Artificial intelligence in Health

Recent advances
Kajol Dahal
Roll no. 140
MPH 2018
Artificial Intelligence in Health
1

Contents
• Introduction &
Terminologies
01
• History02
• Artificial Intelligence in
Nepal
05
04 • Acceptance and scope of AI
in the World
• Conclusion06
• Advancement around the Globe
in Health and Public health
03
2

In computer science, artificial intelligence (AI),
sometimes called machine intelligence,
is intelligence demonstrated by machines, in contrast
to the natural intelligence displayed by humans and
animals.
The term "artificial intelligence" is used to describe
machines that mimic "cognitive" functions that
humans associate with other human minds, such as
"learning" and "problem solving".
Introduction
3

Terminologies
• Algorithms: An algorithm is a set of unambiguous instructions that
a mechanical computer can execute. Many AI algorithms are capable
of learning from data and can themselves write other algorithms.
• Machine learning: It is an application/subfield of artificial
intelligence (AI) that provides systems the ability to automatically
learn and improve from experience without being explicitly
programmed.
4

Neural networks: Artificial neural networks (ANN) are
computing systems vaguely inspired by the biological neural
networks and nodes called artificial neurons. Each connection,
like the synapses in a biological brain, can transmit a signal from
one artificial neuron to another.
Data mining: It is the practice of examining large pre-existing
databases in order to generate new information.
Cloud technologies: Cloud computing refers to the use of a
network of remote servers to store, manage, access and process
data rather than a single personal computer or hard drive.
6/11/2019 5
Terminologies contd…

Weak AI (narrow AI) – non-sentient machine intelligence, typically
focused on a narrow task.
Strong AI / artificial general intelligence (AGI) – machine with the
ability to apply intelligence to any problem, rather than just one
specific problem, typically meaning "at least as smart as a typical
human".
Superintelligence –artificial intelligence far surpassing that of the
brightest and most gifted human minds. Due to recursive self-
improvement, superintelligence is expected to be a rapid outcome of
creating artificial general intelligence.
Types of artificial intelligence
6

Artificial Intelligence in automated driverless cars
https://www.popsci.com/self-driving-cars-cities-usa
7

Artificial intelligence, weather data, and sensors to give farmers insights on plowing,
planting, spraying, and harvesting.
Automatic Recognition of
Ripening Tomatoes by artificial
intelligence
8

Artificial Intelligence in Factories
Japan ranked fourth in the world: In 2016, 303 robots
were installed per 10,000 employees in the
manufacturing industry.
9

Artificial
Intelligence
in Health
Around
the
Globe
10

Timeline of AI in health
Term coined by John
McCarthy. Founded as an
academic discipline in
1956 in US.
1955 Growth of microcomputer and
new levels of network
connectivity. AI systems in
healthcare was designed to
accommodate the absence of
perfect data and build on the
expertise of physicians.
1980s-1990s
• Genomic sequencing
databases
• AI in electronic health
record systems
• Natural language
processing and computer
vision,
• Robot-assisted surgery, etc
2010-2019
•Discovery and
development of
drugs
•Preclinical research
•Personalized Health
Care
•And many more
2019 & onwards
Produced first problem-
solving program, or expert
system, known as Dendral
assisting to identifying
bacteria and
recommending antibiotics
1960-1970
11

Recent advances in Artificial Intelligence in health
13

No longer science fiction, AI and robotics are
transforming healthcare
No longer science fiction, AI is transforming
healthcare
14

Get a modern PowerPoint Presentation that is beautifully designed. I hope and I believe that
this Template will your Time.
M A C H I N E L E A R N I N G
Role of Artificial Intelligence in Health
Technology applications and apps encourage healthier
behaviour in individuals and help with the proactive
management of a healthy lifestyle.
Additionally, AI increases the ability for healthcare
professionals to better understand the day-to-day patterns and
needs of the people they care, for better feedback, guidance and
support.
Health Monitoring: Tools to Support Interventions and
Healthy Behaviors:
Wearable health trackers – like those from FitBit, Apple,
Garmin and others – monitors heart rate and activity levels.
They can send alerts to the user to get more exercise and can
share this information to doctors. 15

Medical chatbots can offer relevant high-quality information,
reassurance, answers, and ways of thinking about the situation related to
human behaviour.
16

AI is already being used to detect diseases, such as cancer,
more accurately and in their early stages.
According to the American Cancer Society, a high proportion
of mammograms yield false results, leading to 1 in 2 healthy
women being told they have cancer. The use of AI is enabling
review and translation of mammograms 30 times faster with
99% accuracy, reducing the need for unnecessary biopsies[1].
Google’s DeepMind Health is working in partnership with
clinicians, researchers and patients to solving and detecting
real-world healthcare problems.
[1] Wired (2016). http://www.wired.co.uk/article/cancer-risk-ai-mammograms
17

Using AI for digital retinopathy screening will allow non-clinicians to be
trained on retinal imaging, obtaining interpretation of the images within
minutes and thus giving patients instant feedback.
18

IBM’s Watson for Health is helping healthcare organizations
review and store far more medical information – every medical
journal, symptom, and case study of treatment and response
around the world – exponentially faster than any human.
Medical Imaging:
Machine learning algorithms can process unimaginable amounts of
information in the blink of an eye and provide more precise than
humans in spotting even the smallest detail in medical imaging.
The company Zebra Medical Vision developed a new platform
called Profound, which analyze of all types of medical imaging
reports that is able to find every sign of potential conditions such
as osteoporosis, breast cancer, aortic aneurysms and many more
with a 90 percent accuracy rate.
19

The AI train a convolutional neural networks
(CNNs) using a dataset of 1,29,450 clinical
images to classify a type of cancer.
20

Improving care requires the alignment of big health data with
appropriate and timely decisions, and predictive analytics can
support clinical decision-making and actions as well as
prioritise administrative tasks.
Digital Consultation
For example, the digital health firm HealthTap developed “Dr.
A.I.,” and apps like Babylon in the UK use AI to give medical
consultation based on personal medical history and common
medical knowledge. Users report their symptoms into the app,
which uses speech recognition to compare against a database of
illnesses and asks patients to specify symptoms to triage whether
they should go to the ED, urgent care, or a primary care doctor.
21

In todays world health emergencies are numerous and medical personnel are limited.
This study has designed a consciousness index to substitute the factor by manpower and
improved the classification accuracy (triage) by applying a machine learning algorithm.
22

Role of AI in Health
Treatment Design
Artificial intelligence systems have been created to analyze data –
notes and reports from a patient’s file, external research, and
clinical expertise – to help select the correct, individually
customized treatment path.
Precision Medicine
Instead of developing treatments for populations and making the
same medical decisions based on a few similar physical
characteristics among patients, medicine has shifted toward
prevention, personalization, and precision.
Genetics and genomics look for mutations and links to disease
from the information in DNA. With the help of AI, body scans can
spot cancer and vascular diseases early and predict the health
issues people might face based on their genetics.
22

These technologies such as genomics, biotechnology, wearable sensors,
or artificial intelligence (AI) are gradually leading to three major
directions. They have been (1) making patients the point-of-care; (2)
created a vast amount of data that require advanced analytics; and (3)
made the foundation of precision medicine.
24

We are living much longer than previous generations, and as we
approach the end of life, we are dying in a different and slower
way, from conditions like dementia, heart failure and
osteoporosis. It is also a phase of life that is often plagued by
loneliness.
AI have ‘conversations’ and other social interactions with people
to keep aging minds sharp.
Medication Management: Improving client adherence
The National Institutes of Health have created the AiCure app to
monitor the use of medication by a patient. A smartphone’s
webcam is partnered with AI to autonomously confirm that
patients are taking their prescriptions and helps them manage
their condition.
24

Role of AI in Health
26
Research on Molecular epidemiology:
Recently, the greatest statistical computational challenge in
molecular epidemiology is to identify and characterize the genes
that interact with other genes and environment factors that bring
the effect on complex multifactorial disease.
This phenomenon cannot be solved by traditional statistical
method due to the high dimensionality of the data and the
occurrence of multiple polymorphism. Hence, there are several
machine learning methods to solve such problems by identifying
such susceptibility gene which are neural networks (NNs),
support vector machine (SVM), and random forests (RFs) in such
common and multifactorial disease

AI allows those in training to go through naturalistic
simulations in a way that simple computer-driven
algorithms cannot.
The advent of natural speech and the ability of an AI
computer to draw instantly on a large database of scenarios,
means the response to questions, decisions or advice from a
trainee can challenge in a way that a human cannot.
27

AI-robot assisted surgery:
Robots have been used in medicine for more
than 30 years. Surgical robots that can either aid
a human surgeon or execute operations by
themselves. They’re also used in hospitals and
labs for repetitive tasks, in rehabilitation,
physical therapy and in support of those with
long-term conditions.
Role of Artificial
Intelligence in Health
28

Role of AI in
Public health
Role of AI in water
treatment
Role of AI in Disease
Surveillance
Role of AI in
screening
Role of AI in Epidemic
Prediction
29

SemanticMD AI Box can
analyze a chest X-ray within
20 seconds and can run off a
portable phone charger
SemanticMD aims to scale its
AI solution to provide low-
cost, accessible TB detection
to vulnerable populations,
particularly throughout
Southeast Asia, China and
Africa.
The company is already
working with partners in
China, South Africa, The
Gambia, Rwanda and Nigeria
– offering instant detection for
less than $1 per scan.
The solution integrates with
X-ray devices to work. It can
be accessed from the cloud or
deployed locally (where
internet access is limited).

Role of AI in Disease Surveillance
This study used a combination of case reports, Baidu (China’s top search
engine) search queries, and climate factors. Then they compared their
working models with existing results from five other provinces, and
discovered that their data models showed stronger statistical significance.
32

How does AI in disease surveillance work

GUARDIAN (Geographic Utilization of Artificial Intelligence in Real-Time for
Disease Identification and Alert Notification) surveillance system is automated
and operates in real time. From a practical point of view, as soon as the cases
come to the Emergency Department, real-time analysis is performed on various
aspects of electronic health records (chief complaints, vital parameters, etc.)
and laboratory results. This means that a physician is informed and alerted of a
case as soon as it is identified.
The main benefit is avoiding delays and preventing further spread of contagious
infectious diseases such as influenza, plague and anthrax.
Role of AI in Symptoms Screening
34

Acceptance and scope of AI in the World
Strategies Acceptance
Future investments Researches
34

GOOD GLOBAL SUMMIT for AI
The “AI for Good Global Summit” took place at ITU in Geneva, Switzerland, on 7-9
June 2017 organized by ITU and the XPRIZE Foundation, in partnership with twenty
UN agencies.
This summit discussed how Artificial Intelligence (AI) could follow a development
course able to assist the achievement of the United Nations’ Sustainable
Development Goals.
36

Countries with AI in its national strategies
37

According to the research firm,
Allied Market Research, the AI
in medicine market was valued at
$719 million in 2017 and is
expected to reach $18,119 million
at the end of 2025.
One analysis has found that the
use of AI applications could
result in approximately $150
billion in saved healthcare costs
annually by 2026 in the USA.
Investments in Artificial intelligence

Researches in AI
1 - CHINA
According to the Times Higher Education, in the period between 2011 and 2015,
China published over 41,000 papers on AI.
2 - UNITED STATES OF AMERICA
Between 2011 and 2015, the US published almost 25,500 papers.
With over 1000 companies and US$10 billion in venture capital, companies like
IBM, Microsoft, Google, Facebook, and Amazon.
3 - JAPAN
11,700 papers published. At present, about 55% of work activities in Japan could be
automated.
Switzerland (2.71)
Impact factor of such researches in AI Singapore (2.24)
Hong Kong (2.00)
40

Artificial Intelligence for Universal Health Coverage
& in SDGs
Healthcare (SDG
Goal 3)
Developing
countries are
endemically short
of medical workers.
AI applications
have the potential
to fill this gap.
Education (SDG
Goal 4)
A UNESCO study
shows trained
teachers are in short
supply in many
countries. AI for
education, AI can
potentially provide
customised teaching
and automated
teaching.
01
02
41
In principle, AI can be applied in all sectors and industries. Therefore, AI can
contribute to achieving all SDGs.
Major goal: Industry, innovation and infrastructure (SDG Goal 9) and responsible
consumption and production of energy (SDG Goal 12)
SDGs

Artificial Intelligence in Nepal
There is a hope….
42

Present uses of AIs in Nepal
In our practical life today, we see, and talk to AI:
• Have you ever wondered how some online shopping websites know your preferences to list relevant items
for you? Or how any email service providers know which email is spam for you?
• Or facebook self tags people in your photos, or collages old photographs or wishes you on your birthday
automatically.
• Siri app; your virtual friend, Zini your mobile doctor are some examples of simple AIs.
Medicine Delivery in the rural area
• Medicine delivery to the rural area is difficult and this has a severe effect on the health of locals in those
areas. Drones are best utilized in such situation with vital medicines being delivered on time and cheaper.
Medical field can have other benefits with the use of AI.
43

Artificial Intelligence in Nepal
• AI is still in infancy period in Nepal. It started in 2011 with the establishment
of Fusemachine company working in the field of Artificial Intelligence.
• As far as our country is concerned, Nepalese youths have done pretty good
work in the field of Artificial Intelligence & Robotics.
However, Fusemachine, AID and Paaila Technology are major tech-company
working in AI for a long time. Still there are around 10+ tech companies working
to come up with innovation in AI. This means we have future of possibility to
work more for AI in our country Nepal.
M-health
DHIS 2
Robot waiters
Nepali Speech Recognition
Query-AI powered chatbots
Nepali Text To Speech
44

Kathmandu, Feb 8: Wiseyak is a health care IT company that uses artificial
intelligence and machine learning to provide services to hospitals, patients and
doctors. The company is trying to build clinical decision support system which
would make it easier for the doctors to reach to the proper diagnosis.
“The software will take the report of the patients, lab results and come to the
conclusion. It will not replace the doctor but will assist the doctor while doing
diagnosis of the patient, so whatever the doctors need is right in front of them. If a
patient comes in to see the doctor with a headache, then the algorithm will ask the
patient about other reoccurring symptoms, making it easier to identify the disease
which will reduce the chances of misdiagnosis providing transparency to the
doctors and patients, also saving the time of both patient and doctor from
unnecessary tests, “said Ravi Bajaracharya, chief technical officer and co-
founder of the company.
A majority of hospitals in Nepal use paper documents instead of electronic record
data and doctors in Nepal are outnumbered by the number of patients, making it
difficult to give time to each patient.
“This innovation will improve the accuracy of the doctor and digitize patient’s
medical records. Another benefit of this technology is that it will make diagnosis
in rural areas easier where doctors are not easily available,” said Dr Hemanta
Shrestha COO and co-founder of the company.
A team of three members came up with an idea of this unique innovation. The
prototype of this technology will be ready in a month and the final product will be
launched within six months in South Asia. This innovation will surely give health
care a new direction in Nepal.
Wiseyak: a health care IT company in
Nepal which uses artificial
intelligence and machine learning to
provide services to hospitals, patients
and doctors.
The company has built clinical
decision support system which would
make it easier for the doctors to reach
to the proper diagnosis. The project is
in piloting stage in some hospitals of
Kathmandu.
This innovation will improve the
accuracy of the doctor and digitalize
patient’s medical records.
Another benefit of this technology is
that it will make diagnosis in rural
areas easier where doctors are not
easily available.
45

This data was fed through an AI engine called AIDR (Artificial Intelligence
Disaster Response) to generate a “Live Crisis Map”. Flowminder, a Swedish
NGO, collaborated with Ncell to use cell phone location data to estimate
population movements after the quake in order to inform the relief efforts.
46
Public Services
Besides impacting the economy and
employment, AI is optimizing the delivery
mechanisms of public goods and
services. During the earthquake in
Nepal, the UN used its 1500 strong
group of volunteers of its Digital
Humanitarian Network to label the
tweets coming out of Nepal as
“urgent needs”, “infrastructure
damage”, and “response effort”.

• On October 27, 2018, project called PD3R, lead by team of Artificial
intelligence for Development (AID), Naxa and BuildChange, won runner
up position in International AI competition called, Call for
Code, organized by IBM.
• Together, the team created Post-Disaster Rapid Response Retrofit
(PD3R). The solution, which is based on AI taught by 3D model images,
has the potential to provide displaced families with immediate access to
engineering advice following a natural disaster.
• PD3R is an AI Solution which uses Deep Learning to classify houses
which can be retrofitted or not.
47

Need and Possibilities of AI in Nepal
• The doctor to population ratio for the whole country is 1:1724. Like most
developing nations, doctors are geographically mal- distributed in Nepal.
• Medicine delivery to the rural area due to its geography is difficult and this has a
severe effect on the health of locals in those areas. There is to mention AI can be
effective in these circumstances.
• Community Leaders Program (CLP) in Nepal is mostly targeted to students and
new learners in AI, so that they can take a lead of their community and organize
events, conduct AI research, build projects, write articles on related topics.
• Likewise, in #SocialGoodSummit 2018, UNDP Nepal has collaborated with Artificial
Intelligence for Development (AID) to explore ways to make tech work for the
Sustainable Development Goals (#SDGs) at the Institute of Engineering in
Pulchowk.
49

Challenges of AI in Nepal
• Unavailable digitization of patients’ records (EHRs)
• Pre-operative planning,
• High costs
• New concepts
• Lack of internet facility at all conditions
• Lack of Governmental strategies
• Safety concerns
• Who will be responsible for harm caused by AI mistakes – the
computer programmer, the tech company, the regulator or the
clinician?
• Fear of losing jobs
50

Conclusion
Technology is changing fast, and the world is changing with it. Concepts that were mere
science fiction only a couple of decades ago -- like artificial intelligence (AI) -- are
quickly becoming commonplace. Advancements of AI in healthcare can assist the
human thoughts, human power, human resources effectively and efficiently.
We know every advancements have both pros and cons. AI could mean a lot of power
will be in the hands of a few who are controlling it.
Also AI dehumanizes warfare as AI technology can kill humans without involving an
actual human to pull the trigger.
In addition, AI does not have the ability to make a judgement call, so the accountability
of their work remains questionable.
But as we accepted computers, digitalization and dependency upon internet through
time, eventually AI will be employed to bring about another revolution in health sector.
51

• Kim D, You S, So S, Lee J, Yook S, Jang DP, et al. A data-driven artificial intelligence model for remote triage in the prehospital environment. Mumtaz W, editor.
PLOS ONE. 2018 Oct 23;13(10):e0206006.
• Rumoro D, Shah S, Hallock MM, Gibbs GS, Trenholme G, Waddell M. A Syndrome Definition Validation Approach for Zika Virus. Online J Public Health Inform
[Internet]. 2017 May 2 [cited 2019 Jun 9];9(1). Available from: http://journals.uic.edu/ojs/index.php/ojphi/article/view/7672
• AI and big data healthcare in Korea [Internet]. [cited 2019 Jun 3]. Available from:
https://www.nature.com/collections/jfbahfhhhi?utm_source=internal&utm_medium=banners&utm_campaign=cpub-
AS_FocalPointAI190328&utm_content=NatureSpringerSciam
• AI in India.pdf.
• Wahl B, Cossy-Gantner A, Germann S, Schwalbe NR. Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings? BMJ
Glob Health. 2018 Aug;3(4):e000798.
• Wong ZSY, Zhou J, Zhang Q. Artificial Intelligence for infectious disease Big Data Analytics. Infect Dis Health. 2019 Feb;24(1):44–8.
• Artificial intelligence in healthcare. 2018;27.
• Sinčak P, Ondo J, Kaposztasova D, Virčikova M, Vranayova Z, Sabol J. Artificial Intelligence in Public Health Prevention of Legionelosis in Drinking Water Systems. Int
J Environ Res Public Health. 2014 Aug 21;11(8):8597–611.
• Panch T, Pearson-Stuttard J, Greaves F, Atun R. Artificial intelligence: opportunities and risks for public health. Lancet Digit Health. 2019 May;1(1):e13–4.
• Artificial_intelligence_in_healthcare_0119.pdf.
• Artificial-Intelligence-AI-in-healthcare-and-research.pdf.
• Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017
Feb;542(7639):115.
• ESCAP_Artificial_Intelligence.pdf [Internet]. [cited 2019 Jun 5]. Available from: https://www.unescap.org/sites/default/files/ESCAP_Artificial_Intelligence.pdf
• First look at cloud-based medical records. [cited 2019 Jun 3]; Available from: http://www.nature.com/articles/d42473-019-00098-4
• Gilad. How AI can solve Australia’s early detection skin cancer challenge; QODE Brisbane 2019 [Internet]. QODE. 2019 [cited 2019 Jun 3]. Available from:
https://qodebrisbane.com/how-ai-can-solve-australias-early-detection-skin-cancer-challenge-qode-brisbane-2019/
• Nadda JP. India’s leadership to end tuberculosis. The Lancet. 2019 Mar 30;393(10178):1270–2.
• Loh E. Medicine and the rise of the robots: a qualitative review of recent advances of artificial intelligence in health. BMJ Lead. 2018 Jun;2(2):59–63.
• Marchalik D. Physician burnout in the modern era. The Lancet. 2019 Mar 2;393(10174):868–9.
• The future is bright for precision medicine in South Korea. [cited 2019 Jun 3]; Available from: http://www.nature.com/articles/d42473-019-00095-7
• Mesko B. The role of artificial intelligence in precision medicine. Expert Rev Precis Med Drug Dev. 2017 Sep 3;2(5):239–41.
• Murray SG, Yim JWL, Croci R, Rajkomar A, Schmajuk G, Khanna R, et al. Using Spatial and Temporal Mapping to Identify Nosocomial Disease Transmission of
Clostridium difficile. JAMA Intern Med. 2017 Dec 1;177(12):1863.
• Wiegand T, Krishnamurthy R, Kuglitsch M, Lee N, Pujari S, Salathé M, et al. WHO and ITU establish benchmarking process for artificial intelligence in health. The
Lancet [Internet]. 2019 Mar 29 [cited 2019 Jun 3];0(0). Available from: https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(19)30762-7/abstract
• Gates B. With immense power to unleash improvements in cost, quality and access, AI is exploding in popularity. Growth in the AI health market is expected to
reach $6.6 billion by 2021—that’s a compound annual growth rate of 40 percent (see Figure 1). :8.
References
52

Thank You
Recently, the President of the Russian Federation said "artificial intelligence is
the future not only of Russia but of all of mankind. There are huge opportunities,
but also threats that are difficult to foresee today. Whoever becomes the leader
in this sphere will become the ruler of the world” 52

Artificial intelligence in Health

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Artificial intelligence in Health

Similar to Artificial intelligence in Health (20)

Recently uploaded

Recently uploaded (20)

Artificial intelligence in Health

Editor's Notes