Multi‑label classification of biomedical data

Diakou,Io; Iliopoulos,Eddie; Papakonstantinou,Eleni; Dragoumani,Konstantina; Yapijakis,Christos; Iliopoulos,Costas; Spandidos,Demetrios A.; Chrousos,George P.; Eliopoulos,Elias; Vlachakis,Dimitrios

doi:10.3892/mi.2024.192

Multi‑label classification of biomedical data

Authors:
- Io Diakou
- Eddie Iliopoulos
- Eleni Papakonstantinou
- Konstantina Dragoumani
- Christos Yapijakis
- Costas Iliopoulos
- Demetrios A. Spandidos
- George P. Chrousos
- Elias Eliopoulos
- Dimitrios Vlachakis
View Affiliations

Affiliations: Laboratory of Genetics, Department of Biotechnology, School of Applied Biology and Biotechnology, Agricultural University of Athens, 11855 Athens, Greece, University Research Institute of Maternal and Child Health and Precision Medicine, National and Kapodistrian University of Athens, ‘Aghia Sophia’ Children's Hospital, 11527 Athens, Greece, School of Informatics, Faculty of Natural and Mathematical Sciences, King's College London, London WC2R 2LS, UK, Laboratory of Clinical Virology, School of Medicine, University of Crete, 71003 Heraklion, Greece
Published online on: September 9, 2024 https://doi.org/10.3892/mi.2024.192
Article Number: 68
Copyright : © Diakou et al. This is an open access article distributed under the terms of Creative Commons Attribution License [CC BY 4.0].

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Biomedical datasets constitute a rich source of information, containing multivariate data collected during medical practice. In spite of inherent challenges, such as missing or imbalanced data, these types of datasets are increasingly utilized as a basis for the construction of predictive machine‑learning models. The prediction of disease outcomes and complications could inform the process of decision‑making in the hospital setting and ensure the best possible patient management according to the patient's features. Multi‑label classification algorithms, which are trained to assign a set of labels to input samples, can efficiently tackle outcome prediction tasks. Myocardial infarction (MI) represents a widespread health risk, accounting for a significant portion of heart disease‑related mortality. Moreover, the danger of potential complications occurring in patients with MI during their period of hospitalization underlines the need for systems to efficiently assess the risks of patients with MI. In order to demonstrate the critical role of applying machine‑learning methods in medical challenges, in the present study, a set of multi‑label classifiers was evaluated on a public dataset of MI‑related complications to predict the outcomes of hospitalized patients with MI, based on a set of input patient features. Such methods can be scaled through the use of larger datasets of patient records, along with fine‑tuning for specific patient sub‑groups or patient populations in specific regions, to increase the performance of these approaches. Overall, a prediction system based on classifiers trained on patient records may assist healthcare professionals in providing personalized care and efficient monitoring of high‑risk patient subgroups.

View Figures

View References

1	Anderson JR: Machine learning: an artificial intelligence approach. Elsevier Science, 1983.
2	Russell S and Norvig P: Artificial intelligence: A modern approach. 3rd edition. Prentice-Hall, Upper Saddle River, 2010.
3	Somani P and Kaur G: A review on supervised learning algorithms. Int J Adv Sci Technol. 29:2551–2559. 2020.PubMed/NCBI View Article : Google Scholar
4	Singh P: Supervised machine learning. In: Learn PySpark: Build Python-based Machine Learning and Deep Learning Models. Singh P (ed). Apress, Berkeley, CA, pp117-159, 2019.
5	Gentleman R and Carey VJ: Unsupervised machine learning. In: Bioconductor Case Studies. Hahne F, Huber W, Gentleman R and Falcon S (eds). Springer New York, New York, NY, pp137-157, 2008.
6	Hady MFA and Schwenker F: Semi-supervised Learning. In: Handbook on Neural Information Processing. Bianchini M, Maggini M and Jain LC (eds). Intelligent Systems Reference Library. Vol. 49. Springer, Berlin, Heidelberg, pp215-239, 2013.
7	Sutton RS and Barto AG: Reinforcement learning: An introduction. MIT Press, 2018.
8	Lee D, Seo H and Jung MW: Neural basis of reinforcement learning and decision making. Annu Rev Neurosci. 35:287–308. 2012.PubMed/NCBI View Article : Google Scholar
9	Czarnul P, Proficz J and Krzywaniak A: Energy-aware high-performance computing: Survey of state-of-the-art tools, techniques, and environments. Sci Program. 2019(8348791)2019.
10	Mascetti L, Arsuaga Rios M, Bocchi E, Vicente JC, Cheong BCK, Castro D, Collet J, Contescu C, Labrador HG, Iven J, et al: CERN disk storage services: Report from last data taking, evolution and future outlook towards Exabyte-scale storage. EPJ Web Conf. 245(04038)2020.
11	Amin R, Vadlamudi S and Rahaman MM: Opportunities and challenges of data migration in cloud. Eng Int. 9:41–50. 2021.
12	Dash S, Shakyawar SK, Sharma M and Kaushik S: Big data in healthcare: Management, analysis and future prospects. J Big Data. 6(54)2019.
13	Wachter RM: Chapter 11. Other complications of healthcare. In: Understanding Patient Safety, 2e. The McGraw-Hill Companies, New York, NY, 2012.
14	Ghosheh GO, Alamad B, Yang KW, Syed F, Hayat N, Iqbal I, Al Kindi F, Al Junaibi S, Al Safi M, Ali R, et al: Clinical prediction system of complications among patients with COVID-19: A development and validation retrospective multicentre study during first wave of the pandemic. Intell Based Med. 6(100065)2022.PubMed/NCBI View Article : Google Scholar
15	van Smeden M, Reitsma JB, Riley RD, Collins GS and Moons KG: Clinical prediction models: Diagnosis versus prognosis. J Clin Epidemiol. 132:142–145. 2021.PubMed/NCBI View Article : Google Scholar
16	de Souza FSH, Hojo-Souza NS, dos Santos EB, da Silva CM and Guidoni DL: Predicting the disease outcome in COVID-19 positive patients through machine learning: A retrospective cohort study with Brazilian data. medRxiv: 2020.2006.2026.20140764, 2020.
17	Ezzoddin M, Nasiri H and Dorrigiv M: Diagnosis of COVID-19 cases from chest X-ray images using deep neural network and LightGBM. IEEE, 2022.
18	Pathak Y, Shukla PK, Tiwari A, Stalin S and Singh S: Deep transfer learning-based classification model for COVID-19 disease. IRBM. 43:87–92. 2022.PubMed/NCBI View Article : Google Scholar
19	Yuan B: Towards a clinical efficacy evaluation system adapted for personalized medicine. Pharmgenomics Pers Med. 14:487–496. 2021.PubMed/NCBI View Article : Google Scholar
20	Kotsiantis SB, Zaharakis ID and Pintelas PE: Machine learning: A review of classification and combining techniques. Artif Intell Rev. 26:159–190. 2006.
21	Wei Y, Xia W, Huang J, Ni B, dong J, Zhao Y and Yan S: CNN: Single-label to multi-label. ArXiv: abs/1406.5726, 2014.
22	Soofi AA and Awan A: Classification techniques in machine learning: Applications and issues. J Basic Appl Sci. 13:459–465. 2017.
23	Tsoumakas G and Katakis I: Multi-label classification: An overview. Int J Data Warehous Min. 3:1–13. 2009.
24	Herrera F, Charte F, Rivera AJ and del Jesus MJ: Multilabel classification. In: Multilabel Classification: Problem Analysis, Metrics and Techniques. Herrera F, Charte F, Rivera AJ and del Jesus MJ (eds). Springer International Publishing, Cham, pp17-31, 2016.
25	Sun Y, Wong AKC and Kamel MS: Classification of imbalanced data: A review. Int J Pattern Recognit Artif Intell. 23:687–719. 2009.
26	Tarekegn AN, Giacobini M and Michalak K: A review of methods for imbalanced multi-label classification. Pattern Recognit. 118(107965)2021.
27	Charte F, Rivera AJ, del Jesus MJ and Herrera F: Dealing with difficult minority labels in imbalanced mutilabel data sets. Neurocomputing. 326-327:39–53. 2019.
28	Charte F, Rivera A, del Jesus MJ and Herrera F: A first approach to deal with imbalance in multi-label datasets. In: Pan JS, Polycarpou MM, Woźniak M, de Carvalho ACPLF, Quintián H and Corchado E (eds). Hybrid Artificial Intelligent Systems. HAIS 2013. Lecture Notes in Computer Science. Vol. 8073. Springer, Berlin, Heidelberg, pp150-160, 2013.
29	Huang Y, Giledereli B, Köksal A, Ozgur A and Ozkirimli E: Balancing methods for multi-label text classification with long-tailed class distribution. arXiv: 2109.04712, 2021.
30	Giraldo Forero AF, Jaramillo-Garzón J, Ruiz-Muñoz J and Castellanos-Dominguez G: Managing Imbalanced Data Sets in Multi-label Problems: A Case Study with the SMOTE Algorithm. In: Ruiz-Shulcloper J, Sanniti di Baja G (eds). Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2013. Lecture Notes in Computer Science. Vol. 8258. Springer, Berlin, Heidelberg, pp334-342, 2013.
31	Tahir MA, Kittler J and Bouridane A: Multilabel classification using heterogeneous ensemble of multi-label classifiers. Pattern Recognit Lett. 33:513–523. 2012.
32	Cao P, Liu X, Zhao D and Zaiane O: Cost sensitive ranking support vector machine for multi-label data learning. In: Abraham A, Haqiq A, Alimi A, Mezzour G, Rokbani N and Muda A (eds). Proceedings of the 16th International Conference on Hybrid Intelligent Systems (HIS 2016). HIS 2016. Advances in Intelligent Systems and Computing. Vol. 552. Springer, Cham, pp244-255, 2017.
33	Saleh M and Ambrose JA: Understanding myocardial infarction. F1000Res. 7(1378)2018.PubMed/NCBI View Article : Google Scholar
34	World Health Organization: Cardiovascular diseases, 2022.
35	Badimon L and Vilahur G: Thrombosis formation on atherosclerotic lesions and plaque rupture. J Intern Med. 276:618–632. 2014.PubMed/NCBI View Article : Google Scholar
36	Asada Y, Yamashita A, Sato Y and Hatakeyama K: Thrombus formation and propagation in the onset of cardiovascular events. J Atheroscler Thromb. 25:653–664. 2018.PubMed/NCBI View Article : Google Scholar
37	Shavadia JS, Chen AY, Fanaroff AC, de Lemos JA, Kontos MC and Wang TY: Intensive care utilization in stable patients with ST-segment elevation myocardial infarction treated with rapid reperfusion. JACC Cardiovasc Interv. 12:709–717. 2019.PubMed/NCBI View Article : Google Scholar
38	Abrignani MG, Dominguez LJ, Biondo G, Di Girolamo A, Novo G, Barbagallo M, Braschi A, Braschi G and Novo S: In-hospital complications of acute myocardial infarction in hypertensive subjects. Am J Hypertens. 18:165–170. 2005.PubMed/NCBI View Article : Google Scholar
39	Malla RR and Sayami A: In hospital complications and mortality of patients of inferior wall myocardial infarction with right ventricular infarction. JNMA J Nepal Med Assoc. 46:99–102. 2007.PubMed/NCBI
40	Babaev A, Frederick PD, Pasta DJ, Every N, Sichrovsky T and Hochman JS: NRMI Investigators. Trends in management and outcomes of patients with acute myocardial infarction complicated by cardiogenic shock. JAMA. 294:448–454. 2005.PubMed/NCBI View Article : Google Scholar
41	Golovenkin SE, Gorban A, Mirkes E, Shulman VA, Rossiev DA, Shesternya PA, Nikulina SY, Orlova YV and Dorrer MG: Myocardial infarction complications Database. Journal, 2020.
42	Yang J and Leskovec J: Defining and evaluating network communities based on ground-truth. Knowl Inf Syst. 42:181–213. 2015.
43	Huang SJ and Zhou ZH: Multi-label learning by exploiting label correlations locally. Proc AAAI Conf Artif Intell. 26:949–955. 2021.
44	Chakravarty A, Sarkar T, Ghosh N, Sethuraman R and Sheet D: Learning decision ensemble using a graph neural network for comorbidity aware chest radiograph screening. Annu Int Conf IEEE Eng Med Biol Soc. 2020:1234–1237. 2020.PubMed/NCBI View Article : Google Scholar
45	Szymański P, Kajdanowicz T and Kersting K: How is a data-driven approach better than random choice in label space division for multi-label classification? Entropy. 18(282)2016.
46	Blondel VD, Guillaume JL, Lambiotte R and Lefebvre E: Fast unfolding of communities in large networks. J Stat Mech. 2008(P10008)2008.
47	Hagberg A, Swart PJ and Chult DA: Exploring network structure, dynamics, and function using NetworkX, 2008.
48	Goutte C and Gaussier E: A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In: Losada DE, Fernández-Luna JM (eds). Advances in Information Retrieval. ECIR 2005. Lecture Notes in Computer Science. Vol. 3408. Springer, Berlin, Heidelberg, pp345-359, 2005.
49	Qin T: Machine learning basics. In: Dual Learning. Qin T (ed). Springer Singapore, Singapore, pp11-23, 2020.
50	Sorower MS: A literature survey on algorithms for multi-label learning. Oregon State University, Corvallis, 2010.
51	Wu J, Chen XY, Zhang H, Xiong LD, Lei H and Deng SH: Hyperparameter optimization for machine learning models based on bayesian optimizationb. J Electron Sci Technol. 17:26–40. 2019.
52	Liashchynskyi P and Liashchynskyi P: Grid search, random search, genetic algorithm: A big comparison for NAS. arXiv: 1912.06059, 2019.
53	Feurer M and Hutter F: Hyperparameter optimization. In: Automated Machine Learning: Methods, Systems, Challenges. Hutter F, Kotthoff L and Vanschoren J (eds). Springer International Publishing, Cham, pp3-33, 2019.
54	Pedregosa F, Varoquaux G, Gramfort A, Michel V and Thirion B: Scikit-learn: Machine learning in python. J Mach Learn Res. 12:2825–2830. 2011.
55	Chen T and Guestrin C: XGBoost: A scalable tree boosting system. KDD ‘16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp785-794, 2016.
56	Mason L, Baxter J, Bartlett P and Frean M: Boosting algorithms as gradient descent. Adv Neural Inf Process Syst. 12:1999.
57	Boehmke B and Greenwell B: Hands-on Machine Learning with R. Chapman and Hall/CRC, New York, NY, pp221-246, 2019.
58	Medar R, Rajpurohit VS and Rashmi B: Impact of training and testing data splits on accuracy of time series forecasting in machine learning. In: 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE, pp1-6. 2017.
59	Sarker IH: Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2(160)2021.PubMed/NCBI View Article : Google Scholar
60	Nti I, Nyarko-Boateng O and Aning J: Performance of machine learning algorithms with different K values in K-fold cross-validation. Int J Inf Technol and Comp Sci. 6:61–71. 2021.
61	Refaeilzadeh P, Tang L and Liu H: Cross-validation. In: Encyclopedia of Database Systems. Liu L and ÖZsu MT (eds). Springer US, Boston, MA, pp532-538, 2009.
62	Sechidis K, Tsoumakas G and Vlahavas I: On the Stratification of Multi-label. Data. In: Gunopulos D, Hofmann T, Malerba D and Vazirgiannis M (eds). Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. Lecture Notes in Computer Science. Vol. 6913. Springer, Berlin, Heidelberg, pp145-458, 2011.
63	Szymański P and Kajdanowicz T: A network perspective on stratification of multi-label data. Proc Mach Learn Res. 74:22–35. 2017.
64	Li W, Liu Y, Liu W, Tang ZR, Dong S, Li W, Zhang K, Xu C, Hu Z, Wang H, et al: Machine learning-based prediction of lymph node metastasis among osteosarcoma patients. Front Oncol. 12(797103)2022.PubMed/NCBI View Article : Google Scholar
65	Tang Z, Wong HS and Yu Z: Privacy-preserving federated learning with domain adaptation for multi-disease ocular disease recognition. IEEE J Biomed Health Inform. 28:3219–3227. 2024.PubMed/NCBI View Article : Google Scholar
66	Chawla NV: Data mining for imbalanced datasets: An overview. In: Maimon O, Rokach L (eds). Data Mining and Knowledge Discovery Handbook. Springer, Boston, MA, pp853-867, 2005.
67	Chawla NV, Bowyer KW, Hall LO and Kegelmeyer WP: SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res. 16:321–357. 2002.