Skip to main content

Advertisement

SpringerLink
Log in

Diagnosis of large-for-gestational-age infants using a semi-supervised feature learned from expert and data

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In recent years, a rapid rise in the incidence of Large for gestational age (LGA) neonate is reported, and health care professionals employed themselves to discover the cause. Utmost of the previous studies were cohort or observational studies that employed simple linear or multivariate regression models, and very few of them employed machine learning (ML) schemes. Therefore, this research proposes to use 1 expert-driven and 7 automated feature selection schemes with well-known ML classifiers using 10 and 30 folds cross-validation. The induced results were compared with existing baselines, and Wilcoxon signed-rank test and the Friedman test were also introduced to verify the results. The ranked 20 features of the proposed expert-driven feature selection scheme outperformed amongst 7 automated feature selection schemes with a prediction precision, accuracy, and AUC scores of 0.94606, 0.84529, and 0.86492, respectively. Out of twenty features, eleven features were found similar to twenty ranked features of the automated feature selection schemes subsets. The classification results of the extracted features were utmost identical to the results of twenty features subset proposed by the expert-driven feature selection scheme. Therefore, we suggest pediatricians to refresh LGA diagnosis process with the proposed scheme because of its practical usage and maximum expert involvement.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Adankon MM, Cheriet M, Biem A (2009) Semisupervised least squares support vector machine. IEEE Trans Neural Netw 20(12):1858–1870

    Google Scholar 

  2. Ai K, Zhang J, Dagvadorj A, Hirayama F, Shibuya K, Souza JP, Gulmezoglu AM (2013) Macrosomia in 23 developing countries: an analysis of a multicountry, facility-based, cross-sectional survey. Lancet 381(9865):476–483

    Google Scholar 

  3. Akhtar F, Li J, Azeem M, Chen S, Pan H, Wang Q, Yang J-J (2019) Effective large for gestational age prediction using machine learning techniques with monitoring biochemical indicators. The Journal of Supercomputing

  4. Bammann K (2006) Statistical models: Theory and practice. Biometrics 62 (3):943–943

    MathSciNet  Google Scholar 

  5. Battaglia FC, Lubchenco LO (1967) A practical classification of newborn infants by weight and gestational age. J Pediatr 71(2):159–163

    Google Scholar 

  6. Blue NR, Jmp Y, Holbrook BD, Nirgudkar PA, Mozurkewich EL (2017) Abdominal circumference alone versus estimated fetal weight after 24 weeks to predict small or large for gestational age at birth A meta-analysis. Am J Perinatol 34 (11):1115–1124

    Google Scholar 

  7. Boney CM, Verma A, Tucker R, Vohr BR (2005) Metabolic syndrome in childhood: association with birth weight, maternal obesity, and gestational diabetes mellitus. Pediatrics 115(3):290–6

    Google Scholar 

  8. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    MATH  Google Scholar 

  9. Chen Q, Wei J, Tong M, Yu L, Lee AC, Gao YF, Zhao M (2015) Associations between body mass index and maternal weight gain on the delivery of lga infants in chinese women with gestational diabetes mellitus. J Diabet Compl 29 (8):1037–1041

    Google Scholar 

  10. Chiavaroli V, Castorani V, Guidone P, Derraik JGB, Liberati M, Chiarelli F, Mohn A (2016) Incidence of infants born small- and large-for-gestational-age in an italian cohort over a 20-year period and associated risk factors. Ital J Pediatr 42(1):1–7

    Google Scholar 

  11. Chou Y-H, Tiu C-M, Hung G-S, Wu S-C, Chang TY, Chiang HK (2001) Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis. Ultrasound Med Biol 27(11):1493–1498

    Google Scholar 

  12. Dietz WH (2004) Overweight in childhood and adolescence. N Engl J Med 350 (9):855–857

    Google Scholar 

  13. Dyer JS, Rosenfeld CR, Rice J, Rice M, Hardin DS (2007) Insulin resistance in hispanic large-for-gestational-age neonates at birth. Early Hum Dev 83 (10):S138–S138

    Google Scholar 

  14. Faucher MA, Barger MK (2015) Gestational weight gain in obese women by class of obesity and select maternal/newborn outcomes: a systematic review. Women Birth 28(3):e70–e79

    Google Scholar 

  15. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182

    MATH  Google Scholar 

  16. Haipin SS, Zhang QW (2015) Design implementation and significance of chinese free pre-pregnancy eugenics checks projec. Natl Med J China 95(3):162–165

    Google Scholar 

  17. Hameed SS, Rawal I, Soni D, Ajay VS, Goenka S, Prabhakaran D (2016) Technology for diagnosis, treatment, and prevention of cardiometabolic disease in india. Prog Cardiovasc Dis 58(6):620–629

    Google Scholar 

  18. Hannaford KE, Tuuli MG, Odibo L, Macones GA, Odibo AO (2017) Gestational weight gain: association with adverse pregnancy outcomes. Amer J Perinatol 34(02):147–154

    Google Scholar 

  19. Harper LM, Jauk VC, Owen J, Biggio JR (2014) The utility of ultrasound surveillance of fluid and growth in obese women. Amer J Obstetr Gynecol 211(5):524.e1–524.e8

    Google Scholar 

  20. Henriksen T (2011) The macrosomic fetus: a challenge in current obstetrics. Acta Obstetr Gynecol Scand 87(2):134–145

    Google Scholar 

  21. Ingrid WMD, Axelsson O, Bergstrom R (2011) Maternal factors associated with high birth weight. Acta Obstetr Gynecol Scand 70(1):55–61

    Google Scholar 

  22. Júnior EA, Peixoto AB, Zamarian ACP, Júnior JE, Tonni G (2017) Macrosomia. Best Pract Res Clin Obstetr Gynaecol 38:83–96

    Google Scholar 

  23. Khambalia AZ, Algert CS, Bowen JR, Collie RJ, Roberts CL (2017) Long-term outcomes for large for gestational age infants born at term. J Paediat Child Health 53(9):876–881

    Google Scholar 

  24. Kominiarek MA, Grobman W, Adam E, Buss C, Culhane J, Entringer S, Simhan H, Wadhwa PD, Kim K-Y, Keenan-Devlin L et al (2018) Stress during pregnancy and gestational weight gain. J Perinatol 38(5):462–467

    Google Scholar 

  25. Kuciene R, Dulskiene V, Medzioniene J (2017) Associations between high birth weight, being large for gestational age, and high blood pressure among adolescents: a cross-sectional study. Eur J Nutr 57(1):1–9

    Google Scholar 

  26. Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22(1):79–86

    MathSciNet  MATH  Google Scholar 

  27. Kursa MB, Jankowski A, Rudnicki WR (2010) Boruta–a system for feature selection. Fund Inf 101(4):271–285

    MathSciNet  Google Scholar 

  28. Lazer S, Biale Y, Mazor M, Lewenthal H, Insler V (1986) Complications associated with the macrosomic fetus. J Reprod Med 31(6):501–505

    Google Scholar 

  29. Li J, Akhtar F, Guan Y (2018) Monitoring bio-chemical indicators using machine learning techniques for an effective large for gestational age prediction model with reduced computational overhead. The 7th International Conference on Frontier Computing (FC 2018) - Theory Technologies and Applications

  30. Li J, Lu L, Zhou MC, Ji JY, Chen S, Liu HT, Wang Q, Pan H, Sun ZH, Tan F (2018) Feature selection and prediction of small-for-gestational-age infants. Journal of Ambient Intelligence and Humanized Computing:1–15

  31. Luangkwan S, Vetchapanpasat S, Panditpanitcha P, Yimsabai R, Subhaluksuksakorn P, Loyd RA, Uengarporn N (2015) Risk factors of small for gestational age and large for gestational age at buriram hospital. J Med Assoc Thai 98 (Suppl 4):S71–S78

    Google Scholar 

  32. Mendez-Figueroa H, Truong VT, Pedroza C, Chauhan SP (2017) Large for gestational age infants and adverse outcomes among uncomplicated pregnancies at term. Am J Perinatol 34(07):655–662

    Google Scholar 

  33. Menze BH, Kelm MB, Masuch R, Himmelreich U, Bachert P, Petrich W, Hamprecht FA (2009) A comparison of random forest and its gini importance with standard chemometric methods for the feature selection and classification of spectral data. Bmc Bioinform 10(1):1–16

    Google Scholar 

  34. Meshari AA, De Silva S, Rahman I (1990) Fetal macrosomia, maternal risks and fetal outcome. Int J Gynecol Obstetr 32(3):215–222

    Google Scholar 

  35. Modinat M, Abimbola A, Abdullateef B, Opeyemi A (2015) Gain ratio and decision tree classifier for intrusion detection. Int J Comput Appl 126(11):975–8887

    Google Scholar 

  36. Moore GS, Kneitel AW, Walker CK, Gilbert WM, Xing G (2012) Autism risk in small- and large-for-gestational-age infants. Amer J Obstetr Gynecol 206(4):314.e1–314.e9

    Google Scholar 

  37. Murtaza G, Shuib L, Mujtaba G, Raza G (2019) Breast cancer multi-classification through deep neural network and hierarchical classification approach. Multimedia Tools and Applications:1–31

  38. Murtaza G, Shuib L, Wahab AWA, Mujtaba G, Raza G, Azmi NA (2019) Breast cancer classification using digital biopsy histopathology images through transfer learning. In: Journal of Physics: Conference Series, vol 1339(1):012035. IOP Publishing

  39. Murtaza G, Shuib L, Wahab AWA, Mujtaba G, Nweke HF, Al-garadi MA, Zulfiqar F, Raza G, Azmi NA (2019) Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges. Artificial Intelligence Review:1–66

  40. Murtaza G, Shuib L, Wahab AWA, Mujtaba G, Raza G (2020) Ensembled deep convolution neural network-based breast cancer classification with misclassification reduction algorithms. Multimedia Tools and Applications:1–33

  41. Pearson K (1900) On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Phil Mag 50(302):157–175

    MATH  Google Scholar 

  42. Piper LK, Stewart Z, Murphy HR (2017) Gestational diabetes. Obstetr Gynaecol Reprod Med 27(6):171–176

    Google Scholar 

  43. Shen Y, Zhao W, Lin J, Liu F (2017) Accuracy of sonographic fetal weight estimation prior to delivery in a chinese han population. J Clin Ultrasound 45 (8):465–471

    Google Scholar 

  44. Shmueli A, Nassie DI, Hiersch L, Ashwal E, Wiznitzer A, Yogev Y, Aviram A (2017) 1241: Prerecognition of large for gestational age (lga) fetus and its consequences 216:S150–S151, 01

  45. Taal HR, Vd Heijden AJ, Steegers EA, Hofman A, Jaddoe VW (2013) Small and large size for gestational age at birth, infant growth, and childhood overweight. Obesity 21(6):1261–1268

    Google Scholar 

  46. Van Assche FA, Devlieger R, Harder T, Plagemann A (2010) Mitogenic effect of insulin and developmental programming. Diabetologia 53(6):1243–1243

    Google Scholar 

  47. Wikstrom I, Axelsson O, Bergstrom R, Meirik O (2011) Traumatic injury in large-for-date infants. Acta Obstetr Gynecol Scand 67(3):259–264

    Google Scholar 

  48. Wolpert DH, Macready WG et al (1995) No free lunch theorems for search. Technical report, Technical Report SFI-TR-95-02-010. Santa Fe Institute

  49. Xu H, Simonet F, Luo ZC (2010) Optimal birth weight percentile cut-offs in defining small- or large-for-gestational-age. Acta Paidiatrica 99(4):550–555

    Google Scholar 

  50. Zhang H, Su J (2004) Naive bayesian classifiers for ranking. In European conference on machine learning. Springer, pp 501–512

  51. Zhu L, Zhang R, Zhang S, Shi W, Yan W, Wang X, Lyu Q, Liu L, Zhou Q, Qiu Q (2015) Chinese neonatal birth weight curve for different gestational age. Zhonghua Er Ke Za Zhi 53(2):97–103

    Google Scholar 

Download references

Acknowledgments

This work is supported by the National Key Research and Development Program of China with project no.2017YFB1400803.

Author information

Authors and Affiliations

  1. School of Software Engineering, Beijing University of Technology, Beijing, 100124, China

    Faheem Akhtar, Jianqiang Li, Azhar Imran, Muhammad Azeem & Bo Liu

  2. Beijing Engineering Research Center for IoT Software and Systems, Beijing, 100124, China

    Faheem Akhtar & Jianqiang Li

  3. Department of Computer science, Sukkur IBA University, 65200, Sukkur, Pakistan

    Faheem Akhtar & Asif Rajput

  4. Computer Science Division, University of Aizu, Aizu-wakamatsu, 965-8580, Japan

    Yan Pei

Authors
  1. Faheem Akhtar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianqiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yan Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Azhar Imran
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Asif Rajput
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Muhammad Azeem
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Bo Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Faheem Akhtar or Yan Pei.

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

Akhtar, F., Li, J., Pei, Y. et al. Diagnosis of large-for-gestational-age infants using a semi-supervised feature learned from expert and data. Multimed Tools Appl 79, 34047–34077 (2020). https://doi.org/10.1007/s11042-020-09081-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-09081-4

Keywords

Search

Navigation