VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI-590018

A Project Report

On

“Prediction Of Fetal Health Status Using Machine Learning”

A Project report submitted in partial fulfillment of the requirements for the award of the
degree of
Master of Computer Applications
of
Visvesvaraya Technological University, Belagavi

Submitted by
Naidile S Saragodu (1DT21MC024)
Under the Guidance of
Dr. Manjula Sanjay Koti
( Prof and HOD, Dept. of MCA)

Department of Master of Computer Applications

DAYANANDA SAGAR ACADEMY OF TECHNOLOGY AND
MANAGEMENT
Accredited by NBA, New Delhi, Accredited by NAAC with Grade A+
Udayapura, Kanakapura Road, Bengaluru-560082
2021-2023
 DECLARATION

I, Naidile S Saragodu, Student of 4th sem MCA, Dayananda Sagar Academy of Technology
And Management bearing USN 1DT21MC024 hereby declare that the project entitled
“Prediction Of Fetal Health Status Using Machine Learning” has been carried out by me
under the supervision of Internal Guide Dr. Manjula Sanjay Koti HOD, Dept. of MCA and
submitted in partial fulfilment of the requirement for the award of the Degree of Master of
Computer Applications by the Vivesvaraya Technological University during the academic
year 2021-2023. This report has not been submitted to any other Organization/University for
any award of degree or certificate.

Name: Naidile S Saragodu

Signature:
 ACKNOWLEDGEMENT

Gives It immense pleasure in bringing out this report of the project entitled. “ Prediction Of
Fetal Health Status Using Machine Learning” Dreams never turn to reality unless a lot of
effort and hard work is put into it and no effort bears fruit in the absence of support and
guidance. It takes a lot of effort to work my way through this goal and having someone to
guide me and help me is always a blessing.

I would like to take this opportunity to thank a few who were closely involved in completing
and executing this Project. At the outset, I thank God almighty for making my endeavor
success. I would like to express my sincere thanks to the Management of Dayananda Sagar
Academy of Technology and Management for providing excellent infrastructure and other
facilities, which enabled me to sharpen my skills.

I would like to express a deep sense of gratitude to Dr. Ravishankar M, Principal of

DSATM, Bengaluru, for providing us with adequate facilities, ways and means by which we
were able to complete this project.
I express my sincere gratitude to Dr. Manjula Sanjay Koti, Professor and Head of
Department of Master of Computer Application for encouraging us to aim higher and
constant support and valuable suggestion without which the successful completion of this
project would not have been possible.

I express my immense indebtedness to all the teachers and staff of Dept. of Master of Computer
Application, Dayananda Sagar Academy of Technology and Management for their
cooperation and support. Finally, we thank all others, and especially our classmates and our
family members who in one way or another helped us in the successful completion of this
work.
 ABSTRACT
The objective of this promising field of research is to improve prenatal care and reduce fetal
morbidity and mortality by using machine learning to predict fetal illness. We describe a
machine learning-based technique for predicting fetal illnesses using clinical data in this paper.
First, we obtained a substantial amount of clinical data from pregnant moms with diverse fetal
abnormalities. We pre-processed the data and extracted relevant characteristics using clinical
recommendations. To train and evaluate our model, we used a variety of machine learning
methods, including logistic regression, support vector machines, decision trees, and random
forests. We assessed our model's performance using a variety of metrics, including accuracy,
sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC).
The results of this study demonstrate how machine learning algorithms can accurately forecast
fetal health status. The developed models achieve good accuracy and AUC-ROC ratings in
order to distinguish between healthy and at-risk fetus. The interpretability study identifies key
clinical characteristics that have a significant impact on the prediction, providing medical
practitioners with useful information when making decisions about prenatal care.

Through the provision of more unbiased and precise assessments of fetal health status, machine
learning techniques incorporated into prenatal care have the potential to transform the industry.
By providing accurate and early projections, this technology can assist healthcare professionals
in identifying high-risk pregnancies and carrying out the necessary procedures, improving
mother and fetal outcomes. Future research should concentrate on verifying and improving
predictive models on larger and more varied datasets to ensure real-world
applicability and reliability.
 CONTENTS

CONTENT PAGE NO

1. INTRODUCTION 1
1.1 OVERVIEW OF MACHINE LEARNING 3
1.2 PROBLEM STATEMENT 7
1.3 OBJECTIVES OF THE PROJECT 8
1.4 SCOPE OF THE PROJECT 9
1.5 CONTRIBUTION TO THE PROJECT 10
2. LITERATURE SURVEY 12
3. METHODOLOGY 18
3.1 DATA SET DESCRIPTION AND PRE-PROCESSING 18
3.2 FEATURE SELECTION 33
3.3 MACHINE LEARNING ALGORITHMS 35
4. EXPERIMENTAL SETUP 44
4.1 SYSTEM REQUIREMENT SPECIFICATIONS 44
4.2 EXPERIMENTS AND RESULTS 50
4.3 INTERPRETATION OF FINDINGS 53
4.4 PERFORMANCE EVOLUTION 56
5. CONCLUSION 58
5.1 FUTURE WORK 60
6. REFERENCES 62
7. APPENDIX 64
7.1 CODE SNIPPETS OR PSEUDO CODE 66
7.2 SUPPORTING FIGURES AND TABLES 69
Appendix A: ABSTRACT ACCEPTANCE 76
Appendix B: PLAGIARISM REPORT 78
 LIST OF FIGURES

Figure No. Title Page No.

1.1 Working Of Machine Learning Algorithm 3
1.2 Classification Of ML 4
3.1 Graphical Representation Of CTG 18
3.2 Learning Model Flow 19
3.3 Detailed System Architecture 21
3.4 System Architecture 22
3.5 High Level Design 22
3.6 Use Case Diagram 23
3.7 Dataset Description & Preprocessing 23
3.8 Fetal Health Status 24
3.9 Picture Of Proof How We Select 5 Parameters 24
3.10 Picture Of Proof Of 5 Parameters Importance In The Prediction 25
3.11 Data Set Values 25

3.12 Baseline Value 26

3.13 Fetal Heart Rate Acceleration 27

3.14 Fetal Movement 27
3.15 Uterine Contraction 28
3.16 Light Deceleration 29
3.17 Severe Deceleration 30
3.18 Prolonged Deccelerations 30
3.19 Abnormal Short-Term Variability 31
3.20 Mean Value Of Long Term Value 32
3.21 Mean Value Of Short Term Variability 32
3.22 Support Vector Machine 36
3.23 Logistic Regression 39
3.24 Random Forest 41
3.25 Decision Tree 43
4.1 Model Loss & Accuracy 50
4.2 Accuracy Score Analysis 52
4.3 Methodology To Build The Classifier 55
7.1 Home Page 69
7.2 Home Page 69
7.3 User Login Page 70
7.4 Login Page 70
7.5 Sample Values 71
7.6 Fetal is Suspect 72
7.7 Diet Plan 72
7.8 WHO 73
7.9 Pathological 74
7.10 Diet Plan For Pathological 74
7.11 Fetal Is Normal 75
7.12 Logout Page 75