Interested in deep learning for healthcare has grown strongly recent years besides with the successes in other domains such as Computer Vision, Natural Language Processing, Speech Recognition and so forth. This talk will try to give a brief look into the recent effort of research in deep learning for healthcare. Especially, this talk focuses on the opportunities and challenges in using electronic health records (EHR) data, which is one of the most important data sources in healthcare domain.
Short presentation for a special lecture on Medicine Graduation Course in Hospital de Clínicas (https://www.hcpa.edu.br/), as part of a one-day special discipline on Machine Learning and Healthcare. The goal was introducing the importance of Deep Learning for Healthcare as well as showing some of the recent impact.
This talk will cover various medical applications of deep learning including tumor segmentation in histology slides, MRI, CT, and X-Ray data. Also, more complicated tasks such as cell counting where the challenge is to count how many objects are in an image. It will also cover generative adversarial networks and how they can be used for medical applications. This presentation is accessible to non-doctors and non-computer scientists.
Prospects of Deep Learning in Medical ImagingGodswll Egegwu
A SEMINAR Presentation on the Prospects of Deep Learning in Medical Imaging Presented to the Department of Computer Science, Nasarawa State Polytechnic, Lafia.
BY:
EGEGWU, GODSWILL
08166643792
http://facebook.com/godswill.egegwu
http://egegwugodswill.name.ng
What is Deep Learning and how it helps to Healthcare Sector?Cogito Tech LLC
To know what is Deep Learning and how it helps to Healthcare Sector check this presentation that shows the top use cases of deep learning process of this technology backed systems, applications or machines in the healthcare industry. The entire presentation shows the deep learning definition and how it is changing the healthcare industry. This PPT is represented by Cogito to get to know the role of deep learning in healthcare as Cogito is providing the training data sets for deep learning and machine learning with best accuracy.
Visit: http://bit.ly/2QRrSc2
Talk @ ACM SF Bayarea Chapter on Deep Learning for medical imaging space.
The talk covers use cases, special challenges and solutions for Deep Learning for Medical Image Analysis using Tensorflow+Keras. You will learn about:
- Use cases for Deep Learning in Medical Image Analysis
- Different DNN architectures used for Medical Image Analysis
- Special purpose compute / accelerators for Deep Learning (in the Cloud / On-prem)
- How to parallelize your models for faster training of models and serving for inferenceing.
- Optimization techniques to get the best performance from your cluster (like Kubernetes/ Apache Mesos / Spark)
- How to build an efficient Data Pipeline for Medical Image Analysis using Deep Learning
- Resources to jump start your journey - like public data sets, common models used in Medical Image Analysis
http://imatge-upc.github.io/telecombcn-2016-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.
Short presentation for a special lecture on Medicine Graduation Course in Hospital de Clínicas (https://www.hcpa.edu.br/), as part of a one-day special discipline on Machine Learning and Healthcare. The goal was introducing the importance of Deep Learning for Healthcare as well as showing some of the recent impact.
This talk will cover various medical applications of deep learning including tumor segmentation in histology slides, MRI, CT, and X-Ray data. Also, more complicated tasks such as cell counting where the challenge is to count how many objects are in an image. It will also cover generative adversarial networks and how they can be used for medical applications. This presentation is accessible to non-doctors and non-computer scientists.
Prospects of Deep Learning in Medical ImagingGodswll Egegwu
A SEMINAR Presentation on the Prospects of Deep Learning in Medical Imaging Presented to the Department of Computer Science, Nasarawa State Polytechnic, Lafia.
BY:
EGEGWU, GODSWILL
08166643792
http://facebook.com/godswill.egegwu
http://egegwugodswill.name.ng
What is Deep Learning and how it helps to Healthcare Sector?Cogito Tech LLC
To know what is Deep Learning and how it helps to Healthcare Sector check this presentation that shows the top use cases of deep learning process of this technology backed systems, applications or machines in the healthcare industry. The entire presentation shows the deep learning definition and how it is changing the healthcare industry. This PPT is represented by Cogito to get to know the role of deep learning in healthcare as Cogito is providing the training data sets for deep learning and machine learning with best accuracy.
Visit: http://bit.ly/2QRrSc2
Talk @ ACM SF Bayarea Chapter on Deep Learning for medical imaging space.
The talk covers use cases, special challenges and solutions for Deep Learning for Medical Image Analysis using Tensorflow+Keras. You will learn about:
- Use cases for Deep Learning in Medical Image Analysis
- Different DNN architectures used for Medical Image Analysis
- Special purpose compute / accelerators for Deep Learning (in the Cloud / On-prem)
- How to parallelize your models for faster training of models and serving for inferenceing.
- Optimization techniques to get the best performance from your cluster (like Kubernetes/ Apache Mesos / Spark)
- How to build an efficient Data Pipeline for Medical Image Analysis using Deep Learning
- Resources to jump start your journey - like public data sets, common models used in Medical Image Analysis
http://imatge-upc.github.io/telecombcn-2016-dlcv/
Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.
Existing model uses structured data to predict the patients of either high risk or low risk.
But for a complex disease, structured data is not a good way to describe the disease.
We propose a new convolutional neural network (CNN)-based multimodal disease risk prediction algorithm using structured and unstructured data from hospital.
In this paper, we mainly focus on the risk prediction of cerebral infarction.
Mengenal Machine/Deep Learning, Artificial Intelligence dan mengenal apa bedanya dengan Business Intelligence, apa hubungannya dengan Big Data dan Data Science/Analytics.
Intro to Deep Learning for Medical Image Analysis, with Dan Lee from Dentuit AISeth Grimes
Dan Lee from Dentuit AI presented an Intro to Deep Learning for Medical Image Analysis at the Maryland AI meetup (https://www.meetup.com/Maryland-AI), May 27, 2020. Visit https://www.youtube.com/watch?v=xl8i7CGDQi0 for video.
Explainable AI (XAI) is becoming Must-Have NFR for most AI enabled product or solution deployments. Keen to know viewpoints and collaboration opportunities.
Differences Between Machine Learning Ml Artificial Intelligence Ai And Deep L...SlideTeam
"You can download this product from SlideTeam.net"
Differences between Machine Learning ML Artificial Intelligence AI and Deep Learning DL is for the mid level managers to give information about what is AI, what is Machine Learning, what is deep learning, Machine learning process. You can also know the difference between Machine learning and Deep learning to understand AI, ML, and DL in a better way for business growth. https://bit.ly/325zI9o
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Brain tumor detection with the mri image and 54900 image Performance analysis of automated brain tumor detection from MR imaging and CT scan using basic image processing techniques based on various hard and soft .This repo is of segmentation and morphological operations which are the basic concepts of image processing. Detection and extraction of tumor from MRI scan images of the brain is done using python.
Heart Disease Prediction using Machine Learning Algorithmijtsrd
Nowadays, Heart disease has become dangerous to a human being, it effects very badly to human body. If anyone is suffering from heart disease, then it leads to blood clotting. Heart disease prediction is very difficult task to predict in the field of medical science. Affiliation has predicted that 12 million people fail horrendously every year as a result of heart disease. In this paper, we propose a k Nearest Neighbors Algorithm KNN way to deal with improve the exactness of heart determination. We show that k Nearest Neighbors Algorithm KNN have better accuracy than random forest algorithm for viewing heart disease. The k Nearest Neighbors Algorithm give more precise and exact outcome . We have taken 13 attributes in the dataset and a target attribute, by applying machine learning we achieved 84 accuracy in the heart disease detection. Ravi Kumar Singh | Dr. A Rengarajan "Heart Disease Prediction using Machine Learning Algorithm" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-2 , February 2021, URL: https://www.ijtsrd.com/papers/ijtsrd38358.pdf Paper Url: https://www.ijtsrd.com/computer-science/other/38358/heart-disease-prediction-using-machine-learning-algorithm/ravi-kumar-singh
Las aplicaciones de Inteligencia Artificial como Machine Learning y Deep Learning se han convertido en parte importante en nuestras vidas. Los productos que compramos, si somos o no aptos para un préstamo bancario, las películas o series que Netflix nos recomienda, coches autoconducidos, reconocimiento de objetos, etc; toda esa información es dirigida hacia nosotros por estos algoritmos.
En la actualidad, estos campos de estudio son los más apasionantes y retadores en computación debido a su alto nivel de complejidad y gran demanda en el mercado. En esta presentación vamos a conocer y aprender a diferenciar estos conceptos, ya que son herramientas inevitables para el mejoramiento de la vida humana.
A continuación, te presentamos algunos de los temas específicos que se expondrán:
- Contexto de ML y DL en Inteligencia Artificial.
- Machine Learning.
- Supervised Learning.
- Unsupervised Learning.
- Deep Learning.
- Artificial Neural Network.
- Convolutional Neural Networks.
- Aplicaciones en ML y DL.
deep learning applications in medical image analysis brain tumorVenkat Projects
The tremendous success of machine learning algorithms at image recognition tasks in recent years intersects with a time of dramatically increased use of electronic medical records and diagnostic imaging. This review introduces the machine learning algorithms as applied to medical image analysis, focusing on convolutional neural networks, and emphasizing clinical aspects of the _eld. The advantage of machine learning in an era of medical big data is that signi_cant hierarchal relationships within the data can be discovered algorithmically without laborious hand-crafting of features. We cover key research areas and applications of medical image classi_cation, localization, detection, segmentation, and registration. We conclude by discussing research obstacles, emerging trends, and possible future directions.
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptxTaminul Islam
Cardiovascular Disease Prediction Using Machine Learning Approaches.
Presentation for CISES 2023. Presentation Outline.
Introduction
Objectives
Literature review
Data Collection
Methodology
Result
Challenges & Future work
Conclusion
Medical Informatics: Computational Analytics in HealthcareNUS-ISS
Presented by Dr Liu Nan, Senior Research Scientist and Principal Investigator, Singapore General Hospital at ISS Seminar: How Analytics is Transforming Healthcare on 31 Oct 2014.
Existing model uses structured data to predict the patients of either high risk or low risk.
But for a complex disease, structured data is not a good way to describe the disease.
We propose a new convolutional neural network (CNN)-based multimodal disease risk prediction algorithm using structured and unstructured data from hospital.
In this paper, we mainly focus on the risk prediction of cerebral infarction.
Mengenal Machine/Deep Learning, Artificial Intelligence dan mengenal apa bedanya dengan Business Intelligence, apa hubungannya dengan Big Data dan Data Science/Analytics.
Intro to Deep Learning for Medical Image Analysis, with Dan Lee from Dentuit AISeth Grimes
Dan Lee from Dentuit AI presented an Intro to Deep Learning for Medical Image Analysis at the Maryland AI meetup (https://www.meetup.com/Maryland-AI), May 27, 2020. Visit https://www.youtube.com/watch?v=xl8i7CGDQi0 for video.
Explainable AI (XAI) is becoming Must-Have NFR for most AI enabled product or solution deployments. Keen to know viewpoints and collaboration opportunities.
Differences Between Machine Learning Ml Artificial Intelligence Ai And Deep L...SlideTeam
"You can download this product from SlideTeam.net"
Differences between Machine Learning ML Artificial Intelligence AI and Deep Learning DL is for the mid level managers to give information about what is AI, what is Machine Learning, what is deep learning, Machine learning process. You can also know the difference between Machine learning and Deep learning to understand AI, ML, and DL in a better way for business growth. https://bit.ly/325zI9o
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Brain tumor detection with the mri image and 54900 image Performance analysis of automated brain tumor detection from MR imaging and CT scan using basic image processing techniques based on various hard and soft .This repo is of segmentation and morphological operations which are the basic concepts of image processing. Detection and extraction of tumor from MRI scan images of the brain is done using python.
Heart Disease Prediction using Machine Learning Algorithmijtsrd
Nowadays, Heart disease has become dangerous to a human being, it effects very badly to human body. If anyone is suffering from heart disease, then it leads to blood clotting. Heart disease prediction is very difficult task to predict in the field of medical science. Affiliation has predicted that 12 million people fail horrendously every year as a result of heart disease. In this paper, we propose a k Nearest Neighbors Algorithm KNN way to deal with improve the exactness of heart determination. We show that k Nearest Neighbors Algorithm KNN have better accuracy than random forest algorithm for viewing heart disease. The k Nearest Neighbors Algorithm give more precise and exact outcome . We have taken 13 attributes in the dataset and a target attribute, by applying machine learning we achieved 84 accuracy in the heart disease detection. Ravi Kumar Singh | Dr. A Rengarajan "Heart Disease Prediction using Machine Learning Algorithm" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-2 , February 2021, URL: https://www.ijtsrd.com/papers/ijtsrd38358.pdf Paper Url: https://www.ijtsrd.com/computer-science/other/38358/heart-disease-prediction-using-machine-learning-algorithm/ravi-kumar-singh
Las aplicaciones de Inteligencia Artificial como Machine Learning y Deep Learning se han convertido en parte importante en nuestras vidas. Los productos que compramos, si somos o no aptos para un préstamo bancario, las películas o series que Netflix nos recomienda, coches autoconducidos, reconocimiento de objetos, etc; toda esa información es dirigida hacia nosotros por estos algoritmos.
En la actualidad, estos campos de estudio son los más apasionantes y retadores en computación debido a su alto nivel de complejidad y gran demanda en el mercado. En esta presentación vamos a conocer y aprender a diferenciar estos conceptos, ya que son herramientas inevitables para el mejoramiento de la vida humana.
A continuación, te presentamos algunos de los temas específicos que se expondrán:
- Contexto de ML y DL en Inteligencia Artificial.
- Machine Learning.
- Supervised Learning.
- Unsupervised Learning.
- Deep Learning.
- Artificial Neural Network.
- Convolutional Neural Networks.
- Aplicaciones en ML y DL.
deep learning applications in medical image analysis brain tumorVenkat Projects
The tremendous success of machine learning algorithms at image recognition tasks in recent years intersects with a time of dramatically increased use of electronic medical records and diagnostic imaging. This review introduces the machine learning algorithms as applied to medical image analysis, focusing on convolutional neural networks, and emphasizing clinical aspects of the _eld. The advantage of machine learning in an era of medical big data is that signi_cant hierarchal relationships within the data can be discovered algorithmically without laborious hand-crafting of features. We cover key research areas and applications of medical image classi_cation, localization, detection, segmentation, and registration. We conclude by discussing research obstacles, emerging trends, and possible future directions.
Cardiovascular Disease Prediction Using Machine Learning Approaches.pptxTaminul Islam
Cardiovascular Disease Prediction Using Machine Learning Approaches.
Presentation for CISES 2023. Presentation Outline.
Introduction
Objectives
Literature review
Data Collection
Methodology
Result
Challenges & Future work
Conclusion
Medical Informatics: Computational Analytics in HealthcareNUS-ISS
Presented by Dr Liu Nan, Senior Research Scientist and Principal Investigator, Singapore General Hospital at ISS Seminar: How Analytics is Transforming Healthcare on 31 Oct 2014.
Proposed Model for Chest Disease Prediction using Data Analyticsvivatechijri
Chest diseases if not properly diagnosed in early stages can be fatal. Because of lack of skilled
knowledge or experiences of real life practitioners, many a times one chest disease is wrongly diagnosed for the
other, which leads to wrong treatment. Due to this the actual disease keeps on growing and become fatal. For
example, muscular chest pains can be treated for the heart disease or COPD is treated for Asthma. Early
prediction of chest disease is crucial but is not an easy task. Consequently, the computer based prediction system
for chest disease may play a significant role as a pre-stage detection to take proper actions with a view to recover
from it. However the choice of the proper Data Mining classification method can effectively predict the early
stage of the disease for being cured from it. In this paper, the three mostly used classification techniques such as
support vector machine (SVM), k-nearest neighbour (KNN) and artificial neural network (ANN) have been studied
with a view to evaluating them for chest disease prediction.
PREDICTIVE ANALYTICS IN HEALTHCARE SYSTEM USING DATA MINING TECHNIQUEScscpconf
The health sector has witnessed a great evolution following the development of new computer technologies, and that pushed this area to produce more medical data, which gave birth to multiple fields of research. Many efforts are done to cope with the explosion of medical data on one hand, and to obtain useful knowledge from it on the other hand. This prompted researchers to apply all the technical innovations like big data analytics, predictive analytics, machine learning and learning algorithms in order to extract useful knowledge and help in making decisions. With the promises of predictive analytics in big data, and the use of machine learning
algorithms, predicting future is no longer a difficult task, especially for medicine because predicting diseases and anticipating the cure became possible. In this paper we will present an overview on the evolution of big data in healthcare system, and we will apply a learning algorithm on a set of medical data. The objective is to predict chronic kidney diseases by using Decision Tree (C4.5) algorithm.
PERFORMANCE OF DATA MINING TECHNIQUES TO PREDICT IN HEALTHCARE CASE STUDY: CH...ijdms
With the promises of predictive analytics in big data, and the use of machine learning algorithms,
predicting future is no longer a difficult task, especially for health sector, that has witnessed a great
evolution following the development of new computer technologies that gave birth to multiple fields of
research. Many efforts are done to cope with medical data explosion on one hand, and to obtain useful
knowledge from it, predict diseases and anticipate the cure on the other hand. This prompted researchers
to apply all the technical innovations like big data analytics, predictive analytics, machine learning and
learning algorithms in order to extract useful knowledge and help in making decisions. In this paper, we
will present an overview on the evolution of big data in healthcare system, and we will apply three learning
algorithms on a set of medical data. The objective of this research work is to predict kidney disease by
using multiple machine learning algorithms that are Support Vector Machine (SVM), Decision Tree (C4.5),
and Bayesian Network (BN), and chose the most efficient one.
A comprehensive study on disease risk predictions in machine learning IJECEIAES
Over recent years, multiple disease risk prediction models have been developed. These models use various patient characteristics to estimate the probability of outcomes over a certain period of time and hold the potential to improve decision making and individualize care. Discovering hidden patterns and interactions from medical databases with growing evaluation of the disease prediction model has become crucial. It needs many trials in traditional clinical findings that could complicate disease prediction. A Comprehensive study on different strategies used to predict disease is conferred in this paper. Applying these techniques to healthcare data, has improvement of risk prediction models to find out the patients who would get benefit from disease management programs to reduce hospital readmission and healthcare cost, but the results of these endeavors have been shifted.
HEALTH PREDICTION ANALYSIS USING DATA MININGAshish Salve
Data mining techniques are used for a variety of applications. In healthcare industry, datamining plays an important
role in predicting diseases. For detecting a disease number of tests should be required from the patient. But using data
mining technique the number of tests can be reduced. This reduced test plays an important role in time and performance.
This report analyses data mining techniques which can be used for predicting different types of diseases. This report reviewed
the research papers which mainly concentrate on predicting various disease
Xavier Amatriain, Cofounder & CTO, Curai at MLconf SF 2017MLconf
ML to Cure the World:
The practice of medicine involves diagnosis, treatment, and prevention of diseases. Recent technological breakthroughs have made little dent to the centuries-old system of practicing medicine: complex diagnostic decisions are still mostly dependent on “educated” work-ups of the doctors, and rely on somewhat outdated tools and incomplete data. All of this often leads to imperfect, biased, and, at times, incorrect diagnosis and treatment.
With a growing research community as well as tech companies working on AI advances to medicine, the hope for healthcare renaissance is definitely not lost. The emphasis of this talk will be on ML-driven medicine. We will discuss recent AI advancements for aiding medical decision including language understanding, medical knowledge base construction and diagnosis systems. We will discuss the importance of personalized medicine that takes into account not only the user, but also the context, and other metadata. We will also highlight challenges in designing ML-based medical systems that are accurate, but at the same time engaging and trustworthy for the user.
Bio: Xavier Amatriain is currently co-founder and CTO of Curai, a stealth startup trying to radically improve healthcare for patients by using AI. Previous to this, he was VP of Engineering at Quora, and Research/engineering Director at Netflix, where he led the team building the famous Netflix recommendation algorithms. Before going into leadership positions in industry, Xavier was a research scientist at Telefonica Research and a research director at UCSB. With over 50 publications (and 3k+ citations) in different fields, Xavier is best known for his work on machine learning in general and recommender systems in particular. He has lectured at different universities both in the US and Spain and is frequently invited as a speaker at conferences and companies.
Diagnosis of rheumatoid arthritis using an ensemble learning approachcsandit
Rheumatoid arthritis is one of the diseases that it
s cause is unknown yet; exploring the field of
medical data mining can be helpful in early diagnos
is and treatment of the disease. In this
study, a predictive model is suggested that diagnos
es rheumatoid arthritis. The rheumatoid
arthritis dataset was collected from 2,564 patients
referred to rheumatology clinic. For each
patient a record consists of several clinical and d
emographic features is saved. After data
analysis and pre-processing operations, three diffe
rent methods are combined to choose proper
features among all the features. Various data class
ification algorithms were applied on these
features. Among these algorithms Adaboost had the h
ighest precision. In this paper, we
proposed a new classification algorithm entitled CS
-Boost that employs Cuckoo search
algorithm for optimizing the performance of Adaboos
t algorithm. Experimental results show
that the CS-Boost algorithm enhance the accuracy of
Adaboost in predicting of Rheumatoid
Arthritis.
DIAGNOSIS OF RHEUMATOID ARTHRITIS USING AN ENSEMBLE LEARNING APPROACH cscpconf
Rheumatoid arthritis is one of the diseases that its cause is unknown yet; exploring the field of
medical data mining can be helpful in early diagnosis and treatment of the disease. In this
study, a predictive model is suggested that diagnoses rheumatoid arthritis. The rheumatoid
arthritis dataset was collected from 2,564 patients referred to rheumatology clinic. For each
patient a record consists of several clinical and demographic features is saved. After data
analysis and pre-processing operations, three different methods are combined to choose proper
features among all the features. Various data classification algorithms were applied on these
features. Among these algorithms Adaboost had the highest precision. In this paper, we
proposed a new classification algorithm entitled CS-Boost that employs Cuckoo search
algorithm for optimizing the performance of Adaboost algorithm. Experimental results show
that the CS-Boost algorithm enhance the accuracy of Adaboost in predicting of Rheumatoid
Arthritis.
LLM Threats: Prompt Injections and Jailbreak AttacksThien Q. Tran
Introducing the concept of prompt jailbreak attacks of LLM, including existing attack methods, an explanation why these attacks succeed and several methods to mitigate such attacks.
Hypothesis testing and statistically sound-pattern miningThien Q. Tran
The availability of large datasets has lead to the need for methods that can extracts patterns in the data while providing statistical guarantees on the quality of the results, in particular with respect to false discoveries. In this talk, we firstly introduce the fundamental concepts behind statistical hypothesis testing. We then explain the computational and statistical challenges in statistically-sound pattern mining and how they have been tackled. Moreover, we will also show some application of these methods in areas such as subgraph mining, social networks analysis, basket analysis, and cancer genomics.
Introduction:
RNA interference (RNAi) or Post-Transcriptional Gene Silencing (PTGS) is an important biological process for modulating eukaryotic gene expression.
It is highly conserved process of posttranscriptional gene silencing by which double stranded RNA (dsRNA) causes sequence-specific degradation of mRNA sequences.
dsRNA-induced gene silencing (RNAi) is reported in a wide range of eukaryotes ranging from worms, insects, mammals and plants.
This process mediates resistance to both endogenous parasitic and exogenous pathogenic nucleic acids, and regulates the expression of protein-coding genes.
What are small ncRNAs?
micro RNA (miRNA)
short interfering RNA (siRNA)
Properties of small non-coding RNA:
Involved in silencing mRNA transcripts.
Called “small” because they are usually only about 21-24 nucleotides long.
Synthesized by first cutting up longer precursor sequences (like the 61nt one that Lee discovered).
Silence an mRNA by base pairing with some sequence on the mRNA.
Discovery of siRNA?
The first small RNA:
In 1993 Rosalind Lee (Victor Ambros lab) was studying a non- coding gene in C. elegans, lin-4, that was involved in silencing of another gene, lin-14, at the appropriate time in the
development of the worm C. elegans.
Two small transcripts of lin-4 (22nt and 61nt) were found to be complementary to a sequence in the 3' UTR of lin-14.
Because lin-4 encoded no protein, she deduced that it must be these transcripts that are causing the silencing by RNA-RNA interactions.
Types of RNAi ( non coding RNA)
MiRNA
Length (23-25 nt)
Trans acting
Binds with target MRNA in mismatch
Translation inhibition
Si RNA
Length 21 nt.
Cis acting
Bind with target Mrna in perfect complementary sequence
Piwi-RNA
Length ; 25 to 36 nt.
Expressed in Germ Cells
Regulates trnasposomes activity
MECHANISM OF RNAI:
First the double-stranded RNA teams up with a protein complex named Dicer, which cuts the long RNA into short pieces.
Then another protein complex called RISC (RNA-induced silencing complex) discards one of the two RNA strands.
The RISC-docked, single-stranded RNA then pairs with the homologous mRNA and destroys it.
THE RISC COMPLEX:
RISC is large(>500kD) RNA multi- protein Binding complex which triggers MRNA degradation in response to MRNA
Unwinding of double stranded Si RNA by ATP independent Helicase
Active component of RISC is Ago proteins( ENDONUCLEASE) which cleave target MRNA.
DICER: endonuclease (RNase Family III)
Argonaute: Central Component of the RNA-Induced Silencing Complex (RISC)
One strand of the dsRNA produced by Dicer is retained in the RISC complex in association with Argonaute
ARGONAUTE PROTEIN :
1.PAZ(PIWI/Argonaute/ Zwille)- Recognition of target MRNA
2.PIWI (p-element induced wimpy Testis)- breaks Phosphodiester bond of mRNA.)RNAse H activity.
MiRNA:
The Double-stranded RNAs are naturally produced in eukaryotic cells during development, and they have a key role in regulating gene expression .
This pdf is about the Schizophrenia.
For more details visit on YouTube; @SELF-EXPLANATORY;
https://www.youtube.com/channel/UCAiarMZDNhe1A3Rnpr_WkzA/videos
Thanks...!
Cancer cell metabolism: special Reference to Lactate PathwayAADYARAJPANDEY1
Normal Cell Metabolism:
Cellular respiration describes the series of steps that cells use to break down sugar and other chemicals to get the energy we need to function.
Energy is stored in the bonds of glucose and when glucose is broken down, much of that energy is released.
Cell utilize energy in the form of ATP.
The first step of respiration is called glycolysis. In a series of steps, glycolysis breaks glucose into two smaller molecules - a chemical called pyruvate. A small amount of ATP is formed during this process.
Most healthy cells continue the breakdown in a second process, called the Kreb's cycle. The Kreb's cycle allows cells to “burn” the pyruvates made in glycolysis to get more ATP.
The last step in the breakdown of glucose is called oxidative phosphorylation (Ox-Phos).
It takes place in specialized cell structures called mitochondria. This process produces a large amount of ATP. Importantly, cells need oxygen to complete oxidative phosphorylation.
If a cell completes only glycolysis, only 2 molecules of ATP are made per glucose. However, if the cell completes the entire respiration process (glycolysis - Kreb's - oxidative phosphorylation), about 36 molecules of ATP are created, giving it much more energy to use.
IN CANCER CELL:
Unlike healthy cells that "burn" the entire molecule of sugar to capture a large amount of energy as ATP, cancer cells are wasteful.
Cancer cells only partially break down sugar molecules. They overuse the first step of respiration, glycolysis. They frequently do not complete the second step, oxidative phosphorylation.
This results in only 2 molecules of ATP per each glucose molecule instead of the 36 or so ATPs healthy cells gain. As a result, cancer cells need to use a lot more sugar molecules to get enough energy to survive.
Unlike healthy cells that "burn" the entire molecule of sugar to capture a large amount of energy as ATP, cancer cells are wasteful.
Cancer cells only partially break down sugar molecules. They overuse the first step of respiration, glycolysis. They frequently do not complete the second step, oxidative phosphorylation.
This results in only 2 molecules of ATP per each glucose molecule instead of the 36 or so ATPs healthy cells gain. As a result, cancer cells need to use a lot more sugar molecules to get enough energy to survive.
introduction to WARBERG PHENOMENA:
WARBURG EFFECT Usually, cancer cells are highly glycolytic (glucose addiction) and take up more glucose than do normal cells from outside.
Otto Heinrich Warburg (; 8 October 1883 – 1 August 1970) In 1931 was awarded the Nobel Prize in Physiology for his "discovery of the nature and mode of action of the respiratory enzyme.
WARNBURG EFFECT : cancer cells under aerobic (well-oxygenated) conditions to metabolize glucose to lactate (aerobic glycolysis) is known as the Warburg effect. Warburg made the observation that tumor slices consume glucose and secrete lactate at a higher rate than normal tissues.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.Sérgio Sacani
The return of a sample of near-surface atmosphere from Mars would facilitate answers to several first-order science questions surrounding the formation and evolution of the planet. One of the important aspects of terrestrial planet formation in general is the role that primary atmospheres played in influencing the chemistry and structure of the planets and their antecedents. Studies of the martian atmosphere can be used to investigate the role of a primary atmosphere in its history. Atmosphere samples would also inform our understanding of the near-surface chemistry of the planet, and ultimately the prospects for life. High-precision isotopic analyses of constituent gases are needed to address these questions, requiring that the analyses are made on returned samples rather than in situ.
Nutraceutical market, scope and growth: Herbal drug technologyLokesh Patil
As consumer awareness of health and wellness rises, the nutraceutical market—which includes goods like functional meals, drinks, and dietary supplements that provide health advantages beyond basic nutrition—is growing significantly. As healthcare expenses rise, the population ages, and people want natural and preventative health solutions more and more, this industry is increasing quickly. Further driving market expansion are product formulation innovations and the use of cutting-edge technology for customized nutrition. With its worldwide reach, the nutraceutical industry is expected to keep growing and provide significant chances for research and investment in a number of categories, including vitamins, minerals, probiotics, and herbal supplements.
The increased availability of biomedical data, particularly in the public domain, offers the opportunity to better understand human health and to develop effective therapeutics for a wide range of unmet medical needs. However, data scientists remain stymied by the fact that data remain hard to find and to productively reuse because data and their metadata i) are wholly inaccessible, ii) are in non-standard or incompatible representations, iii) do not conform to community standards, and iv) have unclear or highly restricted terms and conditions that preclude legitimate reuse. These limitations require a rethink on data can be made machine and AI-ready - the key motivation behind the FAIR Guiding Principles. Concurrently, while recent efforts have explored the use of deep learning to fuse disparate data into predictive models for a wide range of biomedical applications, these models often fail even when the correct answer is already known, and fail to explain individual predictions in terms that data scientists can appreciate. These limitations suggest that new methods to produce practical artificial intelligence are still needed.
In this talk, I will discuss our work in (1) building an integrative knowledge infrastructure to prepare FAIR and "AI-ready" data and services along with (2) neurosymbolic AI methods to improve the quality of predictions and to generate plausible explanations. Attention is given to standards, platforms, and methods to wrangle knowledge into simple, but effective semantic and latent representations, and to make these available into standards-compliant and discoverable interfaces that can be used in model building, validation, and explanation. Our work, and those of others in the field, creates a baseline for building trustworthy and easy to deploy AI models in biomedicine.
Bio
Dr. Michel Dumontier is the Distinguished Professor of Data Science at Maastricht University, founder and executive director of the Institute of Data Science, and co-founder of the FAIR (Findable, Accessible, Interoperable and Reusable) data principles. His research explores socio-technological approaches for responsible discovery science, which includes collaborative multi-modal knowledge graphs, privacy-preserving distributed data mining, and AI methods for drug discovery and personalized medicine. His work is supported through the Dutch National Research Agenda, the Netherlands Organisation for Scientific Research, Horizon Europe, the European Open Science Cloud, the US National Institutes of Health, and a Marie-Curie Innovative Training Network. He is the editor-in-chief for the journal Data Science and is internationally recognized for his contributions in bioinformatics, biomedical informatics, and semantic technologies including ontologies and linked data.
Deep learning in healthcare: Oppotunities and challenges with Electronic Medical Records (EMR) data
1. Deep learning in healthcare
Opportunities and challenges
with Electronic Medical Records (EMR) data
Trần Quang Thiện
University of Tsukuba
(Master student)
1
2. ● Tran Quang Thien (1993)
● Has been in Japan since 2012
● Currently a master student at Tsukuba University
● Researchs
○ Feature selection in prediction of infectious disease using large-scale
search log data (Yahoo Japan search log).
○ Applied research with Long-term care insurance data and Electronic
Medical Record (EMR) data.
● Recent interests
○ Bayesian modeling
○ Selective inference
Introduction
Who am I
2
3. 1. Introduction to Electronic Medical Records (EMR) data
2. Some common tasks and example solutions
3. Opportunities and challenges
Introduction
Agenda
3
4. Introduction
What is EMR data
http://api.sunlab.org/static/media/uxJ/UL5/5b6aef5b241ba60001bec1c1.pdf
Age, sex, race,
incomes ….
- Medicine codes
- Procedure codes
- Vital signs and labs
- Pulse Ox, heart rate,
Temperature, Co2...
- Diagnosis codes
- ICD9, ICD10 ...
- Additional comments
Nowadays, many types of medical data is collecting across multiples institutes
Electronic
Medical
Record
(EMR data)
4
6. ● From wikipedia:
“Diagnostic coding is the translation of written descriptions of
diseases, illnesses and injuries into codes from a particular
classification”
● ICD-9, ICD-10
○ The most popular and currently the international standard
○ Contains diseases, signs, symptoms, external cause, …
○ 14,000 different codes
○ Has a hierarchical structure
Introduction
OK, so what is diagnosis code
6
7. Introduction
Structure of ICD-10 code
https://doctors.practo.com/icd-10-codes-important-doctors
/
Gan hóa sợi và xơ gan có mã bệnh là K74
- Gan hóa sợi K74.0
- Gan hóa xơ K74.1
- Gan hóa sợi với gan hóa xơ K74.2
- Xơ gan mật nguyên phát K74.3
- Xơ gan mật thứ phát K74.4
- Xơ gan mật không xác định K74.5
- Xơ gan khác và không xác định K74.6
7
8. Introduction
A sample of diagnosis code
Risk Prediction on Electronic Health Records with Prior Medical Knowledge, Fenglong Ma et. al
ICD
codes
8
10. Commons tasks
The (typical) overall framework
http://api.sunlab.org/static/media/uxJ/UL5/5b6aef5b241ba60001bec1c1.pdf 10
11. Concept embedding
Learning a mapping from raw EMR data to useful
representation or medical concept.
● Also called as electronic phenotyping task.
● The result embedding can be used in any other tasks
● Many studies focus on diagnosis/medicine/procedure codes
● Some take inspiration from NLP domain (GloVe, skip-gram v..v)
since these codes can be treated as a bag of codes
● Almost trained in unsupervised setting (no ground-truth label)
Commons tasks
11
12. GRAM: Graph-based Attention Model for Healthcare Representation Learning, Edward Choi et. al (KDD 2017)
Concept embedding
Commons tasks
12
13. GRAM: Graph-based Attention Model for Healthcare Representation Learning, Edward Choi et. al (KDD 2017)
Concept embedding
Commons tasks
● An embedding vector of a code is the mixture of the (base) embedding vectors of
○ The current leaf code
○ It’s ancestors
● Advantages:
○ Usable information from high-level nodes, especially useful for rare codes
○ Something like hierarchical bayes model
13
14. GRAM: Graph-based Attention Model for Healthcare Representation Learning, Edward Choi et. al (KDD 2017)
GRAM GloVe skip-gram
● The embedding result matches with medical ontology
● Similar to the shrinkage of parameters in hierarchical models
Concept embedding
Commons tasks
14
15. GRAM: Graph-based Attention Model for Healthcare Representation Learning, Edward Choi et. al (KDD 2017)
● The embedding result matches with medical ontology
● And also help increasing prediction performance for post-embedding
tasks
Concept embedding
Commons tasks
15
16. Detecting whether specific diseases/stage of disease can
be confirmed in the EMR data
● Predicting a target disease using EMR data is not easy
○ Assigning diagnosis is a noisy task due to
different practices of doctors or hospitals
○ Predict diagnosis codes from other data
● Examples:
○ Predicting diagnose code from clinical notes
○ Classification stage of Parkinson’s disease
○ Predict heart failure risk
○ Predict medicine codes ←AI doctor...
Disease/drugs classification
Commons tasks
16
17. Disease/drugs classification
Commons tasks
1. RNN
2. Reinforcement finetune
3. Beam search
Main techniques
LEAP: Learning to Prescribe Effective and Safe Treatment Combinations for Multimorbidity,
Yutao Zhang et. al (KDD 2017) 17
18. Disease/drugs classification
Commons tasks
Scoring criterion
[2] Complete without unfavorable drug-drug interaction
[1] Partially complete without unfavorable interaction
[0] Address less than 50% diagnoses or including
negative interaction
Evaluation criterion: Jaccard coefficient
● The proposed method works better than rule-based or other competitors
● However, the quality seems not enough to be ready in real application yet
18
LEAP: Learning to Prescribe Effective and Safe Treatment Combinations for Multimorbidity,
Yutao Zhang et. al (KDD 2017)
19. Predicting future clinical events based on past
longitudinal event sequences
● For examples:
○ Prediction of 30-day hospital readmission
○ Predict of heart failure risk
○ Predict of mortality in Intensive Care Unit (ICU)
● Useful in grouping/detection patients with high risk
Sequential prediction of clinical events
Commons tasks
19
20. Sequential prediction of clinical events
Commons tasks
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism,
Edward Choi et al. NIPS 2016
- Interpretable model for sequential prediction
- Giving explanation for prediction using attention mechanism
- 2 level of attention
- Importance of each visit
- Importance of each code within a visit
20
21. Sequential prediction of clinical events
Commons tasks
- The attention is calculated using time-reversed RNN model
- Mimic the clinician that look at the ERM data backward
- Recent visit contributes more
21RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism,
Edward Choi et al. NIPS 2016
22. Sequential prediction of clinical events
Commons tasks
MLP Logistic regression with a hidden layer
RNN Two layer of RNN, no attention
RNN+ _M RNN with visit-level attention
RNN+ _R Reversed-RNN with visit-level attention
RETAIN Reversed-RNN with 2 levels attentions
● Task: predict whether an heart failure (HF) event occurs
Input: EMR data until the date HF event happens
● The AUC is around 0.87 (High?)
● However, normal RNN is also high ….
● NOTE: y-axis limit starts from 0.76
22RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism,
Edward Choi et al. NIPS 2016
23. Sequential prediction of clinical events
Commons tasks
● Since the different in performance is not significance
● RETAIN give us the answer for the question WHY
23RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism,
Edward Choi et al. NIPS 2016
24. Data augmentation:
Creating synthesis data elements or patient records
based on real EMR data
● Saving labeling cost
● Generated synthesis data can be useful for privacy issue
● Most researches based on GANs techniques
● medGAN paper reported that generated data is
indistinguishable to a human doctor expert.
Data augmentation
Commons tasks
24
25. Data augmentation
Commons tasks
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
Edward Choi et al. (JMLR 2017)
● Task
Generating synthetic patient records from real data
○ Require 1: (statistically) similar to the real records
○ Require 2: Individual patient information can not be exploited
● Result
Indistinguishable to a human doctor, except a few outliers
25
27. Opportunities
Growing data availability
Adoption of EMR system in Japan
医療実施調査(厚生労働省)
● The data is quite old….
● In 2017, only 41.6% of hospital, clinical in Japan adopted EMR system
● However, the number is about 85% for big hospitals ( >400 beds)
27
28. Opportunities
Growing data availability
Adoption of EMR system in US
● The data is also old ….
● 87% physicians interviewed uses EMR system
● However, the coverage on hospitals/clinicals is unclear 28
29. Opportunities
Growing data availability
Thực hiện Nghị quyết 20, đến nay, Bộ Y tế đã xây dựng xong phần mềm hồ sơ
sức khỏe điện tử (EHR) sử dụng nguồn dữ liệu hộ gia đình tham gia BHYT của
Bảo hiểm xã hội Việt Nam để tạo lập mã số định danh (ID). Theo kế hoạch, từ
tháng 1-2019 đến tháng 6-2019, triển khai và hoàn thiện phần mềm hồ sơ sức
khỏe điện tử cho tám tỉnh, thành phố trong mô hình điểm. Từ tháng 7-2019 tổ
chức triển khai nhân rộng trên toàn quốc. Ðến cuối năm 2019 sẽ hình thành
hệ thống hồ sơ sức khỏe điện tử cho mỗi người dân. Khi người dân đến cơ
sở y tế, người thầy thuốc ở bất kỳ đâu trên lãnh thổ Việt Nam, chỉ cần một động
tác nhấn chuột, máy tính sẽ hiện ra đầy đủ thông tin về hiện trạng sức khỏe của
người đó, giúp ích rất nhiều cho chẩn đoán và điều trị.
(Báo nhân dân điện tử, 31/01/2019)
Adoption of EMR system in Vietnam
● NEW newspaper !
● Nationwide EMR system will be completed in 2019 !
● A better, digitized healthcare system is coming !
29
31. Opportunities
Promising achieves of deep learning
● Have shown outstanding performance in various tasks
○ Computer vision
○ Speech recognition
○ Natural language processing
○ Reinforcement learning
○ …….
● Can bypass the feature engineering process
○ E.g. ICD-10 code contains more than 70,000 types of codes
How can we express these code in our model ?
● Deep learning structures are well suited with various healthcare tasks
○ CNN
○ RNN, LSTM
○ GANs
○ Attention mechanism
○ …...
31
33. Challenges
● Lack of data
○ The EMR system is not ready for some countries, regions
○ Complicated process to get access to healthcare data
due to the significant sensitivity of the data.
○ Combining EMR data across institutions can be complicated
because of difference in EMR versions between institutions.
● Lack of labels (both in quality and quantity)
○ Annotation requires domain knowledge of trained experts
○ Rare diseases implies less data
○ Even noisy between clinicians or institutions
■ E.g. ICD-10 contains many similar codes
■ Different practices of doctors
Challenges with EMR data
33
34. Challenges
Challenges with EMR data
● Heterogeneous types of data
○ Numeric values (lab tests)
○ Discrete codes (diagnosis, medicine, procedures)
○ Continuous monitoring data
○ Free-text clinical notes
○ Medical images
How to effectively use these data altogether ?
● Temporality and irregularity
○ Events are irregularly sampled (and also biased)
○ Long-term and short-term dependencies
34
35. Challenges
Challenges with healthcare domain
● Decision in healthcare is sensitive
○ Require immediate information and decision
○ Sometimes have life or death consequences
○ High standard required
How much of accuracy will be considered enough?
● Model needs interpretability
○ An accurate black-box might not be enough
○ Clinicians often require reasoning behind prediction
● Toward more complex output
○ Question and answer
35
37. Some public datasets
● MIMIC-III, a freely accessible critical care database.
Johnson AEW, Pollard TJ, Shen L, Lehman L, Feng M, Ghassemi M, Moody B, Szolovits P,
Celi LA, and Mark RG. Scientific Data (2016)
https://mimic.physionet.org/
● EMRBOTS, experiment with artificial large medical datasets without
worrying about privacy.
http://www.emrbots.org/
37
38. Other inferences
● Deep learning for healthcare: review, opportunities and challenges
Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang and Joel T. Dudley
● Opportunities and challenges in developing deep learning models
using electronic health records data: a systematic review
Cao Xiao, Edward Choi and Jimeng Sun
● Harnessing the Power of Data in Health
Stanford Medicine 2017 Health Trends Report
● The opportunities and challenges of data analytics in health care
Paul B. Ginsburg, Andrés de Loera-Brust, Caitlin Brandt, and Abigail Durak
● AI And Healthcare: A Giant Opportunity
Insights Team, Insights Contributor FORBES INSIGHTS With Intel AI
38
