Abstract
The World Health Organization (WHO) reported in 2016 that close to 422 million adults live with diabetes. Diabetes is described as the United Kingdom's fastest-growing disease, which in recent decades has almost doubled in prevalence (Zghebi et al., Diabetes Obes Metab 19(11):1537–1545, https://doi.org/10.1111/dom.12964, 2019). The risk of DM is strongly advised, and the diabetes community should concentrate on identifying a pattern that leads to DM and its complications to avoid further complications. This study uses, logistic regression on PIMA Indian Diabetes Dataset, to identify the parameters and combination of parameters that lead to diabetic peripheral neuropathy (DPN) complications. Five different ML algorithms linear discriminant analysis (LDA), Naïve Bayes (NB), C5.0, SVM_RBF (Support Vector Machine_Radial Basis Function and gradient boosting machine (GBM) has been applied for the diagnosis of such disease for enhance the identified models using LR. The prediction performances are evaluated with four different performance metrics that is viz., accuracy, kappa, AUC-ROC, MCC measures. The critical combinations include (1) DM + Glucose + BP + BMI + Age, (2) DM + Glucose + BMI + Age, (3) DM + Glucose + BP + BMI + Age, (4) DM + Glucose + BP + BMI, (5) DM + Glucose + BMI. For each method in this study, LR is used in DPN prediction as the Accuracy and AUC are more close to reality. The results after calculations are: 0.79, 0.77, 0.787, 0.772 and 0.769 respectively, the AUC are 0.83 for all models and the MCC are around 0.5. The prediction was tested with other machine learning methods such as LDA, NB, C5.0, SVM_RBF and GBM have been close to 0.77 and the Kappa is 0.4. In the investigation, the patients should be tracked, and doctors should be notified to prescribe medications to ensure them from further complications, if the behavior indicates either of these combinations.
Similar content being viewed by others
Abbreviations
- DM:
-
Diabetes mellitus
- T2DM:
-
Type II diabetes mellitus
- DPN:
-
Diabetic peripheral neuropathy
- ML:
-
Machine learning
- MLA:
-
Machine learning algorithm
- LR:
-
Logistic regression
- LDA:
-
Linear discriminant analysis
- LDF:
-
Linear discriminant function
- QDA:
-
Quadratic discriminant analysis
- NB:
-
Naïve Bayes
- SVM_RBF:
-
Support Vector Machine_Radial Basis Function
- GBM:
-
Gradient boosting machine
- AUC_ROC:
-
Area under the receiver operating curve
- MCC:
-
Mathew’s correlation coefficient
- BP:
-
Blood pressure
- BMI:
-
Body Mass Index
- KDD:
-
Knowledge discovery in data bases
- RMSE:
-
Root mean square error
- TP:
-
True positive
- FP:
-
False positive
- TN:
-
True negative
- FN:
-
False negative
- UCI:
-
University of California Irvine
- VIF:
-
Variance inflation factor
- MLE:
-
Maximum likelihood estimation
- ANOVA:
-
Analysis of variance
- PCA:
-
Principal component analysis
- ANN:
-
Artificial neural network
- DT:
-
Decision tree
- IBM-SPSS:
-
International Business Machines Corporation-Statistical Package for the Social Sciences
- HGS:
-
Handgrip strength
- MNSI_Q; MNSI-PE:
-
Michigan Neuropathy Screening Instrument Questionnaire (MNSI-Q) and Physical Examination (MNSI-PE)
- CNN; LSTM:
-
Convolutional long short term memory
- RR:
-
R peak to R peak
- ECG:
-
Electrocardiogram
References
Abdar M, Kalhori SR, Sutikno T, Subroto IM, Arji G (2015) Comparing performance of data mining algorithms in prediction heart diseases. Int J Electr Comput Eng. https://doi.org/10.11591/ijece.v5i6.pp1569-1576
Acharya UR et al (2016) Automated diagnosis of diabetes using entropies and diabetic index. J Mech Med Biol 16(01):1640008
Adam M, Ng EYK, Oh SL, Heng ML, Hagiwara Y, Tan JH, Tong JWK, Acharya UR (2018) Automated characterization of diabetic foot using nonlinear features extracted from thermograms. Infrared Phys Technol 89:325–337
Akter T, Akhter QS, Polly ZA, Debsarma S (2020) Risk factors for peripheral neuropathy in patients with diabetes mellitus. IMC J Med Sci 13(2):40–44. https://doi.org/10.3329/imcjms.v13i2.45285
Amin N, Doupis J (2016) Diabetic foot disease: from the evaluation of the ‘foot at risk’ to the novel diabetic ulcer treatment modalities. World J Diabetes 7(7):153. https://doi.org/10.4239/wjd.v7.i7.153
Atul DV (2016) Validity of P-peak to R-peak interval compared to classical PR-interval to assess dynamic beat-to-beat AV conduction variability on surface electrocardiogram. Certain distance degree based Topol. indices Zeolite LTAFram., December 2016, pp 11–14
Balcıoğlu AS (2015) Diabetes and cardiac autonomic neuropathy: Clinical manifestations, cardiovascular consequences, diagnosis and treatment. World J Diabetes 6(1):80. https://doi.org/10.4239/wjd.v6.i1.80
Battineni G, Chintalapudi N, Amenta F (2019) Machine learning in medicine: performance calculation of dementia prediction by support vector machines (SVM). Inform Med Unlocked 16:100200
Bunner AE, Wells CL, Gonzales J, Agarwal U, Bayat E, Barnard ND (2015) A dietary intervention for chronic diabetic neuropathy pain: a randomized controlled pilot study. Nutr Diabetes 5:e158. https://doi.org/10.1038/nutd.2015.8.www.nature.com/nutd
Chicco D, Jurman G (2020) The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom 21(1):1–13. https://doi.org/10.1186/s12864-019-6413-7
Cho G, Yim J, Choi Y, Ko J, Lee SH (2019) Review of machine learning algorithms for diagnosing mental illness. Psychiatry Investig 16(4):262–269. https://doi.org/10.30773/pi.2018.12.21.2. www.psychiatryinvestigation.org(ISSN 1976–3026)
Cruz-Vega I, Hernandez-Contreras D, Peregrina-Barreto H, Rangel-Magdaleno JJ, Ramirez-Cortes JM (2020) Deep learning classification for diabetic foot thermograms. Sensors (Switzerland) 20(6):1–22. https://doi.org/10.3390/s20061762
Cui X et al (2020) On the variability of heart rate variability—evidence from prospective study of healthy young college students. Entropy 22(11):1–26. https://doi.org/10.3390/e22111302
Dagliati A, Marini S, Sacchi L, Cogni G, Teliti M, Tibollo V, De Cata P, Chiovato L, Bellazzi R (2018) Machine learning methods to predict diabetes complications. J Diabetes Sci Technol 12(2):295–302
de Vlaming R, Groenen PJF (2015) The current and future use of ridge regression for prediction in quantitative genetics. Biomed Res Int 2015:18. https://doi.org/10.1155/2015/143712(ArticleID143712)
Dhahri H, Al Maghayreh E, Mahmood A, Elkilani W, Faisal Nagi M (2019) Automated breast cancer diagnosis based on machine learning algorithms. J Healthc Eng 2019:11. https://doi.org/10.1155/2019/4253641(Article ID 4253641)
Duzan H, Shariff NSBM (2015a) Ridge regression for solving the multicollinearity problem: review of methods and models. J Appl Sci 15(3):392–404. https://doi.org/10.3923/jas.2015.392.404
Duzan H, Shariff NSBM (2015) Ridge regression for solving the multicollinearity problem: review of methods and models. J Appl Sci 15(3):392–404 (ISSN 1812-5654)
Eleftheriadou I, Dimitrakopoulou N, Kafasi N, Tentolouris A, Dimitrakopoulou A, Anastasiou IA, Entolouris N (2019) Endothelial progenitor cells and peripheral neuropathy in subjects with type 2 diabetes mellitus. J Diabetes Complicat. https://doi.org/10.1016/j.jdiacomp.2019.107517
Holobar A, Farina D (2014) Blind source identification from the multichannel surface electromyogram. Physiol Meas 35(7):R143–R165. https://doi.org/10.1088/0967-3334/35/7/r143
Jaiswal M, Divers J, Dabelea D, Isom S, Bell RA (2018) Prevalence of and risk factors for diabetic peripheral neuropathy in youth with Type 1 and Type 2 Diabetes: SEARCH for diabetes in youth study. Diabetes Care 40:1226–1232
James WLJ, Mayberry R, Yoo W (2014) A study of effects of multicollinearity in the multivariable analysis. Int J Appl Sci Technol 4(5):9–19
Jelinek HF, Cornforth DJ, Kelarev AV (2016) Machine learning methods for automated detection of severe diabetic neuropathy. J Diabetic Complications Med 1:108. https://doi.org/10.4172/jdcm.1000108
Kaur H, Kumari V (2018) Predictive modelling and analytics for diabetes using a machine learning approach. Appl Comput Inf. https://doi.org/10.1016/j.aci.2018.12.004
Kaur H, Kumari V (2019) Predictive modelling and analytics for diabetes using a machine learning approach. Appl Comput Inform. https://doi.org/10.1016/j.aci.2018.12.004
Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I (2017) Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J 15:104–116
Kazemi M, Moghimbeigi A, Kiani J, Mahjub H, Faradmal J (2016) Diabetic peripheral neuropathy class prediction by multicategory support vector machine model: a cross-sectional study. Epidemiol Health 38:e2016011. https://doi.org/10.4178/epih/e2016011(eCollection2016)
Khawaja NM, Abu-Shennar J (2018) The prevalence and risk factors of peripheral neuropathy among patients with type 2 diabetes mellitus; the case of Jordan. Diabetol Metab Syndr. https://doi.org/10.1186/s13098-018-0309-6
Kheradmand F, Khamseh AA, Khoraskani MM (2017) Application and comparison of neural network, C5.0, and classification and regression trees (CART) algorithms in the credit risk evaluation problem (case study: a standard German credit dataset). Int J Knowl Eng Data Min 4(1):1. https://doi.org/10.1504/ijkedm.2017.10006181
Kim ES, Lee SW, Mo EY, Moon SD, Han JH (2015) Inverse association between serum total billirubin levels and diabetic peripheral neuropathy in patients with type 2 diabetes. Endocrine 50(2):405–412
Koo YS, Jung KY, Lee SH, Cho CS, Yang KS, Jang JH, Kim BJ (2013) Multichannel surface electrodes increase the sensitivity of diagnosis of neuropathy in diabetic patients. J Electromyogr Kinesiol 23:1057–1064
Kumar A, Ranjan A, Chand G, Kumar D, Singh SK, Kumar V (2015) The foot care process of diabetic patients (with and without foot ulcer) attending a Tertiary Care Hospital in India. J Stem Cell Res Therapy. https://doi.org/10.4172/2157-7633.1000280
Lagani V, Chiarugi F, Thomson S, Fursse J, Lakasing E, Jones RW, Tsamardinos I (2015) Development and validation of risk assessment models for diabetes-related complications based on the DCCT/EDIC data. J Diabetes Complicat 29:479–487
Lai H, Huang H, Keshavjee K, Guergachi A, Gao X (2019) Predictive models for diabetes mellitus using machine learning techniques. BMC Endocr Disord 19(1):1–9. https://doi.org/10.1186/s12902-019-0436-6
Le Cessie S, Houwelingen JCV (1992) Ridge estimators in logistic regression. J R Stat Soc Ser C (Appl Stat) 41:191–201
Li B-Q, Zheng L-L, Feng K-Y, Hu L-L, Huang G-H, Chen L (2015) Prediction of linear B-cell epitopes with mRMR feature selection and analysis. Curr Bioinform 11(1):22–31
Lin CL, Fan CL (2019) Evaluation of CART, CHAID, and QUEST algorithms: a case study of construction defects in Taiwan. J Asian Archit Build Eng 18(6):539–553. https://doi.org/10.1080/13467581.2019.1696203
Liu S, Gao Y, Shen Y, Zhang M, Li J, Sun P (2019) Application of three statistical models for predicting the risk of diabetes. BMC Endocr Disord 19(1):1–10. https://doi.org/10.1186/s12902-019-0456-2
Malanda UL, Bot SD, Nijpels G (2013) Self-monitoring of blood glucose in noninsulin-using type 2 diabetic patients: It is time to face the evidence. Diabetes Care 36(1):176–178. https://doi.org/10.2337/dc12-0831
Maniruzzaman M, Rahman MJ, Al-MehediHasan M, Suri HS, Abedin MM, El-Baz A, Suri JS (2018) Accurate diabetes risk stratification using machine learning: role of missing value and outliers. J Med Syst 42:92. https://doi.org/10.1007/s10916-018-0940-7
Mao F, Zhu X, Liu S, Qiao X, Zheng H, Lu B (2019) Age as an independent risk factor for diabetic peripheral neuropathy in Chinese patients with Type 2 diabetes. Aging Dis 10(3):592–600
Mayooran T (2018) A gradient-based optimization algorithm for ridge regression by using R. Int J Res Sci Innov 5(4):38–44 (ISSN 2321–2705)
Metz CE (2008) ROC analysis in medical imaging: a tutorial review of the literature. Radiol Phys Technol 1(1):2–12. https://doi.org/10.1007/s12194-007-0002-1
Mirzajani SS, Salimi S (2018) Prediction and diagnosis of diabetes by using data mining techniques. Avicenna J Med Biochem 6(1):3–7. https://doi.org/10.15171/ajmb.2018.02
Nascimento OJMD, Castelo C, Pupe B, Boiteux E, Cavalcanti U (2016) Diabetic neuropathy neuropatia diabética. Rev Dor São Paulo 17(Suppl 1):46–51. https://doi.org/10.5935/1806-0013.20160047
Nirmaladevi K, Shanthi S, Agila T, Dharani RT, Dhivyapriya P (2020) Analysis and prediction of diabetes using machine learning. Test Eng Manag 83(9):14533–14538
Nisar MU et al (2015) Association of diabetic neuropathy with duration of Type 2 diabetes and glycemic control. Cureus. https://doi.org/10.7759/cureus.302
Oh TJ, Kang S, Lee J-E, Moon JH, Choi SH, Lim S, Jang HC (2019) Association between deterioration in muscle strength and peripheral neuropathy in people with diabetes. J Diabetes Complicat. https://doi.org/10.1016/j.jdiacomp.2019.04.00
Padma S, Murugan R, Senthilkumaran M (2018) Risk factors deciding the prevention and healing of diabetic foot ulcer: a prospective study in Chennai Medical College Hospital and Research Center Irungalur, Trichy, Tamil Nadu, India; a rural based tertiary medical care centre. Int Surg J 5(5):1770–1775. http://www.ijsurgery.com
Pop-Busui R et al (2017) Diabetic neuropathy: a position statement by the American diabetes association. Diabetes Care 40(1):136–154. https://doi.org/10.2337/dc16-2042
Río X, Larrinaga-Undabarrena A, Coca A, Guerra-Balic M (2020) Reference values for handgrip strength in the Basque country elderly population. Biology (Basel) 9(12):1–12. https://doi.org/10.3390/biology9120414
Salh SM (2014) Using ridge regression model to solving multicollinearity problem. Int J Sci Eng Res 5(10):992 (ISSN 2229-5518)
Senaviratna NA and Cooray TM (2019) Diagnosing multicollinearity of logistic regression model. Asian J Probab Stat 5(2):1–9 (ISSN: 2582-0230; Article no. AJPAS.51693)
Su JB, Zhao LH, Zhang XL, Cai HL, Huang HY, Xu F, Chen T, Wang XQ (2018) HbA1c variability and diabetic peripheral neuropathy in type 2 diabetic patients. Cardiovasc Diabetol 17:47. https://doi.org/10.1186/s12933-018-0693-0
Sudharsan B, Peeples M, Shomali M (2014) Hypoglycemia prediction using machine learning models for patients with Type 2 diabetes. J Diabetes Sci Technol 9(1):86–90
Sudharsan B, Peeples M, Shomali M (2015) Hypoglycemia prediction using machine learning models for patients with Type 2 diabetes. J Diabetes Sci Technol. https://doi.org/10.1177/1932296814554260
Suri HS, El-Baz AS, Suri JS (2017) “Comparative approaches for classification of diabetes mellitus data: machine learning paradigm. Comput Methods Prog Biomed 152:23–34
Swapna G, Vinayakumar R, Soman KP (2018) Diabetes detection using deep learning algorithms, The Korean Institute of Communications and Information Sciences (KICS). ICT Express 4:243–246
Tahrani AA, Altaf QA, Piya MK, Barnett AH (2017) Peripheral and autonomic neuropathy in South Asians and White Caucasians with Type 2 diabetes mellitus: possible explanations for epidemiological differences. J Diabetes Res. https://doi.org/10.1155/2017/1273789
Teich MC (2012) Heart rate variability: measures and models heart rate variability: measures and models Malvin C. Teich, Steven B. Lowen, Bradley M. Jost, and Karin Vibe-Rheymer Department of Electrical and Computer Engineering, Boston University, 8 Saint Mary’s Street, Boston, MA 02215 and Conor Heneghan Department of Electronic and Electrical Engineering, University College Dublin, Bel eld, Dublin 4, Ireland, no. November 2012, 2000
Van Eetvelde BLM, Lapauw B, Proot P, Vanden Wyngaert K, Celie B, Cambier D, Calders P (2020) The impact of sensory and/or sensorimotor neuropathy on lower limb muscle endurance, explosive and maximal muscle strength in patients with type 2 diabetes mellitus. J Diabetes Complicat. https://doi.org/10.1016/j.jdiacomp.2020.107562
Verma AK, Pal S, Kumar S (2019) Comparison of skin disease prediction by feature selection using ensemble data mining techniques. Inf Med Unlocked. https://doi.org/10.1016/j.imu.2019.100202
Wallert J, Tomasoni M, Madison G, Held C (2017) Predicting two-year survival versus nonsurvival after first myocardial infarction using machine learning and Swedish national register data. BMC Med Inform Decis Mak 17:99. https://doi.org/10.1186/s12911-017-0500-y
Williams BM et al (2020) An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study. Diabetologia 63(2):419–430. https://doi.org/10.1007/s00125-019-05023-4
Wu H, Yang S, He J (2018) Type 2 diabetes mellitus prediction model based on data mining. Inf Med Unlocked 10:100–107
Xu L, Lin X, Guan M, Liu Y (2018) Correlation between different stages of diabetic nephropathy and neuropathy in patients with T2DM: a cross-sectional controlled study. Diabetes Ther 9(6):2335–2346. https://doi.org/10.1007/s13300-018-0519-9
Xu Q, Wang L, Sansgiry SS (2020) A systematic literature review of predicting diabetic retinopathy, nephropathy and neuropathy in patients with type 1 diabetes using machine learning. J Med Artif Intell 3(MI):6. https://doi.org/10.21037/jmai.2019.10.04
Yang J, Yan PJ, Wan Q, Li H (2017) Association between hemoglobin levels and diabetic peripheral neuropathy in patients with type 2 diabetes: a cross-sectional study using electronic health records. J Diabetes Res. https://doi.org/10.1155/2017/2835981
Ybarra J, Jurado J, Garcia M, Zabaleta E, Mir-Coll T, Zabalegui A (2016) Cardiovascular disease predicts diabetic peripheral polyneuropathy in subjects with type 2 diabetes: a 10-year prospective study. Eur J Cardiovasc Nurs 15(4):248–325
Zghebi SS, Steinke DT, Carr MJ, Rutter MK, Emsley RA, Ashcroft DM (2017) Examining trends in type 2 diabetes incidence, prevalence and mortality in the UK between 2004 and 2014. Diabetes Obes Metab 19(11):1537–1545. https://doi.org/10.1111/dom.12964
Zhang YY, Zhou XB, Wang QZ, Zhu XY (2017) Quality of reporting of multivariable logistic regression models in Chinese clinical medical journals. Medicine 96(21):e6972, https://doi.org/10.1097/MD.0000000000006972. www.md-journal.com
Zhang Z, Zhao Y, Canes A, Steinberg D, Lyashevska O (2019) Predictive analytics with gradient boosting in clinical medicine. Ann Transl Med 7(7):152
Zhou YH, Gallins P (2019) A review and tutorial of machine learning methods for microbiome host trait prediction. Front Genet. https://doi.org/10.3389/fgene.2019.00579.www.frontiersin.org
Zou Q, Qu K, Luo Y, Yin D, Ju Y, Tang H (2018) Predicting diabetes mellitus with machine learning techniques. Front Genet 9:515. www.frontiersin.org
Zweig M, Campbell G (1993) Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 394:561–77
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Usharani, R., Shanthini, A. Neuropathic complications: Type II diabetes mellitus and other risky parameters using machine learning algorithms. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-021-02972-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12652-021-02972-w