Smart Medical Diagnosis System
Smart Medical Diagnosis System
Smart Medical Diagnosis System
Smart Medical
Diagnosis System
Team members:
● Aryan Omkar Ashar 19BAI10094
● Pranav Sharma 19BAI10154
● Shreya Shetye 19BAI10028
● Aiswarya Nair 19BOE10019
● Shireen Soporee 19BOE10049
● Vaidehi Chaudhari 19BOE10051
● Khushii Gupta 19BCE10339
● Kushagra 19BCY10074
3/34
INTRODUCTION TO DIAGNOSIS
Medical diagnosis is basically a pattern classification phenomenon based
on some input provided by a patient, an expert gives a conclusion on the
basis of its knowledge, which is normally stored in a binary form, and
finally the result is calculated i.e., either the patient suffering from a
certain disease or not.
4/34
Disease Diagnosis in Healthcare
In the field of healthcare, the study of disease diagnosis plays a vital role. Any cause or
circumstances that lead to pain, illness, dysfunction, or eventually, a human being’s death
is called a disease. Diseases may affect a person physically and mentally, and it
considerably manipulates the living style of the affected person.
Diagnosis of diseases is the most challenging process at the same time, a very pivotal
phenomenon for a medical care professional as before reaching the conclusion. The
diagnostic process could be very tiresome and complex. To minimize the uncertainty in
medical diagnosis health, the care experts collect empirical data to ascertain a patient’s
disease.
The patient’s correct treatment may be adjourned or missed with serious health issues
due to making fault in the diagnosis process. Some specific AI methods that are
significant in the medical field named as a Rule-based intelligent system, provides a set
of if-then rules in healthcare, which act as a decision support system.
Gradually, intelligent systems are being replaced in the medical field by AI-based
automatic techniques where human intervention is very less.
5/34
AI in Healthcare
• Artificial intelligence is not one technology, but rather a
collection of them. Most of these technologies have
immediate relevance to the healthcare field, but the
specific processes and tasks they support vary widely.
6/34
Deep Learning in Healthcare
Deep learning-based technique can extract features manually without human
intervention, the only condition is to make precise decisions in which the
testing data could be accurate. This technique eliminates the requirement of
a domain expert for feature extraction.
7/34
Machine Learning in diagnosis
Machine learning (ML) is a statistical technique for fitting
models to data and to ‘learn’ by training models with data.
Machine learning is one of the most common forms of AI;
in a 2018 Deloitte survey of 1,100 US managers whose
organizations were already pursuing AI, 63% of companies
surveyed were employing machine learning in their
businesses. It is a broad technique at the core of many
approaches to AI and there are many versions of it.
8/34
Current applications of ML in diagnosis
Chatbots: Companies are using AI-chatbots with speech recognition
capability to identify patterns in patient symptoms to form a potential
diagnosis, prevent disease and/or recommend an appropriate course of
action.
9/34
Oncology • Researchers are using deep learning to train
algorithms to recognize cancerous tissue at a
level comparable to trained physicians.
• Researchers have trained an algorithm to
diagnose skin cancer using deep learning,
specifically deep convolutional neural networks
(CNNs). The algorithm was trained to detect
skin cancer or melanoma using “130,000 images
of skin lesions representing over 2,000 different
diseases.”
• Deep learning algorithm was tested against 21
board-certified dermatologists who reviewed a
reported 370 images and were asked if “they
would proceed with biopsy or treatment, or
reassure the patient” based on each image.
Results showed that the algorithm had the same
ability as the 21 dermatologists in determining
the best course of action across all images.
10/34
Pathology using AI
Pathology is the medical specialty that is concerned with the diagnosis of
disease based on the laboratory analysis of bodily fluids such as blood and
urine, as well as tissues. Machine vision and other machine learning
technologies can enhance the efforts traditionally left only to pathologists
with microscopes.
11/34
Medical Imaging
12/34
AI In Medical Imaging
An AI algorithm could assess x-rays and other images for evidence
of opacities that indicate pneumonia, then alert providers to the
potential diagnoses to allow for speedier treatment. AI can
similarly help to identify high-risk patients when pneumothorax is
suspected, especially when radiologists are not present.
13/34
Image Processing
• Image processing is the method of manipulating an
image to either enhance the quality or extract
relevant information from it. AI Image Processing
Services combine advanced algorithmic technology with
machine learning and computer vision to process large
volumes of pictures easily and quickly.
• Medical image processing encompasses the use and
exploration of 3D image datasets of the human body,
obtained most commonly from a Computed Tomography
(CT) or Magnetic Resonance Imaging (MRI) scanner to
diagnose pathologies or guide medical interventions
such as surgical planning, or for research purposes.
Image processing is an any form of signal processing
for which the input is an image, such as a photograph
or video. frame, the output of image processing may
be either an image or a set of characteristics or
parameters related to the image.
14/34
Now, you would have understood the
basic foundations of our project.
So lets move on to the project.
15/34
Introduction to our Project
In the above slides, we saw some medical terms and some uses of AI,
ML and deep learning diagnosis. But now we aim to collaborate all the
different features and put it together into a one highly accurate
system.
Our project will also be able to generate csv and excel sheets of the
employee data and we can keep updating this data on daily basis. The
project will also generate pdf reports and will be able to calculate the
cost of diagnosis. We can also generate the history of the patient and
can also track of the health by the help of graph.
16/34
Existing Work with Limitations
In this section we discuss current applied AI techniques which are used for disease diagnostic process,
relevant survey articles on diagnostic process and our contribution in regards to the existing work.
Van Mourik et al. [14] carried out a survey on automated surveillance techniques for healthcare-associated
infections. In this review, authors have described how automatic surveillance systems based on machine
learning algorithms bring enhanced performance and reliability compared to manual surveillance methods.
Another finding of this review is that the use of regression models can improve the efficiency and
sensitivity of surveillance programs. There are some challenges that need to be addressed in the near
future such as post discharge surveillance, case-mix adjustment, quantification of device utilization.
One more study on sepsis was performed by Sinha et al. [17]. They reported some drawbacks in routine
blood culture testing for sepsis detection. To analyze suitable automatic sepsis detection methods they
investigated seven molecular technologies that utilize blood samples. In this study, they have discussed the
various present and future trends. In addition, they have also analyzed the impact of machine learning
algorithms with electronic medical records in sepsis detection. They conclude that by merging various
technologies can improve the detection process and minimize the risk of using the wrong antibiotic.
To the best of the knowledge, this is the first attempt to provide a comprehensive survey for
disease prediction using the techniques of fuzzy logics, machine learning and deep learning. In
addition, contrary to existing survey articles available in the literature, this work has focused
on a particular range of sickness.
17/34
Existing Work with Limitations
In the medical field, machine learning and fuzzy logic assists the experts to handle large and
complicated medical data and also helps to investigate the results. The output of this process can be
used for further research.
Machine learning algorithms like Decision trees, Support vector machine, Multilayer perceptron, Bayes
classifiers, K-Nearest Neighbour, Ensemble classifier techniques, etc are used to determine various
ailments. Using machine learning algorithms can lead to rapid disease prediction with high accuracy.
The learning process begins with observations or information, such as examples, direct experience or
instruction. In particular, the algorithms look for data patterns and make better decisions. The key
goal is to allow the machines to learn automatically without human interference and adjust the
response accordingly.
The intended contribution of AI in the field of medical science is to develop programs that can help a
medical expert in practicing expert and more accurate diagnosis. The forecast for diseases plays an
important role in machine learning. Various types of diseases can be predicted using ML techniques.
18/34
Limitations of Existing Diagnostic System
One of the major problems is the imprecision and inaccuracy in many cases.
Some studies have found that between 20 and 50 percent of all advanced imaging results fail
to provide information that improves patient outcome, although these studies do not account
for the value of negative imaging results in influencing decisions about patient management
Not applicable among patients with complex diseases. Lack of flexibility and individuality.
The other limitation for diagnosis is that only research, discussions, and consensus approves
it.
Sometimes, a diagnosis might be diverse from each other even if the symptoms are overlapping. Different diagnoses from
different psychologists can confuse the patient.
19/34
Proposed Work
The proposed work consists of a smart medical diagnostic system which
involves the study of many different branches of engineering and can be of a
great help to the community. This medical diagnostic system is one the major
python projects.
The model will also be able to create a database of all the employee working
at the diagnostic center and also be able to make the work of doctors easier
and safer. Also, we will be able to extract the history of the patient and
derive the seriousness of the disease based on these results.
A PDF report can be generated of the final diagnosis and what the machine
has predicted. We will also be able to create a CSV report for diagnosis,
employees and the charges of the diagnosis.
20/34
Proposed Work
The objective of the model is to predict the patient’s likelihood of getting a particular
sort of health implication on the body. We hope that this model can make more informed
and accurate decisions when in practice.
We propose to use various algorithms in order to diagnose the medical condition of the
patient. We would ensure that the code is bug free and not leave any drawbacks. More
specifically, this system will analyze every symptom and give a complete report of his
illness . This software will keep a complete record of the patients history and his medical
problems .
The user can enter symptoms from different body parts ,then the disease matching all
the symptoms is shown to the user along with other possible symptoms, disease
description and the treatment description.
This software system will be a Medical Diagnostic System for common man . This system
will be designed to immediately diagnose by providing tools to assist the patient , which
would otherwise have to be performed manually. By this system, we will be able to
provide online check up appointments to the patient in their nearby Diagnostic center and
give reports about that person that is easy to understand and use.
21/34
Methodology – Data Pre-processing
Medical data is highly fragmented and difficult to use directly in the project. Thus
first we have to focus on data preprocessing and data cleaning which focuses on
removing outliers and removing the NA data.
We aim to handle missing data by direct imputation and other machine learning
methods. Our goal will be to have a dataset with no missing values.
22/34
Methodology – Model Training
This Model training involves many steps. The first step is to choose a
model. We have to first choose an appropriate algorithm according to our
task.
Next step is using the testing data in order to generate the reports and
results.
23/34
Overall System
Architecture Diagram
24/34
Software Requirements
25/34
Hardware Requirements
26/34
Real-time applications of the project
Before this we saw in the above slides how Machine learning and
artificial intelligence technologies are used in order to make medical
systems. Here we will see how our project can be used in real time and
how it can help the community.
Our project can be accessed by the people living in rural areas who
have very less information on medical diseases. The rural community
can put in their symptoms and then they can get to know the disease
they are suffering with.
27/34
Real-time applications of the project
Poor people can get their health diagnosed quickly and efficiently
and at very minimum cost.
The report of the patient can be exported and thus this system
can be used at diagnostic centres in rural as well as city area and
every person can take the benefits of this device.
28/34
Novelty of the project
Diagnostics systems that are accurate and deliver speedy
findings are required in the healthcare and medical
professions. The evolutionary algorithms have the ability to
improve existing healthcare systems, particularly those that
help populations with limited resources.
Medical and health applications have become major participants in the digital health ecosystem. The
project also can work without any internet connectivity and thus can be accessible at any place on
earth. We do not require internet in order to make this diagnostic system work. Accuracy of the
system is very high.
Medical image processing can assist in disease diagnosis, treatment, and early detection. It has
been regarded as one of the most cutting-edge technologies used to combat the COVID-19 crisis.
One can download reports, export and import data and also visualize the history of the patient and
early diagnosis is a must. Any person can sit at home and can get his/her health checked and can
decide on when to see the doctor based on the urgency.
30/34
Acknowledgements
• We would like to thank our project guide Dr. Kanchan Lata Kashyap for helping us
in the development of our project and guiding us all the way round and encouraging
us to take up this idea. We would also like to thank all the professors involved in
teaching us all the concepts regarding this project which helped us in making a base
for our project.
• We would like to thank authors of all the resources from where the image has been
taken.
• We would also like to thank the review panel members who gave their valuable time
to listen to our ideas and for evaluating our project.
• We would also like to thank VIT Bhopal University for giving us an opportunity and
also our project guide for helping us by giving her valuable time and having faith in
us.
• At last we would like to thank our parents who constantly supported and motivated
us and helped us mentally in order to take up this project
31/34
References
Some of the references we used to make this project are: -
• https://www.hindawi.com/journals/jhe/si/818939/
• https://www.nature.com/articles/s41467-020-17419-7
• https://www.sciencedirect.com/science/article/pii/S2352914821000034
• S. Kaur et al., "Medical Diagnostic Systems Using Artificial Intelligence (AI) Algorithms: Principles and Perspectives," in IEEE
Access, vol. 8, pp. 228049-228069, 2020, doi: 10.1109/ACCESS.2020.3042273.
• Subhashini, M. Sushma, B. Y. Goud, M. Nikhil and G. S. K. Reddy, "AI Medical Diagnosis Application," 2021 5th International
Conference on Intelligent Computing and Control Systems (ICICCS), 2021, pp. 1710-1716, doi:
10.1109/ICICCS51141.2021.9432301.
• L. Bishnoi and S. Narayan Singh, "Artificial Intelligence Techniques Used In Medical Sciences: A Review," 2018 8th International
Conference on Cloud Computing, Data Science & Engineering (Confluence), 2018, pp. 1-8, doi:
10.1109/CONFLUENCE.2018.8442729.
• https://lucid.app/documents#/dashboard
• https://towardsdatascience.com/deep-learning-medical-diagnosis-c04d35fc2830
• Shi F, Wang J, Shi J, Wu Z, Wang Q, Tang Z, He K, Shi Y, Shen D. Review of Artificial Intelligence Techniques in Imaging Data
Acquisition, Segmentation, and Diagnosis for COVID-19. IEEE Rev Biomed Eng. 2021;14:4-15. doi: 10.1109/RBME.2020.2987975.
Epub 2021 Jan 22. PMID: 32305937.
• Mirbabaie, M., Stieglitz, S. & Frick, N.R.J. Artificial intelligence in disease diagnostics: A critical review and classification on the
current state of research guiding future direction. Health Technol. 11, 693–731 (2021). https://doi.org/10.1007/s12553-021-
00555-5
32/34
THANK YOU!!!
34/34