Preloader

Tag: health research

ANOMALIES DETECTION IN HEALTHCARE SERVICES

Srinivasan, U. “Anomalies Detection in Healthcare Services” Using several practical examples of cost and quality-of-care outliers, the author presents a framework to detect outliers and anomalies in healthcare services. Author(s): Srinivasan, U. View Paper

Read More

LEVERAGING BIG DATA ANALYTICS TO REDUCE HEALTHCARE COSTS

The healthcare sector deals with large volumes of electronic data related to patient services. This article describes two novel applications that leverage big data to detect fraud, abuse, waste, and errors in health insurance claims, thus reducing recurrent losses and facilitating enhanced patient care. The results indicate that claim anomalies detected using these applications help

Read More

TIKHONOV OR LASSO REGULARIZATION: WHICH IS BETTER AND WHEN. IN TOOLS WITH ARTIFICIAL INTELLIGENCE

Fei Wang, Sanjay Chawla, and Wei Liu. “Tikhonov or lasso regularization: Which is better and when. In Tools with Artificial Intelligence” (ICTAI), 2013 IEEE 25th International Conference on, pages 795–802. IEEE, 2013. It is well known that supervised learning problems with ℓ1 (Lasso) and ℓ2 (Tikhonov or Ridge) regularizers will result in very different solutions. For example,

Read More

DATA SCIENCE AND THE POLICY COMPLETION PROBLEM

Sanjay Chawla, Federico Girosi, Fei Wang “Data Science and the Policy Completion Problem” The link between policy analysis and data science is more delicate than it may appear. A new policy, by definition, will change the underlying data generating model, rendering classification or supervised learning inapplicable. Perhaps eliciting causal relations from observational data is the

Read More

UNDERSTANDING CHRONIC DISEASE COMORBIDITIES FROM BASELINE NETWORKS – KNOWLEDGE DISCOVERY UTILISING ADMINISTRATIVE HEALTHCARE DATA

Hospitals routinely collect admitted patients’ data for administrative purposes and for reporting to the government and health insurers. These heterogeneous and mostly untapped data contain rich semantic information about patients’ health conditions in the form of standard disease codes. These traces of clinical information can be aggregated over patients to understand how their health progresses

Read More

JOINT PREDICTION OF ONSET CHRONIC CONDITIONS

Chronic conditions can be costly but also preventable as well as predictable. We develop a model to predict in the short term (2-3 years) the onset of one or more chronic conditions. Five chronic conditions are considered: heart disease, stroke, diabetes, hypertension and cancer. Predictions are made on the basis of standard demographic/socio-economic variables, risk

Read More

SOCIAL NETWORK RESEARCH IN HEALTH COULD OPEN THE DOOR FOR SIGNIFICANT SAVINGS

The health industry consumes vast amounts of money and resources and is seen as a “black-hole” in many Government budgets. A ground breaking study using new science could save the industry millions and point the way for future research. Dr Shahadat Uddin CMCRC PhD Graduate Lecturer, U. Sydney Shahadat Uddin is a graduate of the

Read More

A FRAMEWORK FOR ADMINISTRATIVE CLAIM DATA TO EXPLORE HEALTHCARE COORDINATION AND COLLABORATION

Previous studies have documented the application of electronic health insurance claim data for health services research purposes. In addition to administrative and billing details of healthcare services, insurance data reveal important information regarding professional interactions/links that emerge among healthcare service providers through, for example, informal knowledge sharing. By utilising details of such professional interactions and

Read More

CASE-MIX BASED PEER CLUSTERING

We consider the problem of clustering hospitals based on their case-mix distributions. Hospitals belong to the same cluster if they offer the same mix of services and have similar demand for those services. The cluster labels can be used to control for case-mix in hospital level analyses. Methods: We obtained distributions of the 770 AR-DRGv7.0 for

Read More

JOINT PREDICTION OF CHRONIC CONDITIONS ONSET: COMPARING MULTIVARIATE PROBITS WITH MULTICLASS SUPPORT VECTOR MACHINES

We consider the problem of building accurate models that can predict, in the short term (2-3 years), the onset of one or more specific chronic conditions at individual level. Methods: We consider 5 chronic conditions: heart disease, stroke, diabetes, hypertension and cancer and build two different models that predict all possible combinations of these conditions. Covariates

Read More