Tuberculosis sanatorium treatment at the advent of the chemotherapy era

Abstract

Background: The discovery of antibiotics in the mid-twentieth century marked a major transition in tuberculosis (TB) treatment and control. There are few studies describing the duration of TB disease and its treatment from the pre-chemotherapy era and little data on how these treatments changed in response to the development of effective antibiotics. The goal of this research is to understand how inpatient treatment for high incidence populations, the First Nations peoples of Saskatchewan, Canada, changed in response to increasing availability of antibiotics effective against TB. We expected that as treatment regimens transitioned from convalescence-only to triple antibiotic therapy, the length of inpatient treatment would shorten.

Methods: Analyses were performed on records of sanatoria admissions and discharges occurring between 1933 and 1959 in Saskatchewan, Canada. Year of antibiotic discovery was taken as a proxy for treatment regimen: no chemotherapy (pre-1944), mono-therapy (Streptomycin, 1944-1946), dual-therapy (Streptomycin and PAS, 1946-1952), and triple-therapy (Streptomycin, PAS, and INH 1952-). A pooled linear regression of log-transformed length of first admission as predicted by year of admission was modeled to assess the relationship between admission length and year of admission, corrected for clinical and demographic variables.

Results: First admission length increased 19% in the triple-therapy era as compared to the pre-chemotherapy era, from 316 days (10.4 months) to 377 days (12.4 months). After the discovery of INH (1952), we find statistically significant increases in the proportion of successfully completed therapies (0.55 versus 0.60, p = 0.035), but also in patients who left hospital against medical advice (0.19 versus 0.29, p < 0.0001), indicating that as hospitalizations lengthened, more patients chose to discharge without the sanction of their physician. The readmission rate increased from 10 to 50% of all admissions while the province-level TB-specific death rate fell from 63.1 per 10,000 in 1933 to 4.7 per 10,000 in 1958.

Conclusion: Counterintuitively, we find that the length of first admissions increased with the discovery of TB-treating antibiotics. Increasing admission volume and readmission rate indicate an intensification of inpatient TB treatment during this era. These analyses provide a novel estimate of the effect of changing treatment policy on sanatorium admissions in this population.

Keywords: Length of treatment; Sanatorium; Tuberculosis; Tuberculosis treatment.

Fig. 1

(L) Age distribution (n = 784, 70 (8.2%) observations missing) in 2-year bins. (R) Admission length in days in 60-day bins. Year cutoffs denoted by dashed lines

Fig. 2

Median admission length (circles) with inter-quartile range (bars) over time. Circle size reflects total annual first admissions and horizontal lines represent year cutoffs. No first admissions were recorded in 1936

Fig. 3

Median admission length by sex and age on admission

Fig. 4

Results from one imputed dataset showing length of admission plotted over time with mean admission length over time as predicted by admission year smoothed with natural cubic splines

Fig. 5

Distribution of admissions (n = 2040) (top) and discharges (n = 1966) (bottom) by type over study period

Fig. 6

Proportion of readmissions increase as new treatments are implemented

Fig. 7

Province-level tuberculosis-specific death rate for First Nations and total population of Saskatchewan from 1926 to 1960