There are 11 item(s) tagged with the keyword "Data Analytics".
Displaying: 1 - 10 of 11
- Feature Engineering in Healthcare Analytics
Jason Rudy, Data Scientist / Programmer and Matt Lewis, Programmer / Product Manager
In a previous blog post, we walked through the process of building a predictive model using healthcare data. One of the things we touched on briefly there, was how important proper feature engineering can be to creating a useful representation of the underlying data, and how the choices made around shaping data into features can change the nature and performance of the resulting model.
In this post, we’ll be going deeper into the process of feature engineering, and how to convert raw data inputs into a form that will make machine learning not only possible, but effective.
- Targeting Doctor Shopping, Prescription Abuse With Analytics: Population Health Lessons from the Front Lines
In recent years insurers and brokers have had to adapt to rising healthcare costs without much say in the matter. This is in part because brokers and employee benefit managers often have too much on their plates to sleuth out and address the costliest “blind spots” in health coverage. This has left many struggling to find a way to remain competitive in an increasingly technology-driven industry.
- Analytics, Group Benefits Design and The Battle Against Addiction
Like the war general, the best benefits brokers know that implementing a good benefits plan (or war plan) requires a mixture of science, art, technology and even psychology. When it comes to preempting costly diseases and health plan pitfalls, anticipation and an outside-of-the-box mentality is everything. To have a comprehensive understanding on how individuals function and behave within the health plan design is to be a step ahead of the curve.
- Three of the Costliest Health Conditions Ravaging Your Health Plan, and Steps for Prevention
High-cost claimants are only a part of the equation. There is a secondary subset of the insured population who are at-risk of entering the 5-7% of highest cost claimants that predictive modeling can uncover and help address. Not all predictive modeling engines have the capability to identify this subset of the employee population, but with Advanced Plan for Health’s Poindexter’s predictive modeling capabilities, determining the likelihood of an occurrence of coronary events, neurological events, orthopedic events and chronic kidney disease is made easy. Once interventions are made to improve the health of at-risk patients, the analytics system can retrospectively report actual cost versus the original predictive model to measure the positive health and financial effects the interventions created. Without the predictive-modelling enabled ability to identify those at-risk and intervene with targeted prevention strategies, health plan optimization will always be an uphill battle.
- Informed and Healthy Employees Make for Healthy Benefit Plans
Employers have found that it is not only the catastrophic conditions inherent in the high risk employee cohort, but also individuals who have reached the high risk group as a result of many different health issues (co-morbidities), lacking a personal physician, and inappropriately using the hospital or emergent care services for preventable problems. Plan members who are bouncing from one physician to another, because they may not understand what they need or where to obtain the requisite services, also present opportunities to improve clinical and financial metrics.
- Data analytics company Advanced Plan for Health partners with iHealth Labs
- iHealth & APH Partnership
Advanced Plan for Health (APH), a provider of data analytics technology to help organizations improve health benefits programs, today announced it is teaming with iHealth Labs, Inc., a provider of mobile healthcare monitoring solutions.
- Introducing Poindexter
Poindexter is no ordinary predictive modeling engine typical of the Population Health Market. Poindexter is APH's industry-leading phenotype, cross-dimensional predictive modeling engine that examines the entire population.
- Poindexter Predictive Modeling Engine
Poindexter, our data analytics risk engine custom-built for population health management. This tool provides dynamic, reliable insight into your population. With Poindexter you have access to essential insights in just a few simple clicks, whether you are at the strategic, provider or clinical user level. With Poindexter, you have the guidance to work smarter and stay focused without losing the “big picture” perspective. Macro trends can be detailed and compared over time with the ability to drill to specific drivers in minutes—all at your fingertips; no need to wait for answers you need today to stay on track.
Poindexter enables revolutionary predictive modeling by looking at the whole individual, as well as group trends, by examining hard data in a practical format and factoring in the impact of rapid changes in healthcare. The result is the ability to predict conditions, trends, gaps in care, admissions and re-admissions- six to 12 months in advance. This analysis of individuals within a population ultimately identifies opportunities and risks; key information in the creation of APH's customized action plans.
- Company Overview
We are specialists focused on successfully managing risk and optimizing health care benefits and costs; no matter the model of care or type of entity taking on financial risk. We've been in the advanced and predictive healthcare analytics space for years, which has allowed us to continually advance our solutions and refine our action plans so our clients gain unrivaled ROI.
Displaying: 1 - 10 of 11