August 02 2018 | 0 Comments | 88 reads Average Rating: 3
6 Ways Your Health Plan Can Turn Data Mining into a Powerful Overpayment Recovery Tool
Like other consumers, health insurers don’t enjoy feeling the pain that comes with the realization that you’ve paid too much for something. As such, they are known to employ a variety of strategies as part of their overpayment recovery programs.
Data mining is one such tactic. The challenge, however, rests in getting the most out of data mining. For too many health plans, data mining programs have grown stale since they were last updated. To keep this critical part of a payment integrity program up-to-date and maximize the overpayments it finds, your health plan needs to:
#1: Continually innovate. For example, you can move toward longitudinal data mining. With traditional data mining, claims are reviewed one-by-one whereas longitudinal data mining uses past claims behavior to inform the present analysis and identify data mining trends. As such, you can identify rare error patterns that might otherwise go unnoticed.
#2: Utilize “care transition analysis.” Such applications uncover overpayments that occur as members move between sites of care. The ability to link and track claims from site to site enables health plans to uncover questionable coding and billing patterns such as inappropriate referrals or when hospitals and skilled nursing facilities both bill for the same rehabilitative care.
#3: Leverage knowledge to proactively fix issues. Because longitudinal data mining uncovers previously unknown patterns, health plans can use this information along with benchmark trends to identify and fix issues that have been uncovered. For many plans, this is a pragmatic first step toward reducing waste and preventing overpayments from occurring in the first place.
#4: Seek to stop overpayments before they happen. Longitudinal data mining can also be applied as a prepayment or behavior modification solution, which would prevent payment errors.
#5: Add custom content development into the mix. By integrating custom concept development, you can achieve far more accurate results — higher than 95% — and a more favorable ROI. The key is to start with standard queries and then build in customization to ensure any overpayments identified are actionable. As such, you can zero in on overpayments that your plan can realistically collect on.
#6: Employ a hybrid approach. Such an approach builds on data mining to maximize the crossover between human intellect and machine learning. The next generation of hybrid analytics involves machine learning, in which models are trained to understand the data. As data models are optimized, additional patterns and insight emerge, and then those insights feed back into further optimization. As models are refined and scaled up, overpayment recovery and root cause analysis both gain efficiency.
By fine-tuning your data mining efforts, your health plan can increase recoveries without a corresponding increase in provider abrasion. This blog was adapted from “How longitudinal analysis can boost payment integrity programs,” an article that previously appeared in SmartBrief.