Scribd
Upload
207 views4 pages

Machine Learning for Mental Health Diagnosis

This document discusses using machine learning algorithms to detect psychological instability and bipolar disorder by analyzing data collected from working individuals. Random Forest achieved the highest accuracy rate of 87.02% compared to other algorithms at detecting depression. Current methods for diagnosing mental illness rely on experts evaluating symptoms rather than biological tests. The proposed system aims to evaluate state-of-the-art methods for classifying mental illnesses using machine learning techniques like FFNN, XGBoost, logistic regression, SVM and decision trees applied to a dataset with individual symptoms and details to predict the type of psychological problem and mental stability level.

Uploaded by

Theertha S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
207 views4 pages

Machine Learning for Mental Health Diagnosis

This document discusses using machine learning algorithms to detect psychological instability and bipolar disorder by analyzing data collected from working individuals. Random Forest achieved the highest accuracy rate of 87.02% compared to other algorithms at detecting depression. Current methods for diagnosing mental illness rely on experts evaluating symptoms rather than biological tests. The proposed system aims to evaluate state-of-the-art methods for classifying mental illnesses using machine learning techniques like FFNN, XGBoost, logistic regression, SVM and decision trees applied to a dataset with individual symptoms and details to predict the type of psychological problem and mental stability level.

Uploaded by

Theertha S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

SYNOPSIS

Finding Psychological Instability Using Machine Learning

Abstract

As we know that people around the globe work hard to keep up with this racing
world. However, due to this each individual is dealing with different health issues,
one of the most known issue is depression or stress which may eventually lead to
death or other brutal activities. These abnormalities can be termed as the Bipolar
disorder which can be treated by undergoing some treatment suggested by
specialists. For this research, data has been collected from working people which
comprises of all kinds of questions for despondent detection and the dataset has been
run through some machine learning algorithms. Random Forest algorithm gives the
highest accuracy as 87.02% compared to the other algorithms.

Existing system

In today’s world, mental illness has wreaked havoc on society and has risen to the
fore as a major issue. People suffering from anxiety, depression, schizophrenia,
bipolar disorder, panic disorder, and other mental disorders are mainly ignoring the
reality that mental disorders are the world’s most severe problem. [Silvana et al.,
2018] Because mental illnesses are significant issues, they may have an impact on
the environment and people’s stability and security. It has a negative influence and
effect on a person’s life since it causes disruption in their behavior, thoughts, and
emotions. Mental illness causes a wide range of changes and negative consequences
in a person’s life, including a loss of faith in himself and his family. Mental illness
has societal consequences as well as a global economic cost. [Silva et al., 2019]For
the diagnosis of mental illness, no biological tests are performed or accessible. 1
Biological tests are not conducted or available for the diagnosis of mental disease.
The expert’s judgment, based on the numerous symptoms, is used to make the
diagnosis. Based on the person’s bodily symptoms, there might be a clear correlation
and influence.
Proposed system

In this research, the main objective is to evaluate the state-of-the-art methodologies


for mental illness classification. We have used five machine learning technique
selected 2 according to the previous researches which are FFNN, XG Boost, Logistic
Regression, SVM and Decision tree is used among which FFNN and XGBoost are
novel approaches in the state-of-the-art method [Kavitha et al., 2019]. A state-of-
the-art technique is used to assess the type of psychological problem a person is
experiencing based on the symptoms of the person. This research aimed at applying
the Machine learning models using feature selection technology to the information
set for mental disease and testing the model with different performance
measurements. The findings exceeded the techniques described in the article and
examined the success of state-of-the-art approaches. It is still necessary to establish
which approaches are more effective in the identification of mental illness and which
algorithm provides superior results.

Modules

User

Registration

Add age

Add gender

Add employment details

Add Family History

Add medication history

Add Behaviour problems if any

Add present health issues if any

Add stress issues if any


Admin

Login

View age

View gender

Analyse family history details

Analyse medication history details

Analyse Behavioural problems details

Analyse present health issues details

Analyse stress issues setails

View employment details

Predict the mental stability

Generate the result

You might also like