February 17, 2026
ROI
Predict drives 5x ROI with proactive AI detection of high-risk members
Many care programs show ROI in aggregate, but fail to engage the members most likely to drive near-term MSK costs.
Musculoskeletal care is one of the largest healthcare expenses for employers and health plans alike.¹ ² A significant share of that spend is driven by avoidable escalation into costly imaging, injections, and surgery.³ ⁴ Sword Health’s AI-powered solution, Predict, identifies members at elevated risk of near-term high-cost MSK events and prioritizes them for early, conservative care. The result is measurable savings, better outcomes, and a more disciplined approach to MSK cost control.
Validated through a matched control study, this whitepaper reveals how Sword Predict reduces low-value MSK care and delivers a claims-validated 5x return on investment.
$4,279
Additional savings per member per year with Predict
5x
Claims-validated return on investment, independently reviewed by Milliman
What this whitepaper helps you evaluate
Learn how AI-driven early risk identification can reduce avoidable MSK surgeries and deliver defensible, near-term ROI. By using Predict's proactive engagement to help high-risk members recover faster, health plans and employers can expect sustained savings without increasing clinical, financial, or operational risk.
If you are under pressure to generate measurable MSK savings within plan-year, this analysis provides the validated evidence you need to confidently invest in Sword Predict for your member population.
Key learnings inside the whitepaper
- Why reduced surgical utilization is the primary driver of MSK savings³
- How changes in downstream utilization contribute to predictable, within plan-year ROI⁵
- What member engagement and adherence data indicate about durability of results⁵
- How to interpret matched-control study findings through a financial and actuarial lens
- Why targeted engagement of high-risk members unlocks greater savings than broad, undifferentiated MSK programs⁵
Contributors to White Paper
Sword Team
Experts in pain, movement, and digital health
Footnotes
Dieleman JL, Cao J, Chapin A, et al. US health care spending by condition and county, 1996–2016. JAMA. 2020;323(9):863–884. doi:10.1001/jama.2020.0734https://jamanetwork.com/journals/jama/fullarticle/2762309
United States Bone and Joint Initiative. The Burden of Musculoskeletal Diseases in the United States (BMUS), 4th ed. 2020.https://www.boneandjointburden.org
Katz JN, Brownlee SA, Jones MH. The role of arthroscopy in the management of knee osteoarthritis. N Engl J Med. 2013;368:1675–1684. doi:10.1056/NEJMra1301408https://www.nejm.org/doi/full/10.1056/NEJMra1301408
Chou R, Deyo R, Friedly J, et al. Noninvasive treatments for low back pain. Ann Intern Med. 2017;166(7):493–505. doi:10.7326/M16-2459https://www.acpjournals.org/doi/10.7326/M16-2459
Fritz JM, Childs JD, Wainner RS, Flynn TW. Primary care referral of patients with low back pain to physical therapy: impact on future health care utilization and costs. Spine. 2012;37(25):2114–2121. doi:10.1097/BRS.0b013e31825d32f5https://journals.lww.com/spinejournal/Fulltext/2012/12010/Primary_Care_Referral_of_Patients_With_Low_Back.8.aspx