Classical quantification of gastric emptying (GE) and orocaecal transit (OCT) based on half-life time T$ _{50} $, mean gastric emptying time (MGET), orocaecal transit time (OCTT) or mean caecum arrival time (MCAT) can lead to misconceptions when analyzing irregularly or noisy data. We show that this is the case for gastrointestinal transit of control and of diabetic rats. Addressing this limitation, we present an artificial neural network (ANN) as an alternative tool capable of discriminating between control and diabetic rats through GE and OCT analysis. Our data were obtained via biological experiments using the alternate current biosusceptometry (ACB) method. The GE results are quantified by T$ _{50} $ and MGET, while the OCT is quantified by OCTT and MCAT. Other than these classical metrics, we employ a supervised training to classify between control and diabetes groups, accessing sensitivity, specificity, $ f_1 $ score, and AUROC from the ANN. For GE, the ANN sensitivity is 88%, its specificity is 83%, and its $ f_1 $ score is 88%. For OCT, the ANN sensitivity is 100%, its specificity is 75%, and its $ f_1 $ score is 85%. The area under the receiver operator curve (AUROC) from both GE and OCT data is about 0.9 in both training and validation, while the AUCs for classical metrics are 0.8 or less. These results show that the supervised training and the binary classification of the ANN was successful. Classical metrics based on statistical moments and ROC curve analyses led to contradictions, but our ANN performs as a reliable tool to evaluate the complete profile of the curves, leading to a classification of similar curves that are barely distinguished using statistical moments or ROC curves. The reported ANN provides an alert that the use of classical metrics can lead to physiological misunderstandings in gastrointestinal transit processes. This ANN capability of discriminating diseases in GE and OCT processes can be further explored and tested in other applications.
Citation: Anibal Thiago Bezerra, Leonardo Antonio Pinto, Diego Samuel Rodrigues, Gabriela Nogueira Bittencourt, Paulo Fernando de Arruda Mancera, José Ricardo de Arruda Miranda. Classification of gastric emptying and orocaecal transit through artificial neural networks[J]. Mathematical Biosciences and Engineering, 2021, 18(6): 9511-9524. doi: 10.3934/mbe.2021467
Classical quantification of gastric emptying (GE) and orocaecal transit (OCT) based on half-life time T$ _{50} $, mean gastric emptying time (MGET), orocaecal transit time (OCTT) or mean caecum arrival time (MCAT) can lead to misconceptions when analyzing irregularly or noisy data. We show that this is the case for gastrointestinal transit of control and of diabetic rats. Addressing this limitation, we present an artificial neural network (ANN) as an alternative tool capable of discriminating between control and diabetic rats through GE and OCT analysis. Our data were obtained via biological experiments using the alternate current biosusceptometry (ACB) method. The GE results are quantified by T$ _{50} $ and MGET, while the OCT is quantified by OCTT and MCAT. Other than these classical metrics, we employ a supervised training to classify between control and diabetes groups, accessing sensitivity, specificity, $ f_1 $ score, and AUROC from the ANN. For GE, the ANN sensitivity is 88%, its specificity is 83%, and its $ f_1 $ score is 88%. For OCT, the ANN sensitivity is 100%, its specificity is 75%, and its $ f_1 $ score is 85%. The area under the receiver operator curve (AUROC) from both GE and OCT data is about 0.9 in both training and validation, while the AUCs for classical metrics are 0.8 or less. These results show that the supervised training and the binary classification of the ANN was successful. Classical metrics based on statistical moments and ROC curve analyses led to contradictions, but our ANN performs as a reliable tool to evaluate the complete profile of the curves, leading to a classification of similar curves that are barely distinguished using statistical moments or ROC curves. The reported ANN provides an alert that the use of classical metrics can lead to physiological misunderstandings in gastrointestinal transit processes. This ANN capability of discriminating diseases in GE and OCT processes can be further explored and tested in other applications.
| [1] |
J. D. Huizinga, W. J. E. P. Lammers, Gut peristalsis is governed by a multitude of cooperating mechanisms, Am. J. Physiol.-Gastrointest. Liver Physiol., 296 (2009), G1–G8. doi: 10.1152/ajpgi.90380.2008
|
| [2] |
A. D. Suchitra, Relative efficacy of some prokinetic drugs in morphine-induced gastrointestinal transit delay in mice, World J. Gastroenterol., 9 (2003), 779. doi: 10.3748/wjg.v9.i4.779
|
| [3] |
S. S. Davis, J. G. Hardy, M. J. Taylor, D. R. Whalley, C. G. Wilson, The effect of food on the gastrointestinal transit of pellets and an osmotic device (osmet), Int. J. Pharm., 21 (1984), 331–340. doi: 10.1016/0378-5173(84)90191-1
|
| [4] |
J. Yin, J. Chen, J. D. Z. Chen, Ameliorating effects and mechanisms of electroacupuncture on gastric dysrhythmia, delayed emptying, and impaired accommodation in diabetic rats, Am. J. Physiol.-Gastrointest. Liver Physiol., 298 (2010), G563–G570. doi: 10.1152/ajpgi.00252.2009
|
| [5] |
M. Horowitz, R. Fraser, Disordered gastric motor function in diabetes mellitus, Diabetologia, 37 (1994), 543–551. doi: 10.1007/BF00403371
|
| [6] |
M. Park, M. Camilleri, Gastroparesis: Clinical update. CME, Am. J. Gastroenterol., 101 (2006), 1129–1139. doi: 10.1111/j.1572-0241.2006.00640.x
|
| [7] |
S. Rana, A. Bhansali, S. Bhadada, S. Sharma, J. Kaur, K. Singh, Orocecal transit time and small intestinal bacterial overgrowth in type 2 diabetes patients from north india, Diabetes Technol. Ther., 13 (2011), 1115–1120. doi: 10.1089/dia.2011.0078
|
| [8] |
M. Camilleri, Diabetic gastroparesis, New Engl. J. Med., 356 (2007), 820–829. doi: 10.1056/NEJMcp062614
|
| [9] |
F. L. Iber, S. Parveen, M. Vandrunen, K. B. Sood, F. Reza, R. Serlovsky, et al., Relation of symptoms to impaired stomach, small bowel, and colon motility in long-standing diabetes, Dig. Dis. Sci., 38 (1993), 45–50. doi: 10.1007/BF01296772
|
| [10] | A. Keshavarzian, F. L. Iber and J. Vaeth, Gastric emptying in patients with insulin-requiring diabetes mellitus, Am. J. Gastroenterol., 82 (1987), 29–35. |
| [11] |
A. E. Bharucha, M. Camilleri, L. A. Forstrom, A. R. Zinsmeister, Relationship between clinical features and gastric emptying disturbances in diabetes mellitus, Clin. Endocrinol., 70 (2009), 415–420. doi: 10.1111/j.1365-2265.2008.03351.x
|
| [12] |
K. Hveem, K. L. Jones, B. E. Chatterton, M. Horowitz, Scintigraphic measurement of gastric emptying and ultrasonographic assessment of antral area: relation to appetite, Gut, 38 (1996), 816–821. doi: 10.1136/gut.38.6.816
|
| [13] |
K. D. Wutzke, W. E. Heine, C. Plath, P. Leitzmann, M. Radke, C. Mohr, et al., Evaluation of oro-coecal transit time: a comparison of the lactose-[13c, 15n]ureide 13co2- and the lactulose h2-breath test in humans, Eur. J. Clin. Nutr., 51 (1997), 11–19. doi: 10.1038/sj.ejcn.1600353
|
| [14] |
O. Baffa, R. B. Oliveira, J. R. A. Miranda, L. E. A. Troncon, Analysis and development of AC biosusceptometer for orocaecal transit time measurements, Med. Biol. Eng. Comput., 33 (1995), 353–357. doi: 10.1007/BF02510514
|
| [15] |
F. Podczeck, J. M. Newton, K. Yuen, The description of the gastrointestinal transit of pellets assessed by gamma scintigraphy using statistical moments, Pharm. Res., 12 (1995), 376–379. doi: 10.1023/A:1016200501563
|
| [16] | Y. Fukuoka, Artificial neural networks in medical diagnosis, in Computational Intelligence Processing in Medical Diagnosis, Physica-Verlag HD, (2002), 197–228. |
| [17] |
R. D. H. Devi, A. Bai, N. Nagarajan, A novel hybrid approach for diagnosing diabetes mellitus using farthest first and support vector machine algorithms, Obes. Med., 17 (2020), 100152. doi: 10.1016/j.obmed.2019.100152
|
| [18] |
N. A. Apreutesei, F. Tircoveanu, A. Cantemir, C. Bogdanici, C. Lisa, S. Curteanu, et al., Predictions of ocular changes caused by diabetes in glaucoma patients, Comput. Methods Programs Biomed., 154 (2018), 183–190. doi: 10.1016/j.cmpb.2017.11.013
|
| [19] |
N. Anton, E. N. Dragoi, F. Tarcoveanu, R. E. Ciuntu, C. Lisa, S. Curteanu, et al., Assessing changes in diabetic retinopathy caused by diabetes mellitus and glaucoma using support vector machines in combination with differential evolution algorithm, Appl. Sci., 11 (2021), 3944. doi: 10.3390/app11093944
|
| [20] |
P. B. M. Kumar, R. S. Perumal, R. K. Nadesh, K. Arivuselvan, Type 2: Diabetes mellitus prediction using deep neural networks classifier, Int. J. Cognit. Comput. Eng., 1 (2020), 55–61. doi: 10.1016/j.ijcce.2020.10.002
|
| [21] |
R. A. Karim, I. Vassányi, I. Kósa, After-meal blood glucose level prediction using an absorption model for neural network training, Comput. Biol. Med., 125 (2020), 103956. doi: 10.1016/j.compbiomed.2020.103956
|
| [22] | J. Chaki, S. T. Ganesh, S. Cidham, S. A. Theertan, Machine learning and artificial intelligence based diabetes mellitus detection and self-management: A systematic review, J. King Saud Uni.-Comput. Inf. Sci., 2020. |
| [23] |
F. Pace, M. Buscema, P. Dominici, M. Intraligi, F. Baldi, R. Cestari, et al., Artificial neural networks are able to recognize gastro-oesophageal reflux disease patients solely on the basis of clinical data, Eur. J. Gastroenterol. Hepatol., 17 (2005), 605–610. doi: 10.1097/00042737-200506000-00003
|
| [24] |
E. Lahner, Possible contribution of advanced statistical methods (artificial neural networks and linear discriminant analysis) in recognition of patients with suspected atrophic body gastritis, World J. Gastroenterol., 11 (2005), 5867. doi: 10.3748/wjg.v11.i37.5867
|
| [25] |
J. C. Peng, Z. H. Ran, J. Shen, Seasonal variation in onset and relapse of IBD and a model to predict the frequency of onset, relapse, and severity of IBD based on artificial neural network, Int. J. Colorectal Dis., 30 (2015), 1267–1273. doi: 10.1007/s00384-015-2250-6
|
| [26] | T. Takayama, S. Okamoto, T. Hisamatsu, M. Naganuma, K. Matsuoka, S. Mizuno, et al., Computer-aided prediction of long-term prognosis of patients with ulcerative colitis after cytoapheresis therapy, PLOS ONE, 10 (2015), e0131197. |
| [27] |
Y. J. Yang, C. S. Bang, Application of artificial intelligence in gastroenterology, World J. Gastroenterol., 25 (2019), 1666–1683. doi: 10.3748/wjg.v25.i14.1666
|
| [28] |
X. Y. Wang, J. D. Huizinga, J. Diamond, L. W. C. Liu, Loss of intramuscular and submuscular interstitial cells of cajal and associated enteric nerves is related to decreased gastric emptying in streptozotocin-induced diabetes, Neurogastroenterol. Motil., 21 (2009), 1095–e92. doi: 10.1111/j.1365-2982.2009.01336.x
|
| [29] | C. C. Quini, M. F. Américo, L. A. Corá, M. F. Calabresi, M. Alvarez, R. B. Oliveira, et al., Employment of a noninvasive magnetic method for evaluation of gastrointestinal transit in rats, J. Biol. Eng., 6 (2012). |
| [30] |
M. F. Américo, R. G. Marques, E. A. Zandoná, U. Andreis, M. Stelzer, L. A. Corá, et al., Validation of ACB in vitro and in vivo as a biomagnetic method for measuring stomach contraction, Neurogastroenterol. Motil., 22 (2010), 1340–e374. doi: 10.1111/j.1365-2982.2010.01582.x
|
| [31] |
M. F. F. Calabresi, C. C. Quini, J. F. Matos, G. M. Moretto, M. F. Americo, J. R. V. Graça, et al., Alternate current biosusceptometry for the assessment of gastric motility after proximal gastrectomy in rats: a feasibility study, Neurogastroenterol. Motil., 27 (2015), 1613–1620. doi: 10.1111/nmo.12660
|
| [32] |
J. R. Miranda, O. Baffa, R. B. de Oliveira, N. M. Matsuda, An AC biosusceptometer to study gastric emptying, Med. Phys., 19 (1992), 445–448. doi: 10.1118/1.596832
|
| [33] |
L. A. Corá, M. F. Américo, F. G. Romeiro, R. B. Oliveira, J. R. A. Miranda, Pharmaceutical applications of AC biosusceptometry, Eur. J. Pharm. Biopharm., 74 (2010), 67–77. doi: 10.1016/j.ejpb.2009.05.011
|
| [34] |
J. F. Matos, M. F. Americo, Y. K. Sinzato, G. T. Volpato, L. A. Corá, M. F. F. Calabresi, et al., Role of sex hormones in gastrointestinal motility in pregnant and non-pregnant rats, World J. Gastroenterol., 22 (2016), 5761. doi: 10.3748/wjg.v22.i25.5761
|
| [35] | M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, et al., TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Available from: https://www.tensorflow.org. |
| [36] | D. P. Kingma, J. Ba, Adam: A method for stochastic optimization, preprint, arXiv: 1412.6980. |
| [37] | M. Cogswell, F. Ahmed, R. Girshick, L. Zitnick, D. Batra, Reducing overfitting in deep networks by decorrelating representations, preprint, arXiv: 1511.06068. |
| [38] | N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15 (2014), 1929–1958. |
| [39] | W. Zaremba, I. Sutkever, O. Vinyals, Recurrent neural network regularization, preprint, arXiv: 1409.2329. |
| [40] | B. Jason, Better Deep Learning: Train Faster, Reduce Overfitting, and Make Better Predictions, Machine Learning Mastery, 2018. |
| [41] | C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995. |
| [42] | A. Tahmassebi, A. H. Gandomi, I. McCann, M. H. Schulte, A. E. Goudriaan, A. Meyer-Baese, Deep learning in medical imaging: fMRI big data analysis via convolutional neural networks, in Proceedings of the Practice and Experience on Advanced Research Computing, ACM, (2018), 1–4. |
| [43] | J. A. Swets, Roc analysis applied to the evaluation of medical imaging techniques., Invest. Radiol., 14 (1979), 109–121. |
| [44] | D. W. Hosmer Jr, S. Lemeshow, R. X. Sturdivant, Applied Logistic Regression, John Wiley & Sons, 2013. |
| [45] |
L. A. Szarka, M. Camilleri, Methods for measurement of gastric motility, Am. J. Physiol.-Gastrointest. Liver Physiol., 296 (2009), G461–G475. doi: 10.1152/ajpgi.90467.2008
|
| [46] | F. N. Christensen, S. S. Davis, J. G. Hardy, M. J. Taylor, D. R. Whalley, C. G. Wilson, The use of gamma scintigraphy to follow the gastrointestinal transit of pharmaceutical formulations, J. Pharm. Pharmacol., 37 (1985), 91–95. |
| [47] |
S. V. Rana, A. Malik, Hydrogen breath tests in gastrointestinal diseases, Indian J. Clin. Biochem., 29 (2014), 398–405. doi: 10.1007/s12291-014-0426-4
|
| [48] |
M. Camilleri, D. R. Linden, Measurement of gastrointestinal and colonic motor functions in humans and animals, Cell. Mol. Gastroenterol. Hepatol., 2 (2016), 412–428. doi: 10.1016/j.jcmgh.2016.04.003
|
| [49] |
F. A. A. Gondim, J. R. V. da Graça, G. R. de Oliveira, M. C. V. Rêgo, R. B. M. Gondim, F. H. Rola, Decreased gastric emptying and gastrointestinal and intestinal transits of liquid after complete spinal cord transection in awake rats, Braz. J. Med. Biol. Res., 31 (1998), 1605–1610. doi: 10.1590/S0100-879X1998001200015
|
| [50] |
M. Samsom, J. Vermeijden, A. Smout, E. van Doorn, J. Roelofs, P. van Dam, et al., Prevalence of delayed gastric emptying in diabetic patients and relationship to dyspeptic symptoms: A prospective study in unselected diabetic patients, Diabetes Care, 26 (2003), 3116–3122. doi: 10.2337/diacare.26.11.3116
|
| [51] | R. Keshari, S. Ghosh, S. Chhabr, M. Vatsa, R. Singh, Unravelling small sample size problems in the deep learning world, in 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), IEEE, (2020), 134–143. |
| [52] | Y. Bengio, Practical recommendations for gradient-based training of deep architectures, in Lecture Notes in Computer Science, Springer Berlin Heidelberg, (2012), 437–478. |
| [53] | M. Olson, A. Wyner, R. Berk, Modern neural networks generalize on small data sets, in Proceedings of the 32nd International Conference on Neural Information Processing Systems, (2018), 3623–3632. |
| [54] |
S. Lu, X. Shi, M. Li, J. Jiao, L. Feng, G. Wang, Semi-supervised random forest regression model based on co-training and grouping with information entropy for evaluation of depression symptoms severity, Math. Biosci. Eng., 18 (2021), 4586–4602. doi: 10.3934/mbe.2021233
|
| [55] |
A. Vitale, R. Villa, L. Ugga, V. Romeo, A. Stanzione, R. Cuocolo, Artificial intelligence applied to neuroimaging data in parkinsonian syndromes: Actuality and expectations, Math. Biosci. Eng., 18 (2021), 1753–1773. doi: 10.3934/mbe.2021091
|
| [56] |
A. Mujumdar, V. Vaidehi, Diabetes prediction using machine learning algorithms, Procedia Comput. Sci., 165 (2019), 292–299. doi: 10.1016/j.procs.2020.01.058
|
| [57] |
S. Ingrassia, I. Morlini, Neural network modeling for small datasets, Technometrics, 47 (2005), 297–311. doi: 10.1198/004017005000000058
|
Figures(4) / Tables(2)
Anibal Thiago Bezerra, Leonardo Antonio Pinto, Diego Samuel Rodrigues, Gabriela Nogueira Bittencourt, Paulo Fernando de Arruda Mancera, José Ricardo de Arruda Miranda. Classification of gastric emptying and orocaecal transit through artificial neural networks[J]. Mathematical Biosciences and Engineering, 2021, 18(6): 9511-9524. doi: 10.3934/mbe.2021467
DownLoad: