) AND NOT Small sample size (SS). The total number of these articles is 33.</p><p>Literature analysis summarized by three main categories and six subcategories.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325831, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.t004", "stats"=>{"downloads"=>9, "page_views"=>20, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Literature_analysis_summarized_by_three_main_categories_and_six_subcategories_/1325831", "title"=>"Literature analysis summarized by three main categories and six subcategories.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935529"], "description"=>"<p>Area under the curve (AUC) scores of ROC and PRC curves on datasets T1 and T2. The best AUC score in each column is marked with an asterisk (*).</p><p>AUC scores of ROC and PRC for T1 and T2.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325832, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.t005", "stats"=>{"downloads"=>5, "page_views"=>29, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_AUC_scores_of_ROC_and_PRC_for_T1_and_T2_/1325832", "title"=>"AUC scores of ROC and PRC for T1 and T2.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935543"], "description"=>"<div><p>Binary classifiers are routinely evaluated with performance measures such as sensitivity and specificity, and performance is frequently illustrated with Receiver Operating Characteristics (ROC) plots. Alternative measures such as positive predictive value (PPV) and the associated Precision/Recall (PRC) plots are used less frequently. Many bioinformatics studies develop and evaluate classifiers that are to be applied to strongly imbalanced datasets in which the number of negatives outweighs the number of positives significantly. While ROC plots are visually appealing and provide an overview of a classifier's performance across a wide range of specificities, one can ask whether ROC plots could be misleading when applied in imbalanced classification scenarios. We show here that the visual interpretability of ROC plots in the context of imbalanced datasets can be deceptive with respect to conclusions about the reliability of classification performance, owing to an intuitive but wrong interpretation of specificity. PRC plots, on the other hand, can provide the viewer with an accurate prediction of future classification performance due to the fact that they evaluate the fraction of true positives among positive predictions. Our findings have potential implications for the interpretation of a large number of studies that use ROC plots on imbalanced datasets.</p></div>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325835, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432", "stats"=>{"downloads"=>8, "page_views"=>20, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_Precision_Recall_Plot_Is_More_Informative_than_the_ROC_Plot_When_Evaluating_Binary_Classifiers_on_Imbalanced_Datasets_/1325835", "title"=>"The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935513"], "description"=>"<p>(A) The left oval shows two actual labels: positives (P; blue; top half) and negatives (N; red; bottom half). The right oval shows two predicted labels: “predicted as positive” (light green; top left half) and “predicted as negative” (orange; bottom right half). A black line represents a classifier that separates the data into “predicted as positive” indicated by the upward arrow “P” and “predicted as negative” indicated by the downward arrow “N”. (B) Combining two actual and two predicted labels produces four outcomes: True positive (TP; green), False negative (FN; purple), False positive (FP; yellow), and True negative (TN; red). (C) Two ovals show examples of TPs, FPs, TNs, and FNs for balanced (left) and imbalanced (right) data. Both examples use 20 data instances including 10 positives and 10 negatives for the balanced, and 5 positives and 15 negatives for the imbalanced example.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325816, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g001", "stats"=>{"downloads"=>0, "page_views"=>13, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Actual_and_predicted_labels_generate_four_outcomes_of_the_confusion_matrix_/1325816", "title"=>"Actual and predicted labels generate four outcomes of the confusion matrix.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935515"], "description"=>"<p>(A) The ROC space contains one basic ROC curve and points (black) as well as four alternative curves and points; tied lower bound (green), tied upper bound (dark yellow), convex hull (light blue), and default values for missing prediction data (magenta). The numbers next to the ROC points indicate the ranks of the scores to calculate FPRs and TPRs from 10 positives and 10 negatives (See Table A in <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0118432#pone.0118432.s001\" target=\"_blank\">S1 File</a> for the actual scores). (B) The PRC space contains the PR points corresponding to those in the ROC space.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325818, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g002", "stats"=>{"downloads"=>1, "page_views"=>11, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_PRC_curves_have_one_to_one_relationships_with_ROC_curves_/1325818", "title"=>"PRC curves have one-to-one relationships with ROC curves.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935517"], "description"=>"<p>We randomly sampled 250 negatives and 250 positives for Rand, ER-, ER+, Excel, and Perf, followed by converting the scores to the ranks from 1 to 500. Red circles represent 250 negatives, whereas green triangles represent 250 positives.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325820, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g003", "stats"=>{"downloads"=>0, "page_views"=>7, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Combinations_of_positive_and_negative_score_distributions_generate_five_different_levels_for_the_simulation_analysis_/1325820", "title"=>"Combinations of positive and negative score distributions generate five different levels for the simulation analysis.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935518"], "description"=>"<p>T1 contains miRNA genes from miRBase as positives. Negatives were generated by randomly shuffling the nucleotides of the positives. For T2, the RNAz tool was used to generate miRNA gene candidates. Positives are candidate genes that overlap with the actual miRNA genes from miRBase.</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325821, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g004", "stats"=>{"downloads"=>6, "page_views"=>15, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Simple_scheme_diagrams_on_the_generation_of_datasets_T1_and_T2_/1325821", "title"=>"Simple scheme diagrams on the generation of datasets T1 and T2.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}
  • {"files"=>["https://ndownloader.figshare.com/files/1935519"], "description"=>"<p>Each panel contains two plots with balanced (left) and imbalanced (right) for (A) ROC, (B) CROC with exponential function: f(x) = (1 - exp(-αx))/(1 - exp(-α)) where α = 7, (C) CC, and (D) PRC. Five curves represent five different performance levels: Random (Rand; red), Poor early retrieval (ER-; blue), Good early retrieval (ER+; green), Excellent (Excel; purple), and Perfect (Perf; orange).</p>", "links"=>[], "tags"=>["Receiver Operating Characteristics", "use ROC plots", "prc", "imbalanced datasets", "ppv", "future classification performance", "imbalanced classification scenarios", "Many bioinformatics studies", "ROC plots"], "article_id"=>1325822, "categories"=>["Biological Sciences"], "users"=>["Takaya Saito", "Marc Rehmsmeier"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0118432.g005", "stats"=>{"downloads"=>0, "page_views"=>24, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_PRC_is_changed_but_the_other_plots_are_unchanged_between_balanced_and_imbalanced_data_/1325822", "title"=>"PRC is changed but the other plots are unchanged between balanced and imbalanced data.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2015-03-04 03:34:02"}

PMC Usage Stats | Further Information

  • {"unique-ip"=>"37", "full-text"=>"50", "pdf"=>"12", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"4"}
  • {"unique-ip"=>"48", "full-text"=>"52", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"12", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"5"}
  • {"unique-ip"=>"66", "full-text"=>"70", "pdf"=>"15", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"33", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2015", "month"=>"6"}
  • {"unique-ip"=>"87", "full-text"=>"100", "pdf"=>"13", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"26", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2015", "month"=>"7"}
  • {"unique-ip"=>"18", "full-text"=>"17", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2015", "month"=>"3"}
  • {"unique-ip"=>"136", "full-text"=>"148", "pdf"=>"20", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"42", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"8"}
  • {"unique-ip"=>"158", "full-text"=>"145", "pdf"=>"29", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"31", "supp-data"=>"3", "cited-by"=>"0", "year"=>"2015", "month"=>"9"}
  • {"unique-ip"=>"197", "full-text"=>"211", "pdf"=>"24", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"51", "supp-data"=>"3", "cited-by"=>"1", "year"=>"2015", "month"=>"10"}
  • {"unique-ip"=>"152", "full-text"=>"162", "pdf"=>"25", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"30", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2016", "month"=>"2"}
  • {"unique-ip"=>"172", "full-text"=>"186", "pdf"=>"23", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"40", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2015", "month"=>"11"}
  • {"unique-ip"=>"129", "full-text"=>"130", "pdf"=>"20", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"16", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"12"}
  • {"unique-ip"=>"127", "full-text"=>"130", "pdf"=>"20", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"38", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"1"}
  • {"unique-ip"=>"184", "full-text"=>"191", "pdf"=>"21", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"65", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2016", "month"=>"3"}
  • {"unique-ip"=>"216", "full-text"=>"219", "pdf"=>"47", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"44", "supp-data"=>"0", "cited-by"=>"2", "year"=>"2016", "month"=>"4"}
  • {"unique-ip"=>"200", "full-text"=>"218", "pdf"=>"28", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"47", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"5"}
  • {"unique-ip"=>"169", "full-text"=>"184", "pdf"=>"25", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"30", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"6"}
  • {"unique-ip"=>"159", "full-text"=>"184", "pdf"=>"20", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"44", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"7"}
  • {"unique-ip"=>"188", "full-text"=>"245", "pdf"=>"37", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"49", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"8"}
  • {"unique-ip"=>"231", "full-text"=>"281", "pdf"=>"33", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"49", "supp-data"=>"3", "cited-by"=>"3", "year"=>"2016", "month"=>"9"}
  • {"unique-ip"=>"270", "full-text"=>"294", "pdf"=>"31", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"68", "supp-data"=>"5", "cited-by"=>"1", "year"=>"2016", "month"=>"10"}
  • {"unique-ip"=>"346", "full-text"=>"406", "pdf"=>"40", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"82", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2016", "month"=>"11"}
  • {"unique-ip"=>"348", "full-text"=>"405", "pdf"=>"40", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"96", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2016", "month"=>"12"}
  • {"unique-ip"=>"309", "full-text"=>"347", "pdf"=>"36", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"70", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"1"}
  • {"unique-ip"=>"707", "full-text"=>"1211", "pdf"=>"67", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"85", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"630", "full-text"=>"724", "pdf"=>"81", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"125", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"578", "full-text"=>"684", "pdf"=>"47", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"107", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"571", "full-text"=>"702", "pdf"=>"53", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"114", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"491", "full-text"=>"549", "pdf"=>"56", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"123", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"556", "full-text"=>"641", "pdf"=>"71", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"116", "supp-data"=>"2", "cited-by"=>"1", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"535", "full-text"=>"653", "pdf"=>"41", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"149", "supp-data"=>"1", "cited-by"=>"2", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"798", "full-text"=>"951", "pdf"=>"91", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"189", "supp-data"=>"6", "cited-by"=>"2", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"737", "full-text"=>"820", "pdf"=>"64", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"203", "supp-data"=>"3", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
  • {"unique-ip"=>"735", "full-text"=>"831", "pdf"=>"52", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"189", "supp-data"=>"3", "cited-by"=>"0", "year"=>"2017", "month"=>"11"}
  • {"unique-ip"=>"561", "full-text"=>"606", "pdf"=>"53", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"127", "supp-data"=>"3", "cited-by"=>"1", "year"=>"2017", "month"=>"12"}
  • {"unique-ip"=>"649", "full-text"=>"735", "pdf"=>"68", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"146", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2018", "month"=>"1"}
  • {"unique-ip"=>"21", "full-text"=>"22", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"9", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"2"}
  • {"unique-ip"=>"768", "full-text"=>"848", "pdf"=>"76", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"128", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2018", "month"=>"3"}
  • {"unique-ip"=>"652", "full-text"=>"724", "pdf"=>"87", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"31", "supp-data"=>"6", "cited-by"=>"2", "year"=>"2019", "month"=>"1"}
  • {"unique-ip"=>"712", "full-text"=>"864", "pdf"=>"105", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"30", "supp-data"=>"6", "cited-by"=>"1", "year"=>"2018", "month"=>"9"}
  • {"unique-ip"=>"549", "full-text"=>"649", "pdf"=>"67", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"13", "supp-data"=>"6", "cited-by"=>"5", "year"=>"2018", "month"=>"12"}
  • {"unique-ip"=>"598", "full-text"=>"683", "pdf"=>"70", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"21", "supp-data"=>"4", "cited-by"=>"1", "year"=>"2018", "month"=>"4"}
  • {"unique-ip"=>"647", "full-text"=>"775", "pdf"=>"91", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"38", "supp-data"=>"5", "cited-by"=>"1", "year"=>"2018", "month"=>"5"}
  • {"unique-ip"=>"697", "full-text"=>"817", "pdf"=>"85", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"34", "supp-data"=>"2", "cited-by"=>"1", "year"=>"2018", "month"=>"6"}
  • {"unique-ip"=>"520", "full-text"=>"599", "pdf"=>"45", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"16", "supp-data"=>"2", "cited-by"=>"1", "year"=>"2018", "month"=>"7"}
  • {"unique-ip"=>"662", "full-text"=>"815", "pdf"=>"74", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"12", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2018", "month"=>"8"}
  • {"unique-ip"=>"766", "full-text"=>"892", "pdf"=>"91", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"44", "supp-data"=>"4", "cited-by"=>"1", "year"=>"2018", "month"=>"10"}
  • {"unique-ip"=>"799", "full-text"=>"934", "pdf"=>"115", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"32", "supp-data"=>"6", "cited-by"=>"1", "year"=>"2018", "month"=>"11"}
  • {"unique-ip"=>"600", "full-text"=>"710", "pdf"=>"96", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"19", "supp-data"=>"10", "cited-by"=>"1", "year"=>"2019", "month"=>"2"}
  • {"unique-ip"=>"728", "full-text"=>"833", "pdf"=>"96", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"22", "supp-data"=>"4", "cited-by"=>"1", "year"=>"2019", "month"=>"3"}
  • {"unique-ip"=>"874", "full-text"=>"1049", "pdf"=>"142", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"45", "supp-data"=>"7", "cited-by"=>"4", "year"=>"2019", "month"=>"4"}
  • {"unique-ip"=>"1454", "full-text"=>"1883", "pdf"=>"201", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"32", "supp-data"=>"3", "cited-by"=>"4", "year"=>"2019", "month"=>"5"}
  • {"unique-ip"=>"754", "full-text"=>"871", "pdf"=>"122", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"28", "supp-data"=>"2", "cited-by"=>"4", "year"=>"2019", "month"=>"8"}
  • {"unique-ip"=>"780", "full-text"=>"902", "pdf"=>"115", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"33", "supp-data"=>"3", "cited-by"=>"3", "year"=>"2019", "month"=>"9"}
  • {"unique-ip"=>"933", "full-text"=>"1245", "pdf"=>"117", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"29", "supp-data"=>"3", "cited-by"=>"6", "year"=>"2019", "month"=>"10"}
  • {"unique-ip"=>"708", "full-text"=>"859", "pdf"=>"98", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"17", "supp-data"=>"0", "cited-by"=>"10", "year"=>"2019", "month"=>"12"}
  • {"unique-ip"=>"900", "full-text"=>"1046", "pdf"=>"196", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"35", "supp-data"=>"1", "cited-by"=>"5", "year"=>"2020", "month"=>"2"}
  • {"unique-ip"=>"950", "full-text"=>"1168", "pdf"=>"176", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"21", "supp-data"=>"3", "cited-by"=>"5", "year"=>"2020", "month"=>"3"}
  • {"unique-ip"=>"1029", "full-text"=>"1309", "pdf"=>"158", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"25", "supp-data"=>"9", "cited-by"=>"6", "year"=>"2020", "month"=>"4"}
  • {"unique-ip"=>"1086", "full-text"=>"1325", "pdf"=>"151", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"44", "supp-data"=>"5", "cited-by"=>"5", "year"=>"2020", "month"=>"5"}
  • {"unique-ip"=>"1026", "full-text"=>"1310", "pdf"=>"156", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"28", "supp-data"=>"1", "cited-by"=>"3", "year"=>"2020", "month"=>"6"}
  • {"unique-ip"=>"728", "full-text"=>"950", "pdf"=>"97", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"48", "supp-data"=>"7", "cited-by"=>"3", "year"=>"2020", "month"=>"7"}
  • {"unique-ip"=>"690", "full-text"=>"820", "pdf"=>"96", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"17", "supp-data"=>"4", "cited-by"=>"8", "year"=>"2020", "month"=>"8"}
  • {"unique-ip"=>"667", "full-text"=>"778", "pdf"=>"129", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"14", "supp-data"=>"7", "cited-by"=>"4", "year"=>"2020", "month"=>"9"}
  • {"unique-ip"=>"798", "full-text"=>"981", "pdf"=>"117", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"32", "supp-data"=>"2", "cited-by"=>"2", "year"=>"2020", "month"=>"10"}

Relative Metric

{"start_date"=>"2015-01-01T00:00:00Z", "end_date"=>"2015-12-31T00:00:00Z", "subject_areas"=>[]}

F1000Prime | Further Information

Loading … Spinner
There are currently no alerts