Data enabled health and welfare
Purpose of this project is to understand what could be learnt from connecting disparate datasets available with GP Clinics, Pathology laboratories, Government agencies and non-governmental agencies and devices. To understand the economic impact of connecting the varying datasets; and to provide a direction to leverage the latest technologies to save lives using the datasets.
Healthcare industry records are kept in manual files such as text files created by GPs, different data types such as X-rays, MRI’s and CT scans. Imposing a common format across would be improbable and time consuming. The disparity in the datasets can be overcome by transforming into a common format after the retrieval for each use.
Connecting the datasets would enable the health professional to see the required records when required. For example, a patient called Jane has been visiting a GP clinic for the last 10 years but never visited a hospital. Jane met with an accident and admitted in a hospital. The hospital staff have no information about Jane’s medical history whatsoever since the databases are disconnected and disparate. The solution is to connect the databases, which enables the emergency hospital staff to access Jane’s medical history. Accessing the medical history in a raw format is no use for the medical staff since it would be time consuming to read the medical history to retrieve the necessary information. Therefore, the data needs to be visualized to provide single over- arching view of all the data touchpoints, to establish patterns. Additional insights can be obtained if the personal health data from wearables, IoT are leveraged as well.
According to AIHW statistics around 30% of patients are referred to specialists by GPs annually. This would be putting huge burden on the health budget. This can be reduced if the patients’ history can be used to prevent diseases. Preventative healthcare by making use of patient data would result in fewer visits to specialists and hospital admissions.
Predictions of diseases much ahead: If we have long history of cancer patients, for example, then these data sets can be utilized to analyse and investigate to find any indications/anomalies which could have helped in diagnosing the disease much ahead using machine learning algorithms.
MyHealthyCommunities: MBS GP and specialist attendances and expenditure in 2016-17
Description of Use: Economic impact of connecting disparate datasets
Health Expenditure in Australia
Description of Use: This is used for understanding economic benefits of the chosen project
Check back here once the first checkpoint passes to see the challenges this team has entered.