Skip to main content

Advertisement

Log in

A novel PCA-FA-ANN based hybrid model for prediction of fluoride

  • Original Paper
  • Published:
Stochastic Environmental Research and Risk Assessment Aims and scope Submit manuscript

Abstract

Fluoride plays an essential role in terms of the health of human beings. Persistent exposure to fluoride, which is present in drinking water mainly, may result in dental, skeletal, and non-skeletal fluorosis. However, drinking water, being consumed presently, is not sufficient to indicate the degree of exposure to fluoride. The existing literature indicates that nails can be used as indicative (biomarkers) of not only to exposure of fluoride but also the degree of the same. However, because of differential metabolism rate depending on a number of factors like age, gender, nutritional status, water characteristics, etc., exposure to fluoride is not easily detectable in human beings by just testing the fluoride content in nails. Moreover, due to sensitive chemical analysis and lack of facilities, it is difficult to identify the exact concentration of fluoride in nails. The objective of this study is to identify the significant parameters that affect the fluoride content in nail samples. Apart from laboratories test, the application of different artificial intelligence (AI) methods are used for the prediction of fluoride in nails, which will help to identify the degree of fluoride exposure to children, females, and males. The field study covers a collection of 2401 nail samples from eight districts of Rajasthan, India. The samples were taken of different age groups and genders. 1024 water samples were also collected from the same households from where the nails samples were collected. These water and nail samples were tested in laboratories at Birla Institute of Technology and Science, Pilani, India. This data set was used to train, test, and validate the results using AI techniques. The proposed hybrid model (HM) combines Principal Component Analysis (PCA), Firefly Algorithm (FA), and Artificial Neural Network (ANN) to predict fluoride concentration in nails. The model performance was assessed by using different errors and coefficient of relationship. A comparative analysis of the proposed HM was done against ANN and PCA–ANN models. Sensitivity analysis was performed to study the importance of input parameters on the output. Results show that the PCA–FA–ANN–AFpE model having four input parameters (age, fluoride, pH, and electrical conductivity), displayed the best performance with high R2 values of 0.97. The study generates a novel methodology for predicting fluoride concentration in nails, which can be used for the prediction of hotspots in terms of continuous exposure to fluoride.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29
Fig. 30
Fig. 31
Fig. 32
Fig. 33
Fig. 34

Similar content being viewed by others

Data availability

Some or all data, models, or code generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions.

References

  • Akpata ES, Behbehani J, Akbar J, Thalib L, Mojiminiyi O (2014) Fluoride intake from fluids and urinary fluoride excretion by young children in Kuwait: a non-fluoridated community. Commun Dent Oral Epidemiol 42(3):224–233

    Article  Google Scholar 

  • Álvarez-Ayuso E, Giménez A, Ballesteros JC (2011) Fluoride accumulation by plants grown in acid soils amended with flue gas desulphurisation gypsum. J Hazard Mater 192(3):1659–1666

    Article  CAS  Google Scholar 

  • Amaral JG, Freire IR, Valle-Neto EF, Cunha RF, Martinhon CC, Delbem AC (2014) Longitudinal evaluation of fluoride levels in nails of 18–30-month-old children that were using toothpastes with 500 and 1100 μg F/g. Commun Dent Oral Epidemiol 42(5):412–419

    Article  Google Scholar 

  • Ando M, Tadano M, Asanuma S, Tamura K, Matsushima S, Watanabe T, Cao S (1998) Health effects of indoor fluoride pollution from coal burning in China. Environ Health Perspect 106(5):239–244

    Article  CAS  Google Scholar 

  • Antonijevic E, Mandinic Z, Curcic M, Djukic-Cosic D, Milicevic N, Ivanovic M, Antonijevic B (2016) “Borderline” fluorotic region in Serbia: correlations among fluoride in drinking water, biomarkers of exposure and dental fluorosis in schoolchildren. Environ Geochem Health 38(3):885–896

    Article  CAS  Google Scholar 

  • BIS I (2012) 10500 Indian standard drinking water–specification, second revision. Bureau of Indian Standards, New Delhi

    Google Scholar 

  • Beir VII (2005) Health risks from exposure to low levels of ionizing radiation. The National Academies report in brief

  • Bell AJ, Sejnowski TJ (1997) The “independent components” of natural scenes are edge filters. Vision Res 37(23):3327–3338

    Article  CAS  Google Scholar 

  • Beltran, L. (2006). Nonparametric multivariate statistical process control using principal component analysis and simplicial depth.

  • Buzalaf MAR, Massaro CS, Rodrigues MHC, Fukushima R, Pessan JP, Whitford GM, Sampaio FC (2012) Validation of fingernail fluoride concentration as a predictor of risk for dental fluorosis. Caries Res 46(4):394–400

    Article  CAS  Google Scholar 

  • Buzalaf MAR, Pessan JP, Alves KMRP (2006) Influence of growth rate and length on fluoride detection in human nails. Caries Res 40(3):231–238

    Article  CAS  Google Scholar 

  • Buzalaf MAR, Vilhena FV, Iano FG, Grizzo L, Pessan JP, Sampaio FC, Oliveira RC (2009) The effect of different fluoride concentrations and pH of dentifrices on plaque and nail fluoride levels in young children. Caries Res 43(2):142–146

    Article  CAS  Google Scholar 

  • Carvalho RBD, Medeiros UVD, Santos KTD, Pacheco Filho AC (2011) Influence of different concentrations of fluoride in the water on epidemiologic indicators of oral health/disease. Ciencia & saude coletiva 16(8):3509–3518

    Article  Google Scholar 

  • Celinski VR, Ditter M, Kraus F, Fujara F, Schmedt auf der Günne J (2016) Trace determination and pressure estimation of fluorine F2 caused by irradiation damage in minerals and synthetic fluorides. Chem Eur J 22(51):18388–18393

    Article  CAS  Google Scholar 

  • Cerklewski FL (1997) Fluoride bioavailability—nutritional and clinical aspects. Nutr Res 17(5):907–929

    Article  CAS  Google Scholar 

  • Clarkson JJ, McLoughlin J (2000) Role of fluoride in oral health promotion. Int Dent J 50(3):119–128

    Article  CAS  Google Scholar 

  • Cotruvo JA (2017) WHO guidelines for drinking water quality: first addendum to the fourth edition. J Am Water Works Assoc 109(7):44–51

  • De Almeida BS, da Silva Cardoso VE, Buzalaf MAR (2007) Fluoride ingestion from toothpaste and diet in 1-to 3-year-old Brazilian children. Commun Dent Oral Epidemiol 35(1):53–63

    Article  Google Scholar 

  • Edition F (2011) Guidelines for drinking-water quality. WHO Chron 38(4):104–108

    Google Scholar 

  • El-Shafie A, Noureldin AE, Taha MR, Basri H (2008) Neural network model for Nile river inflow forecasting based on correlation analysis of historical inflow data. J Appl Sci 8(24):4487–4499

    Article  Google Scholar 

  • El-Shafie A, Mukhlisin M, Najah AA, Taha MR (2011) Performance of artificial neural network and regression techniques for rainfall-runoff prediction. Int J Phys Sci 6(8):1997–2003

    Google Scholar 

  • Elekdag-Turk S, Almuzian M, Turk T, Buzalaf MAR, Alnuaimi A, Dalci O, Darendeliler MA (2019) Big toenail and hair samples as biomarkers for fluoride exposure–a pilot study. BMC Oral Health 19(1):82

    Article  Google Scholar 

  • Fukushima R, Rigolizzo DS, Maia LP, Sampaio FC, Lauris JRP, Buzalaf MAR (2009) Environmental and individual factors associated with nail fluoride concentration. Caries Res 43(2):147–154

    Article  CAS  Google Scholar 

  • Gandomi AH, Yang XS (2011) Benchmark problems in structural optimization. In: Slawomir K, Xin-She Y (eds) Computational optimization, methods and algorithms. Springer, Berlin, pp 259–281

    Chapter  Google Scholar 

  • Hayati M, Yousefi T, Ashjaee M, Hamidi A, Shirvany Y (2007) Application of artificial neural networks for prediction of natural convection heat transfer from a confined horizontal elliptic tube. In: Proceedings of World Academy of Science, Engineering and Technology, vol. 22, pp 269–274

  • Haykin S (1994) Neural networks: a comprehensive foundation. Prentice Hall PTR.

  • Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366

    Article  Google Scholar 

  • Hossain MA, Rahman MM, Murrill M, Das B, Roy B, Dey S, Chakraborti D (2013) Water consumption patterns and factors contributing to water consumption in arsenic affected population of rural West Bengal, India. Sci Total Environ 463:1217–1224

    Article  CAS  Google Scholar 

  • Khairnar MR, Dodamani AS, Jadhav HC, Naik RG, Deshmukh MA (2015) Mitigation of fluorosis-a review. JCDR 9(6):ZE05

    Google Scholar 

  • Koblar A, Tavčar G, Ponikvar-Svet M (2011) Effects of airborne fluoride on soil and vegetation. J Fluorine Chem 132(10):755–759

    Article  CAS  Google Scholar 

  • Levy FM, Bastos JRDM, Buzalaf MAR (2004) Nails as biomarkers of fluoride in children of fluoridated communities. J Dent Child 71(2):121–125

    Google Scholar 

  • Lima-Arsati YBO, Martins CC, Rocha LA, Cury JA (2010) Fingernail may not be a reliable biomarker of fluoride body burden from dentifrice. Braz Dent J 21(2):91–97

    Article  Google Scholar 

  • Linhares DPS, Garcia PV, Amaral L, Ferreira T, Cury JA, Vieira W, dos Santos Rodrigues A (2016) Sensitivity of two biomarkers for biomonitoring exposure to fluoride in children and women: A study in a volcanic area. Chemosphere 155:614–620

    Article  CAS  Google Scholar 

  • Liong SY, Sivapragasam C (2002) Flood stage forecasting with support vector machines 1. JAWRA 38(1):173–186

    Google Scholar 

  • Liong SY, Lim WH, Paudyal GN (2000) River stage forecasting in Bangladesh: neural network approach. J Comput Civ Eng 14(1):1–8

    Article  Google Scholar 

  • Liong SY, Van Nguyen VT, Gautam TR, Wee L (2001) Alternative well calibrated rainfall-runoff model: genetic programming scheme. In: Urban drainage modeling, pp 777–787

  • Lu WZ, Wang WJ, Wang XK, Xu ZB, Leung AY (2003) Using improved neural network model to analyze RSP, NO x and NO 2 levels in urban air in Mong Kok Hong Kong. Environ Monit Assess 87(3):235–254

    Article  CAS  Google Scholar 

  • MacKay DJ (1992) Bayesian interpolation. Neural Comput 4(3):415–447

    Article  Google Scholar 

  • Makarynskyy O (2004) Improving wave predictions with artificial neural networks. Ocean Eng 31(5–6):709–724

    Article  Google Scholar 

  • Makarynska D, Makarynskyy O (2008) Predicting sea-level variations at the Cocos (Keeling) Islands with artificial neural networks. Comput Geosci 34(12):1910–1917

    Article  Google Scholar 

  • Masters T (1995) Advanced algorithms for neural networks: a C++ sourcebook. Wiley

    Google Scholar 

  • MathWorks: Neural Network Toolbox Release (2019b) MATLAB & Simulink – MathWorks India, Accessed 23 June 2020

  • McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133

    Article  Google Scholar 

  • Moazenzadeh R, Mohammadi B, Shamshirband S, Chau KW (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Eng Appl Comput Fluid Mech 12(1):584–597

    Google Scholar 

  • Moseley R, Waddington RJ, Sloan AJ, Smith AJ, Hall RC, Embery G (2003) The influence of fluoride exposure on dentin mineralization using an in vitro organ culture model. Calcif Tissue Int 73(5):470–475

    Article  CAS  Google Scholar 

  • Muttil N, Chau KW (2006) Neural network and genetic programming for modelling coastal algal blooms. Int J Environ Pollut 28:223

    Article  CAS  Google Scholar 

  • Najah A, Elshafie A, Karim OA, Jaffar O (2009) Prediction of Johor River water quality parameters using artificial neural networks. Eur J Sci Res 28(3):422–435

    Google Scholar 

  • O’Donnel TA (1973) The chemistry of fluorine. Elsevier

    Google Scholar 

  • Paliwal M, Kumar UA (2009) Neural networks and statistical techniques: a review of applications. Expert Syst Appl 36(1):2–17

    Article  Google Scholar 

  • Pao HT (2006) Comparing linear and nonlinear forecasts for Taiwan’s electricity consumption. Energy 31(12):2129–2141

    Article  Google Scholar 

  • Pessan JP, Buzalaf MRA (2011) Historical and recent biological markers of exposure to fluoride. Fluoride Oral Environ 22:52–65

    Article  Google Scholar 

  • Pessan JP, Pin MLG, Martinhon CCR, Silva SMBD, Granjeiro JM, Buzalaf MAR (2005) Analysis of fingernails and urine as biomarkers of fluoride exposure from dentifrice and varnish in 4-to 7-year-old children. Caries Res 39(5):363–370

    Article  CAS  Google Scholar 

  • Reddy SS, Momoh JA (2014) Short term electrical load forecasting using back propagation neural networks. In: 2014 North American Power Symposium (NAPS). IEEE, pp 1–6

  • Schmedt Günne J, Mangstl M, Kraus F (2012) Occurrence of difluorine F2 in nature—in situ proof and Quantification by NMR spectroscopy. Angew Chem Int Ed 51(31):7847–7849

    Article  CAS  Google Scholar 

  • Shinde RL, Khadse KG (2009) Multivariate process capability using principal component analysis. Qual Reliab Eng Int 25(1):69–77

    Article  Google Scholar 

  • Sousa ETD, Alves VF, Maia FBM, Nobre-dos-Santos M, Forte FDS, Sampaio FC (2018) Influence of fluoridated groundwater and 1,100 ppm fluoride dentifrice on biomarkers of exposure to fluoride. Braz Dent J 29(5):475–482

    Article  Google Scholar 

  • Standard I (2006) Methods of sampling and test (physical and chemical) for water and wastewater. Environ Prot Sect Comm CHD 12:10

    Google Scholar 

  • Stojanovic B, Neskovic A (2012) Impact of PCA based fingerprint compression on matching performance. In: 2012 20th telecommunications forum (TELFOR). IEEE, pp 693–696.

  • Turian J, Bergstra J, Bengio Y (2009) Quadratic features and deep architectures for chunking. In: Proceedings of human language technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pp 245–248.

  • Wenzel WW, Blum WEH (1992) Fluoride speciation and mobility in fluoride concentration soil and minerals. Soil Sci 153:357–364

    Article  CAS  Google Scholar 

  • Whitford GM (2005) Monitoring fluoride exposure with fingernail clippings. Schweiz Monatsschr Zahnmed 115(8):685

    Google Scholar 

  • Whitford GM, Sampaio FC, Arneberg P, Von der Fehr FR (1999) Fingernail fluoride: a method for monitoring fluoride exposure. Caries Res 33(6):462–467

    Article  CAS  Google Scholar 

  • World Health Organization (1996) Trace elements in human nutrition and health. World Health Organization

    Google Scholar 

  • World Health Organization (2006) The world health report 2006: working together for health. World Health Organization

    Book  Google Scholar 

  • Yang XS (2010a) Firefly algorithm, stochastic test functions and design optimisation. Int J Bio-inspired Comput 2(2):78–84

    Article  Google Scholar 

  • Yang XS (2010b) Nature-inspired metaheuristic algorithms. Luniver Press

    Google Scholar 

  • Yang XS (2011a) Metaheuristic optimization. Scholarpedia 6(8):11472

    Article  Google Scholar 

  • Yang XS (2011b) Metaheuristic optimization: algorithm analysis and open problems. In: International symposium on experimental algorithms. Springer, Berlin, pp 21–32

  • Yi J, Cao J (2008) Tea and fluorosis. J Fluorine Chem 129(2):76–81

    Article  CAS  Google Scholar 

Download references

Acknowledgements

Project “Costs and Remediation of Groundwater Contamination” was funded by the Department of Economics, University of Virginia, and Global Program of Distinction Award (GPOD).

Author information

Authors and Affiliations

Authors

Contributions

The study was conducted within the Ph.D. research of the first author. All authors contributed to the study conception, design and manuscript writing. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Farhan Mohammad Khan.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Khan, F.M., Gupta, R. & Sekhri, S. A novel PCA-FA-ANN based hybrid model for prediction of fluoride. Stoch Environ Res Risk Assess 35, 2125–2152 (2021). https://doi.org/10.1007/s00477-021-02001-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00477-021-02001-4

Keywords

Navigation