{"id":"https://openalex.org/W7203926516","doi":"https://doi.org/10.26092/elib/6360","title":"Applied Machine Learning in Epidemiology: Feature Selection, Benchmarks, and Software","display_name":"Applied Machine Learning in Epidemiology: Feature Selection, Benchmarks, and Software","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7203926516","doi":"https://doi.org/10.26092/elib/6360"},"language":"en","primary_location":{"id":"pmh:oai:media.suub.uni-bremen.de:elib/25247","doi":null,"is_oa":true,"landing_page_url":"https://media.suub.uni-bremen.de/handle/elib/25247","pdf_url":"http://media.suub.uni-bremen.de/bitstreams/86a68648-eac5-4a36-932d-90387ebcdf38/download","source":{"id":"https://openalex.org/S4306402486","display_name":"Media (https://www.suub.uni-bremen.de/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I180437899","host_organization_name":"University of Bremen","host_organization_lineage":["https://openalex.org/I180437899"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"volume":null,"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://media.suub.uni-bremen.de/bitstreams/86a68648-eac5-4a36-932d-90387ebcdf38/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084280943","display_name":"Lukas Burk","orcid":"https://orcid.org/0000-0001-7528-3795","observed_orcids":["https://orcid.org/0000-0001-7528-3795"]},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Burk, Lukas","raw_affiliation_strings":["Universit\u00e4t Bremen"],"raw_orcid":"https://orcid.org/0000-0001-7528-3795","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Bremen","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5084280943"],"corresponding_institution_ids":["https://openalex.org/I180437899"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14374","display_name":"Statistical Methods in Epidemiology","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0003000000142492354,"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/survival-prediction","display_name":"survival prediction","score":0.8849999904632568},{"id":"https://openalex.org/keywords/cox-proportional-hazards-model","display_name":"Cox proportional hazards model","score":0.878000020980835},{"id":"https://openalex.org/keywords/competing-risks","display_name":"competing risks","score":0.597000002861023},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.9139999747276306},{"id":"https://openalex.org/keywords/feature-importance","display_name":"feature importance","score":0.7540000081062317},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.9120000004768372},{"id":"https://openalex.org/keywords/model-x-knockoffs","display_name":"model-X knockoffs","score":0.9660000205039978},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.625},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.8149999976158142},{"id":"https://openalex.org/keywords/plackett-luce-model","display_name":"Plackett-Luce model","score":0.8629999756813049},{"id":"https://openalex.org/keywords/proportional-hazards-assumption","display_name":"proportional hazards assumption","score":0.6129999756813049},{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.6140000224113464},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7253999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894999742507935},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6191999912261963},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C50382708","wikidata":"https://www.wikidata.org/wiki/Q223218","display_name":"Proportional hazards model","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C203868755","wikidata":"https://www.wikidata.org/wiki/Q5353562","display_name":"Elastic net regularization","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:media.suub.uni-bremen.de:elib/25247","doi":null,"is_oa":true,"landing_page_url":"https://media.suub.uni-bremen.de/handle/elib/25247","pdf_url":"http://media.suub.uni-bremen.de/bitstreams/86a68648-eac5-4a36-932d-90387ebcdf38/download","source":{"id":"https://openalex.org/S4306402486","display_name":"Media (https://www.suub.uni-bremen.de/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I180437899","host_organization_name":"University of Bremen","host_organization_lineage":["https://openalex.org/I180437899"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"doi:10.26092/elib/6360","doi":"https://doi.org/10.26092/elib/6360","is_oa":true,"landing_page_url":"https://doi.org/10.26092/elib/6360","pdf_url":null,"source":{"id":"https://openalex.org/S7407052977","display_name":"Staats- und Universit\u00e4tsbibliothek Bremen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210141311","host_organization_name":"Staats- und Universit\u00e4tsbibliothek Bremen","host_organization_lineage":["https://openalex.org/I4210141311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:media.suub.uni-bremen.de:elib/25247","doi":null,"is_oa":true,"landing_page_url":"https://media.suub.uni-bremen.de/handle/elib/25247","pdf_url":"http://media.suub.uni-bremen.de/bitstreams/86a68648-eac5-4a36-932d-90387ebcdf38/download","source":{"id":"https://openalex.org/S4306402486","display_name":"Media (https://www.suub.uni-bremen.de/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I180437899","host_organization_name":"University of Bremen","host_organization_lineage":["https://openalex.org/I180437899"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"sustainable_development_goals":[{"score":0.8048999905586243,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1978856977","display_name":"FOR 5347: KIFOR Lifespan AI: Von longitudinalen Gesundheitsdaten zur Inferenz im Lebensverlauf","funder_award_id":"459360854","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G2709309844","display_name":"Mehr als nur Pr\u00e4diktion: Statistische Inferenz mit maschinellem Lernen","funder_award_id":"437611051","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8464520668","display_name":"MaRDI  Mathematische Forschungsdateninitiative","funder_award_id":"460135501","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8683068404","display_name":"Pancreatic cancer AI for genomics and personalized Medicine","funder_award_id":"101016851","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320313146","display_name":"Freie Hansestadt Bremen","ror":"https://ror.org/03xhyan61"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203926516.pdf","grobid_xml":"https://content.openalex.org/works/W7203926516.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3133996992","https://openalex.org/W4415101065","https://openalex.org/W4412529429","https://openalex.org/W3215970484","https://openalex.org/W2978378060","https://openalex.org/W4221117853","https://openalex.org/W3140814277","https://openalex.org/W2294933374","https://openalex.org/W3154930957","https://openalex.org/W3212037416"],"abstract_inverted_index":{"Predictive":[0],"modeling":[1],"is":[2,203,238],"central":[3],"to":[4,20,86,120,205,317],"epidemiology,":[5],"biostatistics,":[6],"and":[7,41,65,99,157,247,267,275,283,343,352],"adjacent":[8],"fields.":[9],"The":[10,68,175,194,235,252,270,285],"number":[11],"of":[12,23,79,102,140,148,232,310,336],"available":[13],"algorithms":[14,82,90],"keeps":[15],"growing,":[16],"alongside":[17,313],"related":[18],"techniques":[19],"make":[21],"sense":[22],"them,":[24],"leaving":[25],"practitioners":[26],"with":[27,57,94,219,264,298,333],"three":[28,58,326],"common":[29],"questions:":[30],"Which":[31],"algorithm":[32,356],"should":[33],"they":[34],"choose,":[35],"which":[36,49,202],"features":[37,218],"are":[38,46,162,173],"actually":[39],"relevant,":[40],"if":[42],"so,":[43],"how":[44],"relevant":[45],"they,":[47],"in":[48,129,185,211,240,248,358],"way?":[50],"This":[51],"cumulative":[52],"dissertation":[53],"addresses":[54],"these":[55,171],"questions":[56],"main":[59],"contributions":[60,323,347],"focusing":[61],"on":[62,83,91,197,222,340],"empirical":[63],"evaluation":[64,104],"open-source":[66],"software.":[67],"first":[69],"contribution":[70,177,254],"presents":[71,255],"the":[72,113,124,134,141,149,164,198,223,230,294,311,325,359],"most":[73],"comprehensive":[74],"large-scale":[75],"neutral":[76],"comparison":[77],"study":[78,114,243],"survival":[80,160,331],"prediction":[81],"low-dimensional":[84],"data":[85,246],"date,":[87],"evaluating":[88],"19":[89],"34":[92],"datasets":[93],"two":[95],"distinct":[96],"tuning":[97,109],"measures":[98,278],"a":[100,179,212,241,249,265],"total":[101],"six":[103],"measures.":[105],"After":[106],"extensive":[107],"hyperparameter":[108],"via":[110],"Bayesian":[111],"optimization,":[112],"does":[115],"not":[116],"find":[117],"any":[118],"method":[119,181,195],"statistically":[121],"significantly":[122],"outperform":[123],"Cox":[125,150,209],"proportional":[126,142],"hazards":[127,143],"model":[128,136],"aggregate.":[130],"Sensitivity":[131],"analyses":[132],"using":[133],"Plackett-Luce":[135],"indicate":[137],"that":[138,166,214],"violation":[139],"assumption,":[144],"or":[145,302],"generally":[146],"misspecification":[147],"model,":[151],"changes":[152],"this":[153],"picture.":[154],"Model-based":[155],"boosting":[156],"oblique":[158],"random":[159,304],"forests":[161],"among":[163],"methods":[165],"gain":[167],"an":[168,257,334],"advantage":[169],"when":[170],"assumptions":[172],"violated.":[174],"second":[176],"introduces":[178],"novel":[180],"for":[182,217,260],"feature":[183,261,350],"selection":[184],"competing":[186],"event":[187],"settings,":[188],"named":[189],"cooperative":[190],"penalized":[191,208],"regression":[192],"(CooPeR).":[193],"builds":[196],"feature-weighted":[199],"elastic":[200],"net,":[201],"used":[204],"fit":[206],"cause-specific":[207],"models":[210],"manner":[213],"reduces":[215],"penalization":[216,231],"large":[220],"effect":[221],"respective":[224],"other":[225],"event,":[226],"while":[227,279],"also":[228,287],"amplifying":[229],"noise":[233],"features.":[234],"method's":[236],"effectiveness":[237],"demonstrated":[239],"simulation":[242],"mimicking":[244],"gene-sequencing":[245],"real-data":[250],"application.":[251],"third":[253],"\\xplainfi,":[256],"\\rstats":[258],"package":[259,271,286],"importance":[262,277],"analysis":[263,332],"unified":[266],"modular":[268],"interface.":[269],"supports":[272,288],"perturbation-based,":[273],"refitting-based,":[274],"Shapley-based":[276],"supporting":[280],"both":[281],"model-":[282],"learner-importance.":[284],"multiple":[289],"statistical":[290],"inference":[291],"approaches,":[292],"including":[293],"conditional":[295,349],"predictive":[296],"impact":[297],"either":[299],"model-X":[300],"knockoffs":[301],"adversarial":[303],"forests.":[305],"Empirical":[306],"benchmarks":[307],"demonstrate":[308],"correctness":[309],"results":[312],"reduced":[314],"runtime":[315],"compared":[316],"selected":[318],"reference":[319],"implementations.":[320],"Five":[321],"secondary":[322],"complement":[324],"primary":[327],"research":[328],"areas,":[329],"covering":[330],"overview":[335],"reduction":[337],"techniques,":[338],"work":[339],"performance":[341],"evaluation,":[342],"algorithmic":[344],"fairness.":[345],"Other":[346],"address":[348],"importance,":[351],"community-driven":[353],"machine":[354],"learning":[355],"integration":[357],"mlr":[360],"ecosystem":[361]},"counts_by_year":[],"updated_date":"2026-09-04T10:56:28.161419","created_date":"2026-08-22T00:00:00"}