Diagnostics based patient classification for clinical decision support systems

• Autorzy: Paliwal Gaurav , Bunglowala Aaquil , Kanthed Pravesh

Identyfikatory

DOI

10.14313/JAMRIS/2‐2024/16

• Języki publikacji: EN

Abstrakty

EN

The widespread adoption of Electronic Healthcare Records has resulted in an abundance of healthcare data. This data holds significant potential for improving healthcare services by providing valuable clinical insights and enhancing clinical decision-making. This paper presents a patient classification methodology that utilizes a multiclass and multilabel diagnostic approach to predict the patient’s clinical class. The proposed model effectively handles comorbidities while maintaining a high level of accuracy. The implementation leverages the MIMIC III database as a data source to create a phenotyping dataset and train the models. Various machine learning models are employed in this study. Notably, the natural language processing-based One-Vs-Rest classifier achieves the best classification results, maintaining accuracy and F1 scores even with a large number of classes. The patient diagnostic class prediction model, based on the International Classification of Diseases 9, showcased in this paper, has broad applications in diagnostic support, treatment prediction, clinical assistance, recommender systems, clinical decision support systems, and clinical knowledge discovery engines.

Słowa kluczowe

EN

multiclass patient classification; multi-label patient classification; electronic healthare record; MIMIC III; natural language processing; deep learning

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2024
• Tom: Vol. 18, No. 2
• Strony: 83--96
• Opis fizyczny: Bibliogr. 62 poz., rys.

Twórcy

autor

Paliwal Gaurav

• SVKM’s, Narsee Monjee Insti‐ tute of Management Studies, Indore, India

autor

Bunglowala Aaquil

• Sri Aurobindo Institute of Tech‐ nology, Indore, India

autor

Kanthed Pravesh

• Choithram Interventional Spine & Pain Centre, Indore, India

Bibliografia

• [1] C.-J. Hsiao, E. Hing, “Use and characteristics of electronic health record systems among office-based physician practices,” NCHS Data Brief, vol. 111, 2012, pp. 1–8.
• [2] G.S. Alotaibi, C. Wu, A. Senthilselvan, M.S. McMurtry, “The validity of ICD codes coupled with imaging procedure codes for identifying acute venous thromboembolism using administrative data,” Vasc. Med., vol. 20, no. 4, 2015, pp. 364–368. doi: 10.1177/1358863X15573839.
• [3] W.Q. Wei, P.L. Teixeira, H. Mo, R.M. Cronin, J.L. Warner, J.C. Denny, “Combining billing codes, clinica notes, and medications from electronic health records provides superior phenotyping performance,” J. Am. Med. Inform. Assoc., vol. 23 , no. e1, 2016, pp. 20–27. doi: 10.1093/jamia/ocv130.
• [4] World Health Organization, “International Classification of Diseases (icd),” 2012.
• [5] H. Lamberts, I. Okkes, et al, “Icpc-2,”International Classification of Primary Care, 1998.
• [6] S. Pakhomov, J.D. Buntrock, C.G. Chute, “Automating the assignment of diagnosis codes to patient encounters using example-based and machine learning techniques,” J. Am. Med. Inform. Assoc., vol. 13, no. 5, 2006, pp. 516–525, doi: 10.1197/jamia.M2077.
• [7] M.H. Stanfill, M. Williams, S.H. Fenton, R.A. Jenders, W.R. Hersh, “A systematic literaturę review of automated clinical coding and classification systems,” J. Am. Med. Inform. Assoc., vol. 17, no. 6, 2010, pp. 646–651, doi: 10.1136/jamia.2009.001024.
• [8] A.E.W. Johnson, T.J. Pollard, L. Shen, L.-W.H. Lehman, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L.A. Celi, R.G. Mark, MIMIC-III, “A freely accessible critical care database,” Sci. Data, vol. 3, 2016, p. 160035, doi: 10.1038/sdata.2016.35.
• [9] A. Perotte, R. Pivovarov, K. Natarajan, N. Weiskopf, F. Wood, N. Elhadad, “Diagnosis code assignment: models and evaluation metrics,” J. Am. Med. Inform. Assoc., vol. 21, no. 2, 2014, pp. 231–237, doi: 10.1136/amiajnl-2013-002159.
• [10] M. Subotin, A.R. Davis, “A System for Predicting ICD-10-PCS Codes from Electronic Health Records,” Workshop on BioNLP (BioNLP), 2014, pp. 59–67.
• [11] S. Abhyankar, D. Demner-Fushman, F. Callaghan, “Combining structured and unstructured data to identify a cohort of ICU patients who received dialysis,” J. Am. Med. Inform. Assoc., vol. 21, no. 5, 2014, pp. 801–807.
• [12] J. Pathak, K.R. Bailey, C.E. Beebe, S. Bethard, D.S. Carrell, P.J. Chen, et al, “Normalization and standardization of electronic health records for high-throughput phenotyping: The SHARPn consortium,” J. Am. Med. Inform. Assoc., vol. 20, no. e2, 2013, pp. e341–e348, doi: 10.1136/amiajnl-2013-001939.
• [13] O. Bodenreider, “The Unified Medical Language System (UMLS): Integrating biomedical terminology,” Nucl. Acids Res., vol. 32, suppl. 1, 2004, pp. D267–D270, doi: 10.1093/nar/gkh061.
• [14] RIZIV, Rijksinstituut voor ziekte- en invalidite itsuitkeringen nomenclature, http://www.riziv.fgov.be/NL/nomenclatuur/Paginas/default.aspx>.
• [15] E. Scheurwegs, K. Luyckx, L. Luyten, W. Daelemans, T. Van den Bulcke, “Data integration of structured and unstructured sources for assigning clinical codes to patient stays,” J. Am. Med. Inform. Assoc., vol. 23, no. e1, 2016, pp. 11–19, doi: 10.1093/jamia/ocv115.
• [16] R. Miotto, L. Li, B.A. Kidd, J.T. Dudley, “Deep patient: An unsupervised representation to predict the future of patients from the electronic health records,” Sci. Rep., vol. 6, no. April, 2016, p. 26094, doi: 10.1038/srep26094.
• [17] R. Cohen, M. Elhadad, N. Elhadad, “Redundancy in electronic health record corpora: Analysis, impact on text mining performance and mitigation strategies,” BMC Bioinform., vol. 14, no. 1, 2013, p. 10, doi: 10.1186/1471-2105-14-10.
• [18] S.M. Vieira, L.F. Mendona, G.J. Farinha, J.M.C. Sousa, “Modified binary {PSO} for feature selection using {SVM} applied to mortality prediction of septic patients,” Appl. Soft Comput., vol. 13, no.8, 2013, pp. 3494–3504.
• [19] T. Botsis, M.D. Nguyen, E.J. Woo, M. Markatou, R. Ball, “Text mining for the Vaccine Adverse Event Reporting System: Medical text classification using informative feature selection,” J. Am. Med. Inform. Assoc., vol. 18, no. 5, 2011, pp. 631–638.
• [20] I. Guyon, A. Elisseeff, “An introduction to variable and feature selection,” J. Mach. Learn. Res., vol. 3, 2003, pp. 1157–1182, doi: 10.1016/j.aca.2011.07.027.arXiv:1111.6189v1.
• [21] R. Kohavi, G.H. John, “Wrappers for feature subset selection,” Artif. Intell., vol. 97, no. 1–2, 1997, pp. 273–324, doi: 10.1016/S0004-3702(97)00043-X.
• [22] H.C. Peng, F. Long, C. Ding, “Feature selection based on mutual information: criteria of max-dependency, max-relevance, and minredundancy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 8, 2005, pp. 1226–1238.
• [23] S. Fu, M.C. Desmarais, “Markov blanket based feature selection: a review of past decade,” Proceedings of the World Congress on Engineering 2010, vol. I, 2010, pp. 321–328.
• [24] I. Tsamardinos, L.E. Brown, C.F. Aliferis, “The max-min hill-climbing Bayesian network structure learning algorithm,” Mach. Learn., vol. 65, no. 1, 2006, pp. 31–78, doi: 10.1007/s10994-006-6889-7.
• [25] A.E.W. Johnson, T.J. Pollard, L. Shen, L. Lehman, M. Feng, M. Ghassemi, et al, “MIMIC-III, A freely accessible critical care database,” Scientific Data, 2016, doi: 10.1038/sdata.2016.35. Available from: http://www.nature.com/articles/sdata201635.
• [26] B. Dolhansky, Artificial Neural Networks: Linear Multiclass Classification (Part 3) September 27, 2013 in ml primers, neural networks, http://www.briandolhansky.com/blog/2013/9/23/artificial-neural-nets-linear-multiclass-part-3.
• [27] E. Scheurwegs, B. Cule, K. Luyckx, L. Luyten, W. Daelemans, “Selecting relevant features from the electronic health record for clinical code prediction,” Journal of Biomedical Informatics, vol. 74, 2017, pp. 92–103.
• [28] S.M. Zhou, F. Fernandez-Gutierrez, J. Kennedy, R. Cooksey, M. Atkinson, S. Denaxas, C. Sudlow, “Defining disease phenotypes in primary care electronic health records by a machine learning approach: a case study in identifying rheumatoid arthritis,” PloS one, vol. 11, no. 5, 2016, p. e0154515.
• [29] T. Lingren, P. Chen, J. Bochenek, F. Doshi-Velez, P. Manning-Courtney, J. Bickel, et al, “Electronic health record based algorithm to identify patients with autism spectrum disorder,” PloS one, vol. 11, no. 7, 2016, p. e0159621.
• [30] J. Zhao, P. Papapetrou, L. Asker, H. Boström, “Learning from heterogeneous temporal data in electronic health records,” Journal of Biomedical Informatics, vol. 65, pp. 105–119.
• [31] S. Pai, S. Hui, R. Isserlin, M.A. Shah, H. Kaka, G.D. Bader, “netDx: interpretable patient classification using integrated patient similarity networks,” Molecular Systems Biology, vol. 15, no. 3, 2016, p. e8497.
• [32] P. Courtiol, C. Maussion, M. Moarii, E. Pronier, S. Pilcer, M. Sefta, T. Clozel, “Deep learning-based classification of mesothelioma improves prediction of patient outcome,” Nature Medicine, vol. 25, no. 10, 2019, pp. 1519–1525.
• [33] B. Dolhansky, 2013, Artificial neural networks: Mathematics of backpropagation (part 4), https: //www.briandolhansky.com/blog/2013/9/27/artificial-neural-networks-backpropagation-part-4.
• [34] B. Dolhansky, J.A. Bilmes, “Deep submodular functions: Definitions and learning. Advances in Neural Information Processing Systems,” vol. 29, 2016, pp. 3404–3412.
• [35] G. Paliwal, A. Bunglowala, P. Kanthed, “An architectural design study of electronic healthcare record systems with associated context parameters on MIMIC III,” Health and Technology, 2022, pp. 1–15.
• [36] H. Sharma, C. Mao, Y. Zhang, H. Vatani, L. Yao, Y. Zhong, Y. Luo, “Developing a portable natural language processing based phenotyping system,” BMC Medical Informatics and Decision Making, vol. 19, no. 3, pp. 79–87.
• [37] A.P. Reimer, A. Milinovich, “Using UMLS for electronic health data standardization and database design,” Journal of the American Medical Informatics Association, vol. 27, no. 10, 2020, pp. 1520–1528.
• [38] H. Zhang, T. Lyu, P. Yin, S. Bost, X. He, Y. Guo, J. Bian, “A scoping review of semantic integration of health data and information,” International Journal of Medical Informatics, 2022, p. 104834.
• [39] D. Yuvaraj, A.M.U. Ahamed, M. Sivaram, “A study on the role of natural language processing in the healthcare sector,” Materials Today: Proceedings, 2021.
• [40] H. Sharma, C. Mao, Y. Zhang, H. Vatani, L. Yao, Y. Zhong, et al, “Developing a portable natural language processing based phenotyping system,” BMC Medical Informatics and Decision Making, vol. 19, no. 3, 2019, pp. 79–87.
• [41] S. Moosavinasab, E. Sezgin, H. Sun, J. Hoffman, Y. Huang, S. Lin, “DeepSuggest: Using neural networks to suggest related keywords for a comprehensive search of clinical notes,” ACI open, vol. 5, no. 01, 2021, pp. e1–e12.
• [42] B. Wang, Y. Sun, Y. Chu, D. Zhao, Z. Yang, J. Wang, “Refining electronic medical records representation in manifold subspace,” BMC bioinformatics, vol. 23, no. 1, pp. 1–17.
• [43] E.O. Omuya, G.O. Okeyo, M.W. Kimwele, “Feature selection for classification using principal component analysis and information gain,” Expert Systems with Applications, vol. 174, 2021, p. 114765.
• [44] U.A. Bhatti, L. Yuan, Z. Yu, S.A. Nawaz, A. Mehmood, M.A. Bhatti, et al, “Predictive Data Modeling Using sp-kNN for Risk Factor Evaluation in Urban Demographical Healthcare Data,” Journal of Medical Imaging and Health Informatics, vol. 11, no. 1, 2021, pp. 7–14.
• [45] N. Wang, Y. Huang, H. Liu, Z. Zhang, L. Wei, X. Fei, H. Chen, “Study on the semi-supervised learning-based patient similarity from heterogeneous electronic medical records,” BMC medical informatics and decision making, vol. 21, no. 2, 2021, pp. 1–13.
• [46] C. Comito, D. Falcone, A. Forestiero, Diagnosis prediction based on similarity of patients physiological parameters. In Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 487–494.
• [47] W.M. Shaban, A. Rabie, A.I. Saleh, M.A. Abo-Elsoud, “Accurate detection of COVID-19 patients based on distance biased Nave Bayes (DBNB) classification strategy,” Pattern Recognition, vol. 119, 2021, p. 108110.
• [48] V. Jackins, S. Vimal, M. Kaliappan, M.Y. Lee, “AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,” The Journal of Supercomputing, 77(5), 2021, pp. 5198–5219.
• [49] J.M. Bae, “The clinical decision analysis using decision tree,” Epidemiology and health, vol. 36, 2021.
• [50] S.H. Rukmawan, F.R. Aszhari, Z. Rustam, J. Pandelaki, “Cerebral infarction classification using the k-nearest neighbor and naive bayes classifier,” Journal of Physics: Conference Series, Vol. 1752, No. 1, 2021, p. 012045.
• [51] L.I. Qi, “Patient classification with ensemble treebased modelling for decision support in acute clinical care settings,” Doctoral dissertation, RMIT University.
• [52] A. Singh, A. Dhillon, N. Kumar, M. Hossain, G. Muhammad, M. Kumar, “eDiaPredict: An Ensemble-based framework for diabetes prediction,” ACM Transactions on Multimidia Computing Communications and Applications, vol. 17, no. 2s, 2021, pp. 1–26.
• [53] T. Razzaghi, O. Roderick, I. Safro, N. Marko, “Multilevel weighted support vector machine for classification on healthcare data with missing values,” PloS one, vol. 11, no. 5, 2021, p. e0155119.
• [54] D.M. Abdullah, A.M. Abdulazeez, “Machine Learning Applications based on SVM Classification A Review,” Qubahan Academic Journal, vol. 1, no. 2, 2021, pp. 81–90.
• [55] N. Shahid, T. Rappon, W. Berta, “Applications of artificial neural networks in health care organizational decision-making: A scoping review,” PloS one, vol. 14, no. 2, 2019, p. e0212356.
• [56] W. Liu, Z. Wang, N. Zeng, F.E. Alsaadi, X. Liu, “A PSO-based deep learning approach to classifying patients from emergency departments,” International Journal of Machine Learning and Cybernetics, vol. 12, no. 7, 2021, pp. 1939-1948.
• [57] B.S. Panchbhai, V.M. Pathak, “A Systematic Review of Natural Language Processing in Healthcare,” Journal of Algebraic Statistics, vol. 13, no. 1, 2022, pp. 682–707.
• [58] B. Zhou, G. Yang, Z. Shi, S. Ma, “Natural language processing for smart healthcare,”IEEE Reviews in Biomedical Engineering, 2022.
• [59] K.M. Al-Aidaroos, A.A. Bakar, Z. Othman, “Medical data classification with Naive Bayes approach,” Information Technology Journal, vol. 11, no. 9, p. 1166.
• [60] I. Korobiichuk, A. Ladanyuk, R. Boiko, S. Hrybkov, “Features of Control Processes in Organizational-Technical (Technological) Systems of Continuous Type,” Journal of Automation, Mobile Robotics and Intelligent Systems, vol. 14, no. 4, pp. 11–17. doi: 10.14313/JAMRIS/4-2020/39.
• [61] S. Yousfi, M. Rhanoui, M. Mikram, “Comparative Study of CNN and LSTM for Opinion Mining in Long Text,” Journal of Automation, Mobile Robotics and Intelligent Systems, vol. 14, no. 3, pp. 50–55. doi: 10.14313/JAMRIS/3-2020/34.
• [62] A. Ndayikengurukiye, A. Ez-zahout, A. Aboubakr, Y. Charkaoui, O. Fouzia, “Resource Optimisation in Cloud Computing: Comparative Study of Algorithms Applied to Recommendations in a Big Data Analysis Architecture,” Journal of Automation, Mobile Robotics and Intelligent Systems, vol. 15, no. 4, pp. 65–75. doi: 10.14313/JAMRIS/4-2021/28.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).