The Big Data and Business Analytics are fore frontier of technologies that are generating huge competitive advantage to the companies. Big Data Analytics are playing an important role in developing new innovative products that are enabling companies to engage their customers in a new and disruptive manner.
According to McKinsey Global Institute Report "Big data: The next frontier for innovation, competition, and productivity" - Big Data Capturing its value: $300 billion potential annual value to US health care and $600 billion potential annual consumer surplus from using personal location data globally. Healthcare reaps huge benefits from Big Data Analytics.
We specialize in developing Big Data Healthcare Analytics products. Our first Big Data Healthcare Product, Murai Data Analytics helped save healthcare device makers IT deployment costs in the range of 25% to 40% annually. We have applied Big Data Analytics to Electronic Health Records (EHR) and able to predict disease management (working in collaboration with Indian Council for Medical Research (ICMR) and Health Account Scheme).
Mobile is increasingly ubiquitous. With 6.8 billion mobile subscriptions world wide, access anytime, anywhere through smart gadgets is now putting cheap and connected, mobile computing power in the hands of millions of consumers and healthcare practitioners. Mobile Sensors – accelerometers, location detection, wireless connectivity and cameras– offer another big step towards closing the feedback loop in personalized medicine. There is no more personal data than on-the-body or in-the-body sensors. With so many connected devices generating various vital health related data, integrating these data points to Electronic Health Records not only provide more accurate picture of the patient but also helps to connect with the doctor. In this paper, we propose Sensor integration framework with Electronic Health Records (EHR).We have successfully integrated Mobile Sensor ecosystem with Electronic Health Records to provide location and patient context information to the healthcare professionals. The integration, importantly, not only helped doctors to deliver better care to patients but also enabled patients to manage thier health and disease monitoring.
Analytics platform consists of two core engines:
Healthcare Machine Learning and Patient Recommendation Engine
As part of Sanjeevani Electronic Health Records Cloud (EHR), we collect health records data from individual users. The data include: individual doctor visits data, medications data, immunization data, allergies, doctor notes and medical tests data. We correlate User health records data to fitness activities and update EHR real-time. Our EHR, importantly, correlates individual heath records to family history, geo location data, user demographics data, World heath organization (WHO) identified key parameters data, user behavior data (fitness & food in-take) to recommend exclusive & actionable insights. For instance, a user with sedentary life style (due to professional nature or personal life-style choices), the impact of low physical activities on user’s health.
We provide the user , importantly, the collective intelligence of the users with similar demographics and their respective health trends through the application of collaborative recommendation. The collaborative recommendation provides comparative snapshot view between users EHR data to similar demographics in following areas: health trends, doctor notes, medication usage, allergies and food-nutrition. Sanjeevani provides preventive healthcare actionable insights to users.
We apply Sanjeevani built-in preventive machine learning models on user demographics and user location data to deliver preventive health recommendations to users. For instance, a user with Asthma will get preventive healthcare notification when Sanjeevani Cloud detects change in pollution levels that would adversely affect the asthma user.
We also mine, importantly, social media to alert user when asthma related epidemiological conditions occur near users location. Sanjeevani Healthcare Cloud glean through demographics healthcare data to recommend, importantly, preventive health recommendation of the users with similar demographics that learn good health learning process over the time.
We apply both content and collaborative (patient groups with similar demographics) recommendation systems. The main idea behind content based recommendation system is to derive patient level key attributes and influence of those attributes on patient health management. For instance, progression of patient physical attributes (weight, high blood sugar levels) on patient chronic diseases (high Blood Pressure or diabetic). Coming to collaborative recommendation system, the main idea is to exploit information about past patient behavior (social, food and fitness-health related activities) and correlating it to patient family history for predicting future health and disease management.
Smart Notifications: As part of recommendation system, our architecture applies rule-based analysis on real-time stream processing data and enables insights that link the patient fitness activities to their disease conditions. For instance, borderline high blood pressure patient can correlate fitness activities to increase or decrease of Diastolic Blood Pressure and Systolic Blood Pressure. As the real-time data collection is performed on the mobile app, the architecture immediately elevates rules on the patient vital signs and notifies if any rule violation.
Social presence Analytics: Our recommendation system applies location based social presence analytics to provide most relevant information to manage patient diease management. We have seen by applying Social presence analytics not only drastically improves patient care but also better engage patients.