The Department of Medical Electronics, RIT, in association with The IEEE EMB MSRIT student chapter and IEEE EMB Bangalore chapter organized One Week Workshop on
“Big Data Analytics, Internet of Things and Cloud Computing for Healthcare Applications” at LHC Seminar Hall-II, Ramaiah Institute of Technology.
Day 1:
The commencement of the workshop took place by invocation and introduction of the speaker.
Session 1: Talk by Dr. Anand Vinekar on “How Big Data and the Cloud can prevent Blindness in an infant.
He stressed on the Retinopathy of Prematurity, which is the leading disease across the world. Also India is one of the leading countries affected with ROP. He explained that ROP is examined by Indirect Opthalmology. KIDROP and RBSK have taken major initiatives in this field.
Karnataka Internet Assisted Diagnosis of Retinopathy of Prematurity(KIDROP), is a non-profit infant blindness prevention, detection and treatment program that performs eye screening of infants. But it is not limited to, a potentially blinding condition affecting premature infants called Retinopathy of Prematurity or ROP, but also serves people in remote and rural areas whose have no facilities, resources or training programs. There are skilled technicians, tele-medicine, and passionate ROP experts all committed to a program evolved in an eco-system of pioneering technology, specialized training and multi-disciplinary team-work between private and public organizations in India.
Rashtriya Bal SwasthyaKaryakram (RBSK) is a new initiative aiming at early identification and early intervention for children from birth to 18 years to cover 4 ‘D’s viz. Defects at birth, Deficiencies, Diseases, Development delays including disability.
He also explained how the disease is caused, the various strategies involved in imaging, protocols, segmentation, vasularity index, algorithm, 3D reconstruction of the image, Feature matching between three views and the major problems involved in process.
He provided a brief knowledge about ShishuNethra and 3nethra, technology innovations which helps in screening of common eye problems which can lead to blindness. It is simple, portable,rugged and can be operated by a minimally trained technician.
Session 2: Talk by Dr. Shyam Vasudeva Rao on “Engineering perspective of Big Data, IoT and Cloud Computing” |
He explained about the affordability, availability, appropriateness, quality and safety concerns, challenges involved in the technical innovation, standards and trends, scope of healthcare solutions at point of care, organisational, regional, national and international levels and also about the burden of Chronic Diseases in India.
He gave an insight about the Health record variants like PHR, EMR and EHR, their needs and benefits for Government, the public and for health care providers. He also explained that integration with modalities increases efficiency and reduces cost. He gave a brief explanation on affordable eye screening through 3nethra, which helps to improve the health in slums and building up personal health.
Session 3: Talk by Mr. Shailendra Rao Nalige on “Digi Health Platform- One platform for all Healthcare solutions”
He started with the explanation for need for platform, solution overview, its features and benefits and also about device agnostic, E-learning, Standards, Big data and Analysis.
He gave a brief insight about the partnership ecosystem, WISEROP, Cardio connect, and THULSI. He also explained about the eye disorder screening at eight villages around Mandalay and programme with Sri Sharada Eye and Dental Centre.
WISE-ROP (Wide-field Imaging of Infants for Screening and Education for Retinopathy of Prematurity) has been developed to address the challenge of inadequate number of trained specialists to screen and treat a condition that affects the vision of premature babies, called Retinopathy of Prematurity (ROP). Cardio Connect puts the focus on preventative cardiac health care. THULSI ( Toolkit for Healthy Urban Living in Slums Initiative ) is a NCD Screening programme to improve the health of people living in slums. It was conducted from 3rd May 2017 to 20th May 2017.
Session 4: Talk by AdarshHolavanahalli on “ Cloud care: A Healthcare providers’ story”
He started with a brief explanation of the Sen stroller, data trends, health care conundrum, healthcare demands and its real view. He also explained about a few cloud providers and their healthcare protocols and also about the cloud ecosystem. Cloud ecosystem is a term used to describe the complex system of interdependent components that work together to enable cloud services. He also stressed on the topic IOT management and the health care cloud, Big data and the healthcare cloud. He explained the anatomy of a cloud provider. It consists of the tele care provider, the consumer device manufacturer, the health monitoring provider, the application provider, the discovery and fitment provider.
He gave an insight about the impact of Cloud, IOT and the Big data in healthcare field. He also presented the future possibilities of IOT, Cloud, Big data and FOG computing in the healthcare field which providers a lot of opportunities for the people.
Session 5: Talk by Dr. Arun MavajiSeetharam on “Clinical Data Analytics and Open Challenges”
He explained the definitions of Health Data Analysis and Predictive Analytics. Health care analytics is a term used to describe the healthcare analysis activities that can be undertaken as a result of data collected from four areas within healthcare; claims and cost data, pharmaceutical and research and development (R&D) data, clinical data (collected from electronic medical records (EHRs)), and patient behaviour and sentiment data.
Predictive analytics is the branch of the advanced analytics which is used to make predictions about unknown future events. Predictive analytics uses many techniques from data mining, statistics, modelling, machine learning, and artificial intelligence to analyse current data to make predictions about future.
Also he provided us the information about the Big data in healthcare and its three key words: Data, Information and Intelligence. He also showed us how to break down avoidable Healthcare costs. He also taught is about the disease management which includes enhancing patient care, optimising resource utilisation, fraud detection, clinical outcomes and the challenges involved in it.
Day 2
Session 1: Talk by Dr.Darshan from philips on “ Deep learning application in ultrasound”
He started his presentation with giving us a brief introduction on neural networks and its rising use in the field of health care. He brought out the importance of feature representation in machine learning which helps in detection of required characteristics in a given image much the same way like which annotations are used by radiologists .
This was followed by a brief view on challenges in healthcare which varies from the premium and value segment care and expertise. This further lead to organ detection algorithm developed by his team which uses neural network and deep learning algorithms.
Session 2: Talk by Mitali Dutta and Mr.Prashant from philips healthcare on Insight and analytics in Philips using Big data
She started the presentation with insights on how philips is helping with the health care technology .She spoke about enterprise management which involves analytic strategies on getting the desired results. She also spoke about the action plan that has to be initiated in such occasions with the help of relevant software .
Sir further spoke about digital marketing and its marketing effectiveness in healthcare technology .This also involved the security and encryption o f data which is key in healthcare data analytics .
Session 3: Talk by Dr.Aravind from Triocula technologies on artificial intelligence and neural networks
He started the session with a deep insight on the importance and the power of artificial intelligence in health care .He spoke about the three main products being developed by the company :Spectre,Teleradio and Gemi .Spectre was a surgical based planning software helps the precise identification of the ventricles to give a clear picture before surgery.
He also spoke about Teleradiowhich is a unique device agnostic cloud based radiology platform.He spoke abobut the importance of big data and the uniqueness of processing data to represent it even in a 3dimensional view.
Day 3
Hands on session on IOT based cardio signal processing by RupamDas ,Co founder of Acculi Labs PvtLtd,Intel Software innovator
He started the session by giving us an insight on cloud services and importance of cloud to manage data especially in the case of real time applications .He introduced the Lyfas app which received the cardio signal and used thingspeak to analyze the data.
He demonstrated the importance of analyzing data using cloud services with the help of a bluemix account. This also involved inbuilt processing using matlab.He also highlighted the importance creating simple processing data using simple algorithms.
Day 4
Hands on session on IOT using MSP430FR5969 ULP MCU by SagarMinchal ,applicationengineer,Edgate technologies.
He started the presentation by giving an insight on the benefits of MSP430 and the advantages of it .He also gave an insight on Energia software and the IOT platform.
He also explained about sensor monitoring using a HTTP server which has wide ranged applications in the field of healthcare.He demonstrated the usage of cloud services to generate a call based alert system.This further encouraged the students to design similar projects to get a bigger understanding of big data analytics and cloud computing.
Day 5
Session 1: Talk by MohitVed on “Applications of Machine Learning and an introduction to Deep Learning”
He started his presentation from the definition of Big Data, which says extremely large data sets that may be analysed computationally to reveal patterns, trends, and associations, especially relating to human behaviour and interactions. He also stressed on the major keywords involved in Big Data. Those are: High Volume, High Velocity and High Variety. He explained about the large dataset challenges which include: Storage of Data, Processing Variety of Data, Cost and Infrastructure required.
Then, he explained about Hadoop, which is a software framework for distributed processing of large data sets across large clusters of computers. He also gave a brief explanation on Hadoop promises and performance. He explained the detailed working of Hadoop and the Hadoop ecosystem. He demonstrated Hadoop’s capabilities by a case study about Web Log Analytics, which was about categorising of products in each country.
He also taught us the basics of Machine Learning with an example of Disease Diagnosis. He also explained about the types of Machine Learning: Supervised Learning, Unsupervised Learning and Semi-supervised Learning. He also explained about the decision trees, Big data Software Suits, Core Capabilities and its advantages.
Session 2: Talk by Mr. DhushyanthDachiraju on “IOT communication aspect, IOT protocol stack development and Demo on AWS IOT”
He explained about the COAP history, specialised requirements, design, features, internal architecture“. COAP stands for Constrained Application Protocol. CoAP is an application layer protocol that is intended for use in resource-constrained internet devices, such as wireless sensor network nodes. He also explained in detail about the COAP messaging model, request/response model and its security.
He provided information about COAP using examples if Medical Device Connectivity, Patient Identification and Security. He also explained about the Medical IOT Architecture. He demonstrated AWS IOT which includes device gateway, rules engine, rule actions, device shadows, building solutions.
Session 3: Talk by Mr. Samson on “IOT Applications based on PSoC”
He started by explaining the definition of IOT, which says that IOT is a network of Embedded Devices/Systems capable of interaction. He explained about the typical model of an industrial IOT system, IOT Home Automation, design and implementation flow.
He taught us about the architecture of PSoC and its terminologies such as Microprogrammed, Hard writing, USB special layer, PSoC Creator IDE. He demonstrated an application of IOT and uploading and retrieving data from the Cloud using Thingspeak. The circuit was designed on a PSOC and a potentiometer was used. PSOC was programmed using the IDE. As the potentiometer was turned, its resistance changed which was uploaded to the Cloud and accessed through Thingspeak. Thingspeak allows us to see the code and visualise it using graphs.
Then, he explained about the security and interworking of IOTs, IOT, Big data, Cloud and Data Analytics and the Eco System.
Day 6
Session 1: Talk by Dr. Geetha Manjunath on “Smart Health: Using Machine Intelligence for Healthcare Applications”
She explained the need for early screening for breast screening in an effective way, cost factor, portability, safety, privacy, accuracy and technology. She gave an insight about Thermography which can detect Cancer much earlier and about Nirmai’s solution which uses Machine Learning and is accurate.
Machine Learning includes: Descriptive Analysis, Predictive Analysis, Prescriptive Analysis. It also includes Supervised Learning, Unsupervised Learning and Semi-supervised Learning. It is classified as training and prediction. Models like Linear regression, Non-Linear regression, Multivariate regression, etc. Classifiers such as Decision tree classifier, Random Forest etc. can be used.
She also explained about the classification of benign and malignant tumours with images, disease progression, technical challenges of Machine Learning in healthcare.
Session 2: Hands on session by Mr. Raghu on “Machine Learning and/or Pattern Recognition; Practical Approach Using Matlab”
He taught us about pattern recognition, components of a pattern recognition system, features and patterns, good feature vector. He also explained about multilayer perceptions: input layer, hidden layer and the output layer. He taught us about different methods like the holdout method, K-method, etc. He gave an insight about the Actuation or Transfer functions, Training or Learning functions, performance measure parameters, etc.
Then, we had a hands on session about Machine Learning. We executed programs and plotted graphs, checked errors, counted the number of hidden neurons, transfer function and the training function using different operations on Matlab.
The workshop helped the students to gain knowledge about IOT, Big data and Cloud computing and thereby implement the available technology in the healthcare field