Fast screening of covariates in population models empowered by machine learning View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2021-05-21

AUTHORS

Emeric Sibieude, Akash Khandelwal, Jan S. Hesthaven, Pascal Girard, Nadia Terranova

ABSTRACT

One of the objectives of Pharmacometry (PMX) population modeling is the identification of significant and clinically relevant relationships between parameters and covariates. Here, we demonstrate how this complex selection task could benefit from supervised learning algorithms using importance scores. We compare various classical methods with three machine learning (ML) methods applied to NONMEM empirical Bayes estimates: random forest, neural networks (NNs), and support vector regression (SVR). The performance of the ML models is assessed using receiver operating characteristic (ROC) curves. The F1 score, which measures test accuracy, is used to compare ML and PMX approaches. Methods are applied to different scenarios of covariate influence based on simulated pharmacokinetics data. ML achieved similar or better F1 scores than stepwise covariate modeling (SCM) and conditional sampling for stepwise approach based on correlation tests (COSSAC). Correlations between covariates and the number of false covariates does not affect the performance of any method, but effect size has an impact. Methods are not equivalent with respect to computational speed; SCM is 30 and 100-times slower than NN and SVR, respectively. The results are validated in an additional scenario involving 100 covariates. Taken together, the results indicate that ML methods can greatly increase the efficiency of population covariate model building in the case of large datasets or complex models that require long run-times. This can provide fast initial covariate screening, which can be followed by more conventional PMX approaches to assess the clinical relevance of selected covariates and build the final model. More... »

PAGES

597-609

References to SciGraph publications

  • 2005. A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation in ADVANCES IN INFORMATION RETRIEVAL
  • 1999-02. Modeling of Pharmacokinetic/Pharmacodynamic (PK/PD) Relationships: Concepts and Perspectives in PHARMACEUTICAL RESEARCH
  • 2019-02-11. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence in NATURE MEDICINE
  • 1981-12. Understanding the Dose-Effect Relationship in CLINICAL PHARMACOKINETICS
  • 2001-10. Random Forests in MACHINE LEARNING
  • 1992-10-01. Building population pharmacokineticpharmacodynamic models. I. Models for covariate effects in JOURNAL OF PHARMACOKINETICS AND PHARMACODYNAMICS
  • 1998-06. A Tutorial on Support Vector Machines for Pattern Recognition in DATA MINING AND KNOWLEDGE DISCOVERY
  • 2016-09-07. Enhanced Method for Diagnosing Pharmacometric Models: Random Sampling from Conditional Distributions in PHARMACEUTICAL RESEARCH
  • 2016-03-02. Accelerating Monte Carlo power studies through parametric power estimation in JOURNAL OF PHARMACOKINETICS AND PHARMACODYNAMICS
  • 2007-09-11. Computational Models to Assign Biopharmaceutics Drug Disposition Classification from Molecular Structure in PHARMACEUTICAL RESEARCH
  • 2020-03-16. Machine Learning Analysis of Individual Tumor Lesions in Four Metastatic Colorectal Cancer Clinical Studies: Linking Tumor Heterogeneity to Overall Survival in THE AAPS JOURNAL
  • 2007-05-22. The lasso—a novel method for predictive covariate model building in nonlinear mixed effects models in JOURNAL OF PHARMACOKINETICS AND PHARMACODYNAMICS
  • 2014-07-30. A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening in GENOME MEDICINE
  • 1998-09. Automated Covariate Model Building Within NONMEM in PHARMACEUTICAL RESEARCH
  • 2011-07-02. A Fast Method for Testing Covariates in Population PK/PD Models in THE AAPS JOURNAL
  • 2010. Logistic Regression, A Self-Learning Text in NONE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10928-021-09757-w

    DOI

    http://dx.doi.org/10.1007/s10928-021-09757-w

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1138222486

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/34019213


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Medical and Health Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1115", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Pharmacology and Pharmaceutical Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Algorithms", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Bayes Theorem", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Drug Evaluation, Preclinical", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Humans", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Machine Learning", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Models, Statistical", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neural Networks, Computer", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Pharmacokinetics", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "ROC Curve", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Support Vector Machine", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland", 
              "id": "http://www.grid.ac/institutes/grid.39009.33", 
              "name": [
                "School of Basic Sciences, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland", 
                "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sibieude", 
            "givenName": "Emeric", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Merck Healthcare KGaA, Darmstadt, Germany", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Merck Healthcare KGaA, Darmstadt, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Khandelwal", 
            "givenName": "Akash", 
            "id": "sg:person.010613427050.54", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010613427050.54"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Chair of Computational Mathematics and Simulation Science (MCSS), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland", 
              "id": "http://www.grid.ac/institutes/grid.5333.6", 
              "name": [
                "Chair of Computational Mathematics and Simulation Science (MCSS), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hesthaven", 
            "givenName": "Jan S.", 
            "id": "sg:person.0627474224.07", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0627474224.07"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland", 
              "id": "http://www.grid.ac/institutes/grid.39009.33", 
              "name": [
                "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Girard", 
            "givenName": "Pascal", 
            "id": "sg:person.012661201622.56", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012661201622.56"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland", 
              "id": "http://www.grid.ac/institutes/grid.39009.33", 
              "name": [
                "Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Terranova", 
            "givenName": "Nadia", 
            "id": "sg:person.01175701615.59", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01175701615.59"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1009715923555", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042048349", 
              "https://doi.org/10.1023/a:1009715923555"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11095-007-9435-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034726965", 
              "https://doi.org/10.1007/s11095-007-9435-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1010933404324", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024739340", 
              "https://doi.org/10.1023/a:1010933404324"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1208/s12248-011-9289-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017266963", 
              "https://doi.org/10.1208/s12248-011-9289-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.2165/00003088-198106060-00002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024854213", 
              "https://doi.org/10.2165/00003088-198106060-00002"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13073-014-0057-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1051549373", 
              "https://doi.org/10.1186/s13073-014-0057-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1208/s12248-020-0434-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1125714263", 
              "https://doi.org/10.1208/s12248-020-0434-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10928-007-9057-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033884117", 
              "https://doi.org/10.1007/s10928-007-9057-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf01061469", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000869925", 
              "https://doi.org/10.1007/bf01061469"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10928-016-9468-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003703329", 
              "https://doi.org/10.1007/s10928-016-9468-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1011907920641", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023547498", 
              "https://doi.org/10.1023/a:1011907920641"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4419-1742-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024879451", 
              "https://doi.org/10.1007/978-1-4419-1742-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11095-016-2020-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022365099", 
              "https://doi.org/10.1007/s11095-016-2020-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1011970125687", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042864451", 
              "https://doi.org/10.1023/a:1011970125687"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41591-018-0335-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1112058854", 
              "https://doi.org/10.1038/s41591-018-0335-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-31865-1_25", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011627113", 
              "https://doi.org/10.1007/978-3-540-31865-1_25"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2021-05-21", 
        "datePublishedReg": "2021-05-21", 
        "description": "One of the objectives of Pharmacometry (PMX) population modeling is the identification of significant and clinically relevant relationships between parameters and covariates. Here, we demonstrate how this complex selection task could benefit from supervised learning algorithms using importance scores. We compare various classical methods with three machine learning (ML) methods applied to NONMEM empirical Bayes estimates: random forest, neural networks (NNs), and support vector regression (SVR). The performance of the ML models is assessed using receiver operating characteristic (ROC) curves. The F1 score, which measures test accuracy, is used to compare ML and PMX approaches. Methods are applied to different scenarios of covariate influence based on simulated pharmacokinetics data. ML achieved similar or better F1 scores than stepwise covariate modeling (SCM) and conditional sampling for stepwise approach based on correlation tests (COSSAC). Correlations between covariates and the number of false covariates does not affect the performance of any method, but effect size has an impact. Methods are not equivalent with respect to computational speed; SCM is 30 and 100-times slower than NN and SVR, respectively. The results are validated in an additional scenario involving 100 covariates. Taken together, the results indicate that ML methods can greatly increase the efficiency of population covariate model building in the case of large datasets or complex models that require long run-times. This can provide fast initial covariate screening, which can be followed by more conventional PMX approaches to assess the clinical relevance of selected covariates and build the final model.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s10928-021-09757-w", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1016394", 
            "issn": [
              "1567-567X", 
              "2168-5789"
            ], 
            "name": "Journal of Pharmacokinetics and Pharmacodynamics", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "4", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "48"
          }
        ], 
        "keywords": [
          "neural network", 
          "F1 score", 
          "best F1 score", 
          "machine learning methods", 
          "learning methods", 
          "random forest", 
          "ML models", 
          "large datasets", 
          "stepwise covariate modeling", 
          "computational speed", 
          "vector regression", 
          "ML methods", 
          "empirical Bayes", 
          "selection task", 
          "complex models", 
          "population model", 
          "classical methods", 
          "test accuracy", 
          "conditional sampling", 
          "importance scores", 
          "different scenarios", 
          "model building", 
          "population modeling", 
          "covariate screening", 
          "covariate model building", 
          "scenarios", 
          "relevant relationships", 
          "Bayes", 
          "covariate modeling", 
          "modeling", 
          "machine", 
          "algorithm", 
          "dataset", 
          "network", 
          "model", 
          "performance", 
          "task", 
          "accuracy", 
          "method", 
          "SVR", 
          "covariates", 
          "covariate influences", 
          "approach", 
          "parameters", 
          "additional scenarios", 
          "final model", 
          "effect size", 
          "speed", 
          "efficiency", 
          "characteristic curve", 
          "buildings", 
          "results", 
          "receiver", 
          "data", 
          "sampling", 
          "curves", 
          "number", 
          "respect", 
          "scores", 
          "cases", 
          "objective", 
          "identification", 
          "regression", 
          "forest", 
          "stepwise approach", 
          "size", 
          "fast screening", 
          "relevance", 
          "relationship", 
          "correlation", 
          "influence", 
          "correlation test", 
          "impact", 
          "PMX", 
          "test", 
          "mL", 
          "clinical relevance", 
          "pharmacokinetic data", 
          "screening"
        ], 
        "name": "Fast screening of covariates in population models empowered by machine learning", 
        "pagination": "597-609", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1138222486"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10928-021-09757-w"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "34019213"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10928-021-09757-w", 
          "https://app.dimensions.ai/details/publication/pub.1138222486"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-11-24T21:07", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/article/article_893.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s10928-021-09757-w"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s10928-021-09757-w'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10928-021-09757-w'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10928-021-09757-w'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10928-021-09757-w'


     

    This table displays all metadata directly associated to this object as RDF triples.

    278 TRIPLES      21 PREDICATES      130 URIs      106 LITERALS      17 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10928-021-09757-w schema:about N06d1081ee5ec4fb7b01af709c7bdaa85
    2 N07d90e0c2e2b488aa850f64196aaf036
    3 N1065929f1d5c4d4a81da79a8885d1ddc
    4 N33d83750c0284a7b9c7e20ac1007acb3
    5 N56b5d6db0f55491a8bcbd49587a2eb2a
    6 N8299bd3d63fb42e8bee563b2eec2fe6c
    7 Nb60c4600b4b744be93a28617ba418e2e
    8 Nca32ef90b990449bbeaf35964cd77941
    9 Ndf6f54fc894d4462ad55f9c41f5a8c2a
    10 Ne6cba9df1cca40c79b156d491b6cb0ec
    11 anzsrc-for:11
    12 anzsrc-for:1115
    13 schema:author N86407f13ea724a2197dee5a884dd2250
    14 schema:citation sg:pub.10.1007/978-1-4419-1742-3
    15 sg:pub.10.1007/978-3-540-31865-1_25
    16 sg:pub.10.1007/bf01061469
    17 sg:pub.10.1007/s10928-007-9057-1
    18 sg:pub.10.1007/s10928-016-9468-y
    19 sg:pub.10.1007/s11095-007-9435-9
    20 sg:pub.10.1007/s11095-016-2020-3
    21 sg:pub.10.1023/a:1009715923555
    22 sg:pub.10.1023/a:1010933404324
    23 sg:pub.10.1023/a:1011907920641
    24 sg:pub.10.1023/a:1011970125687
    25 sg:pub.10.1038/s41591-018-0335-9
    26 sg:pub.10.1186/s13073-014-0057-7
    27 sg:pub.10.1208/s12248-011-9289-2
    28 sg:pub.10.1208/s12248-020-0434-7
    29 sg:pub.10.2165/00003088-198106060-00002
    30 schema:datePublished 2021-05-21
    31 schema:datePublishedReg 2021-05-21
    32 schema:description One of the objectives of Pharmacometry (PMX) population modeling is the identification of significant and clinically relevant relationships between parameters and covariates. Here, we demonstrate how this complex selection task could benefit from supervised learning algorithms using importance scores. We compare various classical methods with three machine learning (ML) methods applied to NONMEM empirical Bayes estimates: random forest, neural networks (NNs), and support vector regression (SVR). The performance of the ML models is assessed using receiver operating characteristic (ROC) curves. The F1 score, which measures test accuracy, is used to compare ML and PMX approaches. Methods are applied to different scenarios of covariate influence based on simulated pharmacokinetics data. ML achieved similar or better F1 scores than stepwise covariate modeling (SCM) and conditional sampling for stepwise approach based on correlation tests (COSSAC). Correlations between covariates and the number of false covariates does not affect the performance of any method, but effect size has an impact. Methods are not equivalent with respect to computational speed; SCM is 30 and 100-times slower than NN and SVR, respectively. The results are validated in an additional scenario involving 100 covariates. Taken together, the results indicate that ML methods can greatly increase the efficiency of population covariate model building in the case of large datasets or complex models that require long run-times. This can provide fast initial covariate screening, which can be followed by more conventional PMX approaches to assess the clinical relevance of selected covariates and build the final model.
    33 schema:genre article
    34 schema:isAccessibleForFree true
    35 schema:isPartOf Na173ce9666b94d5d899cd294fd2b2349
    36 Ne8e3a146c4544ff5afd8d507af6b1121
    37 sg:journal.1016394
    38 schema:keywords Bayes
    39 F1 score
    40 ML methods
    41 ML models
    42 PMX
    43 SVR
    44 accuracy
    45 additional scenarios
    46 algorithm
    47 approach
    48 best F1 score
    49 buildings
    50 cases
    51 characteristic curve
    52 classical methods
    53 clinical relevance
    54 complex models
    55 computational speed
    56 conditional sampling
    57 correlation
    58 correlation test
    59 covariate influences
    60 covariate model building
    61 covariate modeling
    62 covariate screening
    63 covariates
    64 curves
    65 data
    66 dataset
    67 different scenarios
    68 effect size
    69 efficiency
    70 empirical Bayes
    71 fast screening
    72 final model
    73 forest
    74 identification
    75 impact
    76 importance scores
    77 influence
    78 large datasets
    79 learning methods
    80 mL
    81 machine
    82 machine learning methods
    83 method
    84 model
    85 model building
    86 modeling
    87 network
    88 neural network
    89 number
    90 objective
    91 parameters
    92 performance
    93 pharmacokinetic data
    94 population model
    95 population modeling
    96 random forest
    97 receiver
    98 regression
    99 relationship
    100 relevance
    101 relevant relationships
    102 respect
    103 results
    104 sampling
    105 scenarios
    106 scores
    107 screening
    108 selection task
    109 size
    110 speed
    111 stepwise approach
    112 stepwise covariate modeling
    113 task
    114 test
    115 test accuracy
    116 vector regression
    117 schema:name Fast screening of covariates in population models empowered by machine learning
    118 schema:pagination 597-609
    119 schema:productId N10e32a08a03b4c6bb64527f99e3961d0
    120 Na22884d2da174cda85f9457bf5085eaa
    121 Ne8d5e4f2a93f4fa58e9aa5782c0291dc
    122 schema:sameAs https://app.dimensions.ai/details/publication/pub.1138222486
    123 https://doi.org/10.1007/s10928-021-09757-w
    124 schema:sdDatePublished 2022-11-24T21:07
    125 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    126 schema:sdPublisher Ne046c548bbb344efac6e9c028c2480b1
    127 schema:url https://doi.org/10.1007/s10928-021-09757-w
    128 sgo:license sg:explorer/license/
    129 sgo:sdDataset articles
    130 rdf:type schema:ScholarlyArticle
    131 N06d1081ee5ec4fb7b01af709c7bdaa85 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    132 schema:name Pharmacokinetics
    133 rdf:type schema:DefinedTerm
    134 N07d90e0c2e2b488aa850f64196aaf036 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    135 schema:name ROC Curve
    136 rdf:type schema:DefinedTerm
    137 N0ac7960c1ca74125bc70b828794366e8 rdf:first sg:person.010613427050.54
    138 rdf:rest N942aa81d9bf94d2c9a4fd231bcccf25f
    139 N1065929f1d5c4d4a81da79a8885d1ddc schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    140 schema:name Models, Statistical
    141 rdf:type schema:DefinedTerm
    142 N10e32a08a03b4c6bb64527f99e3961d0 schema:name dimensions_id
    143 schema:value pub.1138222486
    144 rdf:type schema:PropertyValue
    145 N19a2659434cb4369929e7d351ab069bc schema:affiliation grid-institutes:grid.39009.33
    146 schema:familyName Sibieude
    147 schema:givenName Emeric
    148 rdf:type schema:Person
    149 N33d83750c0284a7b9c7e20ac1007acb3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    150 schema:name Support Vector Machine
    151 rdf:type schema:DefinedTerm
    152 N56b5d6db0f55491a8bcbd49587a2eb2a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    153 schema:name Humans
    154 rdf:type schema:DefinedTerm
    155 N8299bd3d63fb42e8bee563b2eec2fe6c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    156 schema:name Bayes Theorem
    157 rdf:type schema:DefinedTerm
    158 N86407f13ea724a2197dee5a884dd2250 rdf:first N19a2659434cb4369929e7d351ab069bc
    159 rdf:rest N0ac7960c1ca74125bc70b828794366e8
    160 N8ac74e5472014390b8a2ab876f0c6157 rdf:first sg:person.012661201622.56
    161 rdf:rest Na56f95e182ef497281972c0163e0bbc3
    162 N942aa81d9bf94d2c9a4fd231bcccf25f rdf:first sg:person.0627474224.07
    163 rdf:rest N8ac74e5472014390b8a2ab876f0c6157
    164 Na173ce9666b94d5d899cd294fd2b2349 schema:volumeNumber 48
    165 rdf:type schema:PublicationVolume
    166 Na22884d2da174cda85f9457bf5085eaa schema:name pubmed_id
    167 schema:value 34019213
    168 rdf:type schema:PropertyValue
    169 Na56f95e182ef497281972c0163e0bbc3 rdf:first sg:person.01175701615.59
    170 rdf:rest rdf:nil
    171 Nb60c4600b4b744be93a28617ba418e2e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    172 schema:name Machine Learning
    173 rdf:type schema:DefinedTerm
    174 Nca32ef90b990449bbeaf35964cd77941 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    175 schema:name Algorithms
    176 rdf:type schema:DefinedTerm
    177 Ndf6f54fc894d4462ad55f9c41f5a8c2a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    178 schema:name Neural Networks, Computer
    179 rdf:type schema:DefinedTerm
    180 Ne046c548bbb344efac6e9c028c2480b1 schema:name Springer Nature - SN SciGraph project
    181 rdf:type schema:Organization
    182 Ne6cba9df1cca40c79b156d491b6cb0ec schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    183 schema:name Drug Evaluation, Preclinical
    184 rdf:type schema:DefinedTerm
    185 Ne8d5e4f2a93f4fa58e9aa5782c0291dc schema:name doi
    186 schema:value 10.1007/s10928-021-09757-w
    187 rdf:type schema:PropertyValue
    188 Ne8e3a146c4544ff5afd8d507af6b1121 schema:issueNumber 4
    189 rdf:type schema:PublicationIssue
    190 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
    191 schema:name Medical and Health Sciences
    192 rdf:type schema:DefinedTerm
    193 anzsrc-for:1115 schema:inDefinedTermSet anzsrc-for:
    194 schema:name Pharmacology and Pharmaceutical Sciences
    195 rdf:type schema:DefinedTerm
    196 sg:journal.1016394 schema:issn 1567-567X
    197 2168-5789
    198 schema:name Journal of Pharmacokinetics and Pharmacodynamics
    199 schema:publisher Springer Nature
    200 rdf:type schema:Periodical
    201 sg:person.010613427050.54 schema:affiliation grid-institutes:None
    202 schema:familyName Khandelwal
    203 schema:givenName Akash
    204 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010613427050.54
    205 rdf:type schema:Person
    206 sg:person.01175701615.59 schema:affiliation grid-institutes:grid.39009.33
    207 schema:familyName Terranova
    208 schema:givenName Nadia
    209 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01175701615.59
    210 rdf:type schema:Person
    211 sg:person.012661201622.56 schema:affiliation grid-institutes:grid.39009.33
    212 schema:familyName Girard
    213 schema:givenName Pascal
    214 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012661201622.56
    215 rdf:type schema:Person
    216 sg:person.0627474224.07 schema:affiliation grid-institutes:grid.5333.6
    217 schema:familyName Hesthaven
    218 schema:givenName Jan S.
    219 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0627474224.07
    220 rdf:type schema:Person
    221 sg:pub.10.1007/978-1-4419-1742-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024879451
    222 https://doi.org/10.1007/978-1-4419-1742-3
    223 rdf:type schema:CreativeWork
    224 sg:pub.10.1007/978-3-540-31865-1_25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011627113
    225 https://doi.org/10.1007/978-3-540-31865-1_25
    226 rdf:type schema:CreativeWork
    227 sg:pub.10.1007/bf01061469 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000869925
    228 https://doi.org/10.1007/bf01061469
    229 rdf:type schema:CreativeWork
    230 sg:pub.10.1007/s10928-007-9057-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033884117
    231 https://doi.org/10.1007/s10928-007-9057-1
    232 rdf:type schema:CreativeWork
    233 sg:pub.10.1007/s10928-016-9468-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1003703329
    234 https://doi.org/10.1007/s10928-016-9468-y
    235 rdf:type schema:CreativeWork
    236 sg:pub.10.1007/s11095-007-9435-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034726965
    237 https://doi.org/10.1007/s11095-007-9435-9
    238 rdf:type schema:CreativeWork
    239 sg:pub.10.1007/s11095-016-2020-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022365099
    240 https://doi.org/10.1007/s11095-016-2020-3
    241 rdf:type schema:CreativeWork
    242 sg:pub.10.1023/a:1009715923555 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042048349
    243 https://doi.org/10.1023/a:1009715923555
    244 rdf:type schema:CreativeWork
    245 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
    246 https://doi.org/10.1023/a:1010933404324
    247 rdf:type schema:CreativeWork
    248 sg:pub.10.1023/a:1011907920641 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023547498
    249 https://doi.org/10.1023/a:1011907920641
    250 rdf:type schema:CreativeWork
    251 sg:pub.10.1023/a:1011970125687 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042864451
    252 https://doi.org/10.1023/a:1011970125687
    253 rdf:type schema:CreativeWork
    254 sg:pub.10.1038/s41591-018-0335-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112058854
    255 https://doi.org/10.1038/s41591-018-0335-9
    256 rdf:type schema:CreativeWork
    257 sg:pub.10.1186/s13073-014-0057-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051549373
    258 https://doi.org/10.1186/s13073-014-0057-7
    259 rdf:type schema:CreativeWork
    260 sg:pub.10.1208/s12248-011-9289-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017266963
    261 https://doi.org/10.1208/s12248-011-9289-2
    262 rdf:type schema:CreativeWork
    263 sg:pub.10.1208/s12248-020-0434-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1125714263
    264 https://doi.org/10.1208/s12248-020-0434-7
    265 rdf:type schema:CreativeWork
    266 sg:pub.10.2165/00003088-198106060-00002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024854213
    267 https://doi.org/10.2165/00003088-198106060-00002
    268 rdf:type schema:CreativeWork
    269 grid-institutes:None schema:alternateName Merck Healthcare KGaA, Darmstadt, Germany
    270 schema:name Merck Healthcare KGaA, Darmstadt, Germany
    271 rdf:type schema:Organization
    272 grid-institutes:grid.39009.33 schema:alternateName Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland
    273 schema:name Merck Institute for Pharmacometrics (an affiliate of Merck KGaA, Darmstadt, Germany), Merck Serono S.A, Lausanne, Switzerland
    274 School of Basic Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
    275 rdf:type schema:Organization
    276 grid-institutes:grid.5333.6 schema:alternateName Chair of Computational Mathematics and Simulation Science (MCSS), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
    277 schema:name Chair of Computational Mathematics and Simulation Science (MCSS), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
    278 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...