Extracting Association Rules from Turkish Otorhinolaryngology Discharge Summaries

Yıl 2018, , 35 - 42, 31.01.2018

Başak Oğuz Yolcular , Uğur Bilge Mehmet Kemal Samur

https://doi.org/10.17671/gazibtd.319690

Cited By: 1

Öz

The objectives of this study were to structure
otorhinolaryngology discharge summaries with text mining methods and analyze
structured data and extract relational rules using Association Rule Mining
(ARM). In this study, we used otorhinolaryngology discharge notes. We first
developed a dictionary-based information extraction (IE) module in order to
annotate medical entities. Later we extracted the annotated entities, and
transformed all documents into a data table. We applied ARM Apriori algorithm
to the final dataset, and identified interesting patterns and relationships
between the entities as association rules for predicting the treatment
procedure for patients. The IE module’s precision, recall, and f-measure were
95.1%, 84.5%, and 89.2%, respectively.  A
total of fifteen association rules were found by selecting the top ranking
rules obtained from the ARM analysis. These fifteen rules were reviewed by a
domain expert, and the validity of these rules was examined in the PubMed
literature. The results showed that the association rules are mostly endorsed
by the literature. Although our system focuses on the domain of
otorhinolaryngology, we believe the same methodology can be applied to other
medical domains and extracted rules can be used for clinical decision support
systems and in patient care.

Anahtar Kelimeler

Association Rule Mining, Information Extraction, Otorhinolaryngology, Rule Extraction, Text Mining

Kulak Burun Boğaz Taburcu Notlarından Birliktelik Kurallarının Çıkartılması

Öz

The objectives of this study were to structure
otorhinolaryngology discharge summaries with text mining methods and analyze
structured data and extract relational rules using Association Rule Mining
(ARM). In this study, we used otorhinolaryngology discharge notes. We first
developed a dictionary-based information extraction (IE) module in order to
annotate medical entities. Later we extracted the annotated entities, and
transformed all documents into a data table. We applied ARM Apriori algorithm
to the final dataset, and identified interesting patterns and relationships
between the entities as association rules for predicting the treatment
procedure for patients. The IE module’s precision, recall, and f-measure were
95.1%, 84.5%, and 89.2%, respectively.  A
total of fifteen association rules were found by selecting the top ranking
rules obtained from the ARM analysis. These fifteen rules were reviewed by a
domain expert, and the validity of these rules was examined in the PubMed
literature. The results showed that the association rules are mostly endorsed
by the literature. Although our system focuses on the domain of
otorhinolaryngology, we believe the same methodology can be applied to other
medical domains and extracted rules can be used for clinical decision support
systems and in patient care.

Anahtar Kelimeler

Birliktelik Kuralları, Bilgi Çıkarımı, Kulak Burun Boğaz, Kural Çıkarımı, Metin Madenciliği

Kaynakça

• [1] Zhu F, Patumcharoenpol P, Zhang C, et al. Biomedical text mining and its applications in cancer research. J Biomed Inform. 2013; 46: 200-11.
• [2] Khabsa M and Giles CL. Chemical entity extraction using CRF and an ensemble of extractors. J Cheminform. 2015; 7: S12.
• [3] Meystre SM, Savova GK, Kipper-Schuler KC and Hurdle JF. Extracting information from textual documents in the electronic health record: a review of recent research. Yearb Med Inform. 2008: 128-44.
• [4]Lin YK, Chen H and Brown RA. MedTime: a temporal information extraction system for clinical narratives. J Biomed Inform. 2013; 46 Suppl: S20-8.
• [5]Tang B, Wu Y, Jiang M, Chen Y, Denny JC and Xu H. A hybrid system for temporal information extraction from clinical text. J Am Med Inform Assoc. 2013; 20: 828-35.
• [6]Patrick JD, Nguyen DH, Wang Y and Li M. A knowledge discovery and reuse pipeline for information extraction in clinical notes. J Am Med Inform Assoc. 2011; 18: 574-9.
• [7]Jiang M, Chen Y, Liu M, et al. A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries. J Am Med Inform Assoc. 2011; 18: 601-6.
• [8]Sevenster M, van Ommering R and Qian Y. Automatically correlating clinical findings and body locations in radiology reports using MedLEE. J Digit Imaging. 2012; 25: 240-9.
• [9]Chiang JH, Lin JW and Yang CW. Automated evaluation of electronic discharge notes to assess quality of care for cardiovascular diseases using Medical Language Extraction and Encoding System (MedLEE). J Am Med Inform Assoc. 2010; 17: 245-52.
• [10]Schadow G and McDonald CJ. Extracting structured information from free text pathology reports. AMIA Annu Symp Proc. 2003: 584-8.
• [11]Savova GK, Fan J, Ye Z, et al. Discovering peripheral arterial disease cases from radiology notes using natural language processing. AMIA Annu Symp Proc. 2010; 2010: 722-6.
• [12]Cui L, Sahoo SS, Lhatoo SD, et al. Complex epilepsy phenotype extraction from narrative clinical discharge summaries. J Biomed Inform. 2014; 51: 272-9.
• [13]Pradhan S, Elhadad N, South BR, et al. Evaluating the state of the art in disorder recognition and normalization of the clinical narrative. J Am Med Inform Assoc. 2015; 22: 143-54.
• [14]Divita G, Zeng QT, Gundlapalli AV, Duvall S, Nebeker J and Samore MH. Sophia: A Expedient UMLS Concept Extraction Annotator. AMIA Annu Symp Proc. 2014; 2014: 467-76.
• [15]Petkov VI, Penberthy LT, Dahman BA, Poklepovic A, Gillam CW and McDermott JH. Automated determination of metastases in unstructured radiology reports for eligibility screening in oncology clinical trials. Exp Biol Med (Maywood). 2013; 238: 1370-8.
• [16]Botsis T, Woo EJ and Ball R. The contribution of the vaccine adverse event text mining system to the classification of possible Guillain-Barre syndrome reports. Appl Clin Inform. 2013; 4: 88-99.
• [17]Chen E and Garcia-Webb M. An analysis of free-text alcohol use documentation in the electronic health record: early findings and implications. Appl Clin Inform. 2014; 5: 402-15.
• [18]Bozkurt S, Lipson JA, Senol U and Rubin DL. Automatic abstraction of imaging observations with their characteristics from mammography reports. J Am Med Inform Assoc. 2015; 22: e81-92.
• [19]D O. Ontology Based Text Mining in Turkish Radiology Reports. Computer Engineering Department. Ankara: Middle East Technical University, 2012, p. 96.
• [20]Soysal E, Cicekli I and Baykal N. Design and evaluation of an ontology based information extraction system for radiological reports. Comput Biol Med. 2010; 40: 900-11.
• [21]Ordonez C. Association rule discovery with the train and test approach for heart disease prediction. IEEE Trans Inf Technol Biomed. 2006; 10: 334-43.
• [22] SE, Sprague AP, Hardin JM, Waites KB, Jones WT and Moser SA. Association rules and data mining in hospital infection control and public health surveillance. J Am Med Inform Assoc. 1998; 5: 373-81.
• [23]Buczak AL, Baugher B, Guven E, et al. Fuzzy association rule mining and classification for the prediction of malaria in South Korea. BMC Med Inform Decis Mak. 2015; 15: 47.
• [24]Buczak AL, Koshute PT, Babin SM, Feighner BH and Lewis SH. A data-driven epidemiological prediction method for dengue outbreaks using local and remote sensing data. BMC Med Inform Decis Mak. 2012; 12: 124.
• [25]Goh DH and Ang RP. An introduction to association rule mining: an application in counseling and help-seeking behavior of adolescents. Behav Res Methods. 2007; 39: 259-66.
• [26]Tai YM and Chiu HW. Comorbidity study of ADHD: applying association rule mining (ARM) to National Health Insurance Database of Taiwan. Int J Med Inform. 2009; 78: e75-83.
• [27]Erhardt RA, Schneider R and Blaschke C. Status of text-mining techniques applied to biomedical text. Drug Discov Today. 2006; 11: 315-25.
• [28]Eftekhar A, Juffali W, El-Imad J, Constandinou TG and Toumazou C. Ngram-derived pattern recognition for the detection and prediction of epileptic seizures. PLoS One. 2014; 9: e96235.
• [29]Cano C, Blanco A and Peshkin L. Automated identification of diagnosis and co-morbidity in clinical records. Methods Inf Med. 2009; 48: 546-51.
• [30]Ordonez C EN and CA. S. Constraining and summarizing association rules in medical data. Knowl Inf Syst. 2006; 9: 259–83.
• [31]Frank E, Hall M, Trigg L, Holmes G and Witten IH. Data mining in bioinformatics using Weka. Bioinformatics. 2004; 20: 2479-81.
• [32]Agrawal R SR. Fast algorithms for mining association rules. The VLDB Conference. Santiago, Chile1994.
• [33]de Azevedo AF, Pinto DC, de Souza NJ, Greco DB and Goncalves DU. Sensorineural hearing loss in chronic suppurative otitis media with and without cholesteatoma. Braz J Otorhinolaryngol. 2007; 73: 671-4.
• [34]Szaleniec J, Wiatr M, Szaleniec M, et al. Artificial neural network modelling of the results of tympanoplasty in chronic suppurative otitis media patients. Comput Biol Med. 2013; 43: 16-22.
• [35]Kudoh M. [Longitudinal assessment of articulatory and masticatory functions following glossectomy for tongue carcinoma]. Kokubyo Gakkai Zasshi. 2010; 77: 27-34.
• [36]Karadeniz A, Saynak M, Kadehci Z, et al. [The results of combined treatment (surgery and postoperative radiotherapy) for tongue cancer and prognostic factors]. Kulak Burun Bogaz Ihtis Derg. 2007; 17: 1-6.
• [37]Bussu F, Parrilla C, Rizzo D, Almadori G, Paludetti G and Galli J. Clinical approach and treatment of benign and malignant parotid masses, personal experience. Acta Otorhinolaryngol Ital. 2011; 31: 135-43.
• [38]Somefun OA, Oyeneyin JO, Abdulkarrem FB, da Lilly-Tariah OB, Nimkur LT and Esan OO. Surgery of parotid gland tumours in lagos: a 12 year review. Niger Postgrad Med J. 2007; 14: 72-5.
• [39]Markou K, Goudakos J, Triaridis S, Konstantinidis J, Vital V and Nikolaou A. The role of tumor size and patient's age as prognostic factors in laryngeal cancer. Hippokratia. 2011; 15: 75-80.
• [40]Aires FT, Dedivitis RA, Castro MA, Ribeiro DA, Cernea CR and Brandao LG. [Pharyngocutaneous fistula following total laryngectomy]. Braz J Otorhinolaryngol. 2012; 78: 94-8.
• [41]Thompson LD. Chondrosarcoma of the larynx. Ear Nose Throat J. 2004; 83: 609.
• [42]Cohen JT, Postma GN, Gupta S and Koufman JA. Hemicricoidectomy as the primary diagnosis and treatment for cricoid chondrosarcomas. Laryngoscope. 2003; 113: 1817-9.
• [43]Thompson LD and Gannon FH. Chondrosarcoma of the larynx: a clinicopathologic study of 111 cases with a review of the literature. Am J Surg Pathol. 2002; 26: 836-51.
• [44]Brandwein M, Moore S, Som P and Biller H. Laryngeal chondrosarcomas: a clinicopathologic study of 11 cases, including two "dedifferentiated" chondrosarcomas. Laryngoscope. 1992; 102: 858-67.
• [45]Casiraghi O, Martinez-Madrigal F, Pineda-Daboin K, Mamelle G, Resta L and Luna MA. Chondroid tumors of the larynx: a clinicopathologic study of 19 cases, including two dedifferentiated chondrosarcomas. Ann Diagn Pathol. 2004; 8: 189-97.
• [46]Buda I, Hod R, Feinmesser R and Shvero J. Chondrosarcoma of the larynx. Isr Med Assoc J. 2012; 14: 681-4.
• [47]Matos JP, Castro Silva J and Monteiro E. [Causes of death in patients with laryngeal cancer in stages I and II]. Acta Med Port. 2012; 25: 317-22.
• [48]Velupillai S, Mowery D, South BR, Kvist M and Dalianis H. Recent Advances in Clinical Natural Language Processing in Support of Semantic Analysis. Yearb Med Inform. 2015; 10: 183-93.
• [49]Nguyen AN, Lawley MJ, Hansen DP, et al. Symbolic rule-based classification of lung cancer stages from free-text pathology reports. J Am Med Inform Assoc. 2010; 17: 440-5.
• [50]Stevenson M, Agirre E and Soroa A. Exploiting domain information for Word Sense Disambiguation of medical documents. J Am Med Inform Assoc. 2012; 19: 235-40.
• [51]McCowan I, Moore D and Fry MJ. Classification of cancer stage from free-text histology reports. Conf Proc IEEE Eng Med Biol Soc. 2006; 1: 5153-6.
• [52]Nguyen A, Moore D, McCowan I and Courage MJ. Multi-class classification of cancer stages from free-text histology reports using support vector machines. Conf Proc IEEE Eng Med Biol Soc. 2007; 2007: 5140-3.