{"id":"https://openalex.org/W147565337","doi":null,"title":"Developing predictive models using electronic medical records: challenges and pitfalls.","display_name":"Developing predictive models using electronic medical records: challenges and pitfalls.","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W147565337","mag":"147565337","pmid":"https://pubmed.ncbi.nlm.nih.gov/24551396","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132"},"language":"en","primary_location":{"id":"pmh:oai:europepmc.org:2909015","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"volume":null,"type":"article","indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044926286","display_name":"Chris Paxton","orcid":"https://orcid.org/0000-0003-1009-5982","observed_orcids":["https://orcid.org/0000-0003-1009-5982"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Paxton","raw_affiliation_strings":["Computer Science Department, Johns Hopkins University, Baltimore, MD 21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Johns Hopkins University, Baltimore, MD 21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029480393","display_name":"Alexandru Niculescu-Mizil","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandru Niculescu-Mizil","raw_affiliation_strings":["NEC Labs America, Princeton, NJ 08540"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America, Princeton, NJ 08540","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055371276","display_name":"Suchi Saria","orcid":"https://orcid.org/0000-0002-7667-5210","observed_orcids":["https://orcid.org/0000-0002-7667-5210"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suchi Saria","raw_affiliation_strings":["Computer Science Department, Johns Hopkins University, Baltimore, MD 21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Johns Hopkins University, Baltimore, MD 21218","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7279,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97119045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"2013","issue":null,"first_page":"1109","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10350","display_name":"Electronic Health Records Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9900000095367432},{"id":"https://openalex.org/keywords/predictive-modeling","display_name":"predictive modeling","score":0.9169999957084656},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.45500001311302185},{"id":"https://openalex.org/keywords/systematic-bias","display_name":"systematic bias","score":0.5540000200271606},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.5009999871253967},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/clinical-implementation","display_name":"clinical implementation","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642274022102356},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.5959742069244385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5342867374420166},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5058676600456238},{"id":"https://openalex.org/C3018060332","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic medical record","level":2,"score":0.5045434236526489},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.4936850965023041},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.48664888739585876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45351260900497437},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.41956040263175964},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39650601148605347},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.18459033966064453},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11758577823638916},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C512399662","wikidata":"https://www.wikidata.org/wiki/Q3505712","display_name":"Family medicine","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005791","descriptor_name":"Patient Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011379","descriptor_name":"Prognosis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012772","descriptor_name":"Shock, Septic","qualifier_ui":"Q000188","qualifier_name":"drug therapy","is_major_topic":true},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"pmh:oai:europepmc.org:2909015","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3900132","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:24551396","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24551396","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.679.9233","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.679.9233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.niculescu-mizil.org/papers/developing-predictive-models-amia-final.pdf","raw_type":"text"},{"id":"mag:147565337","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24551396","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:europepmc.org:2909015","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3900132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"score":0.8560000061988831,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32857312","https://openalex.org/W1481682751","https://openalex.org/W1489605872","https://openalex.org/W1512463805","https://openalex.org/W1576520375","https://openalex.org/W2006454222","https://openalex.org/W2009527638","https://openalex.org/W2010430808","https://openalex.org/W2015597405","https://openalex.org/W2018861466","https://openalex.org/W2040405391","https://openalex.org/W2040709089","https://openalex.org/W2045380240","https://openalex.org/W2046788142","https://openalex.org/W2048653102","https://openalex.org/W2079862130","https://openalex.org/W2107008379","https://openalex.org/W2107947924","https://openalex.org/W2112011799","https://openalex.org/W2113090945","https://openalex.org/W2118858814","https://openalex.org/W2134697946","https://openalex.org/W2142071150","https://openalex.org/W2160691650","https://openalex.org/W2567673615","https://openalex.org/W2582765108","https://openalex.org/W3023757607","https://openalex.org/W4237666362"],"related_works":["https://openalex.org/W2538637016","https://openalex.org/W3015425135","https://openalex.org/W4414054029","https://openalex.org/W4409654815","https://openalex.org/W3020034398","https://openalex.org/W2978168139","https://openalex.org/W2808043865","https://openalex.org/W2395172628","https://openalex.org/W3044246896","https://openalex.org/W4396834548"],"abstract_inverted_index":{"While":[0],"Electronic":[1],"Medical":[2],"Records":[3],"(EMR)":[4],"contain":[5,36],"detailed":[6],"records":[7],"of":[8,78,85,94,130],"the":[9,51,76,82,90,95],"patient-clinician":[10],"encounter":[11],"-":[12,24],"vital":[13],"signs,":[14],"laboratory":[15],"tests,":[16],"symptoms,":[17],"caregivers'":[18],"notes,":[19],"interventions":[20],"prescribed":[21],"and":[22,64,98,122],"outcomes":[23],"developing":[25,108],"predictive":[26,55,70,96],"models":[27,71,109,124],"from":[28,72],"this":[29,58],"data":[30,35],"is":[31],"not":[32],"straightforward.":[33],"These":[34],"systematic":[37],"biases":[38],"that":[39,100,110],"violate":[40],"assumptions":[41],"made":[42],"by":[43],"off-the-shelf":[44],"machine":[45],"learning":[46],"algorithms,":[47],"commonly":[48],"used":[49],"in":[50,114],"literature":[52],"to":[53,68,102,107],"train":[54],"models.":[56],"In":[57],"paper,":[59],"we":[60,117],"discuss":[61],"key":[62],"issues":[63],"subtle":[65],"pitfalls":[66],"specific":[67],"building":[69],"EMR.":[73],"We":[74],"highlight":[75],"importance":[77],"carefully":[79],"considering":[80],"both":[81],"special":[83],"characteristics":[84],"EMR":[86,126],"as":[87,89,133],"well":[88],"intended":[91],"clinical":[92],"use":[93],"model":[97],"show":[99],"failure":[101],"do":[103],"so":[104],"could":[105],"lead":[106],"are":[111],"less":[112],"useful":[113],"practice.":[115],"Finally,":[116],"describe":[118],"approaches":[119],"for":[120],"training":[121],"evaluating":[123],"on":[125],"using":[127],"early":[128],"prediction":[129],"septic":[131],"shock":[132],"our":[134],"example":[135],"application.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":4}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}