AI and machine learning are becoming increasingly influential in healthcare, enabling tools for disease diagnosis and drug discovery. Deep learning uses artificial neural networks to perform computations on large datasets to solve medical problems. AI can help with tasks like robotic surgery, targeted drug delivery, and automating data entry to free up physician time. While having potential benefits, AI also faces limitations such as data set size and quality that need to be addressed. Overall, AI shows promise as a tool to enhance healthcare and identify accurate diagnoses.

1. Paper Name: Computational
Advances in Cancer
Informatics
Prepared By: Abdullah Shafiq
FA20-BCS-153

2. Abstract
• AI is the use of mathematical algorithms to mimic human cognitive abilities
and address difficult healthcare challenges, such as cancer. Clinical
applications of AI and Machine Learning (ML) in cancer diagnosis and
treatment are the future of medical guidance, allowing researchers to
collaborate in real-time and share knowledge digitally to potentially heal
millions. AI-based assistance to pathologists and physicians could be the
great leap forward towards prediction for disease risk, diagnosis, prognosis,
and treatments.

3. Introduction
• AI and ML are becoming increasingly influential in digital health care, paving the
way for autonomous disease diagnosis tools. ML uses neural network base
algorithms to learn and resolve problems, while DL mimics the human brain's
ability to process data. ANN is composed of input, output, and hidden multi-layer
networks to enhance machine learning processing powers.
• ExCAPE (Exascale Compound Activity Prediction Engine) is a big data analysis
chemogenomic project funded by Horizon 2020 to predict protein interaction and
gene expression for industrial-scale pharmaceutical companies. It is expected to
expand this project further by speeding up ML-based super-computers for rapid
drug discovery. Recent advances in medicine for chemical synthesis include
microfluidic and AI-assisted drug-designing.

5. Materials and Methods
• Deep learning uses artificial neural networks (ANN) to perform
sophisticated computations on large amounts of data to solve the medical
problem.
• Robotic process automation is used in medical companies to automate the
process of data entry this can help in free up the time of physicians and
medical administrators to devote their efforts to more valuable activities.
• The physical system of AI can help in robotic-assisted surgery and nano-
robotic applications for targeted drug delivery.

6. Conclusion
• The scientific community is increasingly interested in using computational input and
assistance to predict and diagnose human health-related issues in real-time. AI-based
DL tools have limitations, such as unregulated training set algorithm, unsupervised
learning implementations, patient data confidentiality, data set size, and classification
based upon more than 100 different types of cancers. Reproducible computation
drug designing has been a promising tool for future drug development, and AI in
clinics does not mean to put radiologists and other medical professionals out of the
business. AI is a novel and potential tool to achieve a specific treatment
performance and to identify the correct diagnosis at the highest possible level.

7. Tools and Algorithms
• Artificial Narrow Intelligence (ANI)
• vector machine algorithm and causal probabilistic network.
• Exascale Compound Activity Prediction Engine (ExCAPE) is a scalable ML model
for complex information management.
• Convolutional neural networks used to understand visual data in medicine industry.
• Machine learning algorithms include regularized General Linear Model regression
(GLMs), Support Vector Machines (SVMs) with a radial basis function kernel, and
single-layer Artificial Neural Networks.