Food anaphylaxis in the United Kingdom: analysis of national data, 1998-2018

Abstract

Objective: To describe time trends for hospital admissions due to food anaphylaxis in the United Kingdom over the past 20 years.

Design: Analysis of national data, 1998-2018.

Setting: Data relating to hospital admissions for anaphylaxis and deaths, and prescription data for adrenaline autoinjector devices.

Participants: UK population as a whole and devolved nations (England, Scotland, Wales, and Northern Ireland).

Main outcome measures: Time trends, age, and sex distributions for hospital admissions for anaphylaxis due to food and non-food triggers, and how these admission rates compare with the case fatality rate (number of fatalities as a proportion of hospital admissions).

Results: Between 1998 and 2018, 101 891 people were admitted to hospital for anaphylaxis. Of these admissions, 30 700 (30.1%) were coded as due to a food trigger. Food anaphylaxis admissions increased from 1.23 to 4.04 per 100 000 population per year (from 1998 to 2018), an annual increase of 5.7% (95% confidence interval 5.5% to 5.9%, P<0.001). The largest increase in hospital admissions was observed in children younger than 15 years, with an increase from 2.1 to 9.2 admissions per 100 000 population per year (an annual increase of 6.6%, 95% confidence interval 6.3% to 7.0%). For comparison, the annual increase was 5.9% (5.6% to 6.2%) in people aged 15-59 years and 2.1% (1.8% to 3.1%) in those aged 60 years and older. 152 deaths were identified where the fatal event was probably caused by food induced anaphylaxis. The case fatality rate decreased from 0.7% to 0.19% for confirmed fatal food anaphylaxis (rate ratio 0.931, 95% confidence interval 0.904 to 0.959, P<0.001) and to 0.30% for suspected fatal food anaphylaxis (0.970, 0.945 to 0.996, P=0.024). At least 46% (86 of 187, which also includes 35 deaths in 1992-98) of deaths were triggered by peanut or tree nut. Cow's milk was responsible for 17 of 66 (26%) deaths in school aged children. Over the same time period, prescriptions for adrenaline autoinjectors increased by 336% (estimated rate ratio 1.113, 95% confidence interval 1.112 to 1.113; an increase of 11% per year).

Conclusions: Hospital admissions for food induced anaphylaxis have increased from 1998 to 2018, however the case fatality rate has decreased. In school aged children, cow's milk is now the most common single cause of fatal anaphylaxis.

Fig 1

Time trends in hospital admissions per 100 000 population from 1998 to 2018 by age. From upper panel downwards: admissions due to “allergy”; all cause anaphylaxis; non-food anaphylaxis; and food induced anaphylaxis. Vertical bars represent standard error of the mean

Fig 2

Impact of sex on hospital admissions for anaphylaxis due to non-food and food triggers. A national four hour target for accident and emergency visits was introduced in 2004. NICE (National Institute for Health and Care Excellence) guidance recommending overnight admission for paediatric anaphylaxis was introduced in 2011. Vertical bars represent standard error of the mean

Fig 3

Sex differences by age for hospital admissions for anaphylaxis due to drug, unspecified, and food triggers. Vertical bars represent standard error of the mean

Fig 4

Upper panel: deaths due to food induced anaphylaxis per 100 000 population, 1998-2018. Lower panel: case fatality rate for food induced anaphylaxis (with line fitted using linear regression), 1998-2018. Vertical bars represent standard error of the mean

Fig 5

Upper panel: hospital admissions and deaths due to food induced anaphylaxis by age group per 100 000 population, 1998-2018. Lower panel: case fatality rate for food induced anaphylaxis by age group, 1998-2018. Vertical bars represent standard error of the mean

Fig 6

Cause of fatal food induced anaphylaxis by trigger in children (younger than 16) and adults, 1992-2018

Fig 7

Changes in the relative proportions of fatal food induced anaphylaxis by specific foods, 1992-2018

Fig 8

Prescription of adrenaline autoinjectors to UK residents from 1998 to 2018, overall and by devolved nation. Data refer to number of prescriptions issued (rather than number of devices)