The data analyst should use aggregate data to investigate the quality issue. The rationale for using this type of data is that it includes numerical or non-numerical information obtained from different sources and using multiple individuals or measures. Aggregate data provide information for groups instead of an individual patient (Longhurst, Harrington, & Shah, 2014; Weber, Mandl, & Kohane, 2014). The method will allow the analyst to examine information using common aspects to predict the disease course and establish the most effective intervention for the condition.
Retrospective Data Warehouse
The data analyst should use a retrospective data warehouse because of the ability to collect and store data from numerous sources to be used for different purposes within and outside the hospital (McCartney, 2015). The tool enables the collection of data across the organization into a single warehouse for easy and fast retrieval.
The most effective analytic approach for the analyst is quantitative analysis. Information such as stroke mortality is numerical and can be collected efficiently using a quantitative approach (Simpson, 2015). The data will also help the analyst to track changes over time, such as to establish whether the rate is increasing or declining.
Casola, Castiglione, Choo, and Esposito (2016) suggested that regardless of the benefits of using electronic health systems, analysts should consider challenges, such as security and privacy risk.
Stiglic et al. (2017) revealed that although electronic health records advance patient care, they depend on data quality and completeness. The use of these sources of data faces the risk of having incomplete records that might negatively affect their use, such as diagnosis of type 2 diabetes mellitus.
Longhurst, Harrington, and Shah (2014) focus on the challenges involved in the collection of data using randomized controlled trials, such as the cost involved. Overall, health care organizations could shift to large-scale retrospective studies to lower the cost.