{"id":"https://openalex.org/W7225268126","doi":"https://doi.org/10.21203/rs.3.rs-11603867/v1","title":"Identifying Youth Somatic Symptom Risk Through Interpretable Machine Learning and Behavioral Phenotyping: A Temporal Validation Study","display_name":"Identifying Youth Somatic Symptom Risk Through Interpretable Machine Learning and Behavioral Phenotyping: A Temporal Validation Study","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225268126","doi":"https://doi.org/10.21203/rs.3.rs-11603867/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11603867/v1","doi":"https://doi.org/10.21203/rs.3.rs-11603867/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11603867/v1","pdf_url":"https://www.researchsquare.com/article/rs-11603867/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11603867/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016955507","display_name":"Yi Sui","orcid":"https://orcid.org/0000-0002-9253-3458","observed_orcids":["https://orcid.org/0000-0002-9253-3458","https://orcid.org/0009-0006-3612-9633"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Sui","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":"https://orcid.org/0009-0006-3612-9633","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016955507"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"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/T11334","display_name":"Psychosomatic Disorders and Their Treatments","score":0.7538999915122986,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11334","display_name":"Psychosomatic Disorders and Their Treatments","score":0.7538999915122986,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.20319999754428864,"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"}},{"id":"https://openalex.org/T10853","display_name":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/somatic-symptoms","display_name":"somatic symptoms","score":0.8579999804496765},{"id":"https://openalex.org/keywords/youth","display_name":"youth","score":0.7179999947547913},{"id":"https://openalex.org/keywords/behavioral-phenotypes","display_name":"behavioral phenotypes","score":0.9509999752044678},{"id":"https://openalex.org/keywords/lifestyle-patterns","display_name":"lifestyle patterns","score":0.9210000038146973},{"id":"https://openalex.org/keywords/insufficient-sleep","display_name":"insufficient sleep","score":0.9089999794960022},{"id":"https://openalex.org/keywords/screen-exposure","display_name":"screen exposure","score":0.9129999876022339},{"id":"https://openalex.org/keywords/psychological-indicators","display_name":"psychological indicators","score":0.6309999823570251},{"id":"https://openalex.org/keywords/information-leakage","display_name":"information leakage","score":0.7229999899864197},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.8659999966621399},{"id":"https://openalex.org/keywords/temporal-validation","display_name":"temporal validation","score":0.9380000233650208},{"id":"https://openalex.org/keywords/nhanes","display_name":"NHANES","score":0.6110000014305115},{"id":"https://openalex.org/keywords/screening","display_name":"screening","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.548799991607666},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.45419999957084656},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C134305767","wikidata":"https://www.wikidata.org/wiki/Q725508","display_name":"Somatic cell","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C83804111","wikidata":"https://www.wikidata.org/wiki/Q1063558","display_name":"Behavioral pattern","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C65499552","wikidata":"https://www.wikidata.org/wiki/Q5421061","display_name":"Experience sampling method","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2651999890804291},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C183698672","wikidata":"https://www.wikidata.org/wiki/Q3332444","display_name":"Behavioral medicine","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11603867/v1","doi":"https://doi.org/10.21203/rs.3.rs-11603867/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11603867/v1","pdf_url":"https://www.researchsquare.com/article/rs-11603867/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11603867/v1","doi":"https://doi.org/10.21203/rs.3.rs-11603867/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11603867/v1","pdf_url":"https://www.researchsquare.com/article/rs-11603867/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"score":1.0,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225268126.pdf","grobid_xml":"https://content.openalex.org/works/W7225268126.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2082132918","https://openalex.org/W2132322340","https://openalex.org/W2164104699","https://openalex.org/W2295124130","https://openalex.org/W2911964244","https://openalex.org/W2912581524","https://openalex.org/W3105368918","https://openalex.org/W4385576721"],"related_works":["https://openalex.org/W7124194851","https://openalex.org/W7153628731","https://openalex.org/W7223121880","https://openalex.org/W7160256129","https://openalex.org/W4414598819","https://openalex.org/W7164831084","https://openalex.org/W4408476063","https://openalex.org/W7160319742","https://openalex.org/W4410301509","https://openalex.org/W7115946869"],"abstract_inverted_index":{"Abstract":[0],"BACKGROUND":[1],"&":[2],"AIMS:":[3],"Psychological":[4],"characteristics":[5,148],"are":[6],"closely":[7],"associated":[8],"with":[9,225],"somatic":[10,22,31,63,78,145,227,272],"symptoms.":[11,23],"However,":[12],"commonly":[13],"used":[14,115],"psychological":[15,138,173],"assessments":[16,29],"often":[17,48],"include":[18],"items":[19],"related":[20],"to":[21,62,69,154,195],"As":[24],"a":[25,103],"result,":[26],"using":[27,130,151,169,183],"such":[28],"for":[30,76,122,239],"symptom":[32,64,79,126,228,273],"risk":[33,80,127,245,274],"prediction":[34,81],"may":[35],"introduce":[36],"information":[37],"leakage":[38],"and":[39,82,96,137,175,179,219,242,261],"inflate":[40],"predictive":[41],"performance.":[42],"In":[43,111,158],"addition,":[44],"existing":[45],"studies":[46],"have":[47],"examined":[49,192],"individual":[50],"lifestyle":[51,60,248,256],"factors":[52],"independently,":[53],"overlooking":[54],"the":[55,93,119,187,214],"potential":[56],"contribution":[57],"of":[58,106,223,270],"combined":[59],"patterns":[61],"risk.":[65,229],"This":[66],"study":[67],"aims":[68],"develop":[70],"an":[71,161,286],"interpretable":[72,278],"machine":[73,279],"learning":[74,280],"approach":[75],"youth":[77],"evaluate":[83],"its":[84],"generalizability":[85],"through":[86],"temporal":[87,288],"validation.":[88],"METHODS:":[89],"Using":[90],"data":[91],"from":[92,118,186],"National":[94],"Health":[95,133],"Nutrition":[97],"Examination":[98],"Survey":[99],"(NHANES),":[100],"we":[101,114],"conducted":[102],"two-stage":[104],"analysis":[105,191,231],"participants":[107,117,185],"aged":[108],"12-24":[109],"years.":[110],"stage":[112,159],"one,":[113],"1,599":[116],"2017-2018":[120],"cycle":[121],"model":[123,166,196,208,240,281],"development.":[124],"Somatic":[125],"was":[128,167,180],"defined":[129],"somatic-related":[131],"Patient":[132],"Questionnaire":[134],"(PHQ)":[135],"items,":[136],"indicators":[139],"were":[140,149,237,265],"reconstructed":[141],"after":[142],"removing":[143],"overlapping":[144],"items.":[146],"Lifestyle":[147],"clustered":[150],"K-means":[152,199],"clustering":[153,200],"derive":[155],"behavioral":[156,176,203,234],"phenotypes.":[157,204],"two,":[160],"ensemble":[162,206],"multilayer":[163],"perceptron":[164],"(MLP)":[165],"trained":[168],"demographic":[170],"characteristics,":[171],"refined":[172],"indicators,":[174],"phenotype":[177,235],"features,":[178],"temporally":[181],"validated":[182],"1,986":[184],"2021-2023":[188,216],"cycle.":[189],"SHAP":[190,230],"feature":[193],"contributions":[194],"predictions.":[197],"RESULTS:":[198],"identified":[201,221,266],"three":[202],"The":[205,277],"MLP":[207],"achieved":[209],"93%":[210],"overall":[211],"accuracy":[212],"in":[213,285,299],"independent":[215,287],"validation":[217,289,293],"dataset":[218],"correctly":[220],"84%":[222],"individuals":[224],"elevated":[226,271],"showed":[232],"that":[233],"features":[236],"important":[238],"interpretation":[241],"helped":[243],"characterize":[244],"differences":[246],"across":[247],"profiles.":[249],"CONCLUSION:":[250],"Behavioral":[251],"profiles":[252],"characterized":[253],"by":[254],"unhealthy":[255],"patterns,":[257],"including":[258],"sleep":[259],"insufficiency":[260],"excessive":[262],"screen":[263],"exposure,":[264],"as":[267],"key":[268],"drivers":[269],"among":[275],"youth.":[276],"demonstrated":[282],"strong":[283],"performance":[284],"dataset,":[290],"although":[291],"further":[292],"is":[294],"needed":[295],"before":[296],"broader":[297],"application":[298],"screening":[300],"settings.":[301]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}