Health
Mobility
By product
Health
Mobility
By industry
Request a free trial
We will contact you within 24 hours
Claims can’t blush or why copying is clearly noticeable not only in lessons
Detection of "added" services using big data
In our previous article, we drew attention to the fact that fraud is a systematic distortion of information by a clinics with the aim of receiving payment from an insurance company.
Clinics disguise such distortions as ordinary, unremarkable sets of services to ensure that the insurance company approves payment for the services provided and does not initiate a detailed examination of the invoices.
Clinics disguise such distortions as ordinary, unremarkable sets of services to ensure that the insurance company approves payment for the services provided and does not initiate a detailed examination of the invoices.
publication date:
September 8, 2023
Tags:
Health Insurance
Trends
Fraud
Share:
Health Insurance
Trends
Fraud
One of the ways to unjustifiably increase the volume of insurance payouts is by "adding" services to those actually provided. In other words, a patient has indeed visited a doctor, received the necessary services A, B, C, but the invoice for treatment also includes services D and E, which the clinic has "added." The difficulty in detecting this type of fraud lies in the fact that the "added" services D and E are selected in such a way that they do not contradict the patient's diagnosis.
In this article, we will explore the detection of such "adding" schemes using big data and examine real examples of anomalies found.
In this article, we will explore the detection of such "adding" schemes using big data and examine real examples of anomalies found.
1. A Common Practice
The use of historical data from the market of the region under consideration
The use of specialized and proprietary natural language processing libraries
1
Regular internal expert medical assessment of classification correctness
2
3
At MAINS LAB, we have been working with data on provided medical services for years, and over the past 5 years, we have accumulated tens of millions of data records that very accurately describe treatment schemes and the frequency of service assignments in different countries. However, using this data "directly" is not possible due to the various taxonomies used to denote services and diagnoses.
At MAINS LAB, the system for unifying medical services is based on:
At MAINS LAB, the system for unifying medical services is based on:
2. How Can Big Data Help?
Examples of such processing include:
The service "CT of pelvis with IV contrast medium" may be referred to as:
· ct pelvis without contrast-13074
· c.t. pelvis with cont
· ct pelvis + contrast
· pelvis scan, etc.
The service "Measurement of LDL cholesterol" may be referred to as:
· ldl
· cholesterol
· l.d.l.c
· low-density lipoprotein cholesterol (LDL cholesterol), etc.
We have done extensive work to clean and unify the data, bringing service names and diagnosis codes into a consistent format, which has opened access to previously hidden frequency patterns. For example, based on the data, we can say that prescribing the antibiotic Klavox (Amoxicillin) for colds is necessary in only 5% of cases. Statistically significant deviations from this figure in the higher direction may indicate unethical practices on the part of the clinic or physician.
3. Example and its Graphic Representation
Below is a heatmap in a specific healthcare institution based on market data for the following services:
• GP consultation;
• prescription of the antibiotic Klavox (amoxicillin);
• prescription of the broad-spectrum anti-inflammatory drug Dexamethasone;
• complete blood count;
• urinalysis.
In and of itself, the presence of such pairs of services is not fraud, but when these services are prescribed by different doctors at a frequency significantly exceeding market norms, it raises legitimate suspicions. In such cases, the insurance company receives a signal of possible fraud based on the fact that the average number of specific pairs (or more) of services for a given diagnosis or for one insured person significantly exceeds market averages.
• GP consultation;
• prescription of the antibiotic Klavox (amoxicillin);
• prescription of the broad-spectrum anti-inflammatory drug Dexamethasone;
• complete blood count;
• urinalysis.
In and of itself, the presence of such pairs of services is not fraud, but when these services are prescribed by different doctors at a frequency significantly exceeding market norms, it raises legitimate suspicions. In such cases, the insurance company receives a signal of possible fraud based on the fact that the average number of specific pairs (or more) of services for a given diagnosis or for one insured person significantly exceeds market averages.
Market Data
Specific Clinic Data
Comparison of heatmaps reveals that physicians at the examined clinic prescribe antibiotics, anti-inflammatory drugs, blood tests, and urine tests significantly more frequently than is customary in the vast majority of clinics.
The method of searching for this type of fraud described above in the article is available with aggregated market data for the specific region and appropriate medical expertise.
Identifying such anomalies allows to detect violations in treatment schemes, uncover unethical clinics, or even individual physicians. Those who prescribe abnormal amounts of drugs, including antibiotics and non-steroidal anti-inflammatory drugs, not only engage in fraudulent activities, but also harm the health of patients.
Thus, the result of using MAINS LAB products is not only to gather an evidence base to facilitate the constructive discussion of insurance companies and clinics about identified fraudulent cases, but also a medical services enhancement and insured persons health maintenance.
Identifying such anomalies allows to detect violations in treatment schemes, uncover unethical clinics, or even individual physicians. Those who prescribe abnormal amounts of drugs, including antibiotics and non-steroidal anti-inflammatory drugs, not only engage in fraudulent activities, but also harm the health of patients.
Thus, the result of using MAINS LAB products is not only to gather an evidence base to facilitate the constructive discussion of insurance companies and clinics about identified fraudulent cases, but also a medical services enhancement and insured persons health maintenance.
4. Conclusion