Healthcare Analytics Model

Healthcare Analytics involves the activities that are undertaken or actions carried out as a result of data collected from different areas within healthcare. These areas are four in number and they are Claims and cost data, pharmaceutical and research development (R&D) data, clinical data (electronic medical records) and patient behavior and sentiment data(i.e patient behaviors and preferences). The healthcare analytics model has picked up momentum in the past and it’s expected to grow exponentially in the coming years.

Healthcare analytics focused on the examination of patterns in various healthcare data in order to provide a comprehensive, clinical analysis, financial analysis, supply chain analysis, as well as, fraud and HR analysis. Because of the many areas covered, Healthcare analytics can be cumbersome and hard to comprehend and apply in an organization hence, Health Catalyst (https://www.healthcatalyst.com/healthcare-analytics-adoption-model/) has developed a framework called the Healthcare Analytics Adoption Model as a guide to classifying different groups of analytics capabilities and provide a systematic sequencing to adopting analytics within healthcare organizations.

The Healthcare Analytics Adoption Model provides a framework for evaluating the industry’s adoption analytics, a roadmap for organizations to measure their own progress toward analytics adoption and finally it also provides a framework for evaluating vendor products. The model has eight levels and they are:

Level 0 – Fragmented Point Solutions

Level 1 – Enterprise Data Warehouse

Level 2 – Standardized Vocabulary & Patient Registries

Level 3 – Automated Internal Reporting

Level 4 – Automated External Reporting

Level 5 – Waste & Care Variability Reduction

Level 6 – Population Health Management and Suggestive Analytics

Level 7 – Clinical Risk Intervention & Predictive Analytics

Level 8 – Personalized Medicine & Prescriptive Analytics

 

Level 0 – Fragmented Point Solutions

The level (0) of the Analytics Adoption Model, focuses on areas with limited analytics capabilities such as finance, acute care nursing, pharmacy, laboratory and physician productivity. This fragmented point solutions and the knowledge it generates is isolated in order to optimize sub-processes at the expense of enterprise-wide processes. Reports tend to be labor-intensive and inconsistent. There is no formal data governance function tasked with maximizing the quality and value of data in the organization.

Level 1 – Enterprise Data Warehouse

This involves collecting and integrating the core data content. When the core transaction systems are integrated into the data warehouse then level 1 has been satisfied. This data could include things like patient financial data, materials and supplies data, clinical data, patient experience data and insurance claims data.

Level 2 – Standardized Vocabulary & Patient Registries

This involves relating and organizing the core data content. At level 2, reference data and master vocabularies are defined and made available. This data includes patient identity, physician identity, procedure codes, diagnosis codes, facility codes, department codes etc.

Level 3 – Automated Internal Reporting

At the level, the analytic model is focused on the efficient, consistent production of reports and widespread availability in the organization. The key criteria for success in this level is efficiency and consistency of reports that are necessary for effective management but alone are not enough to create differentiating value in the market

Level 4 – Automated External Reporting

After an automated internal reporting system is established, the next logical step is to focus on an automated external reporting system. The focus of this level is ensuring the efficient, consistent production of reports and adaptability to changing requirements and the macro environment.  Data governance and stewardship is centralized for external reporting. Stewardship processes exist to maintain compliance with external reporting requirements and govern the process for approving and releasing the organization’s data to external bodies.

Level 5 – Waste & Care Variability Reduction

This level focuses on reducing variability in care processes. Focusing on internal optimization and waste reduction. Here, organizations are moving away from utilitarian internal and external reporting. They have a significant opportunity to differentiate themselves in the market based on quality and cost and enabled by this analytics.

Level 6 – Population Health Management and Suggestive Analytics

This level is characterized by organizations that have achieved a sustainable data-driven culture and established a firm analytic environment for understanding clinical outcomes. Hence, the work towards tailoring patient care based upon population metrics.

Level 7 – Clinical Risk Intervention & Predictive Analytics

Here, organizations are able to dabble in predictive analysis by expanding their optimization of cost per capita populations and payments. Organizational processes for intervention are supported with predictive risk models. Fee- for-quality includes fixed per capita payment.

Level 8 – Personalized Medicine & Prescriptive Analytics

At the final level, patient care can be tailored based on population outcomes and genetic data. At this level, healthcare organizations are completely engaged as a data-driven culture and shift from a fixation with care delivery to an obsession with risk intervention,  health improvement, and  preventive medicine.

Print Email