Artificial Intelligence in

Healthcare

PRESENTED BY-
MENTOR-
Dr Anuj Kumar Anit
Dr Neha Priya Jr-1
Assistant Professor Department of Community Medicine
Department of Community Medicine Rims Ranchi
Rims Ranchi

1
 CONTENTS
• Introduction
• AI in Public Health
• AI in Healthcare in India
• AI in Healthcare in Worldwide
• AI in Healthcare
o Radiology
o Surgery
o Anesthesia
o Dermatology
o Ophthalmology
o Pathology
o Pharma industry
o Clinical trial Research
• ChatGPT in Healthcare
• Challenges Of AI in Healthcare 2
 What is Human intelligence?
• It’s a composition of abilities like

Learning Reasoning Perceiving

Understanding of Language 3
Feeling
INTRODUCTION
• Artificial Intelligence (AI) refers to the ability of machines to perform
cognitive tasks like thinking, perceiving, learning, problem solving and
decision making.
• It is sometimes called as machine intelligence.
• Artificial intelligence system learns from experience, uses the learning
to reason, recognizes images, solves complex problems,
understands languages and creates perspectives.

• AI is a machine, device, robot or tool that is powered by software

programs to display the characteristic reasoning and thinking
patterns of humans.

4
 Core Concept of AI
 Machine Learning (ML):
• Machine Learning is a subset of Artificial Intelligence .
• Based on algorithms that gives the ability to computers to learn from data,
identify patterns and make decisions or predictions with minimal human
intervention.
 Deep Learning(DL):
• Deep Learning is the subset and next evolution of machine learning
• Concerned with algorithms inspired by the structure and function of the
brain called artificial neural networks.
• Like a human brain, computer can identify various features in data
automatically.

5
 Cont..

 Natural Language Processing (NLP):

• Natural language processing is a branch of AI that focuses on enabling
computers to understand, interpret, and generate human language.
• NLP involves tasks such as language translation, sentiment analysis,
named entity recognition, and question answering.

 Computer Vision:
• Computer vision is a field of AI that enables computers to interpret and
understand visual information from images or videos.
• It encompasses tasks such as object detection, image classification, facial
recognition, and scene understanding.

6
Types of Artificial Intelligence
 Narrow AI (Weak AI): designed to perform a specific task or a narrow
range of tasks.
• These AI systems are specialized and focused on solving particular
problems within a limited domain.
 General AI (Strong AI): refers to AI systems that possess human-like
intelligence and can understand, learn, and apply knowledge across a wide
range of tasks and domains.

 Superintelligent AI: refers to AI systems that surpass human intelligence

in all aspects.
• These hypothetical systems would possess cognitive abilities far beyond
those of human beings.

7
8
Introduction to AI in healthcare

9
 AI in Public Health
• The ability of AI models to analyse and interpret large health datasets can
be transformative for public health & epidemiology and lays the foundation
for precision public health.

• The analysis of large health data from many sources may provide more
and better insights on the determinants of disease on both the
personalized and population levels.
• The use of AI in public health is still in its early stages, but it has the
potential to revolutionize the way we prevent, diagnose, and treat disease.

• This can help accelerate public health surveillance and shape public health
policies and implementation activities.

10
 Cont..
• Role of AI in Ayushman Bharat Digital Mission (ABDM) –
• The current ability to digitally identify individuals, physicians, and
healthcare facilities, enable electronic signatures, guarantee non-
repudiable contracts, make paperless payments, securely store digital
records, and make contact with people, opens up possibilities for
streamlining healthcare information through digital management.

• Imaging Biobank for Cancer - NITI Aayog with Department of Bio-

Technology (DBT) aims to build a database of cancer-related radiology and
pathology images of more than 20,000 profiles of cancer patients.

• NITI Aayog, is closely working with Microsoft and the medical start-up
Forus Health to develop automated solutions for early detection of
diabetic retinopathy.
11
12
Cont…
• Wadhwani AI is an official AI partner of Central Tuberculosis (TB) Division,
developing various interventions related to the TB patient care and helping
India’s National TB Elimination Programme (NTEP) become AI-ready.

• The Karnataka government launched “Healthcare Pods” developed by

the Bangalore- based firm Vevra. These pods are innovative movable
hospitals integrated with AI and help in containment of contagious
diseases such as Covid-19 and TB.

13
Cont..
• ePaarvai -
• A smartphone app created by Tamil Nadu
e-Governance Agency (TNeGA) based on
AI for combating Cataract.
• The app may be used to perform a quick
eye screening by just clicking a photo.
Additionally, macular disintegration can be
found using the application.

.
14
Application of AI in Covid-19 Management
• AI is being successfully used in the identification of disease clusters,
monitoring of cases, prediction of the future outbreaks, mortality risk,
diagnosis of COVID-19, disease management by resource allocation,
facilitating training, record maintenance and pattern recognition for studying
the disease trend. It’s applications are;-

• Prediction and tracking: Bluedot identified a cluster of pneumonia cases

and predicted the outbreak and geographical location of the COVID-19
outbreak based on available data using machine learning.
• HealthMap collects the publicly available data on COVID-19 and makes it
readily available to facilitate the effective tracking of its spread.
• Contact tracing: AI can augment mobile heath applications where smart devices
like watches, mobile phones, cameras and range of wearable device can be
employed for diagnosis, contact tracing and efficient monitoring in COVID-19
15
HealthMap COVID 19 TRACKING
16
 Cont…
• Monitoring of COVID-19 cases: AI techniques are applied for monitoring
patients in clinical settings and prediction of course of treatment. Based on the
data derived from vital statistics and clinical parameters.
• AI may provide critical information for resource allocation and decision-making
by prioritizing the need of ventilators and respiratory supports in the ICU.

• Early diagnosis: AI was used for the detection and quantification of COVID-19
cases from chest x-ray and CT scan images.
• Researchers have developed a deep learning model called COVID-19 detection
neural network (COVNet), for differentiating between COVID-19 and
community-acquired pneumonia based on visual 2D and 3D features extracted
from volumetric chest CT scan, thus, reducing the burden for medical
practitioners & HCWs.

17
18
 Cont..
• Disease surveillance and outbreak detection: AI can be used to analyze
large amounts of data from electronic health records, social media, and
other sources to identify patterns of disease and potential outbreaks.
• This information can be used to quickly deploy resources and interventions
to contain outbreaks and prevent the spread of disease.

• Risk prediction and prevention: AI can be used to develop predictive

models that identify individuals who are at high risk for developing certain
diseases.
• This information can be used to target interventions for these individuals,
such as preventive screenings or education programs.

19
 Cont..
• Healthcare planning and policy: AI can be used to analyze data and
develop models to predict the future demand for healthcare services.
• This information can be used to make better decisions about resource
allocation and to plan for future public health challenges.
• Healthcare chatbots: AI chatbots can be used to provide information and
support to patients, as well as to collect data on their health status.
• This information can be used to improve the quality of care and to identify
patients who need additional support.
• Personalized medicine: AI can be used to develop personalized
treatment plans for individuals based on their individual genetic makeup,
medical history, and other factors.
• This can help to improve the effectiveness of treatment and reduce the risk
of side effects.
20
 AI in Healthcare in India

• The Manipal Group of Hospitals has tied up with IBM’s Watson for
Oncology to aid doctors in the diagnosis and treatment of 7 types of
cancer.
• Aravind Eye Care Systems is presently working with Google
Brain, after previously helping Google develop its retinal
screening system by contributing images to train its image parsing
algorithms.
• BeatO – It is a smartphone glucometer, which can be plugged in to a
smartphone to take reading and is then saved in the app.
• Driefcase – Online app and portal which digitizes personal health
records of a person and provide users with a single-point, easy-to-use
access to medical data.
21
 Cont..
• NIRAMAI Health Analytix-
NIRAMAI, have developed a novel artificial intelligence-based
medical device to detect breast cancer at a much earlier stage than
traditional methods or self-examination.

• InstaECG And InstaEcho –

Introduced by Tricog, a startup, which is aided by cloud connected
ECG and Echo machines and in-built algorithms that receive, interpret
and send back analysis.
InstaEcho helps doctors diagnose echocardiograms quickly and
accurately and provide care coordination tools to assist in patient care.

22
 AI in Healthcare in Worldwide

• Fitbit, Apple, and other health trackers can monitor heart rate,
activity levels, sleep levels, and some have even launched ECG tracings
as a new feature.
• Germwatcher is a system developed by the University of Washington
to detect and investigate hospital acquired infections.
• Online consultation: The greatest asset AI brings to preventive
healthcare is providing people with medical aid anywhere, anytime.
• Ex- Babylon (An app that offers online consultation based on individual
medical records and medical database)

23
 Cont..
• AI-therapy is an online course that helps patients treat
their social anxiety using therapeutic approach of
cognitive behavior therapy.
It was developed from a program CBTpsych.com at
University of Sydney.
• IBM’s Watson Health will be equipped to efficiently
identify symptoms of heart disease and cancer.
• Molly is a virtual nurse that is being developed to
provide follow-up care to discharged patients allowing
doctors to focus on more pressing cases.

24
 AI in Radiology
• Till now the most useful applications of AI in healthcare has been in
the field of radiology.
• AI is now analyzing X-rays, CT scans, MRIs and the like for abnormal
readings, just like a radiologist.

X-ray of a hand by automatic

calculations of bone age by software
25
 AI in Surgery
• AI offers precisely accurate surgical robots and finely tuned diagnostic
algorithms to solve various complex surgical and clinical problems.
• A surgical robot is dexterous, fatigue and tremor-free device which
makes it perfect for surgeries.
• Robotic surgery also may reduce blood loss and hospital stay.

26
Contd..
• Automation of suturing: Raven II Surgical robot, PR2 robot - They
have been tested with 87% successful suturing accuracy.

27
 AI in Anesthesia
• Closed Loop Anesthesia Delivery System (CLADS) -
• It is an automated intravenous infusion system using feedback principle.
• It delivers propofol based on patients’ frontal cortex electrical activity
(EEG) as determined by bispectral index (BIS) feedback.
Mcsleepy -
• A system which administers drugs for general anaesthesia and
monitors their separate effects completely, automatically with no manual
intervention.
• Measures 3 separate parameters on an – depth of hypnosis via EEG,
pain via Analgoscore (pain score), muscle relaxation via phonomyography

28
Cont..
• Sedasys -
• A computer assisted personalized sedation system.
• Mild to moderate propofol sedation can be delivered by non-
anesthesiologists.
• Consists of a full monitoring array.

• Kepler Intubation System –

• It is a robotic intubation system.
• Consists of robotic arm ,joy stick, Pentax AWS video
laryngoscope & software control system.
29
 AI in Dermatology
• Content Based Image Retriever (CBIR) -
• DermEngine’s Visual Search – An intelligent dermatology software used for
the imaging, documentation and analysis of skin conditions including skin
cancer.
• Skin Vision - This software focuses on identifying skin cancer images and
gives medical professional visually similar pictures with the diagnosis
and the risk of malignancy of past cases.
• Skin10 - An app developed to help dermatologists diagnose skin condition.
It’s algorithm is built on an extensive database of skin conditions.

30
 AI in Ophthalmology
• AI in Ophthalmology tends to focus on imaging, and the
automated interpretation of fundus photographs and Optical Coherence
Tomography (OCT) scans.
• Other areas of interest include patient management, disease risk
prediction, progression analysis, and automated interpretation of non-
imaging modalities. (e.g. visual field tests)

31
 AI in Pathology
• Whole Slide Imaging (WSI): also commonly referred to as
“virtual microscopy”, aims to emulate conventional light
microscopy in a computer-generated manner.
• WSI consists of two processes.
• The first process utilizes specialized hardware (scanner) to
digitize glass slides, which generates a large representative
digital image .
• The second process employs specialized software (i.e,
virtual slide viewer) to view and/or analyze these enormous
digital files.

WHOLE SLIDE
IMAGING 32
Contd..
• WebMicroscope – It is an online microscopy software that allows users to
store, share and evaluate a massive collection of digitized microscope
samples.
• Pathologists, pharmacologists and medical researchers can access
this information and work together to manage data and discuss results.

33
SCREENSHOT OF WebMicroscope
 AI in Pharma Industry
• AI is being used in pharma industry are drug discovery, drug
manufacturing, diagnostic assistance, and optimizing medical treatment
processes.
• The tech can also help with the repurposing of new drugs. AI and ML
algorithms are able to identify molecules that may have failed in clinical
trials and predict how the same compounds could be applied to target other
diseases.

34
 AI in Clinical Trial Research
• Artificial Intelligence is helping and shaping clinical trial research.
• It can be used for remote monitoring and real time data access for
increased safety.
• Example– Monitoring of biological and other signals for any sign of
harm or death of participants.

35
 ChatGPT in Healthcare
• ChatGPT is a remarkable languagemodel running
on Generative Pretrained Transformer (GPT) and delivers human-like
text in real-time seamlessly.
• Its DL algorithms allow ChatGPT to analyze large amounts of complex datasets
and generate relevant responses in accordance with the user inputs provided.
• Applications –
o Improving healthcare access
o Enhancing diagnostics
o Personalized healthcare support
o Summarization of medical papers for improved medical experience
o Enhanced clinical decision support
o Biomedical research
o Medical education
36
 Challenges of ChatGPT in Healthcare

• Lack of real time data.

• Potential for ChatGPT to reinforce existing biases and inequalities in
healthcare.
• Risk of misdiagnosis or incorrect treatment recommendations.
• Data breaches and unauthorized access to private medical data are
possible.
• Concern about the potential for ChatGPT to replace human decision-
making in healthcare.

37
 Challenges of AI in Healthcare
• Privacy Issues - Patient data contains highly sensitive personally
identifiable information (PII) (e.g., medical histories, identity information,
payment information)
• The large data requirements of most AI models and hospitals concerns over
the possibility of data leakages reduce the adoption of healthcare AI
technologies.
• Accountability and Transparency - Due to the lack of transparency and
accountability associated with machine learning.
• it might be difficult or impossible to understand why an algorithm made a
certain conclusion.
• Bias and Inequality - There are risks involving bias and inequality in
healthcare AI.
• AI systems learn from the data on which they are trained, and they can
incorporate biases from those data.
38
Cont..
• Security and Cyber security - As AI becomes increasingly used to assist
in the execution of cyber-attacks.
• AI software could be hacked, and the data it uses can be changed or
manipulated.
• Training - As healthcare is getting digitized, the medical curriculum has not
kept pace with introducing medical students or residents to new
technologies such as AI, mobile healthcare applications, and telemedicine.
• There is a need to establish a framework where digital concepts are tested
as part of the entrance examinations and training on the use of
technologies is part of the clinical program.
• Standardization - Use of AI in healthcare is impacted by the liability for
the predictions of an algorithm. There can be wide interpatient variability in
terms of available data elements.
• This interpatient variability leads to missing data
39
 Conclusion

• AI can be used as a supporting friend to the overburdened healthcare

sector.
• AI has a huge role to play in precision medicine, personalised
medicine.
• AI can help in analysing huge volume of health data and give us
valuable insights and trends. It can help us making data-driven
decisions.
• Humans are irreplicable provided they adapt to the change and have
the necessary empathy a healthcare staff should possess. Because
that’s the only frontier left for us against algorithms and machines.
40
 References
1. Amisha, Malik P, Pathania M, Rathaur VK. Overview of artificial
intelligence in medicine. J Family Med Prim Care 2019;8:2328-31.
2. Davenport T, Kalakota R. The potential for artificial intelligence in
healthcare. Future Healthc J. 2019 Jun;6(2):94-98. doi:
10.7861/futurehosp.6-2-94. PMID: 31363513; PMCID:
PMC6616181.
3. Wang X, He X, Wei J, Liu J, Li Y, Liu X. Application of artificial
intelligence to the public health education. Frontiers in Public Health
[Internet]. 2023 [cited 2023 Sep 22];10.
4. Jungwirth D, Haluza D. Artificial Intelligence and Public Health: An
Exploratory Study. Int J Environ Res Public Health. 2023 Mar
3;20(5):4541.
41
42