CHAPTER 1

INTRODUCTION

1.1 Introduction:
This project is medical field related. When we are facing the problems therefore, we need
some type of remedies like mixture of milk and turmeric, ginger tea, and also recommend
allopathy medicine like paracetamol for fever, cetirizine for cough, we recommend cough
syrup. With the help of this project, we can find solution for minor and major disease like
cold, fever and cough, etc.
This project presents a Medicine Recommendation System (MRS) designed to provide
tailored medication suggestions based on patient symptoms and medical history.
The MRS processes user symptoms through an interactive interface, extracting key features
and categorizing them into relevant medical conditions.
In an era where technology and healthcare are increasingly intertwined, the demand for
efficient and personalized medical solutions is at an all-time high. As the complexity of
medical knowledge expands, healthcare providers face challenges in keeping up with the vast
array of medications and treatment options available. To address these challenges, we propose
the development of a Medicine Recommendation System (MRS) using Python, aimed at
enhancing the decision-making process for both healthcare professionals and patients.
The MRS is designed to provide intelligent, data-driven medication suggestions based on
individual symptoms and medical histories. By leveraging advanced techniques in data
analysis and machine learning, the system can analyze user inputs and correlate them with a
comprehensive database of medications, thereby facilitating personalized healthcare solutions.
The system employs natural language processing (NLP) to interpret user-reported symptoms,
allowing for a user-friendly interaction that ensures accessibility for individuals without
medical training. Additionally, the integration of collaborative filtering and rule-based
approaches enables the MRS to recommend effective treatments while prioritizing patient
safety and adherence to established medical guidelines.
As we embark on this project, our goal is to develop a robust tool that not only streamlines the
medication recommendation process but also empowers users with the knowledge they need
to make informed health decisions. By improving the efficiency and accuracy of treatment
suggestions, we aim to enhance patient outcomes and contribute to the ongoing evolution of
healthcare technology.

1
1.2 Existing System:
The architecture of the Medicine Recommendation System (MRS) is designed to ensure
modularity, scalability, and ease of use. The following components outline the key elements
of the system:
1.2.1 User Interface (UI)
 Web/Mobile Application: A user-friendly interface where patients or healthcare
providers can input symptoms and medical history. This component will support both
web and mobile platforms to maximize accessibility.
 Input Fields: Options for users to enter symptoms, medical history, and any relevant
personal information.
1.2.2 Data Processing Layer
 Natural Language Processing (NLP) Module:
Analysis user input to extract symptoms and categorize them into medical conditions.
Libraries such as NLTK or SpaCy can be utilized for this purpose.
 Data Validation: Ensures that the input data is valid and adheres to expected formats.
1.2.3 Recommendation Engine
 Symptom-Disease Mapping:
A pre-defined database that maps symptoms to potential medical conditions. This can
be a static dataset or dynamically updated.
 Medication Database:
A comprehensive database of medications, including their indications,
contraindications, dosages, and side effects.
 Recommendation Algorithms:
Collaborative Filtering: Suggests medications based on similar cases or historical user
data.
Rule-Based Logic: Applies medical guidelines to ensure that recommendations are
safe and appropriate.
1.2.4 Backend Server:
Framework: Utilizes a web framework such as Flask or Django to handle requests and
responses between the UI and the recommendation engine.
1.2.5 Analytics and Reporting:
 Usage Tracking: Collects data on user interactions and recommendations provided,
enabling continuous improvement of the system.

2
  Performance Metrics: Evaluates the accuracy and effectiveness of recommendations,
which can be used to refine the algorithms.

1.3 Objectives:
1. User-Centric Design:
Develop an intuitive and user-friendly interface that allows patients and healthcare providers
to easily input symptoms and retrieve medication recommendations.
2. Accurate Symptom Analysis:
Implement Natural Language Processing (NLP) techniques to accurately analyze and interpret
user-reported symptoms, ensuring precise mapping to medical conditions.
3. Comprehensive Medication Database:
Build and maintain a robust database of medications, including detailed information on
indications, dosages, side effects, and contraindications to facilitate informed
recommendations.
4. Personalized Recommendations:
Utilize advanced recommendation algorithms, including collaborative filtering and rule-based
logic, to provide tailored medication suggestions based on individual patient profiles and
historical data.
5. Safety and Compliance:
Integrate medical guidelines and best practices into the recommendation engine to ensure that
all suggested treatments prioritize patient safety and adhere to established healthcare
standards.
6. Performance Tracking and Improvement:
Establish metrics for tracking the accuracy and effectiveness of recommendations, allowing
for continuous refinement and enhancement of the system based on user feedback and
outcomes.
These objectives aim to ensure that the Medicine Recommendation System is effective,
reliable, and valuable for enhancing patient care and supporting healthcare providers.

1.4 Scop of work:

The Medicine Recommendation System (MRS) aims to assist healthcare professionals (such
as doctors, pharmacists, and healthcare providers) in making personalized, evidence-based
medicine recommendations for patients. It integrates patient data, medical history, drug

3
information, and external knowledge sources to suggest the most appropriate treatments and
ensure safety through drug interaction checks.
The scope of work outlines the key deliverables, functional boundaries, and responsibilities
involved in the development and deployment of the MRS.
The scope of work outlines the essential functionalities, security standards, and technical
specifications necessary for developing a comprehensive Medicine Recommendation System
that helps healthcare professionals recommend safe and effective treatments for patients while
ensuring high system performance, security, and scalability.

1.5 Operating Environment:

1.5.1 Hardware Specifications:
The system has minimal Hardware interfaces. A normal personal desktop or a laptop will be a
good choice to run the system. It is recommended for the system to have higher ram and
processing power in order to compute and predict quickly.
 RAM: Minimum 4 GB better performance
 Smartphones or tablets with a modern operating system (iOS or Android)
1.5.2 Software Specification:
To apply machine learning i.e. Neural Networks a library known as Tensor Flow must be
imported in python. in addition, another similar library known as Keras is also imported for
supporting machine learning algorithms. Other supporting libs are Pandas, NumPy, Skit-learn
etc. library known as matplotlib is used to plot the data into graphical form. PyCharm or
Jupyter Notebook is used to run the algorithms.
 Server: Windows Server, or any cloud-based operating system (AWS, Azure, etc.)

1.6 Description of technology used:

The Medicine Recommendation System (MRS) leverages a combination of modern
technologies to provide accurate, efficient, and secure medicine recommendations based on
patient data. The system integrates various software components to facilitate user interaction,
data processing, and seamless communication with external services like medical databases
and hospital management systems. Below is a detailed description of the technologies used in
the system.
1.6.1 Frontend Technologies:

4
The frontend is responsible for providing an intuitive and responsive user interface (UI) for
healthcare professionals and patients.

 Bootstrap:
Both Bootstrap are UI libraries used to ensure the interface is responsive, modern, and
easy to navigate across different devices.
1.6.2. Backend Technologies
The backend of the system processes the logic for medicine recommendations, drug
interaction checks, patient data management, and integration with external services.
 Python with Flask:
As an alternative backend solution, Python is widely used for its rich ecosystem of
libraries and ease of integration with machine learning algorithms and data analysis
tools.
1.6.3 Recommendation Engine Technologies:
The recommendation engine is the heart of the system, providing personalized medicine
suggestions based on patient data and medical history.
 Machine Learning (ML) Models:
If the system is built with AI-based recommendation capabilities, machine learning
algorithms are used to predict the best medications based on historical data, patient
profiles, and conditions.

5
 CHAPTER 2
LITERATURE REVIEW
Recommender systems aim to provide users with personalized products and service to deal
with the increasing online information overload problem. Various recommender system
techniques have been proposed since the mid- 1990s, and many sorts of recommender system
software have been developed recently for a variety of applications. Most of the recommender
technologies are applied to the e- government area, e-business area, e-commerce/shopping
area, eLearning area, e-tourism area and so on. However, medicine area includes rare
recommender technologies, and this will focus on the design of the medicine recommender
system and mining knowledge from medical case data commonly used recommendation
techniques include collaborative filtering (CF), content-based (CB), knowledge-based (KB)
techniques and hybrid recommendation technologies. Each recommendation technology has
advantages and limitations: CB mainly generates recommendations by using traditional
retrieval Methods and machine learning methods, but CB has overspecialized
recommendations; Collaborative filtering (CF)- based recommendation techniques help
people to make choices based on the opinions of other people who share similar interests,
while CF has sparseness, scalability and cold-start problems.

2.1 Knowledge-based recommendation:

Knowledge-based (KB) recommendation offers items to users based on knowledge about the
users, items and/or their relationships. Usually, KB recommendations retain a functional
knowledge base that describes how a particular item meets a specific user's need. To achieve
higher performance and overcome the drawbacks of traditional recommendation techniques, a
hybrid recommendation technique that combines the best features of two or more
recommendation techniques into one hybrid technique has been proposed. When it comes to a
new application area, a new recommendation framework is necessary to solve this problem.
Intelligent medical diagnosis has got more and more concern. Some selected techniques for
data mining in medicine are discussed in.

2.2 Data mining:

6
Data mining technology has been used to predict heart disease, and to diagnosis thyroid
diseases. The workshop on health search and discovery Discusses several challenges and
important topics about search and discovery in the medical domain, indicating that
information retrieval, personalization, expertise modelling, data mining and privacy
preservation are critical to enable advances in health and discovery. These approaches do
solve some problems in medical diagnosis and apply new data driven technologies to the
medical field. However, there does not exist a universal model which can 14 works well for
all the data and conditions. When faced with different data and application scenarios, it is
necessary to build a different model and conduct data analysis. In this paper, we introduce a
universal medicine recommender system framework that is designed and implemented to
apply data mining technologies to the recommender system that use the potential knowledge
We investigate the medicine recommendation algorithms of the SVM (Support Vector
Machine), BP neural network algorithm and ID3 decision tree algorithm based on the
diagnosis data. Finally, SVM is selected for the medicine recommendation model for its high
accuracy, good efficiency and scalability.

7
 CHAPTER 3
PROPOSED SYSTEM/ METHODOLOGY
A Personalized Medicine Recommendation System (PMRS) aims to provide individualized
treatment recommendations by analysing diverse patient data, including genetic information,
medical history, lifestyle factors, and demographic characteristics. This section describes a
detailed methodology for developing a PMRS that integrates various data processing,
machine learning, and recommendation techniques to create a robust and practical system.

3.1. User Requirement Specification:

The Medicine Recommendation System (MRS) is a digital application designed to
recommend appropriate medications based on the user’s health condition, symptoms, and
medical history. The system aims to provide personalized and safe medicine suggestions
while minimizing the risk of adverse effects or drug interactions. By leveraging AI algorithms
and integrating with trusted medical databases, the MRS will offer tailored medication
recommendations to users, both healthcare professionals and patients, in a user-friendly
interface.
The Medicine Recommendation System will:
 Provide a platform for users to input health-related data (e.g., symptoms, existing
conditions, allergies).
 Generate a list of recommended medications based on user input.
 Offer additional information such as dosage, side effects, drug interactions, and
possible alternatives.
 Allow users to access real-time, accurate medical data via integrated medical
databases (FDA, WHO, etc.).
 Help healthcare providers make informed decisions regarding medications based on
patient data.

3.2. Creation of Dataset:

8
Creating a dataset for a medicine recommendation system involves collecting structured data
that can be used to recommend appropriate medications based on various parameters such as
symptoms, medical conditions, patient demographics, and other factors. Here’s a step-by-step
guide to creating such a dataset
3.2.1. Define the Purpose of the System:
The first step is to define the goal of the recommendation system:
Symptom-based recommendations: Recommend medicine based on symptoms (e.g., fever,
headache, cough).
Disease-based recommendations: Recommend medicine based on specific conditions (e.g.,
diabetes, hypertension).
Personalized recommendations: Medicine suggestions based on patient’s demographics,
health history, and other factors.
3.2.2 Data Attributes:
The next step is to define the data attributes (features) that will be collected for each entry in
the dataset. These features can vary based on the type of recommendation system you are
developing.
 Medicine Information
Medicine Name: Name of the medicine (e.g., Paracetamol, Ibuprofen).
Drug Class: Class of the drug (e.g., analgesic, antibiotic, antihypertensive).
Dosage: Recommended dosage (e.g., 500mg, 1 tablet every 6 hours).
Side Effects: List of possible side effects (e.g., dizziness, nausea).
Contraindications: Conditions under which the medicine should not be used (e.g.,
pregnancy, liver disease).
Form: Dosage form (e.g., tablet, liquid, injection).
Price: Price of the medicine (useful for personalized recommendations).
Brand Names: Different brands under which the drug is marketed.
 Patient Demographics (for personalized recommendations)
Age: Patient age (e.g., child, adult, elderly).
Gender: Gender of the patient.
Weight: Patient weight, which could impact drug dosage.
Allergies: Any known allergies (e.g., penicillin).
Comorbidities: Presence of other diseases (e.g., diabetes, asthma).
Pregnancy: Whether the patient is pregnant.
Chronic Conditions: Conditions like hypertension, asthma, or heart disease.

9
  Symptoms
Symptom Name: Name of the symptom (e.g., fever, cough, headache).
Symptom Severity: Mild, moderate, severe.
Symptom Duration: How long the symptom has been present.
Symptom Onset: When the symptom started.
 Diagnosis or Disease
Disease Name: Disease or condition (e.g., flu, pneumonia, hypertension).
Disease Type: Whether the disease is acute or chronic.
Severity: Mild, moderate, or severe stage of the disease.
Complications: Any associated complications with the disease (e.g., kidney failure In
diabetes).
 Medical History
Previous Treatments: Any treatments used previously and their outcomes.
Medical Records: A structured record of past illnesses, surgeries, or treatments.
Lab Results: Relevant test results (e.g., blood sugar levels, liver function tests).
Family History: Family history of diseases (e.g., heart disease, cancer).
3.2.3. Data Sources:
The data for the dataset can be collected from various sources:
 Public databases: Some online medical databases and resources like the Drugs.com
database, MedlinePlus, and FDA Drug Database.
 Electronic Health Records (EHRs): If available, anonymized medical records from
healthcare systems.
 Clinical Trials: Data from clinical trials and research studies.
 Open Data Sets: There are open-source healthcare datasets available, such as the
MIMIC-III dataset, which contains medical records, though it requires careful
consideration of privacy and data anonymization.
 Manual Input from Healthcare Professionals: Doctors, pharmacists, or medical
researchers can help in the curation of the data based on their knowledge and
experience.
3.2.4. Data Structure:
The dataset can be structured in a tabular format (CSV, Excel) or a relational database format.
3.2.5. Data Collection and Cleansing:
 Data Collection: Collect data from multiple reliable sources, ensuring the data is up-
to-date and accurate.

10
  Data Anonymization: When using real patient data, ensure it is anonymized to
protect patient privacy.
 Data Cleansing: Remove any duplicates, missing values, or erroneous data points.
Handle outliers and inconsistencies.

Fig 1: Data Processing

3.2.6 Data Labelling:
If the dataset is to be used for machine learning purposes, you'll need to label the data to train
the recommendation system. For example, labelling medicines for a given symptom or
disease. This can be done based on medical literature, expert advice, or clinical guidelines.
3.2.7 Validation and Evaluation:
 Cross-validation: Split the dataset into training and testing sets to ensure the
recommendation system generalizes well.
 Expert Validation: Having medical experts validate the recommendations is crucial
to ensure clinical relevance and accuracy.

3.3 Pre-processing:
 Data preprocessing is essential to clean and standardize patient data, ensuring
consistency and quality. Key preprocessing steps include:
 Data Cleaning: Remove duplicate records, address missing data, and correct erroneous
entries. Missing values may be handled by techniques such as imputation, based on
average values or other statistical methods.
 Normalization and Scaling: Normalize numerical data (e.g., age, weight, blood
pressure) and scale it to a common range, enhancing compatibility across features.

11
  Text Processing (NLP): For unstructured text data, use natural language processing
(NLP) techniques to extract relevant information. Tokenization, named entity
recognition (NER), and sentiment analysis can identify specific medications,
symptoms, or other medical terms within clinical notes.
 Feature Engineering: Identify and create relevant features that are predictive of
treatment outcomes. For instance, genetic variants associated with drug metabolism
(e.g., CYP450 genes) can be encoded as binary features indicating the presence or
absence of relevant gene variants.
Pre-processed data will be stored in a data warehouse, where it can be accessed for analysis
and model training.

3.4 Feature Extraction:

Feature extraction is a crucial step in building a medicine recommendation system, as it helps
transform raw data into meaningful features that can be used to train machine learning
models. Depending on the type of recommendation system (e.g., content-based, collaborative
filtering, or hybrid), the features will vary. Below are the key features you would extract from
the dataset for a medicine recommendation system:

3.5 Sequence Diagram:

Fig.2: Sequence Diagram of MRS

12
 CHAPTER 4

RESULT AND IMPLEMENTATION

The Results and Implementation section describes how the Personalized Medicine
Recommendation System (MRS) is developed, deployed, and evaluated in a real-world
clinical setting. It covers the technical aspects of system development, data processing,
machine learning model performance, and the observed outcomes and benefits of using the
system in patient care.

4.1. Methods/Techniques:
A medicine recommendation system is an application designed to help suggest appropriate
medicines or treatments based on the patient's symptoms, medical history, and other relevant
data. These systems are typically powered by machine learning (ML), artificial intelligence
(AI), and data mining techniques to make accurate recommendations.

Fig.3: Block Diagram of Machine Learning Model

4.2. Implementation:
A code implementation refers to the actual process of writing and executing code to solve a
specific problem, achieve a particular task, or implement a system or functionality.
4.2.1 Python Code:

13
from flask import Flask, request, render_template, jsonify # Import jsonify
import numpy as np
import pandas as pd
import pickle
# flask app
app = Flask(__name__)
# load databasedataset===================================
sym_des = pd.read_csv("dataset/symtoms_df.csv")
precautions = pd.read_csv("dataset/precautions_df.csv")
workout = pd.read_csv("dataset/workout_df.csv")
description = pd.read_csv("dataset/description.csv")
medications = pd.read_csv('dataset/medications.csv')
diets = pd.read_csv("dataset/diets.csv")
# load model===========================================
svc = pickle.load(open('model/svc.pkl','rb'))
#=====================================================
# custome and helping functions
#==========================helper funtions================
def helper(dis):
desc = description[description['Disease'] == dis]['Description']
desc = " ".join([w for w in desc])
pre = precautions[precautions['Disease'] == dis][['Precaution_1', 'Precaution_2', 'Precaution_3'
, 'Precaution_4']]
pre = [col for col in pre.values]
med = medications[medications['Disease'] == dis]['Medication']
med = [med for med in med.values]
die = diets[diets['Disease'] == dis]['Diet']
die = [die for die in die.values]
wrkout = workout[workout['disease'] == dis] ['workout']
return desc,pre,med,die,wrkout
symptoms_dict = {'itching': 0, 'skin_rash': 1, 'nodal_skin_eruptions': 2, 'continuous_sneezing':
3, 'shivering': 4, 'chills': 5, 'joint_pain': 6, 'stomach_pain': 7, 'acidity': 8, 'ulcers_on_tongue': 9,
'muscle_wasting': 10, 'vomiting': 11, 'burning_micturition': 12, 'spotting_ urination': 13, 'fatigu
e': 14, 'weight_gain': 15, 'anxiety': 16, 'cold_hands_and_feets': 17, 'mood_swings': 18, 'weight

14
_loss': 19, 'restlessness': 20, 'lethargy': 21, 'patches_in_throat': 22, 'irregular_sugar_level': 23, '
cough': 24, 'high_fever': 25, 'sunken_eyes': 26, 'breathlessness': 27, 'sweating': 28, 'dehydratio
n': 29, 'indigestion': 30, 'headache': 31, 'yellowish_skin': 32, 'dark_urine': 33, 'nausea': 34, 'loss
_of_appetite': 35, 'pain_behind_the_eyes': 36, 'back_pain': 37, 'constipation': 38, 'abdominal_p
ain': 39, 'diarrhoea': 40, 'mild_fever': 41, 'yellow_urine': 42, 'yellowing_of_eyes': 43, 'acute_li
ver_failure': 44, 'fluid_overload': 45, 'swelling_of_stomach': 46, 'swelled_lymph_nodes': 47, '
malaise': 48, 'blurred_and_distorted_vision': 49, 'phlegm': 50, 'throat_irritation': 51, 'redness_o
f_eyes': 52, 'sinus_pressure': 53, 'runny_nose': 54, 'congestion': 55, 'chest_pain': 56, 'weakness
_in_limbs': 57, 'fast_heart_rate': 58, 'pain_during_bowel_movements': 59, 'pain_in_anal_regio
n': 60, 'bloody_stool': 61, 'irritation_in_anus': 62, 'neck_pain': 63, 'dizziness': 64, 'cramps': 65,
'bruising': 66, 'obesity': 67, 'swollen_legs': 68, 'swollen_blood_vessels': 69, 'puffy_face_and_e
yes': 70, 'enlarged_thyroid': 71, 'brittle_nails': 72, 'swollen_extremeties': 73, 'excessive_hunge
r': 74, 'extra_marital_contacts': 75, 'drying_and_tingling_lips': 76, 'slurred_speech': 77, 'knee_
pain': 78, 'hip_joint_pain': 79, 'muscle_weakness': 80, 'stiff_neck': 81, 'swelling_joints': 82, 'm
ovement_stiffness': 83, 'spinning_movements': 84, 'loss_of_balance': 85, 'unsteadiness': 86, 'w
eakness_of_one_body_side': 87, 'loss_of_smell': 88, 'bladder_discomfort': 89, 'foul_smell_of
urine': 90, 'continuous_feel_of_urine': 91, 'passage_of_gases': 92, 'internal_itching': 93, 'toxic
_look_(typhos)': 94, 'depression': 95, 'irritability': 96, 'muscle_pain': 97, 'altered_sensorium': 9
8, 'red_spots_over_body': 99, 'belly_pain': 100, 'abnormal_menstruation': 101, 'dischromic _p
atches': 102, 'watering_from_eyes': 103, 'increased_appetite': 104, 'polyuria': 105, 'family_hist
ory': 106, 'mucoid_sputum': 107, 'rusty_sputum': 108, 'lack_of_concentration': 109, 'visual_dis
turbances': 110, 'receiving_blood_transfusion': 111, 'receiving_unsterile_injections': 112, 'com
a': 113, 'stomach_bleeding': 114, 'distention_of_abdomen': 115, 'history_of_alcohol_consumpt
ion': 116, 'fluid_overload.1': 117, 'blood_in_sputum': 118, 'prominent_veins_on_calf': 119, 'pa
lpitations': 120, 'painful_walking': 121, 'pus_filled_pimples': 122, 'blackheads': 123, 'scurring':
124, 'skin_peeling': 125, 'silver_like_dusting': 126, 'small_dents_in_nails': 127, 'inflammatory
_nails': 128, 'blister': 129, 'red_sore_around_nose': 130, 'yellow_crust_ooze': 131}
diseases_list = {15: 'Fungal infection', 4: 'Allergy', 16: 'GERD', 9: 'Chronic cholestasis', 14: 'D
rug Reaction', 33: 'Peptic ulcer diseae', 1: 'AIDS', 12: 'Diabetes ', 17: 'Gastroenteritis', 6: 'Bron
chial Asthma', 23: 'Hypertension ', 30: 'Migraine', 7: 'Cervical spondylosis', 32: 'Paralysis (brai
n hemorrhage)', 28: 'Jaundice', 29: 'Malaria', 8: 'Chicken pox', 11: 'Dengue', 37: 'Typhoid', 40:
'hepatitis A', 19: 'Hepatitis B', 20: 'Hepatitis C', 21: 'Hepatitis D', 22: 'Hepatitis E', 3: 'Alcoholi
c hepatitis', 36: 'Tuberculosis', 10: 'Common Cold', 34: 'Pneumonia', 13: 'Dimorphic hemmorh
oids(piles)', 18: 'Heart attack', 39: 'Varicose veins', 26: 'Hypothyroidism', 24: 'Hyperthyroidis

15
m', 25: 'Hypoglycemia', 31: 'Osteoarthristis', 5: 'Arthritis', 0: '(vertigo) Paroymsal Positional
Vertigo', 2: 'Acne', 38: 'Urinary tract infection', 35: 'Psoriasis', 27: 'Impetigo'}
# Model Prediction function
def get_predicted_value(patient_symptoms):
input_vector = np.zeros(len(symptoms_dict))
for item in patient_symptoms:
input_vector[symptoms_dict[item]] = 0
return diseases_list[svc.predict([input_vector])[0]]
# creating routes========================================
@app.route("/")
def index():
return render_template('index.html')
# Define a route for the home page
@app.route('/predict', methods=['GET', 'POST'])
def home():
if request.method == 'POST':
symptoms = request.form.get('symptoms')
# mysysms = request.form.get('mysysms')
# print(mysysms)
print(symptoms)
if symptoms =="Symptoms":
message = "Please either write symptoms or you have
written misspelled symptoms"
return render_template('index.html', message=message)
else:
# Split the user's input into a list of symptoms
(assuming they are comma-separated)
user_symptoms = [s.strip() for s in symptoms.split(',')]
# Remove any extra characters, if any
user_symptoms = [symptom.strip("[]' ") for symptom in user_symptoms]
predicted_disease = get_predicted_value(user_symptoms)
dis_des, precautions, medications, rec_diet, workout = helper(predicted_disease)
my_precautions = []
for i in precautions[0]:

16
my_precautions.append(i)
return render_template('index.html',
predicted_disease=predicted_disease, dis_des=dis_des,
my_precautions=my_precautions,
medications=medications, my_diet=rec_diet,
workout=workout)
return render_template('index.html')
# about view funtion and path
@app.route('/about.html')
def about():
return render_template('about.html')
# contact view funtion and path
@app.route('/contact.html')
def contact():
return render_template('contact.html')
# developer view funtion and path
@app.route('/developer.html')
def developer():
return render_template('developer.html')
# about view funtion and path
@app.route('/blog.html')
def blog():
return render_template('blog.html')
if __name__ == '__main__':
app.run(debug=True)

4.2.2 HTML Home Page Code:

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>MedicoLife</title>

17
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="styl
esheet" integrity="sha384-4bw+/aepP/
YC94hEpVNVgiZdgIC5+VKNBQNGCHeKRQN+PtmoHDEXuppvnDJzQIu9" crossorigin=
"anonymous">
</head>
<style>
.logo {
width: 50px;
height: 50px;
color: black;
margin-top: 0;
margin-left: 2px;
}
.myimg {
width: 50px;
height: 50px;
border: 2px solid black;
border-radius: 25px;
}
</style>
<body>
<!-- Navbar -->
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container-fluid">
<!-- Logo at the top-left corner -->
<div class="logo">
<img class="myimg" src="{{ url_for('static', filename='lgwnn.png') }}" alt="">
</div>
<a class="navbar-brand" href="#">MedicoLife</a>
<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-
bs-target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-
expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>

18
 <div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav me-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link active" aria-current="page" href="#">Home</a>
</li>
<li class="nav-item">
<a class="nav-link" href="about.html">About</a>
</li>
<li class="nav-item">
<a class="nav-link" href="contact.html">Contact</a>
</li>
<li class="nav-item">
<a class="nav-link" href="developer.html">Developer</a>
</li>
<li class="nav-item">
<a class="nav-link" href="blog.html">Blog</a>
</li>
</ul>
<form class="d-flex" role="search">
<input class="form-control me-2" type="search" placeholder="Search" ar
ia-label="Search">
<button class="btn btn-outline-success" type="submit">Search</button>
</form>
</div>
</div>
</nav>
<!-- main form of page -->
<h1 class="mt-4 my-4 text-center text-green">Medicine Recommendation On Sympto
ms!!!</h1>
<div class="container my-4 mt-4" style="background: black; color: white; border-
radius: 15px; padding: 40px;">
<form action="/predict" method="post">
<div class="form-group">
<label for="symptoms">Select Symptoms:</label>

19
 <input type="text" class="form-control" id="symptoms" name="symptoms" pl
aceholder="type systems such as itching, sleeping, aching etc">
</div>
<br>
<!-- Display the transcribed text here -->
<div name="mysysms" id="transcription"></div>
{% if message %}
<p>{{ message }}</p>
{% endif %}
<br>
<button type="submit" class="btn btn-danger btn-lg" style="width: 100%; paddin
g: 14px; margin-bottom: 5px;">Predict</button>
</form>
</div>
{% if predicted_disease %}
<!-- Results -->
<h1 class="text-center my-4 mt-4">Our AI System Results</h1>
<div class="container">
<div class="result-container">
<!-- Buttons to toggle display -->
<div class="btn-group-vertical" role="group" aria-label="Vertical button group">
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-target="#diseaseModal" styl
e="padding:4px; margin: 5px 40px 5px 0; font-size:20px;font-weight:bold; width:140px; bor
der-radius:5px; background:#F39334;color:black;">Disease</button>
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-target="#descriptionModal"
style="padding:4px; margin: 5px 40px 5px 0; font-size:20px;font-weight:bold; width:140px;
border-radius:5px; background:#268AF3 ;color:black;">Description</button>
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-target="#precautionModal"
style="padding:4px; margin: 5px 40px 5px 0; font-size:20px;font-weight:bold; width:140px;
border-radius:5px; background:#F371F9 ;color:black;">Precaution</button>
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-
target="#medicationsModal" style="padding:4px; margin: 5px 40px 5px 0; font-
size:20px;font-weight:bold; width:140px;border-radius:5px; background:#F8576F ;color:blac
k;">Medications</button>

20
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-target="#workoutsModal" st
yle="padding:4px; margin: 5px 40px 5px 0; font-size:20px;font-weight:bold; width:140px; bo
rder-radius:5px; background:#99F741 ;color:black;">Workouts</button>
<button class="btn btn-primary" data-bs-toggle="modal" data-bs-target="#dietsModal" style=
"padding:4px; margin: 5px 40px 5px 0; font-size:20px;font-weight:bold; width:140px; border
-radius:5px; background:#E5E23D;color:black;">Diets</button>
</div>
</div>
</div>
{% endif %}
<!-- Disease Modal -->
<div class="modal fade" id="diseaseModal" tabindex="-1" aria-
labelledby="diseaseModalLabel" aria-hidden="true">
<div class="modal-dialog">
<div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;"> <!-- Set header
background color inline -->
<h5 class="modal-title" id="diseaseModalLabel">Predicted Disease</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-label="Close"></
button>
</div>
<div class="modal-body;"> <!-- Set modal body background color inline -->
<p>{{ predicted_disease }}</p>
</div>
</div>
</div>
</div>
<!-- Description Modal -->
<div class="modal fade" id="descriptionModal" tabindex="-1" aria-
labelledby="descriptionModalLabel" aria-hidden="true">
<div class="modal-dialog">
<div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;">
<h5 class="modal-title" id="descriptionModalLabel">Description</h5>

21
 <button type="button" class="btn-close" data-bs-dismiss="modal" aria-
label="Close"></button>
</div>
<div class="modal-body">
<p>{{ dis_des }}</p>
</div>
</div>
</div>
</div>
<!-- Precaution Modal -->
<div class="modal fade" id="precautionModal" tabindex="-1" aria-
labelledby="precautionModalLabel" aria-hidden="true">
<div class="modal-dialog">
<div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;
">
<h5 class="modal-title" id="precautionModalLabel">Precaution</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-
label="Close"></button>
</div>
<div class="modal-body">
<ul>
{% for i in my_precautions %}
<li>{{ i }}</li>
{% endfor %}
</ul>
</div>
</div>
</div>
</div>
<!-- Medications Modal -->
<div class="modal fade" id="medicationsModal" tabindex="-1" aria-
labelledby="medicationsModalLabel" aria-hidden="true">
<div class="modal-dialog">

22
 <div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;
">
<h5 class="modal-title" id="medicationsModalLabel">Medications</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-
label="Close"></button>
</div>
<div class="modal-body">
<ul>
{% for i in medications %}
<li>{{ i }}</li>
{% endfor %}
</ul>
</div>
</div>
</div>
</div>
<!-- Workouts Modal -->
<div class="modal fade" id="workoutsModal" tabindex="-1" aria-
labelledby="workoutsModalLabel" aria-hidden="true">
<div class="modal-dialog" >
<div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;
">
<h5 class="modal-title" id="workoutsModalLabel">Workouts</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-
label="Close"></button>
</div>
<div class="modal-body">
<ul>
{% for i in workout %}
<li>{{ i }}</li>
{% endfor %}
</ul>

23
 </div>
</div>
</div>
</div>
<!-- Diets Modal -->
<div class="modal fade" id="dietsModal" tabindex="-1" aria-
labelledby="dietsModalLabel" aria-hidden="true">
<div class="modal-dialog">
<div class="modal-content">
<div class="modal-header" style="background-color: #020606; color:white;
">
<h5 class="modal-title" id="dietsModalLabel">Diets</h5>
<button type="button" class="btn-close" data-bs-dismiss="modal" aria-
label="Close"></button>
</div>
<div class="modal-body">
<ul>
{% for i in my_diet %}
<li>{{ i }}</li>
{% endfor %}
</ul>
</div>
</div>
</div>
</div>
<script>
const startSpeechRecognitionButton = document.getElementById('startSpeechReco
gnition');
const transcriptionDiv = document.getElementById('transcription');
startSpeechRecognitionButton.addEventListener('click', startSpeechRecognition);
function startSpeechRecognition() {
const recognition = new webkitSpeechRecognition(); // Use webkitSpeechRecog
nition for compatibility
recognition.lang = 'en-US'; // Set the language for recognition

24
 recognition.onresult = function (event) {
const result = event.results[0][0].transcript;
transcriptionDiv.textContent = result;
};
recognition.onend = function () {
console.log('Speech recognition ended.');
};
recognition.start();
}
</script>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/
bootstrap.bundle.min.js" integrity="sha384-
HwwvtgBNo3bZJJLYd8oVXjrBZt8cqVSpeBNS5n7C8IVInixGAoxmnlMuBnhbgrkm
" crossorigin="anonymous"></script>
</body>
</html>

4.2.3 About Section HTML Code:

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>About Us</title>
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="styl
esheet" integrity="sha384-4bw+/aepP/
YC94hEpVNVgiZdgIC5+VKNBQNGCHeKRQN+PtmoHDEXuppvnDJzQIu9" crossorigin=
"anonymous">
</head>
<style>
.logo {
width: 50px;
height: 50px;
color: black;

25
 margin-top: 0;
margin-left: 2px;
}
.myimg {
width: 50px;
height: 50px;
border: 2px solid black;
border-radius: 25px;
}
</style>
<body>
<!-- Navbar -->
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container-fluid">
<!-- Logo at the top-left corner -->
<div class="logo">
<img class="myimg" src="{{ url_for('static', filename='lgwnn.png') }}" alt="">
</div>
<a class="navbar-brand" href="#">MedicoLife</a>
<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-
bs-target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-
expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav me-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link active" aria-current="page" href="index.html">Ho
me</a>
</li>
<li class="nav-item">
<a class="nav-link" href="about.html">About</a>
</li>
<li class="nav-item">

26
 <a class="nav-link" href="contact.html">Contact</a>
</li>
<li class="nav-item">
<a class="nav-link" href="developer.html">Developer</a>
</li>
<li class="nav-item">
<a class="nav-link" href="blog.html">Blog</a>
</li>
</ul>
<form class="d-flex" role="search">
<input class="form-control me-2" type="search" placeholder="Search" ar
ia-label="Search">
<button class="btn btn-outline-success" type="submit">Search</button>
</form>
</div>
</div>
</nav>
<div class="container my-4 mt-4">
<h3> About Us</h3>
<p>Welcome to MedicoLife Health care, where health meets technology for a brighter, health
ier future.</p>
<h3>Our Vision</h3>
<p>We envision a world where access to healthcare information is not just a luxury but a fund
amental right. Our journey began with a simple yet powerful idea: to empower individuals wit
h the knowledge and tools they need to take control of their health.</p>
<h3>Who We Are</h3>
<p>We are a passionate team of healthcare professionals, data scientists, and technology enth
usiasts who share a common goal: to make healthcare accessible, understandable, and persona
lized for you. With years of experience in both healthcare and cutting-edge technology, we've
come together to create this platform as a testament to our commitment to your well-being.</
p>
<h3>Our Mission</h3>
<p>At this website, our mission is to provide you with a seamless and intuitive platform that l
everages the power of artificial intelligence and machine learning. We want to assist you in id

27
entifying potential health concerns based on your reported symptoms, all while offering a wea
lth of educational resources to enhance your health literacy.
</p>
<h3>How We Do It</h3>
<p>Our platform utilizes a robust machine learning model trained on a vast dataset of sympto
ms and diseases. By inputting your symptoms, our system generates accurate predictions abou
t potential illnesses, allowing you to make informed decisions about your health.</p>
<h3>Your Well-being, Our Priority</h3>
<p>Your health is our top priority. We understand that navigating the complexities of healthc
are can be daunting. That's why we've gone the extra mile to provide not only accurate predict
ions but also comprehensive information about each disease. You'll find descriptions, recomm
ended precautions, medications, dietary advice, and workout tips to support your journey to b
etter health.
</p>
<h3>Join Us on this Journey
</h3>
<p>We invite you to explore our platform, engage with our educational content, and take cont
rol of your health journey. Together, we can revolutionize the way individuals access and und
erstand healthcare information.
</p>
<p>Thank you for choosing MedicoLife Health Care as your trusted health companionWe are
here to empower you with knowledge, support, and a brighter, healthier future.
</p>
</div>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/
bootstrap.bundle.min.js" integrity="sha384-
HwwvtgBNo3bZJJLYd8oVXjrBZt8cqVSpeBNS5n7C8IVInixGAoxmnlMuBnhbgrkm
" crossorigin="anonymous"></script>
</body>
</html>

4.2.4 Blog Section HTML Code:

<!doctype html>
<html lang="en">

28
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Blog</title>
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="styl
esheet" integrity="sha384-4bw+/aepP/
YC94hEpVNVgiZdgIC5+VKNBQNGCHeKRQN+PtmoHDEXuppvnDJzQIu9" crossorigin=
"anonymous">
</head>
<style>
.logo {
width: 50px;
height: 50px;
color: black;
margin-top: 0;
margin-left: 2px;
}
.myimg {
width: 50px;
height: 50px;
border: 2px solid black;
border-radius: 25px;
}
</style>
<body>
<!-- Navbar -->
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container-fluid">
<!-- Logo at the top-left corner -->
<div class="logo">
<img class="myimg" src="{{ url_for('static', filename='lgwnn.png') }}" alt="">
</div>
<a class="navbar-brand" href="#">MedicoLife</a>

29
 <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-
bs-target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-
expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav me-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link active" aria-current="page" href="index.html">Ho
me</a>
</li>
<li class="nav-item">
<a class="nav-link" href="about.html">About</a>
</li>
<li class="nav-item">
<a class="nav-link" href="contact.html">Contact</a>
</li>
<li class="nav-item">
<a class="nav-link" href="developer.html">Developer</a>
</li>
<li class="nav-item">
<a class="nav-link" href="blog.html">Blog</a>
</li>
</ul>
<form class="d-flex" role="search">
<input class="form-control me-2" type="search" placeholder="Search" ar
ia-label="Search">
<button class="btn btn-outline-success" type="submit">Search</button>
</form>
</div>
</div>
</nav>
<div class="container my-4 mt-4">

30
 <h2 class="text-center"> Building a Symptom-Based Disease Diagnosis Web Ap
p with Flask and Machine Learning</h2>
<p>In the age of technology and information, access to accurate and timely healthcare is more
critical than ever. With the increasing importance of remote healthcare solutions, we embarke
d on a journey to develop a symptombased disease diagnosis web application. Leveraging
Flask for the backend and a Decision Tree Classifier model, we created a userfriendly platfor
m that can help users identify potential illnesses based on their reported symptoms.</p>
<h3>The Problem</h3>
<p>The project began with recognizing a common issue: people often experience symptoms a
nd want quick answers about their health concerns. It can be challenging to differentiate betw
een various diseases, especially when symptoms overlap. Our goal was to provide a convenie
nt solution for users to input their symptoms and receive potential diagnoses.</p>
<h3>The Solution</h3>
<p>We developed a web app that allows users to enter a list of symptoms they are experienci
ng. The app then uses a pre-trained Decision Tree Classifier model to predict the most likely d
isease based on the provided symptoms. Here's how it works:</p><ol>
<li><b><strong>Symptom Input:</strong></b> Users enter their symptoms through a user-
friendly interface. The web app supports a wide range of symptoms, making it versatile for dif
ferent scenarios.</li>
<li><b><strong>Machine Learning Model:</strong></b> We trained a Decision Tree Classifi
er using a dataset containing symptoms and corresponding diseases. The model is capable of p
redicting diseases based on input symptoms.</li>
<li><b><strong>Prediction:</strong></b> The app uses the model to predict the most likely
disease, providing users with instant information about potential health concerns.</li>
<li><b><strong>Additional Information: </strong></b> To enhance user experience, the app
also provides additional information about the predicted disease. This includes a description o
f the disease, recommended precautions, medications, dietary advice, and workout tips.</
li></ol>
<h3>Key Features</h3>
<ul type="circle">
<li><b><strong>UserFriendly Interface:</strong></b> The web app boasts an intuitive and e
asy-to-navigate interface,
ensuring that users can input their symptoms without any hassle.</li>

31
<li><b><strong>Accurate Predictions:</strong></b> Leveraging machine learning, our mode
l provides accurate disease predictions based on the symptoms provided by the user.</li>
<li><b><strong>Comprehensive Information: </strong></b>In addition to predictions, the ap
p offers comprehensive information about the predicted disease, including descriptions, preca
utions, medications, diet recommendations, and workout tips.</li>
<li><b><strong>ducational Content:</strong></b> To empower users with knowledge, the a
pp includes informative blog posts about various health topics.</li>
</ul> <br>
<h3>Conclusion</h3>
<p>Our Symptom Based Disease Diagnosis Web App brings the power of
machine learning and healthcare information to the fingertips of users. It serves as a valuable r
esource for individuals looking to gain insights into their health conditions quickly and conve
niently. By combining technology and healthcare, we aim to make healthcare more accessible
and user-centric.
In an era where remote healthcare solutions are gaining prominence, this project represents a s
ignificant step forward in providing accessible and reliable healthcare information to the mass
es. We hope that this project will contribute to better health awareness and ultimately improve
the well-being of individuals worldwide.</p>
</div>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/
bootstrap.bundle.min.js" integrity="sha384-
HwwvtgBNo3bZJJLYd8oVXjrBZt8cqVSpeBNS5n7C8IVInixGAoxmnlMuBnhbgrkm
" crossorigin="anonymous"></script>
</body>
</html>

4.2.5 Developer Section HTML Code:

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Developer</title>

32
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="styl
esheet" integrity="sha384-4bw+/aepP/
YC94hEpVNVgiZdgIC5+VKNBQNGCHeKRQN+PtmoHDEXuppvnDJzQIu9" crossorigin=
"anonymous">
</head>
<style>
.logo {
width: 50px;
height: 50px;
color: black;
margin-top: 0;
margin-left: 2px;
}
.myimg {
width: 50px;
height: 50px;
border: 2px solid black;
border-radius: 25px;
}
</style>
<body>
<!-- Navbar -->
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container-fluid">
<!-- Logo at the top-left corner -->
<div class="logo">
<img class="myimg" src="{{ url_for('static', filename='lgwnn.png') }}" alt="">
</div>
<a class="navbar-brand" href="#">MedicoLife</a>
<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-
target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-
expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>

33
 <div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav me-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link active" aria-current="page" href="index.html">Home</a>
</li>
<li class="nav-item">
<a class="nav-link" href="about.html">About</a>
</li>
<li class="nav-item">
<a class="nav-link" href="contact.html">Contact</a>
</li>
<li class="nav-item">
<a class="nav-link" href="developer.html">Developer</a>
</li>
<li class="nav-item">
<a class="nav-link" href="blog.html">Blog</a>
</li>
</ul>
<form class="d-flex" role="search">
<input class="form-control me-
2" type="search" placeholder="Search" aria-label="Search">
<button class="btn btn-outline-success" type="submit">Search</button>
</form>
</div>
</div>
</nav>
<div class="container my-4 mt-4">
<h6> About Tushar Ahire : Your Data Scientist </h6>
<h5>Meet the Developer</h5>
<p>Hello, I'm Tushar Ahire, your Data Scientist with over 1 year of Self Lerning+ Project ex
perience in the field. I am passionate about technology to make a positive impact on people's l
ives. Allow me to share a bit about my journey in the world of artificial intelligence and mach
ine learning.</p>
<h5>My Expertise</h5>

34
<p>With a robust foundation in data analysis,machine learning, Model Building , Recommen
dation System , I excel in extracting actionable insights from complex datasets. Proficient in P
ython, SQL, Machine Learning and a range of visualization tools like Tableau and Power BI,
I've led numerous successful projects spanning recommendation systems, sentiment analysis,
and predictive modeling.</p>
<h5>A Commitment to Excellence</h5>
<p>My work is driven by a commitment to excellence and a belief that technology should be
accessible and beneficial to everyone. Whether it's developing predictive models, creating inte
lligent algorithms, or designing user-friendly interfaces, I strive for solutions that are both cutt
ing-edge and user-centric.
</p>
<h5>Join Me on this Journey</h5>
<p>I invite you to explore and experience firsthand the fusion of AI and healthcare. Together,
we can empower individuals with knowledge, promote well-being, and contribute to a brighte
r and healthier future.</p>
</div>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.bundle.min.js" inte
grity="sha384-
HwwvtgBNo3bZJJLYd8oVXjrBZt8cqVSpeBNS5n7C8IVInixGAoxmnlMuBnhbgrkm" cross
origin="anonymous"></script>
</body>
</html>

4.2.6 Contact Section HTML Code:

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Contact Us</title>
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="styl
esheet" integrity="sha384-4bw+/aepP/
YC94hEpVNVgiZdgIC5+VKNBQNGCHeKRQN+PtmoHDEXuppvnDJzQIu9" crossorigin=
"anonymous">

35
 </head>
<style>
.logo {
width: 50px;
height: 50px;
color: black;
margin-top: 0;
margin-left: 2px;
}
.myimg {
width: 50px;
height: 50px;
border: 2px solid black;
border-radius: 25px;
}
</style>
<body>
<!-- Navbar -->
<nav class="navbar navbar-expand-lg navbar-dark bg-dark">
<div class="container-fluid">
<!-- Logo at the top-left corner -->
<div class="logo">
<img class="myimg" src="{{url_for ('static', filename='lgwnn.png') }}" alt="">
</div>
<a class="navbar-brand" href="#">MedicoLife</a>
<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-
target="#navbarSupportedContent" aria-controls="navbarSupportedContent" aria-
expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div class="collapse navbar-collapse" id="navbarSupportedContent">
<ul class="navbar-nav me-auto mb-2 mb-lg-0">
<li class="nav-item">
<a class="nav-link active" aria-current="page" href="/index.html">Home</a>

36
 </li>
<li class="nav-item">
<a class="nav-link" href="about.html">About</a>
</li>
<li class="nav-item">
<a class="nav-link" href="contact.html">Contact</a>
</li>
<li class="nav-item">
<a class="nav-link" href="developer.html">Developer</a>
</li>
<li class="nav-item">
<a class="nav-link" href="blog.html">Blog</a>
</li>
</ul>
<form class="d-flex" role="search">
<input class="form-control me-2" type="search" placeholder="Search" ar
ia-label="Search">
<button class="btn btn-outline-success" type="submit">Search</button>
</form>
</div>
</div>
</nav>
<div class="container my-4 mt-4">
<h4>Contact Us</h4>
<p>Have questions or need assistance? We're here to help! </p>
<h4>Customer Support</h4>
<p>Our dedicated customer support team is available to assist you with any inquiries
or issues you may have. Whether it's a technical question, feedback, or a general inqui
ry, we're just a message away.</p>
<h4>Get in Touch</h4>
<p>Feel free to reach out to us via email or through the contact form below. We value
your feedback and are committed to providing you with the best possible experience.
</p>
<p><b>Email:</b> [email protected]</p>

37
 <p><b>Phone:</b> 78882XXXX</p>
<h4>Stay Connected</h4>
<p>Stay up-to-date with the latest news, updates, and health tips by following us on so
cial media. Connect with us on Facebook or Instagram to join our growing community
. </p>
<h4>Location</h4>
<p>Nashik, Maharashtra, India</p>
</div>
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/
bootstrap.bundle.min.js" integrity="sha384-
HwwvtgBNo3bZJJLYd8oVXjrBZt8cqVSpeBNS5n7C8IVInixGAoxmnlMuBnhbgrkm
" crossorigin="anonymous"></script>
</body>
</html>

4.3 Module Specifications:

A Medicine Recommendation System can be broken down into several modules, each
focusing on different aspects of the system’s functionality. Below is a detailed module
specification for such a system, organized by functional areas.
4.3.1 Patient Profile Module:
To manage the patient’s personal, medical, and health-related information.
4.3.2 Diagnosis Module:
To capture and manage patient diagnoses, linking them to conditions, symptoms, and
prescriptions.
4.3.3 Medicine Management Module:
To manage information related to medicines, including dosage, side effects, and usage.
4.3.4 Prescription Module:
To manage and generate prescriptions based on diagnoses, recommending medicines to the
patient.
4.3.5 Medicine Recommendation Engine Module:
To provide personalized medicine recommendations based on the patient's diagnosis,
symptoms, and medical history.
4.3.6 Notification and Alert System Module:

38
To inform users (patients and doctors) about appointments, prescription updates, and
medicine alerts.
4.3.7 Reporting and Analytics Module:
To generate reports and analyse the data for insights (e.g., prescription trends, popular
medicines).

Disease Medication
Fungal infe['Antifungal Cream', 'Fluconazole', 'Terbinafine', 'Clotrimazole', 'Ketoconazole']
Allergy ['Antihistamines', 'Decongestants', 'Epinephrine', 'Corticosteroids', 'Immunotherapy']
GERD ['Proton Pump Inhibitors (PPIs)', 'H2 Blockers', 'Antacids', 'Prokinetics', 'Antibiotics']
Chronic cho['Ursodeoxycholic acid', 'Cholestyramine', 'Methotrexate', 'Corticosteroids', 'Liver transp
Drug React['Antihistamines', 'Epinephrine', 'Corticosteroids', 'Antibiotics', 'Antifungal Cream']
Peptic ulce['Antibiotics', 'Proton Pump Inhibitors (PPIs)', 'H2 Blockers', 'Antacids', 'Cytoprotective a
AIDS ['Antiretroviral drugs', 'Protease inhibitors', 'Integrase inhibitors', 'Entry inhibitors', 'Fusio
Diabetes ['Insulin', 'Metformin', 'Sulfonylureas', 'DPP-4 inhibitors', 'GLP-1 receptor agonists']
Gastroenter['Antibiotics', 'Antiemetic drugs', 'Antidiarrheal drugs', 'IV fluids', 'Probiotics']
Table 1: Dataset of Medicine Recommendation

Disease PrecautionPrecautionPrecautionPrecaution_4
0 Drug Reactstop irritatconsult neastop takingfollow up
1 Malaria Consult neaavoid oily avoid non keep mosquitos out
2 Allergy apply cala cover area with band use ice to compress itching
3 Hypothyroreduce streexercise eat healthyget proper sleep
4 Psoriasis wash hands stop bleediconsult do salt baths
5 GERD avoid fattyavoid lyingmaintain hexercise
6 Chronic chocold baths anti itch m consult do eat healthy
7 hepatitis AConsult neaw ash handavoid fattymedication
8 Osteoarthriacetamino consult neafollow up salt baths
Table 2: Dataset of Precautions Recommendation

4.4 Data Flow Diagram:

39
 Fig.4: Data Flow diagram of MRS

4.5 Output/Screenshot:

40
 Output 1: Home Page of MRS

Output 2: Enter symptoms in textbox

Output 3: Output of Predicted Disease

41
Output 4: Precautions you need to follow

Output 5: Recommendation of medicine

42
Output 6: About Page

Output 7: Contact Page

43
Output 8: Developer Page

Output 9: Blog Page

44
 CHAPTER 5
CONCLUSION
5.1 Conclusion:
The Medicine Recommendation System (MRS) project represents a significant advancement
in the integration of technology and healthcare, aiming to enhance the decision-making
process for both patients and healthcare providers. By leveraging Python's powerful libraries
and frameworks, we have developed a system that not only streamlines medication
recommendations based on user-reported symptoms but also prioritizes safety and compliance
with medical guidelines.
Throughout the project, we have focused on building a user-friendly interface, ensuring
accurate symptom analysis through natural language processing, and utilizing robust
recommendation algorithms to deliver personalized treatment options. The comprehensive
database of medications, combined with real-time analytics and reporting, positions the MRS
as a valuable tool in the healthcare landscape.
As we move forward, the system's modular architecture allows for scalability and
adaptability, making it possible to integrate future advancements in medical knowledge and
technology. Continuous user feedback and performance tracking will further refine the
recommendations, ultimately enhancing patient outcomes and fostering informed healthcare
decisions.
In conclusion, the Medicine Recommendation System is poised to empower users with
tailored medical insights, reduce the burden on healthcare providers, and contribute to the

45
ongoing evolution of digital health solutions. With the right implementation and ongoing
improvements, this system has the potential to play a pivotal role in modern healthcare
delivery.

5.2 Limitations:
While a medicine recommendation system can significantly improve the efficiency and safety
of prescribing, it is not without its challenges. The limitations outlined above highlight the
importance of careful implementation, ongoing updates, and close integration with healthcare
professionals to ensure the system complements rather than replaces human judgment. To be
effective, these systems need to balance automation with clinical expertise, adhere to strict
ethical standards, and ensure the continuous integration of accurate and up-to-date data.

5.3 Future Enhancement:

The future of medicine recommendation systems lies in deeper integration with emerging
technologies such as AI, genetic data, real-time health monitoring, and blockchain. These
advancements will help create more personalized, accurate, and holistic treatment
recommendations, improving patient outcomes and supporting healthcare providers in making
informed decisions. However, these systems will need to continue evolving to address
challenges related to data privacy, regulatory compliance, ethical considerations, and
integration with existing healthcare infrastructures. As the systems become smarter and more
integrated, they have the potential to revolutionize personalized healthcare and contribute to
more effective, evidence-based medicine.

46
 CHAPTER 6
BIBLIOGRAPHY

 PYTHON, HTML & CSS:

1) https://getbootstrap.com/docs/5.3/gettingstarted/introduction/
2) https://www.w3schools.com
3) https://www.instagram.com/tech_shahnawaz_/

 Image/Diagrams:
1) https://github.com/Ashveenk200/Medicine-Recommendation-System-/blob/
main/static/heal.jpg
2) file:///C:/Users/RISHI%20AHER/Downloads/AIPPaperAmitAbhishek.pdf
3) http://www.ir.juit.ac.in:8080/jspui/bitstream/123456789/3719/1/Medicinal
%20Drug%20Recommendation%20System.pdf
4) https://ijsrset.com/paper/8152.pdf

 Datasets:
https://www.kaggle.com/datasets/noorsaeed/medicine-recommendation-system-
dataset?

47
48