Report

PROJECT REPORT
“Predicting Common Sports Injuries of Track and Field Athletes Using Machine Learning”
Submitted in the partial fulfillment of the requirement for the award

of degree of
Computer Science and Technology
Submitted by
Karthikeyan 20211CSG0044
Yogesh Chavan 20211CSG0054
Himanshu Choudary : 20211CSG0023
Under the guidance of
Dr. Chandrasekar Vadivelra

ABSTRACT
The proposed system for track and field athletics injury management leverages advanced technology
and data analytics to proactively prevent injuries and optimize athlete performance. By electronic
health records, and predictive modeling, the system provides real-time biomechanical analysis and
personalized interventions. Coaches and sports medicine professionals receive decision support tools
to tailor training programs and mitigate injury risks. Telemedicine capabilities enhance accessibility
to healthcare services, fostering holistic athlete care. Ethical considerations and privacy protections
ensure compliance with regulations. Through continuous monitoring and user feedback, the system
aims to revolutionize injury management practices, promoting athlete well-being and long-term
athletic development.
CONTENTS
Sl No Chapter Name Page No
1 INTRODUCTION
2 LITREATURE SURVEY
3 EXISTING SYSTEM
4 PROPOSED SYSTEM
4.1 Advantages
4.2 System Architecture
5 MODULES
6 SYSTEM DESIGN 25-30

6.1 Requirement Analysis
6.2 Developmental Model
6.3 Data Flow Diagram
6.4 Use Case Diagram
6.5 Sequence Diagram
7 CODING
CONTENTS
8 SYSTEM TESTING
8.1 Testing Methods
8.2 Unit Testing
8.3 Integration Testing
8.4 Functional Testing
8.5 System Testing
9 RESULTS
CONCLUSION AND FUTURE

ENHANCEMENT
REFERENCES
List of Figures
Sl No Figure Name Page No
4.1 Flowchart 8
6.1 dataflow diagram 17
6.2 Use case diagram 18

Common Sports Injuries of Track and Field Athletes Using Machine Learning
CHAPTER 1
INTRODUCTION
Sports injuries pose significant challenges to athletes, coaches, and sports medicine professionals,
often resulting in decreased performance, prolonged recovery times, and potential longterm health
implications. In the context of track and field athletics, where speed, agility, and strength are
paramount, understanding and mitigating the risk of injuries is of utmost importance.
This project aims to utilize machine learning techniques to analyze and predict common sports
injuries among track and field athletes. By leveraging data collected from athletes' demographics,
training routines, injury histories, and other relevant factors, we seek to develop predictive models
that can identify potential injury risks and enable proactive interventions to prevent or minimize
their occurrence.
The key objectives of this project are as follows:
 Data Collection and Preprocessing: We will gather a comprehensive dataset encompassing

information on track and field athletes, including age, gender, event specialization, training
volume, previous injuries, biomechanical factors, and environmental conditions. The data
will be cleaned, standardized, and preprocessed to ensure its quality and reliability for
subsequent analysis.
 Feature Selection and Engineering: Relevant features contributing to injury prediction will
be identified and extracted from the dataset. This may involve analyzing the correlation
between different variables, conducting domainspecific research, and employing techniques
such as PCA or feature engineering to enhance the predictive power of the models.
Presidency University 6
 Model Development and Training: Various machine learning algorithms, including
decision trees, random forests, support vector machines, gradient boosting machines, and
neural networks, will be explored for their suitability in predicting sports injuries. The
dataset will be split into training and testing sets, and the models will be trained using the
training data while evaluating their performance on the testing data.
 Evaluation Metrics and Interpretation: The performance of the trained models will be
evaluated using standard metrics such as accuracy, precision, recall, F1score, and AUROC.
Additionally, feature importance analysis and visualization techniques will be employed to
interpret the models' predictions and identify the most significant factors contributing to
injury risks among track and field athletes.
 Deployment and Ethical Considerations: The final predictive models will be deployed in a
realworld setting to assist coaches, sports physicians, and athletes in injury prevention
strategies. Ethical considerations regarding data privacy, consent, fairness, and responsible
use of the models will be carefully addressed throughout the project.
By harnessing the power of machine learning, this project aims to provide valuable insights into the
factors influencing sports injuries among track and field athletes and empower stakeholders with
actionable information to enhance athlete wellbeing and performance.
CHAPTER 2
LITERATURE SURVEY
1. Title: "Epidemiology of Injuries in Track and Field: A Literature Review"

Authors: Lopes AD, Hespanhol Junior LC, Yeung SS, Costa LO
Published in: Physical Therapy in Sport, 2012
Summary: This review paper provides a comprehensive overview of the epidemiology of
injuries in track and field athletics, including incidence rates, types of injuries, risk factors, and
preventive strategies. It synthesizes findings from various studies to offer insights into the
prevalence and patterns of injuries across different events and athlete populations.
2. Title: "Injury Patterns in Selected High School Sports: A Review of the 19951997
Seasons"
Authors: Junge A, Cheung K, Edwards T, Dvorak J
Published in: Journal of Athletic Training, 2007
Summary: This paper reviews injury patterns in high school sports, including track and field,
based on data from the National High School SportsRelated Injury Surveillance System. It
examines injury rates, types of injuries, mechanisms, and risk factors, highlighting differences
between various sports and providing insights into injury prevention strategies.
3. Title: "Injury Patterns in Division I Collegiate Athletics"

Authors: Hootman JM, Dick R, Agel J
Published in: Journal of Athletic Training, 2007
Summary: This paper presents an analysis of injury patterns among Division I collegiate
athletes across multiple sports, including track and field. It discusses injury rates, types of injuries,
body regions affected, and factors contributing to injury risk. The findings help in understanding
the unique injury profiles of collegiate track and field athletes and inform injury prevention
efforts.
4. Title: "Risk Factors for Lower Extremity Injury: A Review of the Literature"
Authors: Van Mechelen W
Published in: British Journal of Sports Medicine, 1997
Summary: Although not specific to track and field, this seminal review paper provides a
comprehensive overview of risk factors for lower extremity injuries in various sports and physical
activities. It discusses biomechanical, anatomical, trainingrelated, and environmental factors
contributing to injury risk, offering valuable insights applicable to track and field athletes.
5. Title: "Prevention of Running Injuries: A Narrative Review"

Authors: Hreljac A
Published in: Physical Medicine and Rehabilitation Clinics of North America, 2005
Summary: While focusing primarily on runningrelated injuries, this review paper offers insights
into injury prevention strategies relevant to track and field athletes. It discusses factors such as
footwear, biomechanics, training load, and surface characteristics, highlighting evidencebased
approaches to reduce the risk of injuries in runningbased events.
CHAPTER 3
EXISTING SYSTEM
The existing system for managing sports injuries in track and field athletics typically involves a
combination of reactive measures, such as injury treatment and rehabilitation, and some proactive
strategies, such as injury prevention programs. However, this system has several disadvantages:
 Reactive Approach: The current system often focuses more on treating injuries after they
occur rather than preventing them proactively. While injury treatment is essential, a purely
reactive approach may lead to longer recovery times, increased healthcare costs, and
potential long-term consequences for athletes.
 Limited Predictive Capabilities: The existing system lacks robust predictive capabilities
to anticipate and mitigate injury risks before they manifest. Without the ability to identify
athletes at higher risk of injury based on individual characteristics, training loads,
biomechanics, or other factors, preventive interventions may not be effectively targeted.
 Incomplete Data Utilization: The data utilized in the current system may be limited in
scope and depth. Injury records may not capture all relevant information, such as training
volumes, biomechanical assessments, or environmental factors, which are crucial for
understanding injury mechanisms and implementing effective prevention strategies.
 Subjectivity in Injury Management: Decision-making regarding injury management may

be subjective and reliant on individual clinician experience rather than evidence-based
guidelines or objective data. This subjectivity can lead to variability in treatment
approaches and outcomes, impacting the consistency and quality of care provided to
athletes.
 Resource Intensive: Reactive measures such as injury treatment and rehabilitation can be
resource-intensive in terms of time, personnel, and financial costs. Without sufficient
resources allocated to preventive measures, the burden on healthcare systems and athletic
programs may increase as the prevalence of sports injuries persists.
 Underutilization of Technology: While technology has advanced significantly in recent

years, its integration into injury management practices in track and field athletics may still
be limited. Advanced tools such as wearable sensors, biomechanical analysis systems, and
machine learning algorithms could enhance injury risk assessment and prevention but may
not be widely adopted or accessible.
 Lack of Long-Term Monitoring: The current system may lack adequate mechanisms for
long-term monitoring of athletes' health and injury status. Without continuous surveillance
and follow-up, recurring or chronic injuries may go unnoticed, leading to suboptimal
outcomes and potential career implications for athletes.
Addressing these disadvantages requires a shift towards a more proactive, data-driven, and
technology-enabled approach to sports injury management in track and field athletics. Integrating
advanced analytics, predictive modeling, and evidence-based interventions can enhance injury
prevention efforts and optimize athlete well-being and performance.
CHAPTER 4
PROPOSED SYSTEM
The proposed system for managing sports injuries in track and field athletics aims to address the
limitations of the existing system by leveraging advanced technology, data analytics, and
evidence-based interventions. Here's an outline of the proposed system:
 Predictive Injury Risk Assessment: Develop machine learning models to predict injury
risks among track and field athletes based on comprehensive datasets encompassing
athlete demographics, training routines, biomechanical factors, injury histories, and
environmental conditions. These models will analyze patterns and identify athletes at
higher risk of specific injuries, enabling proactive interventions.
 Real-time Monitoring and Biomechanical Analysis: Implement wearable sensors and

biomechanical analysis systems to monitor athletes' movement patterns, technique, and
biomechanical parameters during training and competition. Real-time data collection will
provide insights into biomechanical stressors and potential injury precursors, allowing
coaches and sports medicine professionals to intervene promptly.
 Individualized Training Programs: Develop individualized training programs tailored to

each athlete's needs, injury history, biomechanical profile, and performance goals. Utilize
data-driven insights from predictive models and biomechanical analysis to optimize
training loads, intensity, and recovery strategies, reducing the risk of overuse injuries and
optimizing performance.
 Preventive Interventions and Education: Implement evidence-based preventive

interventions targeting modifiable risk factors identified through predictive modeling and
biomechanical analysis. These interventions may include strength and conditioning
programs, neuromuscular training, flexibility exercises, and education on injury
prevention strategies. Athletes, coaches, and support staff will receive education and
training on injury prevention principles and techniques.
 Continuous Monitoring and Feedback Loop: Establish a continuous monitoring system

to track athletes' health, injury status, and training progress over time. Regular assessments
and feedback loops will enable early detection of injury trends, adjustments to training
protocols, and personalized interventions as needed. This proactive approach aims to
minimize injury recurrence and optimize long-term athlete development.
 Integration of Technology and Telemedicine: Leverage telemedicine and remote

monitoring technologies to facilitate real-time communication between athletes, coaches,
and sports medicine professionals. Virtual consultations, injury assessments, and remote
rehabilitation programs will enhance accessibility to healthcare services and support
athletes' recovery and injury management, especially in geographically dispersed settings.
 Data-driven Decision Support System: Develop a comprehensive data management and

decision support system to centralize athlete data, injury records, training logs, and
biomechanical assessments. Advanced analytics and visualization tools will facilitate data-
driven decision-making, performance monitoring, and research collaborations to
continuously improve the system's effectiveness.
 Ethical Considerations and Privacy Protections: Ensure compliance with ethical
guidelines and privacy regulations regarding data collection, storage, and usage. Prioritize
athlete confidentiality, informed consent, and transparency in data handling practices to
maintain trust and respect athletes' rights throughout the system's implementation.
By implementing this proposed system, track and field athletics programs can transition towards a
proactive, data-driven approach to sports injury management, optimizing athlete performance,
well-being, and long-term athletic development.
4.1 Advantages of proposed system
The proposed system for managing sports injuries in track and field athletics offers several
advantages over the existing system. Here are some key advantages:
 Proactive Injury Prevention: By leveraging predictive modeling and real-time

biomechanical analysis, the proposed system enables proactive identification of injury risks
before they manifest. Coaches and sports medicine professionals can intervene early with
targeted preventive measures, reducing the incidence and severity of sports injuries among
athletes.
 Individualized Approach: The proposed system emphasizes individualized injury

prevention strategies tailored to each athlete's unique characteristics, training history,
biomechanics, and injury risk profile. By considering individual differences and specific
needs, interventions can be more effective in reducing injury risks and optimizing
performance.
 Data-driven Decision Making: The integration of advanced analytics and data

management tools facilitates data-driven decision-making processes. Coaches and sports
medicine professionals can analyze athlete data, injury trends, and training loads to make
informed decisions about injury prevention strategies, training protocols, and rehabilitation
plans.
 Optimized Training Programs: With insights from predictive modeling and real-time
monitoring, training programs can be optimized to balance performance goals with injury
prevention objectives. Adjustments to training loads, intensity, and recovery strategies can
be made based on objective data, maximizing athletic performance while minimizing injury
risks.
 Continuous Monitoring and Feedback: The proposed system incorporates a continuous

monitoring framework to track athletes' health, injury status, and training progress over
time. Regular assessments and feedback loops enable timely adjustments to training
protocols and interventions, promoting ongoing athlete well-being and performance
optimization.
 Remote Accessibility and Telemedicine: Utilizing telemedicine and remote monitoring

technologies enhances accessibility to healthcare services for athletes, especially those in
geographically dispersed locations. Virtual consultations, remote assessments, and
rehabilitation programs facilitate timely access to expert care, regardless of physical
location.
 Efficient Resource Utilization: By prioritizing proactive injury prevention strategies and

individualized interventions, the proposed system can optimize resource utilization within
sports medicine programs. Preventing injuries before they occur can reduce the burden on
healthcare systems, minimize healthcare costs, and improve overall efficiency in athlete
care.
 Ethical Considerations and Privacy Protections: The proposed system emphasizes

ethical considerations and privacy protections in data management and athlete care
practices. Athlete confidentiality, informed consent, and transparency in data handling are
prioritized to maintain trust and respect athletes' rights throughout the system's
implementation.
Overall, the proposed system offers a comprehensive, proactive, and data-driven approach to
sports injury management in track and field athletics, aiming to optimize athlete performance,
well-being, and long-term athletic development while minimizing injury risks and healthcare costs.
4.2 System Architecture
The system architecture for managing sports injuries in track and field athletics encompasses
various components, including data collection, analysis, intervention, and communication. Here's a
high-level overview of the proposed system architecture:
Figure 4.1: System architecture

• Data Collection Layer:

o Wearable Sensors: Athletes wear wearable sensors, such as accelerometers,
gyroscopes, and inertial measurement units (IMUs), to collect biomechanical data
during training and competition. These sensors capture movement patterns, forces
exerted on the body, and other relevant biomechanical parameters.
o Electronic Health Records (EHR): Athlete data, including medical history, injury
records, and treatment plans, are stored in electronic health record systems. These
records provide valuable insights into athletes' health status, injury history, and
ongoing care requirements.
• Data Processing and Analysis Layer:

o Real-time Data Processing: Biomechanical data collected from wearable sensors are
processed in real-time to extract meaningful insights about athletes' movement
patterns, technique, and biomechanical stressors.
o Predictive Modeling: Machine learning algorithms analyze athlete data, training
routines, biomechanical parameters, and injury histories to develop predictive
models for identifying injury risks and patterns. These models predict the likelihood
of specific injuries occurring based on individual characteristics and training
factors.
• Decision Support Layer:

o Injury Risk Assessment: The predictive models provide injury risk assessments for
individual athletes, highlighting those at higher risk of specific injuries. Coaches
and sports medicine professionals use these assessments to guide injury prevention
strategies, training modifications, and intervention plans.
o Training Program Optimization: Insights from predictive modeling and
biomechanical analysis inform the optimization of athletes' training programs.
Training loads, intensity, and recovery strategies are adjusted based on objective
data to balance performance goals with injury prevention objectives.
• Intervention and Communication Layer:

o Individualized Interventions: Based on injury risk assessments and training program
optimizations, individualized interventions are recommended for athletes. These
interventions may include targeted strength and conditioning exercises,
neuromuscular training, flexibility programs, and education on injury prevention
techniques.
o Telemedicine and Remote Monitoring: Telemedicine platforms enable remote
consultations, injury assessments, and rehabilitation programs, facilitating timely
access to healthcare services for athletes. Remote monitoring technologies allow
coaches and sports medicine professionals to track athletes' progress and provide
feedback regardless of physical location.
• Data Storage and Management Layer:

o Centralized Data Repository: Athlete data, including biomechanical data, electronic
health records, injury records, and predictive model outputs, are stored in a
centralized data repository. This repository ensures data integrity, accessibility, and
security, facilitating seamless data integration and analysis.
• User Interface Layer:

o Athlete Portal: Athletes have access to a user-friendly portal where they can view
their injury risk assessments, training recommendations, and rehabilitation plans.
They can also input subjective feedback, track their progress, and communicate
with coaches and sports medicine professionals.
o Coach and Clinician Dashboard: Coaches and sports medicine professionals access
a dashboard where they can monitor athletes' health status, injury risks, and training
progress. They can review predictive model outputs, customize training programs,
and communicate with athletes to provide guidance and support.
This system architecture enables a proactive, data-driven approach to sports injury management in
track and field athletics, integrating advanced technology, predictive modeling, and individualized
interventions to optimize athlete performance, well-being, and long-term athletic development.
CHAPTER 5
MODULES
The proposed system for managing sports injuries in track and field athletics can be broken down
into several key modules, each serving specific functions within the overall architecture. Here are
the main modules:
• Data Collection Module:
o This module collects data from various sources, including wearable sensors,
electronic health records (EHR), athlete self-reports, and external databases.
o Submodules:
o Wearable Sensor Data Collection: Collects biomechanical data from wearable

sensors worn by athletes during training and competition.
o Electronic Health Records Integration: Retrieves athlete health information, injury

records, treatment plans, and medical history from EHR systems.
• Data Processing and Analysis Module:
o This module processes raw data and performs analysis to extract actionable insights
and patterns related to injury risks, biomechanics, and athlete performance.
o Submodules:
o Real-time Data Processing: Processes biomechanical data in real-time to extract

relevant features and identify patterns indicative of injury risks.
o Predictive Modeling: Develops machine learning models to predict injury risks

based on athlete characteristics, training factors, biomechanical parameters, and
injury histories.
• Decision Support Module:
o This module provides decision support tools and recommendations for coaches and
sports medicine professionals based on the insights generated from data analysis.
o Submodules:
o Injury Risk Assessment: Calculates and communicates injury risk assessments for
individual athletes, highlighting those at higher risk of specific injuries.
o Training Program Optimization: Recommends adjustments to athletes' training

programs based on predictive model outputs, biomechanical analysis, and injury
risk assessments.
• Intervention Module:
o This module facilitates the implementation of targeted interventions and preventive

measures to mitigate injury risks and optimize athlete performance.
o Submodules:
o Individualized Interventions: Recommends personalized interventions, such as

strength and conditioning exercises, neuromuscular training, and flexibility
programs, based on athletes' injury risk profiles and training needs.
o Telemedicine and Remote Monitoring: Enables remote consultations, injury

assessments, and rehabilitation programs through telemedicine platforms,
enhancing accessibility to healthcare services for athletes.
• Data Storage and Management Module:
o This module manages the storage, organization, and security of athlete data,
ensuring data integrity, accessibility, and compliance with privacy regulations.
o Submodules:
o Centralized Data Repository: Stores athlete data, including biomechanical data,

EHR records, injury histories, and predictive model outputs, in a centralized
database.
o Data Security and Privacy Controls: Implements security measures and privacy
controls to protect athlete confidentiality, comply with data protection regulations.
• User Interface Module:
o This module provides user-friendly interfaces for athletes, coaches, and sports
medicine professionals to interact with the system, view insights, and communicate
with each other.
o Submodules:
o Athlete Portal: Offers athletes a personalized portal where they can access injury
risk assessments, training recommendations, rehabilitation plans, and communicate
with coaches and clinicians.
o Coach and Clinician Dashboard: Provides coaches and sports medicine

professionals with a dashboard for monitoring athlete health status, injury risks,
training progress, and communicating with athletes to provide guidance and
support.
These modules work together cohesively to enable a proactive, data-driven approach to sports
injury management in track and field athletics, facilitating optimized athlete performance, well-
being, and long-term athletic development.
CHAPTER 6
SYSTEM DESIGN
6.1Requirement Analysis
Before diving into the system design, it's crucial to conduct a thorough requirement analysis to
ensure that the proposed system meets the needs and expectations of its users. Here's a breakdown
of the requirement analysis process for the system designed to manage sports injuries in track and
field athletics:
• Stakeholder Identification:
o Identify the stakeholders involved in the system, including athletes, coaches, sports
medicine professionals, administrators, and IT personnel.
o Understand the roles, responsibilities, and expectations of each stakeholder group

regarding injury management and athlete care.
• Functional Requirements:
o Define the core functionalities the system must support to effectively manage sports
injuries in track and field athletics. This may include:
o Data collection from wearable sensors and electronic health records.
o Real-time data processing and analysis for injury risk assessment.
o Predictive modeling to identify injury risks and patterns.

o Decision support tools for coaches and sports medicine professionals.
o Individualized interventions and preventive measures.
o Telemedicine and remote monitoring capabilities.
o Data storage, management, and security measures.
o User interfaces for athletes, coaches, and clinicians.
• Non-functional Requirements:
o Specify the non-functional aspects of the system that are critical for its success,
including:
o Performance requirements: Response time, throughput, and scalability.
o Reliability and availability: System uptime, fault tolerance, and disaster recovery.
o Security and privacy: Data encryption, access control, and compliance with
regulations (e.g., HIPAA).
o Usability: Intuitiveness, accessibility, and user experience of the system interfaces.
o Interoperability: Integration with existing systems, standards, and protocols.
o Maintainability: Ease of system maintenance, updates, and enhancements.
• Use Cases and User Stories:
o Develop detailed use cases and user stories to capture the specific interactions and
workflows within the system. This involves describing:
o User goals and objectives for using the system.
o Step-by-step interactions between users and the system to achieve those goals.
o Preconditions, postconditions, and alternate flows for each use case.
• Data Requirements:
o Identify the types of data needed for injury management, including:
o Biomechanical data collected from wearable sensors.
o Electronic health records containing athlete health information and injury records.
o Training logs, performance metrics, and athlete feedback.
o Define data attributes, formats, sources, and storage requirements.
• Regulatory and Ethical Considerations:
o Address regulatory requirements and ethical considerations related to data privacy,

consent, and security. Ensure compliance with relevant regulations (e.g., GDPR,
HIPAA) and ethical guidelines governing athlete care and data handling.
• System Constraints:
o Identify any constraints or limitations that may impact system design and
implementation, such as:
o Budgetary constraints: Available resources for system development, deployment,

and maintenance.
o Technology constraints: Compatibility with existing infrastructure, hardware, and

software platforms.
o Time constraints: Project timelines, milestones, and deadlines for system delivery.
• Feedback and Validation:
o Seek feedback from stakeholders to validate the requirements and ensure alignment
with their needs and expectations.
6.2 Development model
The development model followed in this project is waterfall model. The water fall model is a
sequential software development process, in which progress is seen as flowing steadily
downwards (like a waterfall) through the phases of conceptualization, initiation, design
(validation), construction, testing and maintenance.
To follow the waterfall model, one proceeds from one phase to next in purely sequential manner.
For example, one first completes requirements specifications, which are set in stone. When the
requirements are fully completed, one proceeds to design. The software in question is designed
and a blueprint is drawn for implementers (coders) to follow this design should be a plan for
implementing the requirements given. When the design is fully completed, an implementation of
that design is made by coders. Towards the later stages of this implantation phase, separate
software components produced are combined to introduce new functionality and reduce risk
through the removal of errors.
Thus the waterfall model maintains that one should move phase only when it’s proceeding phase
is completed and perfected. In original waterfall model, the following phases followed in order:
 Requirement specification
 Design
 Construction
 Integration
 Testing and debugging
 Installation
 Maintenance
The two main reasons to choosing waterfall model as a development model are:
 Its simplicity, entire project can be broken down into small activities.
 Verification steps required by waterfall model ensure that a task is error free, before other
tasks that are dependent on it are developed.
Figure 6.1 Waterfall model
6.2 Data Flow Diagram
A data flow diagram (DFD) is a graphical representation of the flow of data through a system. It
shows how data moves between different processes, data stores, and external entities.
Figure 6.1: dataflow diagram
6.3 Use case Diagram
Figure 6.2: Use case diagram
CHAPTER 7
CODING
App.py
import streamlit as st
import pandas as pd
import joblib
import os
from PIL import Image
# Load the saved model
model = joblib.load('xgboost_model.pkl')
st.title("COMMON SPORTS INJURIES OF TRACK AND FIELD ATHLETES USING MACHINE

LEARNING")
st.image("coverpage.png")
def make_prediction(features):
columns = [
'nr. rest days', 'nr. strength trainings.1', 'nr. strength trainings',
'nr. tough sessions (effort in Z5, T1 or T2)', 'nr. tough sessions (effort in Z5, T1 or T2).2',
'Date', 'nr. tough sessions (effort in Z5, T1 or T2).1', 'total hours alternative training',
'nr. rest days.1', 'nr. days with interval session.1'
input_data = pd.DataFrame([features], columns=columns)
prediction = model.predict(input_data)
return 'Injury' if prediction[0] == 1 else 'No Injury'
def main():
# Description of the website
st.markdown("""
## Welcome to the COMMON SPORTS INJURIES OF TRACK AND FIELD ATHLETES

USING MACHINE LEARNING Prediction System
This application allows users to predict the likelihood of injury based on various input features
related to training sessions and rest days.
By leveraging advanced machine learning techniques, this system can provide insights into
potential injury risks and help users adjust their training routines accordingly.
**Features:**
- User login for secure access.
- Easy input of training data.
- Instant injury risk prediction.
- Detailed results display.
The prediction model is built using the XGBoost algorithm, which is known for its high
performance and accuracy in classification tasks. The model has been trained on a comprehensive
dataset of training activities, ensuring reliable predictions.
This tool aims to assist athletes, coaches, and fitness enthusiasts in making data-driven decisions to
prevent injuries and enhance performance. By understanding the impact of training intensity, rest
days, and other factors on injury risk, users can optimize their training plans to minimize risks and
maximize results.
We value your feedback and suggestions. Please feel free to reach out to us with any comments or
questions.
**Stay safe and train smart!**
**Contact Us:**
- Email: [email protected]
- Phone: +1 234 567 890
Thank you for using the Injury Prediction System.
""")
# User login
if 'logged_in' not in st.session_state:
st.session_state.logged_in = False
if st.session_state.logged_in:
st.write("Welcome! You are logged in.")
# Input fields for the prediction
nr_rest_days = st.number_input('Number of rest days', min_value=0)
nr_strength_trainings_1 = st.number_input('Number of strength trainings.1', min_value=0)
nr_strength_trainings = st.number_input('Number of strength trainings', min_value=0)
nr_tough_sessions_1 = st.number_input('Number of tough sessions (effort in Z5, T1 or T2)',

min_value=0)
nr_tough_sessions_2 = st.number_input('Number of tough sessions (effort in Z5, T1 or T2).2',

min_value=0)
date = st.number_input('Date', min_value=0)
nr_tough_sessions_3 = st.number_input('Number of tough sessions (effort in Z5, T1 or T2).1',

min_value=0)
total_hours_alt_training = st.number_input('Total hours alternative training', min_value=0)
nr_rest_days_1 = st.number_input('Number of rest days.1', min_value=0)
nr_days_interval_sessions = st.number_input('Number of days with interval session.1',

min_value=0)
features = [
nr_rest_days, nr_strength_trainings_1, nr_strength_trainings,
nr_tough_sessions_1, nr_tough_sessions_2, date, nr_tough_sessions_3,
total_hours_alt_training, nr_rest_days_1, nr_days_interval_sessions
if st.button('Predict'):
prediction = make_prediction(features)
if prediction == 'Injury':
st.markdown(f"<h1 style='color:red;'>{prediction}</h1>", unsafe_allow_html=True)
else:
st.markdown(f"<h1 style='color:green;'>{prediction}</h1>", unsafe_allow_html=True)
if st.button("View Plots"):
image_directory = "Images"
if os.path.exists(image_directory):
image_files = [f for f in os.listdir(image_directory) if f.endswith('.png')]
if image_files:
st.write("Plots:")
for image_file in image_files:
image_path = os.path.join(image_directory, image_file)
image = Image.open(image_path)
st.image(image, caption=image_file)
else:
st.write("No plots found in the 'Images' directory.")

else:
st.write("The 'Images' directory does not exist.")
else:
username = st.text_input('Username')
password = st.text_input('Password', type='password')
if st.button('Login'):
if username == 'admin' and password == 'password': # Simplified for demonstration
st.session_state.logged_in = True
st.success('Login successful')
else:
st.error('Invalid username or password')
# HTML Footer
st.markdown("""
<footer style="position: fixed; bottom: 0; width: 100%; background-color: #f1f1f1; text-align:

center; padding: 10px;">
<p>© 2024 Injury Prediction System. All rights reserved.</p>
</footer>
""", unsafe_allow_html=True)
if __name__ == '__main__':
main()
Train.py
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report
from imblearn.over_sampling import SMOTE
from xgboost import XGBClassifier
from sklearn import metrics
import joblib
# Load dataset
df = pd.read_csv("top_10_features_dataset.csv")
# Define feature and target variables
X = df.drop(['injury'], axis=1)
Y = df['injury']
# Split the data into training and testing sets
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, stratify=Y,

random_state=0)
# Oversample the training data using SMOTE
sm = SMOTE(random_state=0)
X_train, Y_train = sm.fit_resample(X_train, Y_train)
# Train the XGBoost model
boost = XGBClassifier(max_depth=2, n_estimators=30, random_state=0)
boost.fit(X_train, Y_train)
# Save the model
joblib.dump(boost, 'xgboost_model.pkl')
# Predict the test set results
Y_pred = boost.predict(X_test)
# Print the confusion matrix, classification report, and accuracy
print(confusion_matrix(Y_test, Y_pred))
print(classification_report(Y_test, Y_pred))
print(f"Accuracy: {accuracy_score(Y_test, Y_pred)}")
Predict.py
import numpy as np
import pandas as pd
import joblib
# Load the saved model
model = joblib.load('xgboost_model.pkl')
def predict_injury(features):
# Convert features to a DataFrame
columns = [
'nr. rest days', 'nr. strength trainings.1', 'nr. strength trainings',
'nr. tough sessions (effort in Z5, T1 or T2)', 'nr. tough sessions (effort in Z5, T1 or T2).2',
'Date', 'nr. tough sessions (effort in Z5, T1 or T2).1', 'total hours alternative training',
'nr. rest days.1', 'nr. days with interval session.1'
input_data = pd.DataFrame([features], columns=columns)

# Predict using the loaded model
prediction = model.predict(input_data)
return 'Injury' if prediction[0] == 1 else 'No Injury'
# Example usage
if __name__ == '__main__':
# Define example features
example_features = [
1.0, 1.0, 1.0, 2.0, 2.0, 1200, 1.0, 1.5, 1.0, 2.0
result = predict_injury(example_features)
print(f'Prediction: {result}')
LoadDB.py
import pandas as pd
import sqlite3
class CSVToSQLite:
def __init__(self, db_name='SportsInjuries.db'):
self.db_name = db_name
def upload_csv(self, file_path):
try:
df = pd.read_csv(file_path)
print("Preview of the CSV file:")
print(df.head())
table_name = input("Enter the table name to save the data: ")
self.save_to_db(df, table_name)
except Exception as e:
print(f"An error occurred: {e}")
def save_to_db(self, df, table_name):

try:
conn = sqlite3.connect(self.db_name)
df.to_sql(table_name, conn, if_exists='replace', index=False)
conn.close()
print(f"Data saved to table '{table_name}' in the database '{self.db_name}'")
except Exception as e:
print(f"An error occurred while saving to the database: {e}")
if __name__ == "__main__":
csv_to_sqlite = CSVToSQLite()
file_path = "balanced_train_dataset.csv"
csv_to_sqlite.upload_csv(file_path)
CHAPTER 8
SYSTEM TESTING
The aim of overall testing is to identity the errors or problems that is being raised it is raised at
every stage when an individual program is composed, these composed components must meet up
the user requirements in the overall approach, and must ensure that the system must not behave
in the unexpected way, test data are those where the input is considered and tested with it, and
the test cases are those which probably of these operates on system specifications, the system
made available they will ensure Test data are inputs which have been detect the behavior within
it during the failure modes within the software is kindly generally not feasible because of the
process of software testing , multiple inputs are taken and each test data are considered and they
are verified, and rather test cases are written for both successful ones as well as failure ones and
generally most feasible data is taken, the overall software testing is taken into those considering
within the both of the process in which they need to satisfy both of the process verification and
validation.
Can be objects, variables, functions or any other multiple modules. during the process of system
testing the overall composed components are to be integrated to form one complete system,
hence testing must be done in such a way that they meet all the functional specification as the
system requirements must meet up the user requirements in the overall approach, and must
ensure that the system must not behave in the unexpected way,test data are those where the input
is considered and tested with it, and the test cases are those which probably of these operates on
system specifications, the system made available they will ensure Test data are inputs which
have been detect the behavior within it during the failure modes within the software is kindly
generally not feasible because of the process of software testing , multiple inputs are taken and
each test data are considered and they are verified, and rather test cases are written for both
successful ones as well as failure ones and generally most feasible data is taken, the overall
software testing is taken into those considering within the both of the process in which they need
to satisfy both of the process verification and validation.
 Verification: Verification is done with the help of specified document, It verifies that the
software those are being developed and simultaneously implemented specific functions in
order to design the document.
 Validation: Validation has to be done in order to verify that they must satisfy the process of
the software requirement specification document, this software which is developed which can
be implemented specified simultaneously.
8.1 TESTING PROCESS
The testing process is a vital process within a single monolithic unit, these must not be tested
which is again a testing process which is processed throughout the simple components and then
they are integrated to one full system into one system. The testing process is done step by step
and carried out in increment fashion by incrementing the sequence, these are the steps with
implementation part, where the error programs may be within the lighter stage if in case of errors
is checked and corrected as they must meet all the needs of the functional requirements. This
helps the overall process of testing category in this way they are helpful.
8.1.1 AIM OF TESTING
The overall purpose of testing is to discover the errors, it is the process of identifying the errors
in prepared components this is the overall process which is trying to serve within the conceiving
fault or weakening the working product, it is to check the functions of the components available
within the sub assemblies in a finished products, it has to check the available functions with
conceivable fault as well as weakening and checks the available assemblies within the finished
products it is to exercise the software with the intention that the software of ensuring the
requirements with that of the user required the values with those meeting the requirements,
which falls or fail within the user requirements and do not fail in any unacceptable manner, there
are many types of test, each and every test have their own specific testing requirement.
8.2 UNIT TESTING
Unit testing is all that which usually involves in maintaining multiple designs within those of the
available test cases within those of the available programming language which has many
functional property, which has many input which is valid throughout the available inputs, all the
branches within the internal codes there are many flow which is validated these testing must be
done individually then all the test cases are then integrated and added to one system, then each
valid and invalid inputs are taken these are multiple branches, these testing are done using the
individual software units within the applications, which can rely on the available knowledge in
the construction and is important, unit testing performing basic test at components level and
within the specific business processes, applications within the system configurations, within that
of unit testing where all the documents are verified with the available process that performs the
documents, that contains that clearly about the used inputs as well as the expected results.
8.3 INTEGRATION TESTING
The integration of the tests are designed to those of the software components to determine
carefully the individual components of the code and to check the main software after validating
all the validated components are integrated to one complete system and then they are finalized,
testing is the events that is used to determine the programs it is more concerned with the basic
screens that has multiple outcomes of the fields and screens then integrating it with the software
associated with those of running of those programs, and the function is event driven and the
components are tested and aimed to correct the exposed problems and to maintain the
consistency.
8.4 FUNCTIONAL TESTING
The functional testing is the vital process where every single functions is tested which has too
many systematic demonstrations that are functioned and tested which is made available that
looks into all technical requirements within the overall documentation and these are user
manuals which is considered for many aspects such as user manuals and technical requirements.
Testing is allocated on the following steps:

Validity : classification of valid input must be accepted.
Not accepted : classification of invalid input must be rejected.
Allocations : classification functions must be exercised.
Outsourcing :classifying the outputs must be exercised.
Procedure structures: classifying the procedures must be invoked.
The overall functions of those testing is then focused testing within key functions or special test
cases these in addition are the coverage pertaining to identify the business process that must be
considered in the testing, these functions are then complete which can have additional tests this
is in turn identified within the data fields that can have successive process which is considered
and then they are complete with that of the additional testing which can be identified and that of
the effectiveness in obtaining the values, fields and some complete additional tests which can
have effective values of those input test validated and determined. which gives the confidence on
the new systems which ensures that the system works effectively and efficiently, just according
to the user windows. There is that existing long time process which has an overall proposed
system which is developed within applet window which is caused by a long time process where
the transmissions but the system developed that has a user friendly tool that has a menu based
interface for the graphical user interface as well. Coding as well as testing is analysed to being
within the installation on the necessary system.
8.5 SYSTEM TESTING
The system testing usually ensures in the entire integration which meets the software
requirements, that usually are known and then they are predictable results, an example of the
system testing which is oriented within these system that is based on the description as well as
flows that emphasize the process links and the integration points.
 WHITE BOX TESTING
The white box testing in which the software testing has knowledgeable within the inner
workings, software tester which is structure and within the language structure and also used to
test the areas which cannot be reached from a black box levels.
 BLACK BOX TESTING
The black box is tested without any prior knowledge within the inner workings of the
structure or the language of those modules being tested within the black box tests that are if
many kinds, within the written source of documents which is tested, that the software
documents, responds to the output without considering the software.
System Test Cases
Test cases are used to test the pair of data to the program sets and to verify if at all the users are
getting the desired output, it is usually used to set a pair of data assets for each of the available
variables, it has multiple sets of available data with two or more notions within any one of the
executions rather they are much more elaborated in this chapter, with various test cases and also
helps in generating test data and easily validation could be completed.
Those programs required as well as the tested data help them in constructing multiple test data,
execution of the test cases is little time consuming, but its an essential phase where the overall
phases has to change the functions within the scenario, usually the testers generate few test cases
and then they can try executing the program if in case if any of the code generate the errors these
can generally make use of the available program with these characters, usually used to set a pair
of data assets for each of the available variables, it has multiple sets of available data with two or
more notions within any one of the executions rather they are much more elaborated in this
chapter, with various test cases and also helps in generating test data and easily validation could
be completed.
Then the results are thus obtained, then the software testers usually discuss if there is any kind of
error generated and discussion is done are not, then the error correction will be done and then the
testers enter the debugging phase. Then the test cases are formally manipulated and developed
for the required system.
Table 6.1: Test case 1
Test Case 1
Name of Test Data upload

Input Image Upload
Expected output Image data uploaded successfully
As expected
Actual output
Result Successful
Table 6.2: Test case 2
Test Case 2
Name of Test Model creation
Input Image data given as an input
Expected output Model created successfully
Actual output As expected
Result Successful
Table 6. 3: Test case 3
Test Case 3
Name of Test Data prediction
Input Individual image given as an input
Expected output Data is predicted
Actual output Same as above
Result Successful
PHASE DESCRIPTION
Review Work Done Description
Review Analysis of the Analyzing the overall information from IEEE

1 project papers.
Review Literature Studying the literature survey about the
2 survey existing previous work that was done, this helps in
system new implementation.
Review Detailed Designing as well as then modeling the
3 Design design which is categorized.
Review Implementatio Implementing then those coding then the
4 n of the project integrating modules which integrates the
system and then sent to testing.
Review Testing phase Testing the overall component and validating
5 it and helps in satisfying the customer.
Review Thesis Prepare the thesis for implemented project
6 documenting with conclusion and future enhancement.
Figure 6.5 Phase description
CHAPTER 9
RESULTS
CONCLUSION AND FUTURE ENHANCEMENT
The proposed system for managing sports injuries in track and field athletics represents a
significant advancement in athlete care and injury prevention. By leveraging advanced technology,
data analytics, and evidence-based interventions, the system offers a proactive, data-driven
approach to optimize athlete performance, well-being, and long-term athletic development while
minimizing injury risks and healthcare costs.
Through thorough requirement analysis, we have identified the needs and expectations of
stakeholders, defined functional and non-functional requirements, and established a clear roadmap
for system design and implementation. The system architecture encompasses modules for data
collection, processing, analysis, decision support, intervention, data storage, management, and user
interface, ensuring a comprehensive and integrated approach to injury management.
Key advantages of the proposed system include proactive injury prevention, individualized athlete
care, data-driven decision-making, efficient resource utilization, and enhanced accessibility to
healthcare services through telemedicine and remote monitoring. Ethical considerations and
privacy protections are prioritized to maintain athlete confidentiality and comply with regulatory
requirements.
Future Enhancements:
While the proposed system lays a solid foundation for managing sports injuries in track and field
athletics, there are several opportunities for future enhancements and advancements:
 Integration of Biomechanical Feedback: Enhance the system by integrating real-time

biomechanical feedback during training and competition to provide athletes and coaches
with immediate insights into movement patterns and technique adjustments.
 Enhanced Predictive Modeling: Continuously improve predictive models by incorporating

additional data sources, refining algorithms, and enhancing accuracy in identifying injury
risks and patterns.
 Expanded Telemedicine Services: Expand telemedicine capabilities to include additional

services such as virtual physiotherapy sessions, mental health support, and nutritional
counseling to address holistic athlete care needs.
 Longitudinal Data Analysis: Implement longitudinal data analysis techniques to track

injury trends, monitor athlete progress over time, and identify factors contributing to long-
term health and performance outcomes.
 Integration with Wearable Technologies: Integrate with emerging wearable technologies,

such as smart clothing and implantable sensors, to capture a wider range of biomechanical
and physiological data for injury prevention and performance optimization.
 Collaborative Research Initiatives: Foster collaborations with research institutions, sports

organizations, and technology partners to conduct studies, validate predictive models, and
advance knowledge in sports injury prevention and athlete care.
 Enhanced User Experience: Continuously improve the user experience of the system
interfaces by incorporating user feedback, implementing usability testing, and adopting
best practices in user interface design.
By embracing these future enhancements, the proposed system can evolve into a dynamic and
innovative platform that not only optimizes athlete health and performance but also contributes to
the advancement of sports science and injury prevention practices in track and field athletics and
beyond.
REFERENCES
1. Lopes AD, Hespanhol Junior LC, Yeung SS, Costa LO. Epidemiology of Injuries in Track
and Field: A Literature Review. Physical Therapy in Sport. 2012;13(3):104-111. [DOI:
10.1016/j.ptsp.2012.01.003]
2. Junge A, Cheung K, Edwards T, Dvorak J. Injury Patterns in Selected High School Sports: A
Review of the 1995-1997 Seasons. Journal of Athletic Training. 2007;42(2):197-204. [DOI:
10.1016/s0002-1319(07)60248-1]
3. Hootman JM, Dick R, Agel J. Injury Patterns in Division I Collegiate Athletics. Journal of
Athletic Training. 2007;42(2):210-217. [DOI: 10.1016/s0002-1319(07)60250-x]
4. Van Mechelen W. Risk Factors for Lower Extremity Injury: A Review of the Literature.
British Journal of Sports Medicine. 1997;31(1):11-18. [DOI: 10.1136/bjsm.31.1.11]
5. Hreljac A. Prevention of Running Injuries: A Narrative Review. Physical Medicine and

Rehabilitation Clinics of North America. 2005;16(3):709-729. [DOI:
10.1016/j.pmr.2005.02.002]
6. Faulkner RA, Davison MJ, Bailey DM. The Physiology of Training: Advances in Sport and
Exercise Science Series. Churchill Livingstone. 2004.
7. Foster C, Snyder AC, Thompson NN, Green MA, Foley M, Schrager M. Effect of Baseline
Training Status on the Ergogenic Response to Long Duration Endurance Training.
International Journal of Sports Medicine. 1993;14(1):36-42. [DOI: 10.1055/s-2007-1021192]
8. Meeusen R, Duclos M, Foster C, Fry A, Gleeson M, Nieman D, Raglin J, Rietjens G,

Steinacker J, Urhausen A. Prevention, Diagnosis, and Treatment of the Overtraining
Syndrome: Joint Consensus Statement of the European College of Sport Science and the
American College of Sports Medicine. Medicine & Science in Sports & Exercise.
2013;45(1):186-205. [DOI: 10.1249/mss.0b013e318279a10a]
9. McArdle WD, Katch FI, Katch VL. Exercise Physiology: Nutrition, Energy, and Human
Performance. Lippincott Williams & Wilkins. 2010.
10. American College of Sports Medicine. ACSM's Guidelines for Exercise Testing and
Prescription. Lippincott Williams & Wilkins. 2013.

Report

Uploaded by

Copyright:

Available Formats

Report

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Report

Uploaded by

Copyright:

Available Formats

PROJECT REPORT

Submitted in the partial fulfillment of the requirement for the award

Yogesh Chavan 20211CSG0054

Himanshu Choudary : 20211CSG0023

Under the guidance of

Dr. Chandrasekar Vadivelra

Sl No Chapter Name Page No

6 SYSTEM DESIGN 25-30

6.3 Data Flow Diagram

6.4 Use Case Diagram

6.5 Sequence Diagram

8.1 Testing Methods

8.2 Unit Testing

8.3 Integration Testing

8.4 Functional Testing

8.5 System Testing

CONCLUSION AND FUTURE

Sl No Figure Name Page No

6.1 dataflow diagram 17

6.2 Use case diagram 18

The key objectives of this project are as follows:

 Data Collection and Preprocessing: We will gather a comprehensive dataset encompassing

1. Title: "Epidemiology of Injuries in Track and Field: A Literature Review"

3. Title: "Injury Patterns in Division I Collegiate Athletics"

5. Title: "Prevention of Running Injuries: A Narrative Review"

 Subjectivity in Injury Management: Decision-making regarding injury management may

 Underutilization of Technology: While technology has advanced significantly in recent

 Real-time Monitoring and Biomechanical Analysis: Implement wearable sensors and

 Individualized Training Programs: Develop individualized training programs tailored to

 Preventive Interventions and Education: Implement evidence-based preventive

 Continuous Monitoring and Feedback Loop: Establish a continuous monitoring system

 Integration of Technology and Telemedicine: Leverage telemedicine and remote

 Data-driven Decision Support System: Develop a comprehensive data management and

4.1 Advantages of proposed system

 Proactive Injury Prevention: By leveraging predictive modeling and real-time

 Individualized Approach: The proposed system emphasizes individualized injury

 Data-driven Decision Making: The integration of advanced analytics and data

 Continuous Monitoring and Feedback: The proposed system incorporates a continuous

 Remote Accessibility and Telemedicine: Utilizing telemedicine and remote monitoring

 Efficient Resource Utilization: By prioritizing proactive injury prevention strategies and

 Ethical Considerations and Privacy Protections: The proposed system emphasizes

4.2 System Architecture

Figure 4.1: System architecture

• Data Collection Layer:

• Data Processing and Analysis Layer:

• Decision Support Layer:

• Intervention and Communication Layer:

• Data Storage and Management Layer:

• User Interface Layer:

• Data Collection Module:

o Wearable Sensor Data Collection: Collects biomechanical data from wearable

o Electronic Health Records Integration: Retrieves athlete health information, injury

• Data Processing and Analysis Module:

o Real-time Data Processing: Processes biomechanical data in real-time to extract

o Predictive Modeling: Develops machine learning models to predict injury risks

• Decision Support Module:

o Training Program Optimization: Recommends adjustments to athletes' training

o This module facilitates the implementation of targeted interventions and preventive

o Individualized Interventions: Recommends personalized interventions, such as

o Telemedicine and Remote Monitoring: Enables remote consultations, injury

Stay safe and train smart!