{"id":"https://openalex.org/W7225426166","doi":"https://doi.org/10.21203/rs.3.rs-11638201/v1","title":"Deep Survival Analysis with Temporal Trajectory Embedding for Substandard Life Insurance Pricing: A DeepSurv Modeling Study of Type 2 Diabetes Mellitus","display_name":"Deep Survival Analysis with Temporal Trajectory Embedding for Substandard Life Insurance Pricing: A DeepSurv Modeling Study of Type 2 Diabetes Mellitus","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225426166","doi":"https://doi.org/10.21203/rs.3.rs-11638201/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11638201/v1","doi":"https://doi.org/10.21203/rs.3.rs-11638201/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11638201/v1","pdf_url":"https://www.researchsquare.com/article/rs-11638201/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11638201/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160735915","display_name":"Yuantao Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuantao Xie","raw_affiliation_strings":["University of International Business and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of International Business and Economics","institution_ids":["https://openalex.org/I146563203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161044681","display_name":"Qinzheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinzheng Wang","raw_affiliation_strings":["University of International Business and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of International Business and Economics","institution_ids":["https://openalex.org/I146563203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146563203"],"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/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.5687999725341797,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.5687999725341797,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.1754000037908554,"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/T12394","display_name":"Insurance and Financial Risk Management","score":0.13089999556541443,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/type-2-diabetes","display_name":"type 2 diabetes","score":0.8799999952316284},{"id":"https://openalex.org/keywords/deepsurv","display_name":"DeepSurv","score":0.9169999957084656},{"id":"https://openalex.org/keywords/deep-survival-analysis","display_name":"deep survival analysis","score":0.753000020980835},{"id":"https://openalex.org/keywords/comorbidity-interaction","display_name":"comorbidity interaction","score":0.734000027179718},{"id":"https://openalex.org/keywords/two-part-model","display_name":"two-part model","score":0.5400000214576721},{"id":"https://openalex.org/keywords/inpatient-claims","display_name":"inpatient claims","score":0.45899999141693115},{"id":"https://openalex.org/keywords/chronic-disease-risk","display_name":"chronic disease risk","score":0.3240000009536743},{"id":"https://openalex.org/keywords/c-index","display_name":"concordance index","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C2910068830","wikidata":"https://www.wikidata.org/wiki/Q3025883","display_name":"Type 2 Diabetes Mellitus","level":3,"score":0.6010000109672546},{"id":"https://openalex.org/C10515644","wikidata":"https://www.wikidata.org/wiki/Q543310","display_name":"Survival analysis","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C73269764","wikidata":"https://www.wikidata.org/wiki/Q954529","display_name":"Poisson regression","level":3,"score":0.4894999861717224},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.46799999475479126},{"id":"https://openalex.org/C50382708","wikidata":"https://www.wikidata.org/wiki/Q223218","display_name":"Proportional hazards model","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.43950000405311584},{"id":"https://openalex.org/C70519679","wikidata":"https://www.wikidata.org/wiki/Q6666755","display_name":"Log-linear model","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4104999899864197},{"id":"https://openalex.org/C3020299011","wikidata":"https://www.wikidata.org/wiki/Q626608","display_name":"Life insurance","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3440000116825104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3237000107765198},{"id":"https://openalex.org/C151205565","wikidata":"https://www.wikidata.org/wiki/Q4385634","display_name":"Cox\u2013Ingersoll\u2013Ross model","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C179755657","wikidata":"https://www.wikidata.org/wiki/Q58702","display_name":"Mortality rate","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C2777180221","wikidata":"https://www.wikidata.org/wiki/Q3025883","display_name":"Type 2 diabetes","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11638201/v1","doi":"https://doi.org/10.21203/rs.3.rs-11638201/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11638201/v1","pdf_url":"https://www.researchsquare.com/article/rs-11638201/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11638201/v1","doi":"https://doi.org/10.21203/rs.3.rs-11638201/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11638201/v1","pdf_url":"https://www.researchsquare.com/article/rs-11638201/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8048999905586243,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225426166.pdf","grobid_xml":"https://content.openalex.org/works/W7225426166.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4311360319","https://openalex.org/W2953435646","https://openalex.org/W4402830616","https://openalex.org/W2108196540","https://openalex.org/W6958408040","https://openalex.org/W4399706848","https://openalex.org/W4388600230","https://openalex.org/W7134062713","https://openalex.org/W2417324401","https://openalex.org/W2198052525"],"abstract_inverted_index":{"Abstract":[0],"Substandard":[1],"(impaired)":[2],"lives":[3],"have":[4],"long":[5,426],"been":[6],"excluded":[7],"from":[8,148,411,539],"commercial":[9],"health":[10,437],"in-":[11],"surance":[12],"because":[13],"conventional":[14],"actuarial":[15,544,625],"tools":[16],"fail":[17],"to":[18,150,272,285,361,543],"capture":[19,273],"the":[20,28,52,67,73,79,105,113,127,138,142,162,172,187,208,212,225,246,292,340,345,355,373,393,402,446,455,462,489,515,559,597,614],"nonlinear":[21,281],"progres-":[22],"sion":[23],"of":[24,76,119,166,171,201,219,258,294,307,315,443,467,620],"chronic":[25,501],"diseases":[26],"and":[27,112,122,129,135,191,284,335,368,415,470,509,551,563,596,617],"high-dimensional":[29,274],"interactions":[30],"among":[31,277],"comorbidities.":[32],"Taking":[33],"type":[34],"2":[35],"diabetes":[36,526],"mellitus":[37],"(T2DM)":[38],"as":[39,474,514],"a":[40,46,85,182,197,241,263,280,303,310,412,425,475,536,547,552,569],"case":[41,571],"study,":[42],"this":[43],"paper":[44],"constructs":[45],"substandard-life":[47,621],"rate-making":[48],"framework":[49],"centered":[50],"on":[51,66,193,488],"DeepSurv":[53,259,341],"deep":[54,183],"survival":[55,252,540,605],"model.":[56],"Using":[57],"1,883,235":[58],"T2DM":[59],"inpatient":[60],"claim":[61],"records":[62],"with":[63,186,309,520,568,607],"mini-batch":[64],"training":[65],"full":[68,490],"sample,":[69],"we":[70,327,423,534],"first":[71],"expose":[72],"failure":[74,367,511],"boundaries":[75],"traditional":[77],"methods:":[78],"extra":[80],"mortality":[81],"(EM)":[82],"model":[83,108,618],"suffers":[84],"rate":[86],"inversion":[87],"(118.22%":[88],"for":[89,96,215,236,431,478],"T2S1":[90],"com-":[91],"plicated":[92],"cases":[93],"versus":[94],"88.87%":[95],"T2S2":[97],"target-organ-damage":[98],"cases)":[99],"driven":[100],"by":[101,126],"age-":[102],"structure":[103,174],"confounding;":[104],"generalized":[106],"linear":[107,295],"(GLM)":[109],"two-part":[110],"approach":[111],"Tweedie":[114],"compound":[115],"model,":[116],"while":[117,354,395,623],"capable":[118],"decomposing":[120],"frequency":[121,164],"severity,":[123],"remain":[124],"constrained":[125],"proportional-hazards":[128],"linear-additivity":[130],"assumptions;":[131],"after":[132],"incorporating":[133],"province":[134],"year":[136],"controls,":[137],"age":[139,177,495,573],"coe\ufb00icient":[140,165],"in":[141,175,251,262,269,529],"Gamma":[143],"severity":[144],"regression":[145],"is":[146,155],"corrected":[147],"\u22120.0002":[149],"+0.0028":[151],"(the":[152],"directional":[153],"bias":[154],"re-":[156,398],"paired),":[157],"yet":[158,453],"remains":[159],"far":[160],"below":[161],"Poisson":[163],"0.031,":[167],"indicating":[168],"limited":[169],"capacity":[170],"linear-additive":[173],"capturing":[176],"effects.":[178],"Deep-":[179],"Surv,":[180],"coupling":[181],"neural":[184],"network":[185,430],"Cox":[188],"partial":[189],"likelihood":[190],"trained":[192],"1,840,774":[194],"records,":[195],"attains":[196],"concordance":[198],"index":[199],"(C-index)":[200],"0.695.":[202],"It":[203],"should":[204],"be":[205],"emphasized":[206],"that":[207,344,386,588],"Tweedie/GLM":[209],"area":[210],"under":[211,601],"curve":[213],"(AUC)":[214],"binary":[216,233],"dis-":[217],"crimination":[218],"excess":[220],"events":[221],"reaches":[222],"0.715,":[223],"but":[224,268],"two":[226],"metrics":[227,591],"are":[228,324,599],"not":[229,261],"directly":[230,557],"comparable\u2014AUC":[231],"measures":[232,248],"classification":[234],"power":[235],"whether":[237],"out-of-pocket":[238],"expenses":[239],"exceed":[240],"10,000":[242],"RMB":[243],"threshold,":[244],"whereas":[245],"C-index":[247,304,394],"concor-":[249],"dance":[250],"time":[253],"ranking.":[254],"The":[255],"core":[256],"value":[257,466],"lies":[260],"dominant":[264],"single":[265],"discrimination":[266],"metric,":[267],"its":[270,440,471],"ability":[271],"interac-":[275],"tions":[276],"comorbidities":[278,363,522],"through":[279],"risk":[282,518],"surface":[283],"provide":[286,535],"premium":[287,561,566,579],"attribution":[288,567],"via":[289],"SHAP\u2014capabilities":[290],"beyond":[291],"reach":[293],"models.":[296],"Bootstrap":[297,583],"resampling":[298],"(B":[299],"=":[300,390,450,459,497],"50)":[301],"confirms":[302],"standard":[305,594],"error":[306],"0.0031":[308],"95%":[311],"con-":[312,586],"fidence":[313],"interval":[314],"[0.684,":[316],"0.695],":[317],"confirming":[318,461],"robust":[319],"discrimination.":[320],"Methodologically,":[321],"our":[322],"contributions":[323],"fivefold.":[325],"First,":[326],"incorporate":[328],"Elastic":[329,387,608],"Net":[330,388,609],"regularization\u2014embedding":[331],"both":[332],"L1":[333,346],"(Lasso)":[334],"L2":[336,356],"(Ridge)":[337],"penalties":[338],"into":[339,558],"loss":[342],"function\u2014so":[343],"component":[347,357],"drives":[348],"weak-signal":[349],"features":[350],"to-":[351],"ward":[352],"zero":[353],"assigns":[358],"similar":[359],"weights":[360],"collinear":[362,413],"1":[364],"(e.g.,":[365],"heart":[366,370,503,510],"ischemic":[369,502],"disease),":[371],"achieving":[372],"ideal":[374],"\u201cequal":[375],"within":[376],"group,":[377],"sparse":[378],"across":[379],"groups\u201d":[380],"feature":[381],"selection.":[382,421],"Empirical":[383],"comparison":[384],"demonstrates":[385],"(\u03b1":[389],"0.5)":[391],"preserves":[392],"effectively":[396],"shrinking":[397],"dundant":[399],"features,":[400],"resolving":[401],"dilemma":[403],"where":[404],"pure":[405,416],"Lasso":[406],"arbitrarily":[407],"selects":[408],"one":[409],"variable":[410,420],"group":[414],"Ridge":[417],"cannot":[418],"perform":[419],"Second,":[422],"introduce":[424],"short-term":[427],"memory":[428],"(LSTM)":[429],"independent":[432],"rate-prediction":[433],"benchmarking":[434],"against":[435],"time-varying":[436],"trajectories;":[438],"empirically,":[439],"temporal":[441,468],"R2":[442],"0.391":[444],"outperforms":[445],"GLM":[447],"cross-section":[448],"(R2":[449,458],"0.197,":[451],"+99%)":[452],"trails":[454],"lagged-mean":[456],"benchmark":[457],"0.455),":[460],"incremental":[463],"predic-":[464],"tive":[465],"information":[469],"future":[472],"potential":[473],"feature-embedding":[476],"module":[477],"DeepSurv.":[479],"Third,":[480],"SHAP":[481],"(SHapley":[482],"Additive":[483],"exPlanations)":[484],"gradient":[485],"ap-":[486],"proximation":[487],"1.84":[491],"million":[492],"sample":[493],"identifies":[494],"(mean|SHAP|":[496],"0.269),":[498],"DX_T2S2":[499],"(0.129),":[500],"disease":[504],"COMB_I25":[505],"(0.123),":[506],"DX_T2S1":[507],"(0.107),":[508],"COMB_I50":[512],"(0.107)":[513],"top":[516],"five":[517],"drivers,":[519],"cardiovascular":[521],"approaching":[523],"or":[524],"exceeding":[525],"staging":[527],"itself":[528],"at-":[530],"tribution":[531],"weight.":[532],"Fourth,":[533],"complete":[537],"mapping":[538],"probabil-":[541],"ities":[542],"premiums,":[545],"introducing":[546],"sojourn-time":[548],"factor":[549,555],"A(\u03c4)":[550],"health-":[553],"management":[554],"H(r)":[556],"gross":[560,578],"formula,":[562],"demonstrate":[564],"SHAP-driven":[565],"high-risk":[570],"(male,":[572],"65,":[574],"cardiac":[575],"co-":[576],"morbidities,":[577],"14,802":[580],"RMB).":[581],"Fifth,":[582],"robustness":[584],"checks":[585],"firm":[587],"all":[589],"key":[590],"exhibit":[592],"acceptable":[593],"errors,":[595],"findings":[598],"reproducible":[600],"repeated":[602],"sampling.":[603],"Deep":[604],"analysis":[606],"reg-":[610],"ularization":[611],"markedly":[612],"improves":[613],"fairness,":[615],"discrimination,":[616],"parsimony":[619],"pricing":[622],"preserving":[624],"interpretability.":[626]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-07T00:00:00"}