Improving Musculoskeletal Care Quality With a Web-Based Clinical Decision Support System in UK Primary Care: Mixed Methods Cluster-Randomized Controlled Trial.
Jonathan Hill, Hollie Birkinshaw, Muhammed Usman et al.
✦ AI-curated · Sources linked
In 30 seconds
This mixed methods, cluster-randomized controlled trial evaluated CrossCover, a web-based clinical decision support system for adult musculoskeletal consultations in UK general practice. Nineteen practices were randomized, and the intervention was available for 3 months. Among 10,182 eligible patients, clinicians used the system in 365 cases (8.6%). In per-protocol review, suboptimal care was recorded in 3% (2/60) of CDSS-guided consultations versus 25% (15/60) of control consultations (adjusted odds ratio 12.30, 95% CI 2.52-59.9; P =.002). Intention-to-treat analysis found increased self-management alone; overall engagement was limited.
Key findings
- The CDSS was used in 365 patient cases, representing 8.6% of eligible intervention cases.
- Per-protocol review found suboptimal care in 3% (2/60) of CDSS-guided consultations vs 25% (15/60) of control consultations (adjusted odds ratio 12.30, 95% CI 2.52-59.9; P =.002).
- Intention-to-treat analysis showed increased self-management alone; per-protocol analysis also found more self-management advice and community referrals, and less prescribing and fit-note use.
- Safety concerns were logged in 6.6% (24/365) of uses, with no high-risk issues identified.
Why it matters
The findings suggest that a digital decision support tool may improve the quality of musculoskeletal management when clinicians use it, while also influencing advice, referrals, and prescribing. However, low uptake limits the likely population-level effect. The reported implementation challenges highlight that clinical content alone may not be sufficient; integration with practice workflows is relevant to realizing potential benefits.
What to keep in mind
CDSS uptake was limited, and the favorable suboptimal-care result came from per-protocol analysis. Clinicians were not blinded, and the primary outcome was assessed in 120 records.