Healthcare providers have known for years that a one-size-fits-all strategy doesn’t work in healthcare billing. With a one-size-fits-all approach cost to collect is higher, payments are lower and patient engagement misses the mark:
- Resources (like employee time and talent) are wasted on calling patients who always pay, or who never pay, regardless of call frequency, timing or flexible payment options.
- Patients who need assistance or require more attention may fall through the cracks, as efforts are spread evenly across all patient payers.
- Patients who would pay if offered a payment plan are reached late, delaying account resolution.
- Elite payers, patients who always pay their bills, are annoyed by unwarranted phone calls and texts, or are confused by repeat statements.
With a one-size-fits-all approach, providers end up using unnecessary time, resources and money — and miss key opportunities to truly engage and assist their patients. Providers know that different patients need different approaches. But understanding how to best segment patient accounts and how to construct effective patient engagement strategies for each segment are steep challenges. Here are four pillars for moving data-driven and ROI-focused self-pay collections strategy.
1. Go Beyond a Score
There are many solutions that score patient accounts. But a score is one-dimensional — patients are more than a number. A propensity-to-pay (P2P) score doesn’t fully quantify payment behavior, and with a simple score, the burden falls to the provider to determine how to interpret and take action. Broad segmentation isn’t much better. At Sift we’ve found that broad segments leave out payers who, with the right outreach, would be able to resolve their accounts. For many patients, the right message, timing, channel and payment option have a significant impact on their ability to pay. Micro-segments or one-to-one recommendations are the most effective way to reach these patients that can be missed in broader segments.
2. Add Machine Learning
Historical payments data builds the best picture of future payment behavior. In comparison to credit scores, historical payments data is more accurate, less intrusive and less expensive. But historical payments data is vast. Normalizing and organizing payments data is a challenge, and surfacing the attributes that best predict payment behavior requires data science expertise. But this approach is worth the time and effort. Machine learning models are effective at leveraging a provider’s historical payments data, micro-segmenting patient accounts and determining the most appropriate workflows. Plus, machine learning drives continuous improvement. When true machine learning is in place, segmentation gets better and better over time and results are transparent — providers can easily see the impact of their workflows and measure the ROI of their efforts.
3. Build an ROI-Based Outreach Strategy
Patient account segmentation is intelligence. Building optimized workflows that best serve each segment turns this intelligence into action. The most effective segmentation efforts take into account the best treatment approach for each segment and automatically match segments to corresponding workflows. ROI-optimized workflows should cover patient outreach: method (text, call, statement), timing and frequency; as well as payment plan provisioning (the best fit amount and duration). Putting these pieces together improves patient engagement, account resolution and resource management.
Scores, segments and any sort of data-driven outreach strategy won’t work unless they’re fully integrated into your patient engagement platform. In terms of both dollars and time, it is too expensive for most providers to add a new screen, new software and require more employee training. Dynamically feeding scores or segment assignments into your existing platform makes it feasible, and easy, for your team to adjust and shift to a strategy that prioritizes work efforts based on ROI.
It’s important to understand how each patient account segment performs, the effectiveness of work strategies and to track progress. Reporting that allows you to see a holistic picture of performance as well as drill into details enables you to measure ROI, find new opportunities, respond to trends and consistently improve. Any scoring system or workflow optimization too should include robust reporting around KPIs and operational metrics.
As patients continue to bear more financial responsibility for their healthcare costs, it will become increasingly important to ensure your approach to self-pay collections is set up to proactively meet the needs of your patients. Sift’s machine learning driven segmentation and integrated intelligence equip healthcare providers to optimize workflows, be more strategic in their billing approach, prevent premature outsourcing and make better use of employee time and talent — all of which work to reduce the cost to collect. Learn more about Sift’s approach to patient payments.