1- AI has achieved high sensitivity of 91-94% and specificity of 96-100% in detecting lung cancer from chest radiography images, demonstrating its ability to support medical imaging analysis.
2- While AI will not replace medical professionals, it can serve as a tool to assist clinicians by analyzing large amounts of data, aiding clinical decisions, and improving outcomes. Primary care physicians may use AI for tasks like note-taking and presenting insights into patients' needs.
3- For AI to be implemented responsibly, its development must address issues like privacy, bias, and transparency to avoid harmful consequences and build trust with clinicians and the public. Collaboration between technology developers and civil society can help ensure AI is developed and applied
2. -In 1940s the American Science Fiction writer Issac Asimov
published a short story that inspired generation of scientists
in the field of robotics, artificial intelligence, and computer
science.
-The birth of AI was denoted by Alan Turing's work "Computing Machinery and
Intelligence” which was published in 1950.
-In this paper, Turing asks the following question, "Can machines think?" From
there, he offers the "Turing Test", where a human interrogator would try to
distinguish between a computer and human text response. While this test has
undergone much scrutiny since its publish, it remains an important part of the
history of AI as well as an ongoing concept within philosophy as it utilizes ideas
around linguistics.
3. -Stuart Russell and Peter Norvig published in 1995, ( Artificial Intelligence: A
Modern Approach) which becomes one of the leading textbooks in the study of
AI. In it, they delve into four potential goals/definitions of AI, which
differentiates computer systems on the basis of rationality and thinking vs. acting:
Human approach:
Systems that think like humans
Systems that act like humans
-AI term was first coined in 1956 by the
American computer scientist, John
McCarthy who defined it as “the
science and engineering of creating
intelligent machines”.
Ideal approach:
Systems that think rationally
Systems that act rationally
4. Generative everything:
AI systems can now compose text, audio, and images to a sufficiently
high standard that humans have a hard time telling the difference
between synthetic and non-synthetic outputs for some constrained
applications of the technology.
STL-10 image generation benchmark
5. 1-Reactive AI
The most basic type of artificial intelligence is reactive AI, which is programmed
to provide a predictable output based on the input it receives. Reactive machines
always respond to identical situations in the exact same way every time, and they
are not able to learn actions or conceive of past or future.
● Deep Blue, the chess-playing IBM supercomputer that bested world
champion Garry Kasparov
● Spam filters for our email that keep promotions and phishing attempts out of
our inboxes
● The Netflix recommendation engine
2- Limited Memory AI
Limited memory AI uses historical, observational data in combination with pre-
programmed information to make predictions and perform complex
classification tasks.
It is the most widely-used kind of AI today.
• Autonomous vehicles use limited memory AI to observe other cars’ speed and
direction, helping them “read the road” and adjust as needed.
6. 3- Theory of Mind AI
With this type of AI, machines will acquire true decision-making capabilities that
are similar to humans.
• The Kismet robot head, developed by Professor Cynthia Breazeal, could
recognize emotional signals on human faces and replicate.
• Humanoid robot Sophia, developed by Hanson Robotics in Hong Kong, can
recognize faces and respond to interactions with her own facial expressions.
4- Self-aware AI
The most advanced as machines can be aware of their own emotions, as well as
the emotions of others around them, they will have a level of consciousness and
intelligence similar to human beings. This type of AI will have desires, needs,
and emotions as well.
7. AI is able to analyze large amounts of data stored by healthcare organizations in
the form of images, clinical research trials and medical claims, and can identify
patterns and insights often undetectable by manual human skill sets.
1- AI algorithms are taught to identify and label data patterns.
2-NLP (Natural Language Processing) allows these algorithms to isolate relevant
data.
3- With DL (Deep Learning) the data is analyzed and interpreted with the help of
extended knowledge by computers.
8. • AI technologies are showing
progress in transforming the
legacy models from being
physic AI technologies are
showing progress in
transforming the legacy models
from being physician centric to
become more patient centric.
• The healthcare sector is
undergoing rapid transformation
globally due to AI.
9. 1- AI in Diagnosis:
• AI has already been deployed in a
few hospitals to diagnose critical
diseases, such as cancer.
• Enlitic, a US based medical
imaging startup, is using deep
learning for tumor detection; its
algorithms have been designed to
detect tumors in human lungs with
the help of (CT) scan.
2- Data mining:
• AI is currently being used in data
mining of medical records.
IBM Watson Health is helping
healthcare organizations apply
cognitive technology to unlock vast
amounts of health data to power
diagnosis.
10. 3- Health assistants & Personal trainers
• AI-based chatbots are being used as health
assistants and personal trainers.
Some of the use cases of chatbots in
healthcare include scheduling doctor
appointments, providing medication
reminders, and identifying the condition
based on symptoms.
• Start-ups like Babylon Health and Your
MD are well-known AI powered healthcare
assistant applications, which helps physicians,
patients and care-givers in the above
functionalities.
• Helix, an AI start-up uses machine
learning to respond to verbal questions and
requests, thus enabling researchers to increase
efficiency, improve lab safety, stay updated
on relevant research topics, and manage
inventory.
11. 4- Drug discovery
• It is now possible to automate
drug design and compound selection
due to AI. Peptone uses AI with Keras
and TensorFlow integration to predict
protein characteristics and features to
reduce complexity in protein design,
detect production and characterization
issues.
5- Clinical trials
• AI is also widely used in clinical trials, like GNS Healthcare which uses AI
to transform diverse streams of biomedical and healthcare data into computer
models. The models enable doctors to identify patients’ responses to treatments
based on their characteristics, thereby, helping deliver personalized medicine
and treatment at scale.
12. 6- Surgical robots
• AI-powered surgical robots are currently being conceptualized by
many technology companies, by leveraging the capabilities of machine
learning applications like Google DeepMind, IBM Watson and others.
• Deploying robots with AI capabilities can result in less damage,
increased precision and speedy recovery.
• Throughout the process it will
be critical to ensure that AI does not
obscure the human face of medicine
because the biggest impediment to
AI’s widespread adoption will be
the public’s hesitation to embrace
an increasingly controversial
technology.
13.
14. -It shows that the effects of COVID-19 on AI development have multiple
perspectives. Many AI startup used machine-learning-based techniques to
accelerate COVID-related drug discovery during the pandemic.
-The AI in healthcare market is expected to be valued at USD 4.9 billion in 2020
and is likely to reach USD 45.2 billion by 2026; it is projected to grow at a
(CAGR) Compound Annual Growth Rate of 44.9% during the forecast period.
-AI investment in drug design and discovery increased significantly “Drugs,
Cancer, Molecular, Drug Discovery” received the greatest amount of private AI
investment in 2020, with more than USD 13.8 billion, 4.5 times higher than 2019.
15. - AtomNet was able to predict the binding of small molecules to proteins by
analyzing hints from millions of experimental measurements and thousands of
protein structures.
- This process enabled convolutional neural networks to identify a safe and
effective drug candidate from the database searched, reducing the cost of
developing medicine.
- The Machine Learning tools are created to draw insights from biological datasets
that are too complex for human interpretation, decreasing the risk for human bias.
Identifying new uses for known drugs is an appealing strategy for Big Pharma
companies, since it is less expensive to repurpose and reposition existing drugs
than to create them from scratch.
16. Recursion Pharmaceuticals raises $13M to discover new drugs using AI to
build complex and consolidated platforms for drug discovery platform
- AI algorithms are able to identify new drug applications, tracing their toxic
potential as well as their mechanisms of action. This technology enables the
company to repurpose existing drugs and bioactive compounds.
-By combining the best elements of biology, data science and chemistry with
automation and the latest AI advances, the founding company of this platform is
able to generate around 80 terabytes of biological data that is processed by AI
tools across 1.5 million experiments weekly.
17. - In 2015, during the West African Ebola virus outbreak, Atomwise partnered
with IBM and the University of Toronto to screen the top compounds capable
of binding to a glycoprotein that prevented Ebola virus penetration into cells in
an in vivo test.
- From the tested compounds, the one selected was chosen because it acted on
other viruses with a similar mechanism of cell penetration.
- This AI analysis occurred in less than a day, a process that would have usually
taken months or years, enabling the development of a treatment for the Ebola
virus
18. AI supports medical imaging analysis
Intro: Lung cancer is a leading cause of cancer related deaths worldwide,
accounting for up to one quarter of all cancer deaths. Because lung cancer is
diagnosed in an advanced stage, screening of early stages lung cancer has
emerged as a powerful strategy for reducing lung cancer mortality.
Problem: Chest radiography is widely used as an initial screening tool for
several important thoracic diseases that is due to its low cost, easy accessibility,
negligible radiation dose, and excellent diagnostic capability. However, the low
sensitivity of lung cancer detection (61%), low specificity (67%), substantial
inter and intra reader variability, and vulnerability to observer error remains a
persistent weakness of chest radiography as a screening tool.
Solution: Deep learning algorithms have staked out a place in lung cancer
detection on chest radiographs and have demonstrated excellent diagnostic
performance in disease enriched settings.
19.
20. Conclusion: AI has achieved:
1. Sensitivity of (91-94%)
2. Specificity of (96-100%)
21. -We are sure that A.I. is Not going to replace medical professionals.
-Due to the spectacular ability of AI in pattern recognition:
Radiology & Pathology are the most susceptible specialties to the dominance of
AI.
-it’s going to be the stethoscope of the 21st century.
-In a Forbes report, Brian Kalis, managing director of digital health and innovation
at Accenture, said:
“ AI would be widely used in US hospitals. AI has the ability to analyze big data
sets – pulling together patient insights and leading to predictive analysis. Quickly
obtaining patient insights helps the healthcare ecosystem discover key areas of
patient care that require improvement. Wearable healthcare technology also uses AI
to better serve patients”.
22.
23. -AI reduces the complications and errors that can occur during surgery and
makes the hospital stay shorter.
-AI technology is emerging as a partner to rapidly complete work, assist with
clinical decisions and improve patient outcomes.
-Primary care physicians can use AI to take their notes, analyze their
discussions with patients, and enter required information directly into EHR
systems. These applications will collect and analyze patient data and present it to
primary care physicians alongside insight into patient's medical needs.
-Applying AI in certain healthcare processes can reduce the time and resources
needed to examine and diagnose patients. With this, medical personnel can
save more lives by acting faster. Machine learning (ML) algorithms can identify
risk exponentially faster and with much more accuracy than traditional
workflows.
24. 1- Empathy cannot be replaced: the core of compassion, there is the process of
building trust, listening to the other person, paying attention to their needs,
expressing the feeling of understanding and responding in a manner that
the other person knows they were understood.
2- Physicians have a non-linear working method: Setting up a diagnosis and
treating a patient are not linear processes. It requires creativity and
problem-solving skills that algorithms and robots will never have.
3- It has never been tech vs. human : since technological innovations always
serve the purpose to help people. Collaboration between humans and technology
is the ultimate response.
25. Major restraints for the market:
1- The reluctance among medical
practitioners to adopt AI-based technologies.
2- Lack of a skilled workforce.
26.
27. 1- The increasing volume of healthcare data and complexities of datasets.
2- The intensifying need to reduce towering healthcare costs, improving
computing power and declining hardware costs.
3- Growing number of cross-industry partnerships and collaborations.
4- Rising imbalance between health workforce and patients.
5- The adoption of this technology by multiple pharmaceutical and
biotechnology companies across the world to expedite vaccine or drug
development processes for COVID-19.
28. -The use of various AI technologies can lead to unintended but harmful
consequences, such as privacy intrusion; discrimination based on gender,
race/ethnicity, sexual orientation, or gender identity; and opaque decision-making,
among other issues.
-Though a number of groups are producing a range of qualitative or normative
outputs in the AI ethics domain, the field generally lacks benchmarks that can be
used to measure or assess the relationship between broader societal discussions
about technology development and the development of the technology itself.
-Furthermore, researchers and civil society view AI ethics as more important than
industrial organizations.
-Addressing existing ethical challenges and building responsible, fair AI
innovations before they get deployed has never been more important. We should
tackle the efforts to address the ethical issues that have arisen alongside the rise of
AI applications.