The healthcare industry has immense opportunities to leverage patient data to improve the quality of care provided. The cost of providing care has gone up significantly over the last couple of decades in the US. All entities in the ecosystem such as payers and providers have to figure means to reduce their costs. Electronic Health Records present such an opportunity. They represent the historical evolution of care delivery records by health professionals from paper-based handwritten formats to electronic formats. They contain information which can be classified like admissions, lab measurements, caregiver details, demographics, etc. This whitepaper covers how implementing Machine Learning on attributes from electronic health records can help derive useful insights and how these insights can help providers identify those patients who are at risk of getting readmitted and take appropriate measures.