big data approaches to healthcare systems

19
Big Data Approaches to Healthcare Systems Shubham Jain Shrawan Ram B.E. final year student Assistant Professor

Upload: shubham-jain

Post on 15-Apr-2017

333 views

Category:

Engineering


7 download

TRANSCRIPT

Page 1: Big data approaches to healthcare systems

Big Data Approaches to Healthcare Systems

Shubham Jain Shrawan Ram B.E. final year student Assistant Professor

Page 2: Big data approaches to healthcare systems

Big Data

Page 3: Big data approaches to healthcare systems
Page 4: Big data approaches to healthcare systems

Volume Variety Velocity Veracity Value

Page 5: Big data approaches to healthcare systems

Key Points about Big Data

Every day, we create 2.5 quintillion bytes of data - According to IBM survey with close to 92% of world’s data has been created in last two years.

By 2020, the International Data Corporation (IDC) predicts world’s data will grow to almost 40 zettabytes(ZB). Generates Jobs opportunity. Tsunami of analytics. B2C retailers: consumption patterns, stock, ordering, returns, sales – and how all of this ties in to online advertising campaigns, conversion, and efforts; ad delivery In healthcare systems to derive predictive models for people, costs, treatments, and propensity for disease.

Page 6: Big data approaches to healthcare systems

Big Data in Healthcare

Page 7: Big data approaches to healthcare systems
Page 8: Big data approaches to healthcare systems

Overview of Big data in Healthcare In the global healthcare sector, there are three major types of digital data: Clinical

records, health research records, and business/organization operations records In 2005 VPH (Virtual Physiological Human) technology was introduced which is a

framework for collaborative investigation of human body as a complex single system with multi-level modelling.

In 2008 Google developed Google Flu Trends (GFT) for monitoring millions of users’ health tracking behaviours online and with the help of large number of search queries

McKinsey estimates that big data analytics can enable more than $300 billion in savings per year in U.S. healthcare, two thirds of that through reductions of approximately 8% in national healthcare expenditures

McKinsey believes big data could help reduce waste and inefficiency in the following three areas: In Clinical operations, In Research & development ,Public health.

Page 9: Big data approaches to healthcare systems

Virtual Physiological Human methodological and technological frameworkenable collaborative investigation of the human body as a single complex systemDescriptive - allow observations made in laboratories, hospitals and the field Integrative - enable experts to analyse these observations collaboratively and

develop systemic hypothesesPredictive - possible to interconnect predictive models defined at different scales,

with multiple methods and varying levels of detail, into systemic networks. possible to verify networks validity by comparison with other clinical or laboratory

observations. formed by large collections of anatomical, physiological, and pathological dataaim to integrate physiological processes across different length and time scales

(multi-scale modelling). combination of patient-specific data with population-based representations

Page 10: Big data approaches to healthcare systems

Aim of Virtual Physiological Human personalized care solutions reduced need for experiments on animals more holistic approach to medicine preventative approach to treatment of disease More use of in silico (by computer simulation) modelling and testing of drugs better patient safety and drug efficacy body treated as a single multi organ system rather than as a collection of

individual organs make possible Personalised, Predictive, and Integrative medicine

Page 11: Big data approaches to healthcare systems

Advantages to healthcare Systems Making healthcare data digitally available gives power of combining big data with cloud computing and IoT envisioning versatile healthcare solutions. efficient and fast treatment facilities detecting diseases at earlier stages managing individual health profile for further analysis patient segmentation detecting healthcare fraud more quickly big data analytics in healthcare can contribute to Evidence-based medicine Individualized care

Page 12: Big data approaches to healthcare systems

Contra Cancrum

Page 13: Big data approaches to healthcare systems

Overview of Cancer Generic term for a large group of diseases that can affect any part of the body Rapid creation of abnormal cells that grow beyond their usual boundaries Metastasizing, Metastases are the major cause of death from cancer Cancers figure among the leading causes of morbidity and mortality worldwide, with approximately 14 million new cases and 8.2 million cancer related deaths in 2012 The number of new cases is expected to rise by about 70% over the next 2 decades Around one third of cancer deaths are due to the 5 leading behavioural and dietary risks: high body mass index, low fruit and vegetable intake, lack of physical activity, tobacco use, alcohol use annual cancer cases will rise from 14 million in 2012 to 22 within the next 2 decades

Page 14: Big data approaches to healthcare systems

Overview of ContraCancrum will integrate and optimise the simulator for implementing two clinical studies- scenarios corresponding to the two tumour types glioma and lung Six University Hospital Departments possessing world acclaimed expertise in

running clinical trials will provide multilevel and multimodality sets of data for about 200 patients per year (including both glioma and lung cancer cases)

The predictions of the simulators to be developed will rely on the imaging, histopathological, molecular and clinical data of the patient

Fundamental biological mechanisms involved in tumour development and tumour and normal tissue treatment response such as metabolism, cell cycle, tissue mechanics, cell survival following treatment etc. will be modelled

From the mathematical point of view the simulators will exploit several discrete and continuous mathematics methods such as cellular automata, the generic Monte Carlo technique, finite elements, differential equations, novel dedicated algorithms etc.

Page 15: Big data approaches to healthcare systems

Aim of ContraCancrum The ContraCancrum i.e. the Clinically Oriented Translational Cancer Multilevel

Modelling project aims at developing a composite multilevel platform for simulating malignant tumour development and tumour and normal tissue response to therapeutic modalities and treatment schedules

to provide a better understanding for cancer at various levels of biocomplexity and most importantly to optimize disease treatment procedure in the patient’s individualized context by simulating the response to various therapeutic regimens

to enhance the existing tumour simulators well beyond the state-of-the-art, especially on the biochemical level (molecular dynamics), on the molecular level (detailed molecular networks) and on the cellular and upper biocomplexity levels (angiogenesis, embryology considerations, biomechanics, medical image analysis etc.

will model and simulate cancer/normal tissue behaviour at different levels of biocomplexity, and also model a facet of the systemic circulation via pharmacokinetics and synthesize models of haematological reactions to chemotherapy

Page 16: Big data approaches to healthcare systems

In a country like India, where the population is huge, the resultant pressures are visible in the infrastructure and healthcare system

majority of the people in the country do not have health insurance given the high cost of treatment, families are often forced into financial crisis According to surveys conducted, non-communicable diseases such as cancer,

diabetes, obesity, respiratory diseases, cardiovascular diseases, obesity and so on were the leading cause of death in India in 2008

The biggest healthcare challenge facing the country today is not only the acute shortage of doctors and beds but also the affordability of treatment in Tier two and three cities and the rural areas

big data analytics can go a long way in improving the quality of treatment across all regions while keeping in mind its cost in india.

Big data in Healthcare systems :India Perspective

Page 17: Big data approaches to healthcare systems

Big data in Healthcare systems :India PerspectiveThe cellular network data traffic more than doubled in 2010 and is expected to

increase by more than 13 times to 25000 petabytes per annum by 2015 in India. In terms of healthcare, this sector in India contributes less than 12 percent of the

volume generated in India it is anticipated that this opportunity can grow to around 25 percent of the overall

data generated by 2015 The current Indian healthcare system is in need of a radical reinvention Traditional approaches have not brought the rapid change required by aging

populations and the rising costs of healthcare Big data analysis is of immense help when the data is too large and complex, i.e., it is

difficult to capture, curate, store, search, share, transfer and analyse By including descriptive, diagnostic, operational, predictive and prescriptive analytical

values, big data analysis can be used fruitfully to mitigate future risks and plan the road ahead

Page 18: Big data approaches to healthcare systems

Summary Data is most relevant emerging asset class of the economy. Healthcare is one of the biggest concern of every society in this world. By combining VPH technologies with big data will result into some profound

consequence. ContraCancrum is expected to contribute to the achievement of higher cancer cure

rates for the potentially curable patients whereas for the non curable patients it is expected to contribute to the achievement of increased life expectancy and better quality of life.

The management of resources where there is a concerning lack, investment in suitable medical infrastructure and the workflow in hospitals can all be improved to a great degree in India with the help of big data.

Page 19: Big data approaches to healthcare systems

References

[1] O. Terzo, P. Ruiu, E. Bucci, and F. Xhafa, “Data as a service (DaaS) for sharing and processing of large data collections in the cloud,” in Proc. Int. Conf. Complex Intell. Softw. Intensive Syst., 2013, pp. 475–480. [2] An initiative of the World Economic Forum February 2011 in Collaboration with Bain & Company, Inc., “Personal Data: The Emergence of a New Asset Class. Retrieved from http://www.bain.com/Images /WEF_ Personal_Data%20_A_New_Asset_Class_Telecom_opportunities.pdf. [3] IBM definition of big data, Retrieved from https://www-01.ibm.com/ software/data/bigdata/what-is-big-data.html. [4] Raghupathi and Raghupathi Health Information Science and Systems 2014, 2:3 http://www.hissjournal.com/content/2/1/3 [5] (2008).Google Flu Trends [wikipedia].Available: https://en.wikipedia.org /wiki/Google_Flu_Trends. [6] Marco Viceconti, Peter Hunter, and Rod Hose, “Big Data, Big Knowledge: Big Data for Personalized Healthcare”, ieee journal of biomedical and health informatics, vol. 19, no. 4, july 2015. [7] Worldwide cancer statistics [Online]. Available: http://www.cancerresearchuk.org/healthprofessional/cancerstatistics/worldwidecancer. [8] K.Marias, V. Sakkalis, A. Roniotis, C. Farmaki, G. Stamatakos, D. Dionysiou, S.Giatili, N. Uzunoglou, N. Graf, R. Bohle, E. Messe, P. V. Coveney, S. Manos, S. Wan, A. Folarin, S. Nagl, P. Büchler, T. Bardyn, M. Reyes, G. Clapworthy, N. Mcfarlane, E. Liu, T. Bily, M. Balek, M. Karasek, V. Bednar, J. Sabczynski, R. Opfer, S. Renisch, and I. C. Carlsen, Clinically Oriented Translational Cancer Multilevel Modeling: The ContraCancrum project, WC 2009 World Congress of Medical Physics and Biomedical Engineering, Sept 7-12, Munich. [9] Dr. Vikram, Healthcare thought leader, How Big data can help healthcare [blog post]. Available: http://www.healthcare-in- india.net/uncategorized/how-big-data-can-help-healthcare. [10] Kapil Khandelwal, Mentor, Investor and a Healthcare Expert, [blog post]. Available:http://yourstory.com/2013/06/is-big-data-big-business-in- healthcare-in-india.