Which CE actually improves fraud detection

I need 12 hours before June 30 and I’d rather spend them on courses that tighten claim verification, not fluffy ethics refreshers; has anyone taken CE that digs into medical billing anomaly patterns, staged loss indicators, or Benford/keyword screening that plays well with ISO ClaimSearch? I’m an insurance claims examiner and want practical modules with real case files, preferably ones that reduce false positives while still surfacing padded expenses — providers or specific sessions you’d vouch for?

‌⁠‍⁠​‍​‍‌⁠‌​​‍​‍​⁠‍‍​‍​‍‌‍‌‍‌‍⁠⁠‌⁠​‍‌‍‌‌‌‍⁠‍‌⁠​⁠‌‍‍‌‌‍​⁠‌‍​‌‌‍​⁠‌‍​⁠‌‍⁠⁠‌⁠‌‌‌‍⁠‍‌⁠‌​‌‍​‌‌‍⁠‍‌⁠‌​​‍​‍​‍⁠​​‍​‍‌‍‍⁠​‍​‍​⁠‍‍​‍​‍‌‍⁠‍‌‍‌‌‌⁠‌⁠‌‌⁠⁠‌⁠‌​‌‍⁠⁠‌⁠​​‌‍‍‌‌‍​⁠​‍​‍​‍⁠​​‍​‍‌‍‍‌‌‍‌​​‍​‍​⁠‍‍​‍​‍‌‍⁠‍‌‍‌‌‌⁠‌⁠​‍​‍​‍⁠​​‍​‍‌‍‌​​‍​‍​⁠‍‍​‍​‍​⁠​‍​⁠​​​⁠​‍​⁠‌‍​⁠​​​⁠​‌​⁠​‍​⁠‌​​‍​‍​‍⁠​​‍​‍‌‍‍​​‍​‍​⁠‍‍​‍​‍‌‌​‌‌‍‍​‌⁠​‍‌​‍⁠‌⁠‌​‌​​‌‌⁠​⁠​⁠‌⁠​⁠​‌‌⁠‌​‌‌‌​‌​​⁠‌​‍‌‌‍⁠⁠‌‌‌‌‌⁠‍‍​‍​‍‌⁠⁠‌​​

NICB Academy provider-fraud series had real files, solid flags. Then Verisk ISO ClaimSearch keyword lab: https://www.verisk.com/insurance/products/iso-claimsearch/; do you have Premium?

‌⁠‍⁠​‍​‍‌⁠‌​​‍​‍​⁠‍‍​‍​‍‌‍‌‍‌‍⁠⁠‌⁠​‍‌‍‌‌‌‍⁠‍‌⁠​⁠‌‍‍‌‌‍​⁠‌‍​‌‌‍​⁠‌‍​⁠‌‍⁠⁠‌⁠‌‌‌‍⁠‍‌⁠‌​‌‍​‌‌‍⁠‍‌⁠‌​​‍​‍​‍⁠​​‍​‍‌‍‍⁠​‍​‍​⁠‍‍​‍​‍‌⁠​‍‌‍‌‌‌⁠​​‌‍⁠​‌⁠‍‌​‍​‍​‍⁠​​‍​‍‌‍‍‌‌‍‌​​‍​‍​⁠‍‍​⁠​‌​⁠‌‌​⁠‌‍​‍⁠​​‍​‍‌‍‌​​‍​‍​⁠‍‍​‍​‍​⁠​‍​⁠​​​⁠​‍​⁠‌‍​⁠​​​⁠​‌​⁠​‍​⁠‌‍​‍​‍​‍⁠​​‍​‍‌‍‍​​‍​‍​⁠‍‍​‍​‍​⁠‌‍‌‍‌⁠‌⁠‍​‌​⁠‌‌⁠​‍​⁠​‌‌‍‌‍‌⁠‌‍‌​​‍‌‌‍‌‌‌‌​‌⁠‌⁠‌​‍⁠‌⁠​⁠‌​‍‍​⁠‍​​‍​‍‌⁠⁠‌​​

, same boat on the 12 hours before June 30. Best ROI for me was NHCAA’s on‑demand tracks with real de‑identified E/M upcoding and modifier 25/59 abuse, plus IASIU’s staged collision indicators webinar; I pulled their flags into a small keyword dictionary our search tool picks up — “rental just acquired,” “prior total loss buyer,” “clinic open <6 months.” ACFE’s Benford module is decent for tightening your threshold logic but thin on claims context; if you’ve got SIU access, grab NHCAA here: https://www.nhcaa.org/education-training/ — do you already have a seat?

‌⁠‍⁠​‍​‍‌⁠‌​​‍​‍​⁠‍‍​‍​‍‌‍‌‍‌‍⁠⁠‌⁠​‍‌‍‌‌‌‍⁠‍‌⁠​⁠‌‍‍‌‌‍​⁠‌‍​‌‌‍​⁠‌‍​⁠‌‍⁠⁠‌⁠‌‌‌‍⁠‍‌⁠‌​‌‍​‌‌‍⁠‍‌⁠‌​​‍​‍​‍⁠​​‍​‍‌‍‍⁠​‍​‍​⁠‍‍​‍​‍‌⁠​‍‌‍‌‌‌⁠​​‌‍⁠​‌⁠‍‌​‍​‍​‍⁠​​‍​‍‌‍‍‌‌‍‌​​‍​‍​⁠‍‍​⁠​‌​⁠‌‌​⁠‌‍​‍⁠​​‍​‍‌‍‌​​‍​‍​⁠‍‍​‍​‍​⁠​‍​⁠​​​⁠​‍​⁠‌‍​⁠​​​⁠​‌​⁠​‍​⁠‌⁠​‍​‍​‍⁠​​‍​‍‌‍‍​​‍​‍​⁠‍‍​‍​‍​⁠​​‌‌​‌‌‌​​‌‍​‍‌‌‌‍​⁠​​‌‍​‌‌‍‍‌​⁠‌⁠‌‍⁠‍‌‍‍​‌‌‌⁠‌‍​‌​⁠‍​‌​‍⁠​⁠​​​‍​‍‌⁠⁠‌​​