Variation in antibiotic prescribing and its impact on recovery in patients with acute cough in primary care: prospective study in 13 countries

Abstract

Objective: To describe variation in antibiotic prescribing for acute cough in contrasting European settings and the impact on recovery.

Design: Cross sectional observational study with clinicians from 14 primary care research networks in 13 European countries who recorded symptoms on presentation and management. Patients followed up for 28 days with patient diaries.

Setting: Primary care.

Participants: Adults with a new or worsening cough or clinical presentation suggestive of lower respiratory tract infection.

Main outcome measures: Prescribing of antibiotics by clinicians and total symptom severity scores over time.

Results: 3402 patients were recruited (clinicians completed a case report form for 99% (3368) of participants and 80% (2714) returned a symptom diary). Mean symptom severity scores at presentation ranged from 19 (scale range 0 to 100) in networks based in Spain and Italy to 38 in the network based in Sweden. Antibiotic prescribing by networks ranged from 20% to nearly 90% (53% overall), with wide variation in classes of antibiotics prescribed. Amoxicillin was overall the most common antibiotic prescribed, but this ranged from 3% of antibiotics prescribed in the Norwegian network to 83% in the English network. While fluoroquinolones were not prescribed at all in three networks, they were prescribed for 18% in the Milan network. After adjustment for clinical presentation and demographics, considerable differences remained in antibiotic prescribing, ranging from Norway (odds ratio 0.18, 95% confidence interval 0.11 to 0.30) to Slovakia (11.2, 6.20 to 20.27) compared with the overall mean (proportion prescribed: 0.53). The rate of recovery was similar for patients who were and were not prescribed antibiotics (coefficient -0.01, P<0.01) once clinical presentation was taken into account.

Conclusions: Variation in clinical presentation does not explain the considerable variation in antibiotic prescribing for acute cough in Europe. Variation in antibiotic prescribing is not associated with clinically important differences in recovery.

Trial registration: Clinicaltrials.gov NCT00353951.

Fig 1 Patient flow chart

Fig 2 Choice of antibiotic by network

Fig 3 Unadjusted and adjusted odds ratios for antibiotic prescribing by network (both adjusted for clustering within clinician). All networks are compared with overall mean

Fig 4 Unadjusted median symptom severity scores over time by network

Fig 5 Predicted recovery curves by network for those prescribed antibiotics from ARMA model