Business Maverick

TECH REMEDY

Medical schemes’ R13bn annual fraud problem might be solved through AI

Medical schemes’ R13bn annual fraud problem might be solved through AI
Illustration: iStock Medical aid fraud, puppet.

AI and technology may well be the answer the medical schemes industry sorely needs to tackle its R13-billion fraud, waste and abuse problem.

Speaking at the Board of Healthcare Funders’ annual conference in Cape Town this week, Dr Hleli Nhlapo, managing director of the medical schemes division at Dental Information Systems, says perpetrators are employing increasingly sophisticated tactics, leveraging technology and syndicates to orchestrate large-scale schemes, while regulatory delays and prosecutorial challenges hinder effective resolution.

“Despite (these challenges), collaboration among healthcare funders has emerged as a crucial solution, with recent initiatives indicating a promising shift towards industry-wide cooperation in addressing these complex challenges,” he said.

Roxane Ferreira, head of operations at the Association of Certified Fraud Examiners, alluded to several global trends with tremendous financial impacts. In the US, for example, fraud, waste and abuse are estimated to lead to losses of $68-billion annually.

“In South Africa the problem is not much better, with between R8-billion and R13-billion being lost annually. With between 15% and 35% of all claims submitted regarded as being fraudulent or abusive, the plight is adding approximately R22-billion to the cost of private healthcare,” she told delegates.

Healthcare fraud across the board

Healthcare fraud is perpetrated by a variety of actors within the system, ranging from medical scheme staff to service providers, syndicates and even scheme members themselves. These perpetrators exploit vulnerabilities at different points in the healthcare process, whether through falsifying claims, overbilling or engaging in other deceptive practices.

Ferreira highlighted the multifaceted approach used in identifying healthcare fraud, citing that 70% of cases stem from tip-offs or received information, while the remaining 30% are uncovered through data mining, audits and investigations.

The more common fraud scenarios in the medical scheme sector include:

  • Merchandising, where pharmacies sell non-healthcare merchandise, but claim for a healthcare service;
  • False claims by claiming for services not rendered;
  • ATM scams, where doctors submit false claims and provide cash to patients;
  • Card farming, where members lend their membership cards to non-members;
  • Code gaming, which involves doctors manipulating billing rules to increase revenue; and
  • Hospital cash plan fraud, which entails doctors and members colluding to arrange unnecessary hospital admissions.

AI to the rescue

In response to the escalating challenges of healthcare fraud, Ferreira says the health sector is increasingly turning to innovative solutions, with the integration of artificial intelligence (AI) emerging as a pivotal strategy.

“AI technology offers the capability to analyse large volumes of data rapidly and accurately, enabling the identification of suspicious patterns and behaviours,” she says. “By leveraging AI algorithms, healthcare providers can proactively identify questionable activities, thereby safeguarding resources and maintaining the integrity of healthcare systems.”

Using these advanced algorithms, AI can swiftly identify irregularities, such as sudden spikes in billed procedures and visit rates. It can also be used to compare billing practices, verify purchases, compare the geographical location of a patient against the practice, and treatments billed for the same or similar treatment by other practices.

In the fight against healthcare fraud, waste and abuse, collaboration and technological innovation are emerging as critical pillars. By harnessing advancements such as AI, healthcare systems can effectively detect and prevent fraudulent activities, thus safeguarding resources, upholding the integrity of patient care and rebuilding trust. 

Laura Fitzgerald, head of brand and digital experience at Pindrop, an AI authentication and security company, says the advent of voice deepfakes and caller ID spoofing has further complicated the landscape of phone-based healthcare fraud. Fraudsters can now more convincingly impersonate officials from trusted institutions, making it harder for individuals to recognise fraudulent calls. “By requiring voice verification for transactions and inquiries conducted over the phone, healthcare organisations can significantly reduce the risk of fraud, ensuring that sensitive information and healthcare services are accessed only by authorised individuals,” she says. DM

Gallery

Comments - Please in order to comment.

  • Dominic Rooney says:

    “…between R8-billion and R13-billion being lost annually…”
    “…the plight is adding approximately R22-billion to the cost of private healthcare…”
    “…between 15% and 35% of all claims submitted regarded as being fraudulent …”

    These numbers don’t make a lot of sense to me.

    To take the maximum figures, if R13-billion is being lost then why is R22-billion being added to the cost of private health-care ? Where is the R9-billion going ?

    I’m confident that medical aid fraud has increased substantially since 1994 so was interested to read 70% of cases are created from tip-offs and only 30% from analysis. It will be interesting to see what additional genuine cases of fraud will be detected by the techniques described. I anticipate increased hassle, bureaucracy and “computer says no” for the large majority of medical aid members which consists of honest people.

Please peer review 3 community comments before your comment can be posted

X

This article is free to read.

Sign up for free or sign in to continue reading.

Unlike our competitors, we don’t force you to pay to read the news but we do need your email address to make your experience better.


Nearly there! Create a password to finish signing up with us:

Please enter your password or get a sign in link if you’ve forgotten

Open Sesame! Thanks for signing up.

Daily Maverick Elections Toolbox

Download the Daily Maverick Elections Toolbox.

+ Your election day questions answered
+ What's different this election
+ Test yourself! Take the quiz