Abstract
In the first few days of life, neonatal jaundice is the situation that causes yellow discoloration on the baby’s skin. The yellowish pigmentation is the gesture of an increase in bilirubin levels. It is common in 2/3 of all active infants. It is a condition caused by the problems of poor breastfeeding, the lifespan of red blood cells, or the hydration level. Every year, about 1.1 million infants are affected by hyperbilirubinemia. The approach and knowledge of the purpose of neonatal jaundice are restricted. Exploring the purpose of neonatal jaundice has superior significance in reducing jaundice-related infant mortality and morbidity. According to pudmed.com, case-control analysis is carried out and produces a medical chart of 272 infants for public healthcare units. Proper diagnosis of the disease is required to reduce the mortality rate. Computer vision techniques are essential to diagnose the disease. It can be done with the appropriate machine learning techniques. The existing system uses machine learning methodology to analyze the presence of disease. The severity level of the disease is determined by using a bilirubin meter. It may lead to poor performance due to a lack of severity level identification. Fifth, AdaBoost-Random Forest is carried out to identify the presence of neonatal hyperbilirubinemia. Sixth, the CNN model was trained along with color-card techniques to identify their severity level. Finally, the time series property is included to perform continuous monitoring of neonatal hyperbilirubinemia. The performance evaluation of the model provides class 1 and class 2 specificity of 0.98 and 0.98, the accuracy of the 0.98 and 0.98, MCC of 0.97 and 0.96, and f-measure of 0.98 and 0.98 respectively. The maximum epochs are 100 for training the model. The best validation is obtained at the 22nd epoch. The training performance is 0.24991 at epoch 2.
Similar content being viewed by others
References
Lake EA, Abera GB, Azeze GA, Gebeyew NA, Demissie BW (2019) The magnitude of neonatal jaundice and its associated factor in neonatal intensive care units of Mekelle city public hospitals, Northern Ethiopia. Int J Pediatr 2019(2):1–9. https://doi.org/10.1155/2019/1054943
Zahed Pasha Y, Alizadeh-Tabari S, Zahed Pasha E, Zamani M (2020) Etiology and therapeutic management of neonatal jaundice in Iran: a systematic review and meta-analysis. World J Pediatr 16(5):480–493
Hoy D, Brooks P, Woolf A, Blyth F, March L, Bain C et al (2012) Assessing risk of bias in prevalence studies: modification of an existing tool and evidence of interrater agreement. J Clin Epidemiol 65:934–939
Adoba P, Ephraim RK, Kontor KA, Bentsil JJ, Adu P, Anderson M, Sakyi SA, Nsiah P (2018) Knowledge level and determinants of neonatal jaundice: a cross-sectional study in the effutu municipality of Ghana. Int J Pediatr 2018(2):1–9. https://doi.org/10.1155/2018/3901505
Abbey P, Kandasamy D, Naranje P (2019) Neonatal jaundice. Indian J Pediatr 86(9):830–841
Ma XL, Chen Z, Zhu JJ, Shen XX, Wu MY, Shi LP, Du LZ, Fu JF, Shu Q (2020) Management strategies of neonatal jaundice during the coronavirus disease 2019 outbreak. World J Pediatr 16(3):247–250
Slusher TM, Zipursky A, Bhutani VK (2011) A global need for affordable neonatal jaundice technologies. Semin Perinatol 35(3):185–191
Ives NK (2015) Management of neonatal jaundice. Paediatr Child Health (Oxf) 25(6):276–281
Romagnoli C, Zecca E, Catenazzi P, Barone G, Zuppa AA (2012) Transcutaneous bilirubin measurement: comparison of Respironics BiliCheck and JM-103 in a normal newborn population. Clin Biochem 45(9):659–662
Daunhawer I, Kasser S, Koch G, Sieber L, Cakal H, Tütsch J, Pfister M, Wellmann S, Vogt JE (2019) Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning. Pediatr Res 86(1):122–127
Bakar AHA, Hassan NM, Zakaria A, Halim KAA, Halim AAA (2017) March. Jaundice (Hyperbilirubinemia) detection and prediction system using color card technique. In: 2017 IEEE 13th international colloquium on signal processing & its applications (CSPA). IEEE, pp 208–213
Shaban M, Ogur Z, Mahmoud A, Switala A, Shalaby A, Abu Khalifeh H, Ghazal M, Fraiwan L, Giridharan G, Sandhu H, El-Baz AS (2020) A convolutional neural network for the screening and staging of diabetic retinopathy. PLoS ONE 15(6):e0233514
Dissaneevate S, Wongsirichot T, Siriwat P, Jintanapanya N, Boonyakarn U, Janjindamai W, Thatrimontrichai A, Maneenil G (2022) A mobile computer-aided diagnosis of neonatal hyperbilirubinemia using digital image processing and machine learning techniques. Int J Innov Res Sci Stud 5(1):10–17
Spoorthi SM, Dandinavar SF, Ratageri VH, Wari PK (2019) Prediction of neonatal hyperbilirubinemia using 1st day serum bilirubin levels. Indian J Pediatr 86(2):174–176
Ying Q, You X, You J, Wang J (2020) The accuracy of transcutaneous bilirubin to identify hyperbilirubinemia in jaundiced neonates. J Matern Fetal Neonatal Med 2(3):147–150. https://doi.org/10.15171/ijbsm.2017.27
Bhagat PV, Raghuwanshi MM, Singh K, Damke S, Quazi S Development of jaundice detection approaches in neonates. J Univ Shanghai Sci Technol. https://doi.org/10.51201/12312 ISSN: 1007-6735
Mandal A, Bannerji R, Ray J, Mitra M, Azad SM, Basu S (2018) Correlation between transcutaneous bilirubin estimation and total serum bilirubin estimation in neonatal hyperbilirubinemia. BLDE Univ J Health Sci 3(1), 36
Sravya RS, Kulshan SN, Guptha RS, Manogna V, Prasad MSN (2020) Jaundice detection. UGC Care Group I Listed J 5(4):63. https://doi.org/10.3390/designs5040063
Egejuru NC, Asinobi AO, Adewunmi O, Aderounmu T, Adegoke SA, Idowu PA (2019) A classification model for severity of neonatal Jaundice using deep learning. Am J Pediatr 5(3):159–169
Yin M, Liu X, Liu Y, Chen X (2018) Medical image fusion with parameter-adaptive pulse coupled neural network in nonsubsampled shearlet transform domain. IEEE Trans Instrum Meas 68(1):49–64
Manchanda M, Sharma R (2018) An improved multimodal medical image fusion algorithm based on fuzzy transform. J Vis Commun Image Represent 51:76–94
Maqsood S, Javed U (2020) Multi-modal medical image fusion based on two-scale image decomposition and sparse representation. Biomed Signal Process Control 57:101810
Li Y, Zhao J, Lv Z, Li J (2021) Medical image fusion method by deep learning. Int J Cogn Comput Eng 2:21–29
Boskabadi H, Sezavar M, Zakerihamidi M (2020) Evaluation of neonatal jaundice based on the severity of hyperbilirubinemia. J Clin Neonatol 9(1):46
Chakraborty A, Goud S, Shetty V, Bhattacharyya B (2020) Neonatal jaundice detection system using CNN algorithm and image processing. Int J Electr Eng Technol 18(15):178–201. https://doi.org/10.3991/ijoe.v18i15.32053
Bezdek JC, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10:2–3
Lei T, Jia X, Zhang Y, He L, Meng H, Nandi AK (2018) Significantly fast and robust fuzzy c-means clustering algorithm based on morphological reconstruction and membership filtering. IEEE Trans Fuzzy Syst 26(5):3027–3041
Nida N, Irtaza A, Javed A, Yousaf MH, Mahmood MT (2019) Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering. Int J Med Inform 124:37–48
Kaplan K, Kaya Y, Kuncan M, Ertunç HM (2020) Brain tumor classification using modified local binary patterns (LBP) feature extraction methods. Med Hypotheses 139:109696
Kavitha J (2017) Melanoma detection in dermoscopic images using global and local feature extraction. IJMUE 12(5):19–28
Routray S, Ray AK, Mishra C (2017) Analysis of various image feature extraction methods against noisy image: SIFT, SURF, and HOG. In: 2017 second international conference on electrical, computer and communication technologies (ICECCT), Coimbatore, February, pp 1–5
Hashmi MF, Anand V, Keskar AG (2014) Copy-move image forgery detection using an efficient and robust method combining un-decimated wavelet transform and scale invariant feature transform. AASRI Procedia 9:84–91
Mirjalili S, Gandomi AH, Mirjalili SZ, Saremi S, Faris H, Mirjalili SM (2017) Salp swarm algorithm: a bio-inspired optimizer for engineering design problems. Adv Eng Softw 114:163–191
Hegazy AE, Makhlouf MA, El-Tawel GS (2020) Improved salp swarm algorithm for feature selection. J King Saud Univ Comput Inform Sci 32(3):335–344
Yifan D, Jialin L, Boxi F (2021) Forecast model of breast cancer diagnosis based on RF-AdaBoost. In: 2021 international conference on communications, information system and computer engineering (CISCE). IEEE, pp 716–719
Irmak E (2021) COVID-19 disease severity assessment using CNN model. IET Image Process 15(8):1814
Acknowledgements
There is no acknowledgement involved in this work.
Funding
No funding is involved in this work.
Author information
Authors and Affiliations
Contributions
There is no authorship contribution.
Corresponding author
Ethics declarations
Conflict of interest
Conflict of Interest is not applicable in this work.
Ethics Approval and Consent to Participate
No participation of humans takes place in this implementation process.
Human and Animal Rights
No violation of human and animal rights is involved.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Nayagi, S.B., Angel, T.S.S. Diagnosis of Neonatal Hyperbilirubinemia Using CNN Model Along with Color Card Techniques. J. Electr. Eng. Technol. 18, 3861–3879 (2023). https://doi.org/10.1007/s42835-023-01460-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42835-023-01460-9