Einzeltreffer — DigiBib

Heart failure is a life-threatening syndrome that is diagnosed in 3.6 million people worldwide each year. We propose a deep fusion learning model (DFL-IMP) that uses time series and category data from electronic health records to predict in-hospital mortality in patients with heart failure. We considered 41 time series features (platelets, white blood cells, urea nitrogen, etc.) and 17 category features (gender, insurance, marital status, etc.) as predictors, all of which were available within the time of the patient's last hospitalization, and a total of 7696 patients participated in the observational study. Our model was evaluated against different time windows. The best performance was achieved with an AUC of 0.914 when the observation window was 5 days and the prediction window was 30 days. Outperformed other baseline models including LR (0.708), RF (0.717), SVM (0.675), LSTM (0.757), GRU (0.759), GRU-U (0.766) and MTSSP (0.770). This tool allows us to predict the expected pathway of heart failure patients and intervene early in the treatment process, which has significant implications for improving the life expectancy of heart failure patients.

Titel:	Predicting heart failure in-hospital mortality by integrating longitudinal and category data in electronic health records.
Autor/in / Beteiligte Person:	Ma, M ; Hao, X ; Zhao, J ; Luo, S ; Liu, Y ; Li, D
Link:	Full Text Finder (Volltext)
Zeitschrift:	Medical & biological engineering & computing, Jg. 61 (2023-07-01), Heft 7, S. 1857-1873
Veröffentlichung:	New York, NY : Springer ; <i>Original Publication</i>: Stevenage, Eng., Peregrinus., 2023
Medientyp:	academicJournal
ISSN:	1741-0444 (electronic)
DOI:	10.1007/s11517-023-02816-z
Schlagwort:	Humans Hospital Mortality Electronic Health Records Hospitalization Machine Learning Heart Failure diagnosis
Sonstiges:	Nachgewiesen in: MEDLINE Sprachen: English Publication Type: Observational Study; Journal Article Language: English [Med Biol Eng Comput] 2023 Jul; Vol. 61 (7), pp. 1857-1873. <i>Date of Electronic Publication: </i>2023 Mar 24. MeSH Terms: Machine Learning* ; Heart Failure* / diagnosis ; Humans ; Hospital Mortality ; Electronic Health Records ; Hospitalization References: Chen J, Aronowitz P (2022) Congestive heart failure[J]. Medical Clinics 106(3):447–458. https://doi.org/10.1016/j.mcna.2021.12.002. (PMID: 10.1016/j.mcna.2021.12.00235491065) ; Wang H, Chai K, Du M et al (2021) Prevalence and incidence of heart failure among urban patients in China: a national population-based analysis[J]. Circ Heart Fail 14(10):e008406. https://doi.org/10.1161/CIRCHEARTFAILURE.121.008406. (PMID: 10.1161/CIRCHEARTFAILURE.121.00840634455858) ; Błaziak M, Urban S, Wietrzyk W et al (2022) An artificial intelligence approach to guiding the management of heart failure patients using predictive models: a systematic review[J]. Biomedicines 10(9):2188. https://doi.org/10.3390/biomedicines10092188. (PMID: 10.3390/biomedicines10092188361402899496386) ; Kao DP (2022) Electronic health records and heart failure[J]. Heart Fail Clin 18(2):201–211. https://doi.org/10.1016/j.hfc.2021.12.004. (PMID: 10.1016/j.hfc.2021.12.004353415359167063) ; Reimer AP, Dai W, Smith B et al (2021) Subcategorizing EHR diagnosis codes to improve clinical application of machine learning models[J]. Int J Med Inform 156:104588. https://doi.org/10.1016/j.ijmedinf.2021.104588. (PMID: 10.1016/j.ijmedinf.2021.104588346072908571032) ; Lv H, Yang X, Wang B et al (2021) Machine learning-driven models to predict prognostic outcomes in patients hospitalized with heart failure using electronic health records: retrospective study[J]. J Med Internet Res 23(4):e24996. https://doi.org/10.2196/24996. (PMID: 10.2196/24996338713758094022) ; Javeed A, Khan S U, Ali L et al (2022) Machine Learning-Based Automated Diagnostic Systems Developed for Heart Failure Prediction Using Different Types of Data Modalities: A Systematic Review and Future Directions[J]. Computational and Mathematical Methods in Medicine 2022:9288452. https://doi.org/10.1155/2022/9288452. ; Benke KK (2019) Data Analytics and Machine Learning for Disease Identification in Electronic Health Records[J]. JAMA Ophthalmol 137(5):497–498. https://doi.org/10.1001/jamaophthalmol.2018.7055. ; König S, Pellissier V, Hohenstein S et al (2021) Machine learning algorithms for claims data-based prediction of in -hospital mortality in patients with heart failure[J]. ESC Heart Fail 8(4):3026–3036. https://doi.org/10.1002/ehf2.13398. (PMID: 10.1002/ehf2.13398340857758318394) ; Adler ED, Voors AA, Klein L et al (2020) Improving risk prediction in heart failure using machine learning[J]. Eur J Heart Fail 22(1):139–147. https://doi.org/10.1002/ejhf.1628. (PMID: 10.1002/ejhf.162831721391) ; Angraal S, Mortazavi BJ, Gupta A et al (2020) Machine learning prediction of mortality and hospitalization in heart failure with preserved ejection fraction[J]. JACC Heart Fail 8(1):12–21. https://doi.org/10.1016/j.jchf.2019.06.013. (PMID: 10.1016/j.jchf.2019.06.01331606361) ; Davide C, Giuseppe J (2020) Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone[J]. BMC Medical Informatics and Decision Making 20(1):16. https://doi.org/10.1186/s12911-020-1023-5. ; Xie F, Yuan H, Ning Y et al (2022) Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies[J]. J Biomed Inform 126:103980. https://doi.org/10.1016/j.jbi.2021.103980. ; Penso M, Solbiati S, Moccia S et al (2022) Decision Support Systems in HF based on Deep Learning Technologies[J]. Current Heart Failure Reports 19(2):38–51. https://doi.org/10.1007/s11897-022-00540-7. ; Haq IU, Chhatwal K, Sanaka K et al (2022) Artificial intelligence in cardiovascular medicine: current insights and future prospects[J]. Vasc Health Risk Manag 18:517. https://doi.org/10.2147/VHRM.S279337. (PMID: 10.2147/VHRM.S279337358557549288176) ; Doppalapudi S, Qiu R G, Badr Y (2021) Lung cancer survival period prediction and understanding: Deep learning approaches[J]. International Journal of Medical Informatics 148:104371. ; Gupta VK, Gupta A, Kumar D et al (2021) Prediction of COVID-19 confirmed, death, and cured cases in India using random forest model[J]. Big Data Min Anal 4(2):116–123. https://doi.org/10.26599/BDMA.2020.902001. ; Tong R, Lei L, Zhou Y et al (2019) Representation learning for clinical time series prediction tasks in electronic health records[J]. BMC Med Inform Decis Mak 19(Suppl 8):259. https://doi.org/10.1186/s12911-019-0985-7. (PMID: 10.1186/s12911-019-0985-7) ; Amal S, Safarnejad L, Omiye JA et al (2022) Use of Multi-Modal Data and Machine Learning to Improve Cardiovascular Disease Care[J]. Frontiers in Cardiovascular Medicine 9:840262. https://doi.org/10.3389/fcvm.2022.840262. ; Wang Z, Zhu Y, Li D et al (2020) Feature rearrangement based deep learning system for predicting heart failure mortality[J]. Comput Methods Prog Biomed 191:105383. https://doi.org/10.1016/j.cmpb.2020.105383. (PMID: 10.1016/j.cmpb.2020.105383) ; Jun E, Mulyadi A W, Choi J, et al (2020). Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction[J]. IEEE Transactions on Neural Networks and Learning Systems 32(9):4052–4062. https://doi.org/10.1109/TNNLS.2020.3016670. ; Men L, Ilk N, Tang X et al (2021) Multi-disease prediction using LSTM recurrent neural networks[J]. Expert Syst Appl 177:114905. https://doi.org/10.1016/j.eswa.2021.114905. (PMID: 10.1016/j.eswa.2021.114905) ; Priyanga P, Pattankar VV, Sridevi S (2021) A hybrid recurrent neural network-logistic chaos-based whale optimization framework for heart disease prediction with electronic health records[J]. Comput Intell 37(1):315–343. https://doi.org/10.1111/coin.12405. (PMID: 10.1111/coin.12405) ; Yoon J, Zame W R, van der Schaar M (2018) Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks[J]. IEEE Transactions on Biomedical Engineering 66(5):1477–1490. https://doi.org/10.1109/TBME.2018.2874712. ; McGilvray MMO, Heaton J, Guo A et al (2022) Electronic health record-based deep learning prediction of death or severe decompensation in heart failure patients[J]. Heart Fail 10(9):637–647. https://doi.org/10.1016/j.jchf.2022.05.010. (PMID: 10.1016/j.jchf.2022.05.010) ; Chu J, Dong W, Huang Z (2020) Endpoint prediction of heart failure using electronic health records[J]. J Biomed Inform 109:103518. https://doi.org/10.1016/j.jbi.2020.103518. (PMID: 10.1016/j.jbi.2020.10351832721582) ; Radhachandran A, Garikipati A, Zelin N S, et al (2021) Prediction of short-term mortality in acute heart failure patients using minimal electronic health record data[J]. BioData Mining 14(1):23. https://doi.org/10.1186/s13040-021-00255-w. ; Zheng G, Han G, Soomro NQ (2019) An inception module CNN classifiers fusion method on pulmonary nodule diagnosis by signs[J]. Tsinghua Sci Technol 25(3):368–383. https://doi.org/10.26599/TST.2019.9010010. ; Zhi Z, Elbadawi M, Daneshmend A, et al (2022) Multimodal Diagnosis for Pulmonary Embolism from EHR Data and CT Images[C]. 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, pp 2053–2057. https://doi.org/10.1109/EMBC48229.2022.9871041. ; Zheng Yi, Xiangpei Hu (2020) Healthcare predictive analytics for disease progression: a longitudinal data fusion approach. J Intell Inf Syst 55(2):351–369. https://doi.org/10.1007/s10844-020-00606-9. (PMID: 10.1007/s10844-020-00606-9) ; Niu K, Lu Y, Peng X et al (2022) Fusion of sequential visits and medical ontology for mortality prediction[J]. J Biomed Inform 127:104012. https://doi.org/10.1016/j.jbi.2022.104012. (PMID: 10.1016/j.jbi.2022.10401235144001) ; Lin M, Wang S, Ding Y, et al (2021) An empirical study of using radiology reports and images to improve ICU-mortality prediction[C]. 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI). IEEE, Victoria, BC, Canada, pp 497–498. https://doi.org/10.1109/ICHI52183.2021.00088. ; Hess LM, Han Y, Zhu YE et al (2021) Characteristics and outcomes of patients with RET-fusion positive non-small lung cancer in real-world practice in the United States[J]. BMC Cancer 21(1):1–12. (PMID: 10.1186/s12885-020-07714-3) ; Chung J , Kastner K , Dinh L et al (2015) A recurrent latent variable model for sequential data[J]. Advances in neural information processing systems 28. ; Ross A, Jain A (2003) Information fusion in biometrics[J]. Pattern Recogn Lett 24(13):2115–2125. https://doi.org/10.1016/S0167-8655(03)00079-5. (PMID: 10.1016/S0167-8655(03)00079-5) ; Alistair LS, Johnson EW, Pollard TJ (2016) Data descriptor: MIMIC-III a freely accessible critical care database[J]. Thromb Haemost 76(2):258–262. https://doi.org/10.1038/sdata.2016.35. (PMID: 10.1038/sdata.2016.35) ; Gurwitz JH, Magid DJ, Smith DH et al (2013) Contemporary prevalence and correlates of incident heart failure with preserved ejection fraction[J]. Am J Med 126(5):393–400. https://doi.org/10.1016/j.amjmed.2012.10.022. (PMID: 10.1016/j.amjmed.2012.10.022234993283627730) ; Li B, Shi Y, Cheng L, et al (2022) MTSSP: Missing value imputation in multivariate time series for survival prediction[C]. 2022 International Joint Conference on Neural Networks (IJCNN). Padua, Italy, pp 1–8. https://doi.org/10.1109/IJCNN55064.2022.9892806 . ; Shickel B, Silva B, Ozrazgat-Baslanti T et al (2022) Multi-dimensional patient acuity estimation with longitudinal EHR tokenization and flexible transformer networks[J]. Front Digital Health 4:1029191. https://doi.org/10.3389/fdgth.2022.1029191. ; Li Y, Mamouei M, Salimi-Khorshidi G et al (2022) Hi-BEHRT: Hierarchical Transformer-Based Model for Accurate Prediction of Clinical Events Using Multimodal Longitudinal Electronic Health Records[J]. IEEE J Biomed Health Inform27(2):1106–1117. https://doi.org/10.1109/JBHI.2022.3224727. ; Liu S, Wang X, Hou Y et al (2022) Multimodal Data Matters: Language Model Pre-Training Over Structured and Unstructured Electronic Health Records[J]. IEEE Journal of Biomedical and Health Informatics 27(1):504–514. https://doi.org/10.1109/JBHI.2022.3217810. Grant Information: 62027819 High-speed Real-time Analyzer for Laser Chip's Optical Catastrophic Damage Process; 62076177 Research on Risk Assessment Model for Heart Failure Incorporating Multi-modal Big Data; 2020XXX007 Guangdong Key Laboratory of Innovation Method and Decision Management System; NO.202102020101006 Key research and development program of Shanxi Province Contributed Indexing: Keywords: Deep learning; Electronic health records; Fatal outcome; Feature fusion; Heart failure Entry Date(s): Date Created: 20230324 Date Completed: 20230620 Latest Revision: 20230620 Update Code: 20240513

Klicken Sie ein Format an und speichern Sie dann die Daten oder geben Sie eine Empfänger-Adresse ein und lassen Sie sich per Email zusenden.

BibTeX Citavi, JabRef, u.a.
(Literaturverwaltung)

PDF kein Volltext!
(Merkzettel, Notizen)

RIS Endnote, Citavi u.a.
(Literaturverwaltung)

MODS
(XML zur Weiterverarbeitung)

oder

Wählen Sie das für Sie passende Zitationsformat und kopieren Sie es dann in die Zwischenablage, lassen es sich per Mail zusenden oder speichern es als PDF-Datei.

Gewünschter Zitations-Stil:

oder

Bitte prüfen Sie, ob die Zitation formal korrekt ist, bevor Sie sie in einer Arbeit verwenden. Benutzen Sie gegebenenfalls den "Exportieren"-Dialog, wenn Sie ein Literaturverwaltungsprogramm verwenden und die Zitat-Angaben selbst formatieren wollen.

Predicting heart failure in-hospital mortality by integrating longitudinal and category data in electronic health records.