Background Paracetamol (acetaminophen) is vastly recommended as the first-line analgesic for osteoarthritis of the hip or knee. However, there has been controversy about this recommendation given recent studies have revealed small effects of paracetamol when compared with placebo. Nonetheless, past studies have not systematically reviewed and appraised the literature to investigate the effects of this drug on specific osteoarthritis sites, that is, hip or knee, or on the dose used. Objectives To assess the benefits and harms of paracetamol compared with placebo in the treatment of osteoarthritis of the hip or knee. Search methods We searched the Cochrane Central Register of Controlled Trials, MEDLINE, Embase, AMED, CINAHL, Web of Science, LILACS, and International Pharmaceutical Abstracts to 3 October 2017, and ClinicalTrials.gov and the World Health Organization International Clinical Trials Registry Platform (ICTRP) portal on 20 October 2017. Selection criteria We included randomised controlled trials comparing paracetamol with placebo in adults with osteoarthritis of the hip or knee. Major outcomes were pain, function, quality of life, adverse events and withdrawals due to adverse events, serious adverse events, and abnormal liver function tests. Data collection and analysis Two review authors used standard Cochrane methods to collect data, and assess risk of bias and quality of the evidence. For pooling purposes, we converted pain and physical function (Western Ontario and McMaster Universities Osteoarthritis Index function) scores to a common 0 (no pain or disability) to 100 (worst possible pain or disability) scale. Main results We identified 10 randomised placebo-controlled trials involving 3541 participants with hip or knee osteoarthritis. The paracetamol dose varied from 1.95 g/day to 4 g/day, and the majority of trials followed participants for three months only. Most trials did not clearly report randomisation and concealment methods and were at unclear risk of selection bias. Trials were at low risk of performance, detection, and reporting bias. At 3 weeks' to 3 months' follow-up, there was high-quality evidence that paracetamol provided no clinically important improvements in pain and physical function. Mean reduction in pain was 23 points (0 to 100 scale, lower scores indicated less pain) with placebo and 3.23 points better (5.43 better to 1.02 better) with paracetamol, an absolute reduction of 3%(1% better to 5% better, minimal clinical important difference 9%) and relative reduction of 5% (2% better to 8% better) (seven trials, 2355 participants). Physical function improved by 12 points on a 0 to 100 scale (lower scores indicated better function) with placebo and was 2.9 points better (0.95 better to 4.89 better) with paracetamol, an absolute improvement of 3%(1% better to 5% better, minimal clinical important difference 10%) and relative improvement of 5% (2% better to 9% better) (7 trials, 2354 participants). High-quality evidence from eight trials indicated that the incidence of adverse events was similar between groups: 515/1586 (325 per 1000) in the placebo group versus 537/1666 (328 per 1000, range 299 to 360) in the paracetamol group (risk ratio (RR) 1.01, 95% confidence interval (CI) 0.92 to 1.11). There was less certainty (moderate-quality evidence) around the risk of serious adverse events, withdrawals due to adverse events, and the rate of abnormal liver function tests, due to wide CIs or small event rates, indicating imprecision. Seventeen of 1480 (11 per 1000) people treated with placebo and 28/1729 (16 per 1000, range 8 to 29) people treated with paracetamol experienced serious adverse events (RR 1.36, 95% CI 0.73 to 2.53; 6 trials). The incidence of withdrawals due to adverse events was 65/1000 participants in with placebo and 77/1000 (range 59 to 100) participants with paracetamol (RR 1.19, 95% CI 0.91 to 1.55; 7 trials). Abnormal liver function occurred in 18/1000 participants treated with placebo and 70/1000 participants treated with paracetamol (RR 3.79, 95% CI 1.94 to 7.39), but the clinical importance of this effect was uncertain. None of the trials reported quality of life. Subgroup analyses indicated that the effects of paracetamol on pain and function did not differ according to the dose of paracetamol (3.0 g/day or less versus 3.9 g/day or greater). Authors' conclusions Based on high-quality evidence this review confirms that paracetamol provides only minimal improvements in pain and function for people with hip or knee osteoarthritis, with no increased risk of adverse events overall. Subgroup analysis indicates that the effects on pain and function do not differ according to the dose of paracetamol. Due to the small number of events, we are less certain if paracetamol use increases the risk of serious adverse events, withdrawals due to adverse events, and rate of abnormal liver function tests. Current clinical guidelines consistently recommend paracetamol as the first-line analgesic medication for hip or knee osteoarthritis, given its low absolute frequency of substantive harm. However, our results call for reconsideration of these recommendations.
