Iranian Journal of Biomedical Engineering (IJBME)

تشخیص اختلالات توام حرکتی مری بر اساس دادگان مانومتری رزولوشن بالا

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی دکتری، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

2 استاد، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

3 استادیار، پژوهشکده‌ی بیماری‌های گوارش و کبد، دانشگاه علوم پزشکی تهران، تهران، ایران

4 استاد، پژوهشکده‌ی بیماری‌های گوارش و کبد، دانشگاه علوم پزشکی تهران، تهران، ایران

چکیده
اختلالات حرکتی مری یکی از بیماری‌های سیستم گوارش است که در آن حرکت توده‌ی غذایی در طول مری به صورت طبیعی اتفاق نمی‌افتد. روش استاندارد برای تشخیص این موارد، بهره‌گیری از مانومتری رزولوشن بالا است. علی‌رغم وجود راهنماهای پزشکی مانند راهنمای شیکاگو برای تحلیل نتایج مانومتری، این موضوع کماکان امر دشواری بوده که نیاز به تجربه‌ی بالای پزشک و یا استفاده از دیگر روش‌های کمکی ثانویه برای تشخیص دارد. از سوی دیگر بسیاری از اختلالات مذکور می‌توانند به صورت توام در یک فرد ظاهر شده و تشخیص‌گذاری را پیچیده‌تر کنند. تمرکز این مطالعه روی بیمارانی با بیش از یک اختلال به صورت توام بوده و موضوع تشخیص بیماری به صورت یک مساله‌ی طبقه‌بندی چندبرچسبی مطرح شده است. از این رو ساختار طبقه‌بند فازی که پیش‌تر توسط نویسندگان این مقاله به منظور تشخیص تک‌بیماری معرفی شده، توسعه یافته است تا علاوه بر یادگیری فضای ورودی نمونه‌ها، از اطلاعات هم‌شیوعی اختلالات نیز برای بهبود پیش‌بینی استفاده کند. نتایج به دست آمده نشان داده که اضافه کردن این اطلاعات به فرایند تعلیم طبقه‌بند نه تنها عمل‌کرد آن را نسبت به حالت پایه به شکل قابل ملاحظه‌ای افزایش داده، بلکه منجر به ساختاری از طبقه‌بندی کننده‌ی فازی شده است که نسبت به روش‌های دیگر طبقه‌بندی چندبرچسبی برتری دارد. روش معرفی شده قادر است با هزینه‌ی همینگ متوسط 08/0±18/0 اختلالات حرکتی مری را تشخیص دهد که نسبت به سایر روش‌ها عمل‌کرد بهتری به شمار می‌آید.

کلیدواژه‌ها

موضوعات


عنوان مقاله English

Distinguishing Multiple Concurrent Esophageal Motility Disorders using High-Resolution Manometry

نویسندگان English

Safa Rafieivand 1
Mohammad Hassan Moradi 2
Zahra Momayez Sanat 3
Hosein Asl Soleimani 4
1 Ph.D. Student, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
2 Professor, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
3 Assistant Professor, Digestive Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
4 Professor, Digestive Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
چکیده English

Esophageal mobility disorders are a type of digestive system problem characterized by abnormal bolus movement in the esophagus. The standard diagnostic method for these kinds of disorders is High-Resolution Manometry (HRM). Despite the availability of guidelines like “Chicago” for the analysis of HRM results, diagnosis is still a challenging task that is relies on the physician's skills or requires additional assessment modalities. Additionally, it is typical for esophageal mobility disorders to co-occur in one person, leading to a more complex situation for problem identification. The current study focuses on cases who suffering from more than one disorder simultaneously. Then the problem of disorder identification can be interpreted as a multi-label classification problem. Consequently, the fuzzy classifier architecture that was previously introduced for automatic single-disorder diagnosis by the authors is modified. The presented classifier in this paper not only learns the input space from the samples but also utilizes the co-morbidity of disorders to enhance the prediction results. The outcomes show that adding this information to the learning procedure of the base classifier enhances its performance and generates a new fuzzy classifier that overcomes other multi-label classifiers. The presented method is able to differentiate esophageal mobility disorders with an average Hamming loss of 0.18±0.08 which is better than other competitor methods.

کلیدواژه‌ها English

Esophageal Manometry
Esophageal Mobility Disorders
Multi-Label Classification
Fuzzy Classification
  1. C. Ghoshal, Evaluation of Gastrointestinal Motility and its Disorders. New Delhi: Springer India, 2016.
  2. A. Carlson and S. Roman, “Esophageal provocation tests: Are they useful to improve diagnostic yield of high resolution manometry?,” Neurogastroenterol. Motil., vol. 30, no. 4, p. e13321, Apr. 2018.
  3. Yadlapati et al., “Esophageal motility disorders on high‐resolution manometry: Chicago classification version 4.0 ©,” Neurogastroenterol. Motil., vol. 33, no. 1, pp. 1–21, Jan. 2021.
  4. A. Carlson, Z. Lin, W. Kou, and J. E. Pandolfino, “Inter-rater agreement of novel high-resolution impedance manometry metrics: Bolus flow time and esophageal impedance integral ratio,” Neurogastroenterol. Motil., vol. 30, no. 6, p. e13289, Jun. 2018.
  5. Jungheim et al., “Calculation of upper esophageal sphincter restitution time from high resolution manometry data using machine learning,” Physiol. Behav., vol. 165, pp. 413–424, Oct. 2016.
  6. G. Alcala Gonzalez, R. A. B. Oude Nijhuis, A. J. P. M. Smout, and A. J. Bredenoord, “Normative reference values for esophageal high‐resolution manometry in healthy adults: A systematic review,” Neurogastroenterol. Motil., vol. 33, no. 1, Jan. 2021.
  7. Rengarajan, J. Drapekin, A. Patel, and C. P. Gyawali, “Comparison of two high-resolution manometry software systems in evaluating esophageal motor function,” Neurogastroenterol. Motil., vol. 28, no. 12, pp. 1836–1843, Dec. 2016.
  8. L. Carniel et al., “A physiological model for the investigation of esophageal motility in healthy and pathologic conditions,” Proc. Inst. Mech. Eng. Part H J. Eng. Med., vol. 230, no. 9, pp. 892–899, Sep. 2016.
  9. Frigo, M. Costantini, C. G. Fontanella, R. Salvador, S. Merigliano, and E. L. Carniel, “A Procedure for the Automatic Analysis of High-Resolution Manometry Data to Support the Clinical Diagnosis of Esophageal Motility Disorders,” IEEE Trans. Biomed. Eng., vol. 65, no. 7, pp. 1476–1485, Jul. 2018.
  10. Wang, M. Hou, L. Yan, Y. Dai, Y. Yin, and X. Liu, “Deep learning for tracing esophageal motility function over time,” Comput. Methods Programs Biomed., vol. 207, 2021.
  11. Wang et al., “Attention graph convolutional nets for esophageal contraction pattern recognition in high-resolution manometries,” Biomed. Signal Process. Control, vol. 68, no. April, p. 102734, Jul. 2021.
  12. Kou et al., “A multi-stage machine learning model for diagnosis of esophageal manometry,” Artif. Intell. Med., vol. 124, p. 102233, Feb. 2022.
  13. R. Fox et al., “Inter-observer agreement for diagnostic classification of esophageal motility disorders defined in high-resolution manometry,” Dis. Esophagus, vol. 28, no. 8, pp. 711–719, Nov. 2015.
  14. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering,” Jun. 2016.
  15. Rafieivand, M. H. Moradi, Z. Momayez Sanat, and H. Asl Soleimani, “A fuzzy-based framework for diagnosing esophageal mobility disorder using high-resolution manometry,” J. Biomed. Inform., vol. 141, p. 104355, May 2023.
  16. -L. Zhang and Z.-H. Zhou, “ML-KNN: A lazy learning approach to multi-label learning,” Pattern Recognit., vol. 40, no. 7, pp. 2038–2048, Jul. 2007.
  17. Clare and R. D. King, “Knowledge Discovery in Multi-label Phenotype Data,” in Principles of Data Mining and Knowledge Discovery, A. De Raedt, L., Siebes, Ed. Springer Berlin Heidelberg, 2001, pp. 42–53.
  18. E. Schapire and Y. Singer, “BoosTexter: A Boosting-based System for Text Categorization,” Mach. Learn., vol. 39, pp. 135–168, 2000.
  19. N. Tarekegn, M. Giacobini, and K. Michalak, “A review of methods for imbalanced multi-label classification,” Pattern Recognit., vol. 118, p. 107965, 2021.
  20. Zhu, J. T. Kwok, and Z.-H. Zhou, “Multi-Label Learning with Global and Local Label Correlation,” IEEE Trans. Knowl. Data Eng., vol. 30, no. 6, pp. 1081–1094, Jun. 2018.
  21. Alvares-Cherman, J. Metz, and M. C. Monard, “Incorporating label dependency into the binary relevance framework for multi-label classification,” Expert Syst. Appl., vol. 39, no. 2, pp. 1647–1655, Feb. 2012.
  22. Takagi and M. Sugeno, “Fuzzy identification of systems and its applications to modeling and control,” IEEE Trans. Syst. Man. Cybern., vol. SMC-15, no. 1, pp. 116–132, Jan. 1985.
  23. Liu and X. Yao, “Ensemble learning via negative correlation,” Neural Networks, vol. 12, no. 10, pp. 1399–1404, Dec. 1999.
  24. Brown, J. L. Wyatt, and P. Tiňo, “Managing diversity in regression ensembles,” J. Mach. Learn. Res., vol. 6, pp. 1621–1650, 2005.
  25. Wang, X. Pan, G. Wei, J. Fei, and X. Lu, “A faster convergence and concise interpretability TSK fuzzy classifier deep-wide-based integrated learning,” Appl. Soft Comput., vol. 85, no. xxxx, p. 105825, Dec. 2019.
  26. Lughofer, “Evolving multi-label fuzzy classifier,” Inf. Sci. (Ny)., vol. 597, pp. 1–23, Jun. 2022.
  27. S. Choi, S. H. Cha, and C. C. Tappert, “A survey of binary similarity and distance measures,” WMSCI 2009 - 13th World Multi-Conference Syst. Cybern. Informatics, Jointly with 15th Int. Conf. Inf. Syst. Anal. Synth. ISAS 2009 - Proc., vol. 3, no. 1, pp. 80–85, 2009.
  28. C. Prati, “Fuzzy rule classifiers for multi-label classification,” in 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2015, vol. 2015-Novem, no. Cmcc, pp. 1–8.
  29. Gibaja and S. Ventura, “Multi-label learning: a review of the state of the art and ongoing research,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 4, no. 6, pp. 411–444, Nov. 2014.
  30. -L. Zhang and Z.-H. Zhou, “A Review on Multi-Label Learning Algorithms,” IEEE Trans. Knowl. Data Eng., vol. 26, no. 8, pp. 1819–1837, Aug. 2014.
  31. Tsoumakas, I. Katakis, and I. Vlahavas, “Random k-Labelsets for Multilabel Classification,” IEEE Trans. Knowl. Data Eng., vol. 23, no. 7, pp. 1079–1089, Jul. 2011.
  32. Sun and M. Kudo, “Optimization of classifier chains via conditional likelihood maximization,” Pattern Recognit., vol. 74, pp. 503–517, Feb. 2018.
دوره 17، شماره 2
تابستان 1402
صفحه 125-136

  • تاریخ دریافت 02 آبان 1402
  • تاریخ بازنگری 29 آبان 1402
  • تاریخ پذیرش 07 آذر 1402