Scribd
Upload
28 views1 page

Artificial Intelligence in Healthcare

Artificial intelligence has several current and potential applications in healthcare, including disease diagnosis, interpretation of patient genomes, treatment selection, and automated surgery. Techniques like neural networks, machine learning, and improved computing power have enabled these applications. Many areas of medicine rely on analyzing images, such as radiology, optometry, dermatology and pathology. AI can help automate image-based diagnosis and detection of conditions through techniques like convolutional neural networks. While AI shows promise in areas like predictive healthcare and precision medicine, it also faces challenges in data acquisition, security, certification of clinical applications, and legal issues that still need to be addressed before it can be fully realized.

Uploaded by

joudet
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
28 views1 page

Artificial Intelligence in Healthcare

Artificial intelligence has several current and potential applications in healthcare, including disease diagnosis, interpretation of patient genomes, treatment selection, and automated surgery. Techniques like neural networks, machine learning, and improved computing power have enabled these applications. Many areas of medicine rely on analyzing images, such as radiology, optometry, dermatology and pathology. AI can help automate image-based diagnosis and detection of conditions through techniques like convolutional neural networks. While AI shows promise in areas like predictive healthcare and precision medicine, it also faces challenges in data acquisition, security, certification of clinical applications, and legal issues that still need to be addressed before it can be fully realized.

Uploaded by

joudet
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Artificial Intelligence in Healthcare

This review article is about recent and gradual advancements in healthcare and biomedical
research by the breakthroughs made in the field of Artificial Intelligence i.e., a branch of
Computer Science that attempts to understand and build intelligent entities, often instantiated
as a software program. Digitized data acquisition, machine learning, and computing
infrastructure are the progressive outcomes of AI.
A few current and potential AI applications in medicine are disease diagnosis, interpretation
of patient genomes, treatment selection, automated surgery, patient monitoring, patient risk
stratification for primary invention. And what in AI made this possible are techniques and
concepts such as neural network, deep neural network, convolutional neural network,
machine learning, supervised and unsupervised ML, improved GPUs and FLOPS, acquisition
of data, dimensionality reduction, recurrent neural networks. AI and medicine were meant to
be acquaintances because the core of medicine is diagnosis, and most diagnostics are image-
based. And so, coincidently what in AI is most progressive outcome? It is Computer vision,
which seeks to understand and automate what human vision system can do. Radiology,
ophthalmology, dermatology, and pathology all rely on image-based diagnosis. Radiologists
use imaging modalities such as MRI, radiography, computer tomography etc. and then the
output images are visualized for diagnosis and treatment. Dermatology inspection of images
in diagnosing types of skin lesion and ophthalmology also involves use of fundus
photography, again inspection of images. These processes can be automated using
convolutional neural networks. Supervised and unsupervised classifiers can be trained by
providing carefully acquired data, a field advancing like never before.
Genome interpretation, biomarker discovery, health status devices, autonomous robotic
surgery, clinical predictions and patient monitoring also have huge prospects of growing big
in the future. Genomic studies can help detect or predict presence of sickness even before a
person is born, wearables such as heart monitors, blood sugar level monitors are advancing.
Biomarkers are being discovered every day, since machine learning can provide multiple
indicators for presence of a disease. There are technical, social, economic and legal
challenges faced by AI faces. The major reason for the challenges is the data. In so many
ways the data is a major challenge, its acquisition, handling, curating it. Then there are
challenges to the security of that data. Clinical AI applications require a series of
certifications before large-scale deployment, human training for such applications is an
economic issue. Plus, there are uncertainties, the legal challenges are tremendous. There’s so
much that needs to be done before real-AI can bloom. AI has and definitely can change the
entire landscape of medical science All AI applications need to coevolve with the healthcare
system and the huge financial strain needs to be accommodated, with the rapid advancements
in AI treasures such as molecular and genomic studies. AI still has a long way to go.

You might also like