• Health Analitika

healthanalitika

 

Health Analitika harnesses the power of clinical analytics to contribute to the triple aim in healthcare: improving the patient experience, enhancing health and reducing per capita cost. A portal with prepayment analytic systems to reduce fraudulent medical claims

Our experienced team works with payor organizations, providers and physician led practices to apply data mining and clinical analytics to improve performance.


 

Insurers are efficiently and accurately paying millions of claims that they should never pay at all. In fact, of all the key drivers of health care costs, losses from unnecessary payment is one of the few that insurers can immediately affect. At HealthAnalitika, we define state-of-the-art prepayment analytic systems with the aim of flagging and reducing claims insurers process, which should never be paid at all.

A 2001 audit of Medicare fee-for-service claims payments, for example, revealed that of the $191.8B in claims audited, 6.3%, or $12.1B were illegitimate or inappropriate. Industry-wide in the US, estimates of fraud losses range from 3% to 10% of every health care dollar.

Why, given concern about rising health care costs, haven’t payers been able to stop these losses? One reason is that “prompt pay” laws have forced payers to make a trade-off between higher processing efficiency and lower losses. Claims must be paid within specified time ranges, and there are stiff penalties for noncompliance. Delaying processing for more in-depth detection is not an option. Another reason is that today’s complex reimbursement methodologies have left loopholes— opportunities for billing and policy errors that go unnoticed by claims edit systems. In some cases, these loopholes are being intentionally exploited by savvy fraudsters.

The good news is that payer organizations no longer have to make unnecessary payments. The thorough analysis required to accurately detect fraudulent, abusive and erroneous claims can now be performed before checks are cut, without slowing claims processing. It can even be done in real time as claims are received. HealthAnalitika can build this capacity into your existing systems with a layer of business intelligence developed by clinical and quality experts.

 

Benefits of Prepayment Analytics 

  • Reduce fraud, error and abuse losses by improving detection accuracy
  • Reduce investigative, legal and administrative expenses by avoiding “pay and chase”
  • Shape billing behavior through denial of abusive claims, thereby building awareness of prepayment measures
  • Strengthen provider relations by reducing the number of legitimate claims investigated
  • Improve quality of care through improved visibility into trends and issues. For instance, fraud schemes, which used to be focused around billing for services not rendered or unbundling of services, have moved toward billing for unnecessary services, such as paying patients to have procedures they do not need.

With all the pressure on healthcare organizations to perform in the increasingly competitive market, HealthAnalitika offers valuable tools to measure what is truly happening in the institution and to their patients. HealthAnalitika can help your organization properly employ data mining for healthcare, to protect your budget and quality rating. In addition to reducing fraud and unnecessary claims, our tools can assist you with:

 

Smarter Treatment Methodologies 

Data mining for healthcare is useful in evaluating the effectiveness of medical treatments. Through comparing and contrasting various causes, symptoms, and treatment methodologies, data mining can produce an analysis of which treatments correct specific symptoms most effectively.

Data mining can also help physicians discover which medications are the most cost-efficient while still working effectively. Still other data mining applications could be used to associate the most common side-effects of a medication, to collate typical symptoms in order to improve the accuracy of diagnosis, or to discover proactive steps to reduce the risk of affliction.

 

Improved Healthcare Management 

In order to improve healthcare management, data mining applications are able to work to identify and track high-risk patients in order to design appropriate interventions as a means to lower the number of admissions, re-admissions, and claims.

For example, the Arkansas Data Network evaluates re-admissions and resource utilization, compares the data against current scientific literature, and then determines the best treatment options to lower spending.

Another example can be found in the Group Health Cooperative which sorts its patients by their demographic traits and medical conditions in order to discover which groups use the most resources. In this way, programs can be developed to help educate “problem” populations on how to better prevent or manage their conditions.

In other cases, data mining for healthcare has been used to decrease patient length-of-stay, avoid medical complications, improve patient outcomes, hospital infection control and early warning systems, etc.

 

Better Customer Relations 

Customer relationships are invaluable within the healthcare industry – especially since your customers now have a say in your Medicare, or payor organization, ranking. By understanding patient preferences, patterns, and characteristics, you can significantly improve their level of satisfaction.

Because of this, the Customer Potential Management Corp. has created a Consumer Healthcare Utilization Index that uses data mining for healthcare in order to indicate an individual patient’s propensity toward using specific healthcare services. This determination is defined by 25 major diagnostic categories and is based upon millions of healthcare transactions. The end result is an ability to identify patients who would receive the most benefit from specific services and to encourage these patients to do so.

Data mining is also helpful in finding patterns amongst patients surveyed as a means of setting reasonable wait time expectations, discovering what patients want from their healthcare providers, and finding ways to improve services.

 

Decreased Insurance Fraud

Another advantage to data mining for health care is the ability to detect and decrease insurance fraud. Data mining applications are able to establish norms and then identify any abnormal patterns and claims in order to eliminate inappropriate prescriptions or referrals, and fraudulent medical claims.

With the right tolls, the data mining for healthcare can significantly impact your Medicare quality rating and your overall budget.