Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformer

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorChen, Zhaoyangen_US
dc.contributor.authorSiltala-Li, Linaen_US
dc.contributor.authorLassila, Mikkoen_US
dc.contributor.authorMalo, Pekkaen_US
dc.contributor.authorVilkkumaa, Eevaen_US
dc.contributor.authorSaaresranta, Tarjaen_US
dc.contributor.authorVirkki, Arho Velien_US
dc.contributor.departmentSchool Common, BIZen
dc.contributor.departmentDepartment of Information and Service Managementen
dc.contributor.organizationAalto University School of Businessen_US
dc.contributor.organizationDepartment of Information and Service Managementen_US
dc.contributor.organizationTurku University Hospitalen_US
dc.contributor.organizationUniversity of Turkuen_US
dc.date.accessioned2023-06-14T08:50:19Z
dc.date.available2023-06-14T08:50:19Z
dc.date.issued2023en_US
dc.descriptionPublisher Copyright: Author
dc.description.abstractBackground: Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare. Objective: For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures. Methods and procedures: The authors propose a translational engineering method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. This method effectively adapts state-of-the-art Transformer models to create practical cost prediction solutions that can be implemented in OSA management, potentially enhancing patient care and resource allocation. Results: The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's R2 from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the R2 considerably, from 61.6% to 81.9%. Conclusion: The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure. Clinical and Translational Impact Statement: Public Health- Lack of high-quality source data hinders data-driven analytics-based research in healthcare. The paper presents a method that couples data augmentation and prediction in cases of scant healthcare data.en
dc.description.versionPeer revieweden
dc.format.extent306-317
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationChen, Z, Siltala-Li, L, Lassila, M, Malo, P, Vilkkumaa, E, Saaresranta, T & Virkki, A V 2023, ' Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformer ', IEEE Journal of Translational Engineering in Health and Medicine, vol. 11, pp. 306-317 . https://doi.org/10.1109/JTEHM.2023.3276943en
dc.identifier.doi10.1109/JTEHM.2023.3276943en_US
dc.identifier.issn2168-2372
dc.identifier.otherPURE UUID: 0b939613-ef1e-4f1b-b2b2-f86153d19947en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/0b939613-ef1e-4f1b-b2b2-f86153d19947en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85160265776&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/112828772/BIZ_Chen_at_al_Predicting_Visit_Cost_of_Obstructive_Sleep_Apnea.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/121427
dc.identifier.urnURN:NBN:fi:aalto-202306143804
dc.language.isoenen
dc.publisherIEEE
dc.relation.ispartofseriesIEEE Journal of Translational Engineering in Health and Medicineen
dc.relation.ispartofseriesVolume 11en
dc.rightsopenAccessen
dc.subject.keywordCost predictionen_US
dc.subject.keywordCostsen_US
dc.subject.keywordData modelsen_US
dc.subject.keywordDeep learningen_US
dc.subject.keywordhealthcare data augmentationen_US
dc.subject.keywordMedical servicesen_US
dc.subject.keywordObstructive sleep apneaen_US
dc.subject.keywordPredictive modelsen_US
dc.subject.keywordSleep apneaen_US
dc.subject.keywordTransformeren_US
dc.subject.keywordTransformersen_US
dc.titlePredicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformeren
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files
Collections
[article-cris] Palvelut / Services