Fraud Detection Tool Predicts Hospital Quality
By HospiMedica International staff writers Posted on 16 Oct 2013 |
A new study reexamines patient satisfaction scores in measuring hospital quality, putting into use a health-care fraud tool.
Researchers at Thomas Jefferson University (Philadelphia, PA, USA) developed a theoretical model to justify the application of PRIDIT—a method originally developed for the detection of health-care fraud—in the investigation of hospital quality. They then applied the PRIDIT method to a national, multiyear data set on US hospital quality variables and outcomes, creating a steady, predictable scale for hospital quality so that actuaries could map out reimbursement rates over years for programs like Medicare and the Patient Protection Affordable Care Act (ACTA).
The results demonstrate how the PRIDIT method can be used to predict future health outcomes based on currently available quality measures. The method scoring of hospital quality includes indicators such as patient satisfaction and medical outcomes, and is weighted heavily by factors such as mortality rates and the number of beds at the hospital, as more beds indicates more cases and better outcomes. Under the model, a patient in a highly rated hospital might dislike the noise and bad food, but survive a life-threatening heart attack. The study was published online on September 30, 2013, in Risk Management and Insurance Review.
“There is a lot of information patients can use to select a hospital. However, this is usually a laundry list of indicators that may not mean much for the lay person, or that they may be unaware even exists,” said lead author Assistant Professor Robert D. Lieberthal, PhD, of the school of population health. “Our method compares hospitals directly, so that a patient choosing between two or three hospitals can easily compare them and choose the highest quality facility.”
The PRIDIT method makes use of fraud predictor variables to obtain an overall suspicion score for each claim, and to classify these claims accordingly without access to a set of audited claims. It is based on a scoring technique called RIDIT (Relative to an Identified Distribution Integral Transform) analysis developed for epidemiological literature.
Related Links:
Thomas Jefferson University
Researchers at Thomas Jefferson University (Philadelphia, PA, USA) developed a theoretical model to justify the application of PRIDIT—a method originally developed for the detection of health-care fraud—in the investigation of hospital quality. They then applied the PRIDIT method to a national, multiyear data set on US hospital quality variables and outcomes, creating a steady, predictable scale for hospital quality so that actuaries could map out reimbursement rates over years for programs like Medicare and the Patient Protection Affordable Care Act (ACTA).
The results demonstrate how the PRIDIT method can be used to predict future health outcomes based on currently available quality measures. The method scoring of hospital quality includes indicators such as patient satisfaction and medical outcomes, and is weighted heavily by factors such as mortality rates and the number of beds at the hospital, as more beds indicates more cases and better outcomes. Under the model, a patient in a highly rated hospital might dislike the noise and bad food, but survive a life-threatening heart attack. The study was published online on September 30, 2013, in Risk Management and Insurance Review.
“There is a lot of information patients can use to select a hospital. However, this is usually a laundry list of indicators that may not mean much for the lay person, or that they may be unaware even exists,” said lead author Assistant Professor Robert D. Lieberthal, PhD, of the school of population health. “Our method compares hospitals directly, so that a patient choosing between two or three hospitals can easily compare them and choose the highest quality facility.”
The PRIDIT method makes use of fraud predictor variables to obtain an overall suspicion score for each claim, and to classify these claims accordingly without access to a set of audited claims. It is based on a scoring technique called RIDIT (Relative to an Identified Distribution Integral Transform) analysis developed for epidemiological literature.
Related Links:
Thomas Jefferson University
Latest Critical Care News
- Powerful AI Risk Assessment Tool Predicts Outcomes in Heart Failure Patients
- Peptide-Based Hydrogels Repair Damaged Organs and Tissues On-The-Spot
- One-Hour Endoscopic Procedure Could Eliminate Need for Insulin for Type 2 Diabetes
- AI Can Prioritize Emergecny Department Patients Requiring Urgent Treatment
- AI to Improve Diagnosis of Atrial Fibrillation
- Stretchable Microneedles to Help In Accurate Tracking of Abnormalities and Identifying Rapid Treatment
- Machine Learning Tool Identifies Rare, Undiagnosed Immune Disorders from Patient EHRs
- On-Skin Wearable Bioelectronic Device Paves Way for Intelligent Implants
- First-Of-Its-Kind Dissolvable Stent to Improve Outcomes for Patients with Severe PAD
- AI Brain-Age Estimation Technology Uses EEG Scans to Screen for Degenerative Diseases
- Wheeze-Counting Wearable Device Monitors Patient's Breathing In Real Time
- Wearable Multiplex Biosensors Could Revolutionize COPD Management
- New Low-Energy Defibrillation Method Controls Cardiac Arrhythmias
- New Machine Learning Models Help Predict Heart Disease Risk in Women
- Deep-Learning Model Predicts Arrhythmia 30 Minutes before Onset
- Breakthrough Technology Combines Detection and Treatment of Nerve-Related Disorders in Single Procedure