Guru Gobind Singh College of Engineering Nasik
Department of Basic Engineering Science
Academic Year 2023-24
Sem-II
AUDIT COURSE REPORT
Class: SE Computer
Title of Project: SMART CITIES:- Smart health care system
Group Members:
Roll No. Name
31 Sanika Dusane
17 Varda Bhat
7 Ritika Amarale
28 Janvhi Dange
1
INDEX
Sr.No. Topic Page No.
1 Introduction 3
2 Objective 4
3 Methodology 5
4 Technology
6
5 Future 12
6 Advantages 13
7 Disadvantages 14
8 Challenges 15
9 Conclusion 17
10 References 18
2
Introduction
Artificial intelligence (AI) and related technologies are increasingly
prevalent in business and society, and are beginning to be applied to
healthcare. These technologies have the potential to transform many
aspects of patient care, as well as administrative processes within provider,
payer and pharmaceutical organisations.
There are already a number of research studies suggesting that AI can
perform as well as or better than humans at key healthcare tasks, such as
diagnosing disease. Today, algorithms are already outperforming
radiologists at spotting malignant tumours, and guiding researchers in how
to construct cohorts for costly clinical trials. However, for a variety of
reasons, we believe that it will be many years before AI replaces humans
for broad medical process domains. In this article, we describe both the
potential that AI offers to automate aspects of care and some of the barriers
to rapid implementation of AI in healthcare.
Expert systems based on collections of ‘if-then’ rules were the dominant
technology for AI in the 1980s and were widely used commercially in that
and later periods. In healthcare, they were widely employed for ‘clinical
decision support’ purposes over the last couple of decades5 and are still in
wide use today. Many electronic health record (EHR) providers furnish a set
of rules with their systems today.
Expert systems require human experts and knowledge engineers to
construct a series of rules in a particular knowledge domain. They work well
up to a point and are easy to understand. However, when the number of
rules is large (usually over several thousand) and the rules begin to conflict
with each other, they tend to break down. Moreover, if the knowledge
domain changes, changing the rules can be difficult and time-consuming.
They are slowly being replaced in healthcare by more approaches based on
data and machine learning algorithms.
Because radiographs are the most common imaging tests conducted in
most radiology departments, the potential for AI to help with triage and
interpretation of traditional radiographs (X-ray pictures) is particularly
noteworthy.
3
Objective
Using AI in healthcare has the potential improve predicting, diagnosing and
treating diseases. Through machine learning algorithms and deep learning,
AI can analyse large sets of clinical data and electronic health records and
can help to diagnose the disease more quickly and precisely.
AI programs are applied to practices such as diagnostics, treatment
protocol development, drug development, personalized medicine, and
patient monitoring and care.
Because radiographs are the most common imaging tests conducted in
most radiology departments, the potential for AI to help with triage and
interpretation of traditional radiographs (X-ray pictures) is particularly
noteworthy.
As widespread use of AI in healthcare is relatively new, research is ongoing
into its application in various fields of medicine and related industries.
Using AI also presents unprecedented ethical concerns related to issues
such as data privacy, automation of jobs, and amplifying already existing
biases.Furthermore, new technologies brought about by AI in healthcare
are often resisted by healthcare leaders, leading to slow and erratic
adoption.
4
Methodology
The existing methodologies are focused on addressing individual aspects of
the COVID-19 pandemic in isolation (e.g. tracking, managing, securing,
vaccinating), while COVID-19 has shown us that we need a combination of
approaches applied in a synchronised approach that supports and enhances
the overall process. To secure the complex and coupled healthcare
systems, we need to start constructing combinations of possible solutions—
learning from the COVID-19 pandemic.
One such solution is to refer to the concept of digital modernity and smart
manufacturing (i.e. Industry 4.0) and develop a dynamic and self-adapting
system for predictive edge analytics of health devices supported with
artificial intelligence and real-time data. Such AI system should be based
on deep learning algorithms, mathematical principles and quantitative data.
This approach would intersect knowledge from AI, healthcare, supply
chains, economics, risk assessment, and edge computing.
By applying an interdisciplinary multi-method, this system would also
record a snapshot in time and collect a diverse set of data on COVID-19,
which can be reused for Disease X by future researchers long after COVID-
19 is gone, promoting the development of a standardised COVID-19 open
data sources . The multi-method interdisciplinary research does not mean
that the proposed system should present incremental research, but quite
the opposite. According to current data, COVID-19 presents once in a
century opportunity to study a global pandemic of this magnitude. Hence,
by designing a system based on applying a multi-method interdisciplinary
research, the emerging system would present novel knowledgeSince
COVID-19 is a rare event, the system would need to be constructed with
an iterative methodology, building upon knowledge developed through
individual phases. For this approach to be successful, the methodology
would need to be designed with the different phases organised in six steps
(i.e. six cycles), namely ‘prepare’, ‘measure’, ‘adapt’, ‘predict’, ‘defence’
and ‘improved’ the readiness for a Disease X event.
The process and activities in the workflow include using data from COVID-
19 observations to prepare narratives for a Disease X event; using data
from COVID-19 to measure and quantify the primary and secondary risks
from a disease × event, using existing digital technologies (e.g. Industry
4.0, Internet of Things) to adapt the vaccine production and supply chains;
using predictive algorithms for assessment of failures and losses; using AI
algorithms for securing (defending) the healthcare system; and using
existing AutoML methods for improving such AI algorithms.
To construct categorisations of concepts related to AI, real time data, and
edge analytics, we first conducted a quantitative search for research data
records on the Web of Science core collection. This resulted in a large data
set, which we firstly analysed with the Web of Science results analysis tool.
5
AI Technology used in Health Care
AI-Driven Drug Distribution
Artificial intelligence (AI) has emerged as a powerful tool that harnesses
anthropomorphic knowledge and provides expedited solutions to complex
challenges. Remarkable advancements in AI technology and machine
learning present a transformative opportunity in the drug discovery,
formulation, and testing of pharmaceutical dosage forms. By utilizing AI
algorithms that analyze extensive biological data, including genomics and
proteomics, researchers can identify disease-associated targets and predict
their interactions with potential drug candidates. This enables a more
efficient and targeted approach to drug discovery, thereby increasing the
likelihood of successful drug approvals. Furthermore, AI can contribute to
reducing development costs by optimizing research and development
processes. Machine learning algorithms assist in experimental design and
can predict the pharmacokinetics and toxicity of drug candidates .
AI-For Disease Prediction and Prevention
Clinical prediction is integral to modern healthcare, leveraging current and
historical medical data to forecast health outcomes. The integration of
Artificial Intelligence (AI) in this field significantly enhances diagnostic
accuracy, treatment planning, disease prevention, and personalised care
leading to better patient outcomes and healthcare efficiency.This
systematic review implemented a structured four-step methodology,
including an extensive literature search in academic databases (PubMed,
Embase, Google Scholar), applying specific inclusion and exclusion criteria,
data extraction focusing on AI techniques and their applications in clinical
6
prediction, and a thorough analysis of the collected information to
understand AI's roles in enhancing clinical prediction.
IoT for HealthCare
IoT for Hospitals:- Apart from monitoring patients’ health, there are many
other areas where IoT devices are very useful in hospitals. IoT devices
tagged with sensors are used for tracking real time location of medical
equipment like wheelchairs, defibrillators, nebulizers, oxygen pumps and
other monitoring equipment
IoT for Health Insurance Companies – There are numerous opportunities
for health insurers with IoT-connected intelligent devices. Insurance
companies can leverage data captured through health monitoring devices
for their underwriting and claims operations.
IoT for Physicians - By using wearables and other home monitoring
equipment embedded with IoT, physicians can keep track of patients’
health more effectively. They can track patients’ adherence to treatment
plans or any need for immediate medical attention .
IoT for Patients - Devices in the form of wearables like fitness bands and
other wirelessly connected devices like blood pressure and heart rate
monitoring cuffs, glucometer etc. give patients access to personalized
attention.
The major advantages of IoT in healthcare include:
7
Cost Reduction: IoT enables patient monitoring in real time, thus
significantly cutting down unnecessary visits to doctors, hospital stays and
re-admissions.
Improved Treatment: It enables physicians to make evidence-based
informed decisions and brings absolute transparency.
Faster Disease Diagnosis: Continuous patient monitoring and real time data
helps in diagnosing diseases at an early stage or even before the disease
develops based on symptoms.
Proactive Treatment: Continuous health monitoring opens the doors for
providing proactive medical treatment.
Drugs and Equipment Management: Management of drugs and medical
equipment is a major challenge in a healthcare industry. Through
connected devices, these are managed and utilized efficiently with reduced
costs.
Error Reduction: Data generated through IoT devices not only help in
effective decision making but also ensure smooth healthcare operations
with reduced errors, waste and system costs.
AI in Patient Monitoring
The use of Artificial Intelligence (AI) for patient monitoring has opened
new doors in the world of remote healthcare In this article, we'll explore
how AI is used to monitor patients, its benefits, difficulties, and future
prospects. Remote Patient Monitoring leverages technology to gather and
transmit patient data to healthcare providers in different locations
Early Detection of Complications: AI algorithms can identify subtle
changes in vital signs and predict potential complications, enabling
preventive measures.
Personalized Treatment Plans: AI analyzes individual patient data to
create personalized treatment and care plans, enhancing patient
engagement and outcomes.
Enhanced Communication: AI-driven chatbots and applications foster
improved communication between patients and healthcare providers
Bridging Geographical Gaps: By facilitating remote patient monitoring, AI
enables healthcare provision in remote and underserved regions where
access to medical facilities is limited.
8
24/7 Availability: AI-driven monitoring tools offer round-the-clock
supervision, ensuring that care is available whenever needed, regardless
of location
Virtual HealthCare Assistants
AI-powered healthcare virtual assistants can deftly handle simple tasks so
that skilled medical professionals can use their time to effectively manage
more complex jobs that they have been trained for.
Massive reduction care costs: Virtual assistants help to significantly reduce
business overheads of manning the desk or call centers.
Ease the burden on doctors: It is nearly impossible for doctors to attend to
all patients on a tight schedule, whereas medical virtual assistants are
accessible 24*7.
Anonymity: AI-powered medical chat is designed to maintain an individual’s
anonymity which is beneficial for sensitive cases.
Timely monitoring: A healthcare virtual assistant can help monitor a
patient’s health, suggest treatment, or give follow-up reminders.
Scalability: Virtual assistants can seamlessly handle numerous customers
without compromising the quality or adding to the cost.
Patient satisfaction: A healthcare virtual assistant safely provides timely
and intelligent solutions, which, in turn, increases patient satisfaction...
Blockchain for Medical Records
Waste from factors like failure of care delivery and failure of care
coordination is responsible for up to 16 percent of national healthcare
spending in the U.S. Blockchain-based medical records offer a cure for
these ills. The decentralized nature of the technology creates one
ecosystem of patient data that can be efficiently referenced by doctors,
hospitals, pharmacists and anyone else involved in treatment. In this way,
the blockchain can lead to better diagnoses and personalized care plans.
9
Blockchain has serious implications for pharmaceutical supply chain
management, and its decentralization virtually guarantees full
transparency in the shipping process. Once a ledger for a drug is created,
it will mark the point of origin. The ledger will then continue to record data
every step of the way, including who handled it and where it has been, until
it reaches the consumer.
AI In Mental Health Services
AI with the use of NLP and ML can be used to help diagnose individuals with
mental health disorders. It can be used to differentiate closely similar
disorders based on their initial presentation to inform timely treatment
before disease progression. For example, it may be able to differentiate
unipolar from bipolar depression by analyzing imaging and medical scans.
AI also has the potential to identify novel diseases that were overlooked
due to the heterogeneity of presentation of a single disorder.[8] Doctors
may overlook the presentation of a disorder because while many people
get diagnosed with depression, that depression may take on different forms
and be enacted in different behaviors. AI can parse through the variability
found in human expression data and potentially identify different types of
depression.
AI in Ederly Care
10
AI-powered systems can assist older adults in performing daily activities,
such as medication management, fall detection, and navigation, enabling
them to live independently for longer . The system can send a real-time
alarm to the family, care facility, or medical agent without human
assistance if it determines that something odd might occur (broadly) or
something is wrong with the user's health practices or medical
recommendations. In addition, AI-driven wearable devices can monitor
vital signs and activity levels, promoting a healthier and more
independent lifestyle.AI algorithms have the potential to revolutionize
health monitoring for older adults. By analyzing data from wearable
devices, electronic health records, and other sources, AI can provide real-
time data analysis, detect early warning signs of diseases, and provide
personalized treatment plans and recommendations. AI-enabled
telemedicine platforms also enable remote monitoring and virtual
consultations, improving access to healthcare for older adults in remote or
underserved areas. In addition to a diagnostic and management
algorithm, humankind has created an iPad software with Reshma
Merchant in Singapore for geriatric syndromes (RGA). It has been
demonstrated that AI can read retinal scans like doctors . AI will also be
crucial in the deprescription process. These methods will be used often in
medicine over the next 10 years. Other possible applications include the
ongoing development of virtual medicine and improved assessment of
osteoporosis and fracture risk concerning age, frailty, and life expectancy.
11
Future of AI In HealthCare
Artificial intelligence (AI) is transforming the way we interact, consume
information, and obtain goods and services across industries. In health
care, AI is already changing the patient experience, how clinicians practice
medicine, and how the pharmaceutical industry operates. The journey has
just begun.As AI finds its way into everything from our smartphones to the
supply chain, applications in health care fall into three broad groupings1:
Patient-oriented AI
Clinician-oriented AI
Administrative- and operational-oriented AI
The future of AI in health care could include tasks that range from simple
to complex—everything from answering the phone to medical record
review, population health trending and analytics, therapeutic drug and
device design, reading radiology images, making clinical diagnoses and
treatment plans, and even talking with patients.
The future of artificial intelligence in health care presents:A health care-
oriented overview of artificial intelligence (AI), natural language processing
(NLP), and machine learning (ML)Current and future applications in health
care and the impact on patients, clinicians, and the pharmaceutical industry
A look at how the future of AI in health care might unfold as these
technologies impact the practice of medicine and health care over the next
decade.Based on our work with clients on applications of AI in health care,
we offer these insights:Factor in extra time and cost for early adoption:
even relatively small projects require additional time and effort up front
performing business case validations and proof of concept. Reduce cost and
complexity by leveraging open-source technologies and limiting
customization. Build solutions for average transaction length and volumes
but with capacity for longer transactions and peak volumes.Involve
personnel with a combination of technology and health care backgrounds
who have a clearer understanding of end users’ needs and preferences, as
well as options for technology solutions. Carefully select the data used to
“train” any AI/ML model: Make sure it accurately represents the production
data and does not incorrectly train and bias the model. Since training of
models is an ongoing process, expected return on investment (ROI) should
include the time period and time frame.
12
Advantages
1) Ability to analyse data and improve diagnosis
2) Better patient care
3) Reduced cost of care
4) Real-time, accurate data
5) Improved workload and reduced staff stress
6) Support with administrative tasks
7) Health monitoring and digital consultations
Whether it’s wearable technologies that help monitor a patient’s health or
digital consultations that can be done on a smart device, AI is a great way
of improving the way medical professionals record and analyse data. It also
allows patients to monitor their own health and receive expert assistance
online. It’s no secret that jobs in healthcare can be incredibly stressful, and
quite often departments find themselves short-staffed. Artificial intelligence
in healthcare could help to address this issue, taking on some of the
workloads to help ease the burden.
When it comes to medical issues, it’s incredibly important to offer a
diagnosis as quickly as possible. To do this, it’s vital that medical
professionals receive accurate data that allows them to make critical
decisions more effectively.
Saving time on administrative tasks means medical professionals can place
more focus on patient care and other important areas of their job. Tasks AI
can help with include maintaining records, scan analysis and data entry.
There are plenty of ways AI can reduce costs, both financially and time-
wise. Machine learning in healthcare can ease the burden of time-
consuming administrative tasks, reduce medical errors, and complete tasks
a lot more quickly than a human may be able to. If implemented correctly,
AI in healthcare should improve the patient care that’s offered. Integrating
medical AI into clinician workflows can also give healthcare professionals
valuable context while they’re making important decisions about
treatments.
13
Disadvantages
1. Training complications
2. Risk of creating unemployment
3. Too much change can be difficult to manage
4. Still requires human input
5. Increased security risk
6. Social variables may not be considered
7. Inaccuracies could occur
Not only do medical professionals need to receive extensive training to use
a lot of AI technologies, but the AI tools themselves also need to be trained
with curated data in order to perform properly. In both cases, this can lead
to complications that wouldn’t exist without the introduction of AI. The
robots are coming! In the past, it was often joked that robots would take
over the world and steal our jobs, but AI and automation do actually pose
a very real threat to a lot of sectors. Healthcare is no different, where the
introduction of AI could mean that a lot of administrative roles are made
redundant.
No matter the industry, too much change can be incredibly disruptive.
That’s why it’s important to strike a balance and ensure departments are
ready for AI before it’s rolled out.
This is particularly important in healthcare, where key decisions can quite
literally be the difference between life and death. The healthcare sector
needs to be sure that AI can be used effectively and that all staff understand
how medical technology works. AI systems can be vulnerable to security
risks, which poses a massive problem to the healthcare industry, as patient
data needs to be kept confidential.
Cyber attacks are becoming more sophisticated and accurate, while also
proving harder to predict and prevent. This means that healthcare
institutions will need to invest an awful lot of money to ensure they keep
cybercriminals at bay.
14
Challenges
1. Lack of Quality Medical Data
Clinicians require high-quality datasets for the clinical and technical
validation of AI models.
However, due to the fragmentation of medical data across several EHRs
and software platforms, collecting patient information and images to test
AI algorithms becomes challenging.
Another obstacle is that the medical data from one organization may not
be compatible with other platforms due to interoperability problems. To
increase the amount of data available for testing AI systems, the healthcare
sector must concentrate on techniques for standardizing medical data.
2. Clinically Irrelevant Performance Metrics
The measures used to gauge an AI model’s success are not necessarily
transferable to clinical settings. The discrepancy between the clinical
efficacy demonstrated in the real world and the technical precision of AI
tests is referred to as the AI chasm.
To avoid this gap, developers and clinicians should collaborate to
investigate how AI algorithms enhance patient care. To do this, they can
assess AI models for accuracy using decision curve analysis.
This method enables them to evaluate the clinical usefulness of a prediction
model by comparing the datasets and estimating the chances of an AI
model’s success in the real world.
3. Methodological Research Flaws
There are not enough established methodologies, prospective research, or
peer-reviewed studies of AI in healthcare.
The majority of studies have been retrospective and based on historical
patient medical records. However, to realize the true value of AI diagnosis
in real-world settings, physicians must study current patients over time,
which means prospective research.
And for reliable prospective research, doctors should monitor the health of
their patients by combining physical examinations with telehealth visits and
remote monitoring technologies (sensors and trackers).
15
The healthcare industry has emerged in the middle of transformation.
This shift is being driven by the growing cost of health care as well as the
resulting scarcity of educated experts. As a result, the healthcare industry
is attempting to integrate new IT-based technologies and processes that
may cut costs and give solutions to these expanding difficulties .
Accessibility, high costs, waste, and an aging population are just a few of
the numerous difficulties confronting the world's healthcare systems.
During pandemics such as the coronavirus (COVID-19), healthcare systems
are stressed, resulting in concerns such as insufficient protective
equipment, insufficient or erroneous diagnostic tests, overworked
physicians, and a lack of information exchange. More crucially, a healthcare
tragedy like COVID-19 or the introduction of the human immunodeficiency
virus (HIV) in the 1980s exposes the flaws in our healthcare systems. When
crises exacerbate existing difficulties , such as uneven access to treatment,
a lack of on-demand services, unreasonably expensive costs, and a lack of
price transparency, we may envision and implement new systems of care
and administrative support for healthcare .
When tackling these issues, we must keep in mind their interdependence
belief that accessing healthcare is difficult, even though it is distributed via
complex networks. This is not to say that providing high-quality healthcare
is simple, but it does imply that we have some alternatives to create
simpler mechanisms that will offer better care and benefit everyone.
16
Conclusions
Implementation of AI is needed in the efficiency of health service
management as well as making medical decisions. The challenge is
facilitating early adoption and ongoing implementation in the health care
system, and we consider some of the ethical problem lists faced by AI
clinical application. The remainder of this essay will concentrate on the most
essential applications of AI. There are several obstacles to successfully
implementing any information technology in healthcare, much alone AI.
These obstacles arise at all levels of AI adoption, including data collecting,
technological development, clinical application, and ethical and societal
concerns. This paper enlightens the drawbacks of AI in the healthcare
industry besides its benefits.AI promises to change the practice of medicine
in hitherto unknown ways, but many of its practical applications are still in
their infancy and need to be explored and developed better. Medical
professionals also need to understand and acclimatize themselves with
these advances for better healthcare delivery to the masses.
AI is growing into the public health sector and is going to have a major
impact on every aspect of primary care. AI-enabled computer applications
will help primary care physicians to better identify patients who require
extra attention and provide personalized protocols for each individual. A
study conducted in 2016 found that physicians spent 27% of their office
day on direct clinical face time with their patients and spent 49.2% of their
office day on electronic hospital records and desk work. When in the
examination room with patients, physicians spent 52.9% of their time on
EHR and other work. In conclusion, the physicians who used documentation
support such as dictation assistance or medical scribe services engaged in
more direct face time with patients than those who did not use these
services.
17
References
1. Sordo M. Introduction to neural networks in healthcare. OpenClinical,
2002.
2. Fakoor R, Ladhak F, Nazi A, Huber M. Using deep learning to enhance
cancer diagnosis and classification. A conference •presentation The 30th
International Conference on Machine Learning, 2013.
3. Davenport TH, Glaser J. Just-in-time delivery comes to knowledge
management. Harvard Business Review 2002.
4. Bush J. How AI is taking the scut work out of health care. Harvard
Business Review 2018.
5. Shimabukuro D, Barton CW, Feldman MD, Mataraso SJ, Das R. Effect of
a machine learning-based severe sepsis prediction -algorithm on patient
survival and hospital length of stay: a -randomised clinical trial.
6. Commins J. Nurses say distractions cut bedside time by 25%.
HealthLeaders, 2010.
7. Davenport TH, Dreyer K. AI will change radiology, but it won't replace
radiologists. Harvard Business Review 2018.
8. Char DS, Shah NH, Magnus D. Implementing machine learning in health
care – addressing ethical challenges.
9. Utermohlen K. Four robotic process automation (RPA) applications in the
healthcare industry. Medium, 2018.
10. McKinsey Global Institute A future that works: automation,
employment, and productivity. McKinsey Global Institute, 2017.
***
18
19
