Clinical decision support

Abstract

Health care is an extremely challenging field where the demand for enhanced quality of service and to deliver more value-based services has always been steadily growing. Thus the players in the Health care sector are under immense pressure to provide the best patient care and improve diagnosis success rates while at the same time reducing overheads. Consequently health care organisations are trying to move from a volume based (fee for service) business model to a value based (fee for performance) business model. Furthermore, studies also suggest inefficiencies in existing health care in that the available information is not put to proper use. An important point to note here is that there is a lot of clinical data such as patient information, lab test results, surgical instrument utilisation, medical prescriptions and clinical decision outcomes being collected by health care organizations which are underutilised currently. These information if analysed effectively could provide insights that would help the organizations address the challenges in the future. Health care organisations have now realised that big data and Analytics can help reduce costs and improve care. Need for Study:- Clinical decision support has moved from providing static clinical reference information to a more intellectual guidance using predictive analytics. Building efficient mathematical models can help the health care organizations harness the huge amount of data being collected on a daily basis to create actionable insights. This will help them improve the quality of service and add more value to the results of the clinical diagnostic tests. With the advancement in analytics and abundant information available in the health care sector, these information could be utilized to gather more insights on the medical conditions of patients. This would enable providing clinical assistance to physicians in terms of suggestions based on primitive test results. This would help reduce the overheads involved significantly in that it eliminates more complex medical test by providing a clue through the primitive tests. Grouping together patients with similar test results and suggesting common course of action would reduce the time spent by the physicians through individual interaction with the patients. Risk factors which arise as a result of the habits of patients could be sensitized to them. Clusters could be formed for patients with particular risk factors and specific prescriptions could be directed to them. Forecasting the occurrences of critical health risks for patients enables them take precautions and help them lead a healthier lifestyle based on the suggestions provided the clinical support system. This would also help them plan for their future as they could take medical insurances For corporates this would give a glimpse of the health statuses of their employees and help them estimate the imminent losses due to absenteeism of employees owing to illness. This loss could be minimized by recognizing the condition of employees and addressing them beforehand. The aim is to build a predictive analysis to build a model that would offer clinical decision support to physicians based on the results of primitive clinical tests.