VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)

ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

Artificial Intelligence in Mental Health

Rikita Mukul Sheth1, Omkar Sunil Raut2
(Masters in Computer Application, VIVA Institute of Technology, Virar(E))
(Masters in Computer Application, VIVA Institute of Technology, Virar(E))

Abstract : Over the period of years, technology has done wonders around us [1]. From creating chatbots to
creating first human-like robot. Artificial Intelligence (AI) has been reaching new heights in every sector of life.
When Covid-19 came into our lives as a pandemic, every part of medical industry had been ushered into a new
era of care delivery. Due to lockdowns being imposed, healthcare sector had to quickly find new ways of safely
providing quality care to patients. In the mental health field, this has become particularly prevalent. The rise of
digital mental healthcare has also brought up the use of a technology: Artificial Intelligence.
With the on-set of Covid-19 and all the stress that came with it, organizations have turned to artificial Intelligence
to potentially broaden access to and availability of mental health services.

Keywords – Artificial Intelligence, Artificial Intelligence in Mental health, Covid-19, Depression Digital Mental
Health, Disorders Medical View, Mental Health, Research View, Wellbeing

I. INTRODUCTION
In 1940's with the invention of the programmable digital computer [2], came the thought of a Programmic
Intelligence that is similar to that of Human Thinking, this mere thought came by the classical philosophers who
described the process of human thinking similar to the manipulation of Symbol. The device and the idea of
Programmic Intelligence inspired many scientists to begin seriously discussing the possibility of building an
electronic brain, this idea gave the birth to Artificial Intelligence. In the start of 21st century, machine learning
was a huge success in various field of academia and industry due to new methods and powerful hardware’s and
new softwires to due to this, investments and efforts increased in the field of AI.
The definition of mental health refers to the behavioural, emotional, and cognitive well-being of a person.
It may refer to a person's state of mind, thoughts, feelings, and behaviour. Sometimes the term "mental health" is
also used in terms of the absence of mental disorders. The environment that surrounds us also affects our mental
health and decision-making. Mental Health can be disrupted by various factors, such as interpersonal connections,
the current situation of a person, the mindset of the person, physical factors, and many more. Mental health is
important as it preserves a person's ability to enjoy life and have a positive attitude towards life. Conditions like
stress, depression, insomnia, anxiety sometimes serve as signs of bad mental health.
As technology evolves, the stress in our work-life and personal life increases. We tend to overlook our
mental health, in order to pursue our professional/personal goals. When the pandemic was announced and
lockdown was implemented, people were confined to their homes and work and personal life became imbalanced.
Mental health took a big hit. Depression, insomnia and such diseases took a spike in the graph. Due to the lack of
human touch, Artificial Intelligence saw a spike in the field of mental health.

F-75
www.viva-technology.org/New/IJRI
VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)
ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

II. DEFINING ARTIFICIAL INTELLIGENCE AND MENTAL HEALTH

2.1 DEFINITION OF ARTIFICIAL INTELLIGENCE
The definition of AI is the ability of a computer or a robot controlled by a computer to do tasks that are
usually done by humans as they require human intelligence and discernment. Artificial Intelligence usually
requires deep knowledge about machine learning and speciality in hardware and software, languages like
Python, java, R are popular when it comes to AI as not any particular language is synonymous with AI[5].
With AI, systems mainly work by ingesting large amount of training data or collection of data, analyse the
data for patterns to make the predictions for future states.

2.2 IMPORTANCE OF ARTIFICIAL INTELLIGENCE

The importance of AI is differed in various fields as per the requirements.AI gives enterprises insights
into their operations that they might have overlooked previously, and hence sometimes, AI can perform tasks
better than humans, especially when it comes to repetitive or detailed oriented tasks like analysing data or
documents to ensure the relevancy in the fields as they complete their jobs quickly and with few to none
errors[5].

This has helped fuel an explosion in efficiency and opened the door to entirely new business opportunities
for some larger enterprises. Prior to the current wave of AI, it would have been hard to imagine using
computer software to connect riders to taxis, or helping a person out of depression or anxiety, but today Uber
has become one of the largest companies in the world by doing just that, and apps like Woebot Health uses it
smart algorithm to understand the user’s needs and converse with them.

2.3 MEANING AND DEFINATION OF MENTAL HEALTH

"A State of wellbeing in which an individual realizes his/her own abilities and state of mind, so can cope
up with the stress occurring in the daily life", is the common definition of Mental health. The deep definition
of mental health can be quotes as "Health is a state of complete physical, mental and social well-being and
not merely the absence of diseases or infirmity ", by this definition we can say that mental health is more than
just the absence of mental disorders or disabilities. Mental Health is rudimentary to our collective ability as
humans to emote, feel, think, and interact with each other, earn a living and live a good life. Mental Health
of an individual can be affected by various different factors as per their current circumstances and choices. It
helps us to determine how we can handle our stress, relate to others, and make healthy choices.

Mental Health is the primary key to every stage of life, that is from childhood to adulthood. People often
confuse Mental Health with Mental illness. A person can have poor mental health but not be have with mental
illness, the same way a person can have mental illness but can experience periods of social, menta and
physical well-being.

2.4 DETERMINANTS OF MENTAL HEALTH

The level of mental health of a person can be determined by various factors such as biological strain,
psychological elements or multiple social factors. For instance, violence or socio-economic pressures are
the risks to poor mental health. Sexual violence is one of the most common and the clearest evidence of
poor mental health.
Excessive work load, unhealthy lifestyle, rapid social changes, gender discrimination, physical
disabilities are some of the reasons as for poor mental health. There are particular psychological and
personality factors that make people vulnerable to mental health problems.

F-76
www.viva-technology.org/New/IJRI
VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)
ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

III. METHODOLOGY

Over the past decades, AI techniques have been seen in the fields of medicine and health in general.
Medical Applications of AI usually include diagnosis, therapy, classifications and robotics and many more.
Usually, AI uses fuzzy logic or neural networks to work around, but when it comes to mental health AI has taken
a different approach. Some of the systems that are used in AI are:[4]

3.1 Expert Systems in Medicine

The ability to capture expert knowledge, facts and reasoning techniques to help care providers in routine
work. To solve a proposed problem by the rules used by ES, the system is used to gather the knowledge from the
rules. These processes can be done through direct input by an expert or database knowledge made up of past case
studies and their results.

3.2 ANN
Human Brain is the collection of 10 billion interconnected neurons. The complex connections of our
human brain inspired the birth of ANN or known as Artificial Neural Network. The idea was to receive several
inputs and generate only one output. Just like our brains makes any decisions, in ANN each connection or the
network has an assigned weight as per importance of the output. ANN Learns by training with inputs known to it,
compares the actual output with its known output and adjusts weight as per errors in previous knowledge.

3.3 Deep learning

Deep Learning is the subset or we can say the child of Machine Learning, which is based on the concept
of behaviour of neurons in the human brain. In order to carry out the process of classification, it tends to
contemplate an evolution of ANN by utilizing a hierarchical level of ANN.
Deep learning algorithms are immensely cogent in learning processes and it ultimately provides a high
degree of intelligence to systems based on them. Some other methodologies are altered into Artificial Intelligence
after deciding on its theory, like usage of Cognitive Behavioural Therapy (CBT), Interpersonal Psychotherapy
(IPT), and Dialectical Behavioural Therapy (DBT) are some of the approaches that experts use while giving
therapeutic support to clients.
To provide more insights into the user problem and self-learning programs, such theories which are
mixed with artificial Intelligence are used. These blends help the users to feel more connected to AI, at the same
time the program self learns the needs of the user and improves automatically.

3.4 DT
DT refers to Decision Tree when we talk about Artificial Intelligence. It is a graphical representation
of a dataset that describes data in a tree-structure, representing a very intuitive way of understanding the
rules. Nodes, branches and leaves is what Decision Tree comprises of. In Decision Tree, leaves represent an
outcome and a node represent a decision. The DT always starts from the root node and grows down by splitting
the data at each level into new nodes.
Accumulating a knowledge from specific dataset through a learning algorithm are often created by DT.
After, the DT structure has been defined, the knowledge can also be represented as sets of if-then rules to improve
human readability [4].

F-77
www.viva-technology.org/New/IJRI
VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)
ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

IV. WORKING OF AI IN MENTAL HEALTH

FIG: 1 Structure of Literature Review

The Growing research in AI and mental health inpatient flow issues, studies adequately combine the two
fields. Different criteria were taken into consideration and then the research was done. The main themes or the
categories are: The literature review revealed a wide range of applications with three main themes: diagnosis,
prognosis and treatment [9].
4.1.1 Diagnosis
Diagnosis of mental health disease still lacks objective measures, often relying on subjective self-
reported questionnaires leading to commonplace misdiagnosis and underdiagnosis. Problems with diagnosis lead
to poor outcomes and resource inefficiencies.
4.1.2 Prognosis
Predictive models are crucial in evidence-based medicine, as they guide healthcare professionals'
decisions on investigations and treatments.
4.1.3 Treatment
Pharmaceutical and psychotherapeutic treatments are only effective for 30–50% of mental health patients
and currently there is no objective gold standard for a combination of psychotherapy and pharmacological
treatments.
Each Person has a different case, and solutions are always different, but the AI follows the terms: Diagnosis
– Prognosis – Treatment.

Sometimes it becomes difficult to detect poor mental health in the early stages, which is of crucial importance
to the prompt and successful treatment of the patient. With the new technologies it has become easier to
to detect cancer with the help of AI, so the thought raised that what if AI could show signals similar to that
of warning signs about your mental health, and notice the relevant symptoms and act as an early detection
mechanism [9].
There is at-least one psychiatrist for every 100,000 people to be treated. It is clear that access to treatment is
a luxury that many people around the globe do not have or cannot afford on top of improving access to mental
health treatments, AI can play a big role within personalized treatments.

F-78
www.viva-technology.org/New/IJRI
VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)
ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

FIG: 2 Working of AI in a Mental Health app

Since AI is very effective when it comes to diagnosis of poor mental health, many companies have come
up with AI based apps, that help the user to improve their mental health. Woebot App is an example when it comes
to Implementing Artificial Intelligence in Mental Health, it is a chat application that not only provides medical
assistance to improve one’s mental health but also interact with their members whose mental health is not stable.
It gives people immediate access to tools they can use anyplace, anytime, at a moment’s notice [6]. Their
automated, relational platform engages people with the right intervention at the right time,
and provides invaluable support that people can depend on.

The Diagram [7] shows a very simple chart of the working of AI in mobile application. Some of our dark
moments escape our mind boxes when we are most vulnerable, they may escape when in a meeting, or lying-in
bed at the middle of the night. Since counselors cannot be there 24x7, apps that uses AI for their diagnosis and
treatment for psychological treatments come in handy they work in the simplest way while having a vast data
network connected through various algorithms and databases, where in the code of the system runs in. Once the
question is asked by the system to the user, and upon the answer of the user, the system searches for similar cases
across its network and comes up with the appropriate outcome for the user, side by side implementing self-learn.
The system keeps learning from the various responses given by the users and understands their response and then
gives feedback. The system also makes sure that the user follows the treatment and gives regular feedback, till it
has not achieved its goal - Improved Mental Health

F-79
www.viva-technology.org/New/IJRI
VIVA-Tech International Journal for Research and Innovation Volume 1, Issue 5 (2022)
ISSN(Online): 2581-7280
VIVA Institute of Technology
10th National Conference on Role of Engineers in Nation Building – 2022 (NCRENB-2022)

V. CONCLUSION

AI holds each unbelievable guarantee and plenty of next-level complexities, together with an associate
array of moral pitfalls [15].AI is more and more vicinity of digital medication and can contribute to psychological
state analysis and apply. various community of specialists unconditional in psychological state analysis and care,
together with scientists, clinicians, regulators, and patients should communicate and collaborate to understand the
complete potential of AI.
AI is huge and continuous improvement within the psychological state sector will do wonders for the
users. because of recent states of lockdowns, folks have turned to AI for psychological state comforts and
designation. The essential part
is combining human intelligence with AI to confirm construct validity, appreciate unobserved factors not
accounted for in information, assess the impact of information biases, and proactively determine and mitigate
potential AI mistakes. the long run of AI in mental attention is promising.
The literature review of Al in psychological state discovered that AI may be used for rising diagnostic
accuracy, personalization of treatment, and predicting clinical [15]. Outcomes to confirm timely delivery of
interventions; the most objective typically being the advance of the standard of patient care.
The literature review on victimization AI patient flow explored predicting evitable readmissions, rising care
potency, optimizing resource allocation, reducing the length of keep, and corroboratory existing algorithms for
additional generalized functions. In each area, studies vary in their accuracy and generalizability. There’s a
necessity for additional analysis which will focus specifically on patient flow in psychological state units. though
this review targeted solutions within the hospital setting, it's vital to focus on that the long run of attention can
embody high integration between services, so any community interventions can have a big indirect impact on the
patient's flow.
These potential AI implementations will affect patients’ expertise either completely or negatively.
additional studies ought to check up on the patient perspective on the mixing of AI in attention as patient expertise
could be a key thought in attention, particularly during a patient-centered approach. Addressing patient issues is
crucial to the wider-scale implementation of Al to take care of patient autonomy around their sensitive
information, notably within the field of medical specialty.
The use of Al in psychiatric attention remains for the most part undiscovered. vital aspects like the patient’s
expertise, clinical significance, and moral issues need additional studies and analysis.

Acknowledgements
We are pleased to present the research paper "AI in Mental Health" as part of the 'Master of Computer
Application' curriculum. We express our deepest gratitude to our research paper guide Prof. Shreya Bhamare
who’s patient guidance, enthusiastic encouragement, made it possible to write the research paper wholeheartedly
and giving useful criticism of this research work.

REFERENCES

[1] Artificial Intelligence for Mental Health and Mental

Sarah Graham1,2 & Colin Depp1,2,3 & Ellen E. Lee1,2,3 & Camille Nebeker4 & Xin Tu1,2 & Ho-Cheol Kim5 & Dilip V. Jeste1,2,6,
[2] Artificial Intelligence in Behavioral and Mental Health Care
[3] Artificial Intelligence in mental health and the biases of language-based models
[4] Artificial Intelligence Methodologies and Their Application to Diabetes
[5] Mental Health – CDC
[6] Woebot Health app – official website
[7] Artificial Intelligence Technique-ScienceDirect
[8] AI's push to understand psychiatry research has the potential to tackle mental illness
[9] Applications of artificial intelligence to improve patient flow on mental health inpatient
[10] 3 ways AI could help our mental health – weforum.org
[11] 5 ways AI could help revolutionize mental health – forbes.com
[12] Using AI for mental health Effectively – verywellhealth.com
[13] AI for mental health and mental illness - pubmed.ncbi.nlm.nih.gov
[14] AI application in decision making
[15] Artificial Intelligence in Behavioral and Mental Health Care – David Luxton

F-80
www.viva-technology.org/New/IJRI