How Big Data can save your life

A 56-year old suffering from acute leukemia was rushed to the hospital with a little chance of survival. Acute leukemia is a challenge to the medical community as it progresses very quickly and causes a sudden increase in the number of malignant (cancerous) immature white blood cells. Often times, patients find themselves in ER with wildly fluctuating prognosis. But despite the odds, this 56-year old was lucky.

Thanks to IT. Let's explain. When a patient's life hangs by a thread, the treatment protocols and options are limited. Some can be done and some cannot be done due to lack of information. This is where IT enters the operating room. Coming back to this case, this patient survived because he got the right stem cells in time.

But getting the right stem cells match is not easy for it requires sophisticated analytics and graphing techniques. But solutions like CordMatch-an innovative big data search platform is helping in the fight against cancer. CordMatch is a tool developed by Berlin-based Cytolon and this tool uses big data techniques and a unique matching algorithm to quickly find cord blood matches for cancer patients in need of a stem cell transplant.For instance, blood from the umbilical cord or cord blood, is rich in stem cells that can be used to treat diseases such as leukemia. The process for matching cord blood units to patients used to take hours.

Working with Cytolon, an innovator in stem cell matching, CSC developed an Internet-based system that matches donor cord blood with patients quickly and easily. Using CordMatch is like Facebook, it is ‘who knows who,' so it can match all corresponding codes to one code. In the above mentioned case, we are referring to, using CordMatch a donor was found in another few hours and the life was eventually saved. He was fortunate enough but there are nearly 14 mn unfortunate ones who are succumbing to cancer each year. And a recent report by WHO adds that this burden will grow by 70% over the two decades.

In situations like this, analytics' can be a game changer as it helps healthcare providers the needed insights and outcomes about patient care, and also gives actionable intelligence.

RELYING MAINLY ON PRIVATE HEALTHCARE

Despite all its economic prowess, healthcare in India stands at a paradoxical juncture. Its healthcare spending has increased at a CAGR of 10% over the past decade, but the returns on this expenditure have been sub-optimal as they have not generated corresponding improvements. Moreover, India ranks among the bottom five countries with the lowest public health spending globally and accounts for 21% of the world's burden of diseases.

A 2010 World Bank Report estimates that India is losing more than 6% of its GDP annually due to premature deaths and preventable illnesses. While in most developed nations, total spending on health ranges between 6-8% of the GDP, and public money outweighs private money by 3:1 but in India though the overall health spending does reach 6% of the GDP but most of that is private money.

NEED FOR ANALYTICS

CDC (Center for Disease Control) estimates that by the time human cases of any infectious disease are seen, most 50% of the epidemic life cycles elapsed. A report of Institute of Medicine Committee on the Quality of Healthcare in America estimated that hundreds of patients die each year due to medical errors. A survey report also adds that by 2020, there would be 50 times increase in the amount of digital healthcare data.

In such a situation, these analytic solutions would be savior for hundreds of thousands of people dying of some fatal diseases. These solutions can give answers to why a particular thing is happening or what happens if trend continues or what will happen next and what is the best next course of action. And with real-time surveillance, the ‘time to reaction' can be significantly reduced, leading to not only economic savings, but a much more efficient outbreak intervention mechanism as well.

A report from about a year ago projected that usage of advanced data analytics in hospitals will reach about 50% adoption rates by 2016. And according to HIMSS Analytics, only about 30% of hospitals had a clinical data warehouse or data mining solutions in place in 2011.

Like many other verticals, the healthcare industry is also reeling under the pressure of doing more with less. Big data analytics can be a boom for them in order to better manage care and achieve cost efficiencies. But in spite of driving better healthcare outcomes and predicting future trends, Indian healthcare organizations are only scratching the surface. So, there is a dire need to harness the data, use analytics to turn that data into information, and then apply those insights in a way that creates a better more sustainable future.

WHY ANALYTICS IS NOT TAKING OFF

Going forward organizations across the Indian healthcare industry will be keen on embracing an analytical culture and empowering the non-technical business users, doctors, decision makers with the power of analytics. The country has numerous public health IT systems like MCTS (Mother and Child Tracking System), HMIS (Health Management Information Systems), Integrated Disease Surveillance (IDSP), etc, but all working in ‘silos'.

States have their own initiatives to implement IT systems for various purposes. For instance, we have two RCH (Reproductive and Child Health) systems concurrently running at the national level, namely MCTS and HMIS. DHIS-2 is an example of facility based reporting of RCH data from district level in many states which gets aggregated at the national level into the national HMIS portal. MCTS, on the other hand, is a name-based reporting system at the national level.

Secondly, the technologies for natural language processing and semantic technologies have significantly improved over the past few decades and found their way from academic research to commercial use in various industries, while healthcare is still lagging significantly in adopting text analytics.

Bipin Thomas, President, Health Group, UST Global adds, "Most EHRs use rudimentary tools for text analytics and lack the sophistication of advanced text analytics engines available in other industries." He further adds that modernization of legacy systems and deployment of real-time advanced analytic platforms is a significant investment.

Another challenge faced while implementing unstructured data analytics solution is the non-availability of comprehensive disease specific ontologies and lack of standardization for data input and storage. Jordan Battani, Managing Director of CSC's Global Institute for Emerging Healthcare Practices adds, "The other challenge is with patient feedback through non-traditional communication channels such as social media. Some hospitals have set up special ‘social media response teams' to monitor Twitter and Facebook for opportunities to assist patients and respond to patient concerns. New tools will be needed, however, to make that type of engagement more efficient."

The key challenge is absence of usage of unique IDs by the Medical fraternity so is by the respective diagnostics industry, believes Mukul Bagga, Managing Director, Quest Diagnostics India.

LOOKING GLOBAL

Singapore's National Electronic Healthcare Record (NEHR) is the cornerstone of its connected health strategy and is working on a vision of ‘one Singaporean, one health record'. This initiative is a summary of healthcare profiles and a consolidated view of a patient's current problems, medications, and investigations. On the other hand, Australia's strategy revolves around the concept of ‘Connected Health' and its nationwide personally controlled electronic health record (PCEHR) system is under development for initial deployment in July 2012.

In the US, the Veterans Administration has a voluntary program that's using blood sample and health information from various military veterans. Over 150,000 have enrolled to help give us a better understanding of healthcare. There are similar programs in Iceland and other countries where long-term healthcare and statistical data from the population are being used to help spot and address healthcare challenges before they become real problems.

RECOMMENDATIONS

Better data helps in driving better health outcomes. In India, the organizations are ‘drowning in information, but dying of thirst,' as the various health IT systems are working in silos. The following initiatives need to be taken:

Implementing Hospital Information Systems and Records Digitization: The various Hospital Information system(s) or sub-systems have been in place but all working without exchange of data resulting in no improvement in the state of healthcare delivery. This ecosystem needs to be integrated to patients across states and center.

Automation of Supply Chain: In India, drugs and medicines are procured at three different levels: National level, state level, district level within a state. This automation will result in efficient inventory management at all levels, tracking of consumption and expiry dates till PHC and sub-centers, management of supply interventions, and greater transparency in drug procurement.

Handheld based data collection: Given the limitations of providing hard IT infrastructure in the vast reaches of rural India, it is proposed that handheld based data collection modules would result in significant advantages like real-time information availability to decision makers, on the spot basic analytics, effective feedback loop integration which can therefore enable diagnostic decision support, etc.

Empowering Citizens through Information Dissemination: A citizen portal would aim at providing information and services transparently to public with the vision to enhance the citizen's experience. It would lead to Better Messaging, Greater Efficiency, and Improved Citizen Engagement

The entire healthcare system should be under one roof within a state where people from any part of the state would have access to information and services through citizen portal. This portal should be available both on web and mobile.
(The recommendations are based on the study titled ‘Connected health to redefine India's journey as an economic superpower - Accenture report 2014)

Swaminathan Rajamani, Director, Europe Delivery & Solutions, BIM India shares, "The EHRs must be able to communicate with existing systems within the healthcare provider IT landscape."

All these recommendations can plug-in several inefficiencies in the healthcare value chain in India. These measures will consequently result in increased healthcare access to citizens, without significantly increasing the spending on the same. While most of these proposed interventions have either been rolled out, or envisaged in parts of India, the implementation, almost always, has been partial or incomplete. What seems to be required is a whole-hog approach to the country-wide rollout of these interventions, failing which, the real benefits may not be fully realized.