Quality of life during a randomized trial of a therapeutic-workplace intervention for opioid use disorder: Web-based mobile assessments reveal effects of drug abstinence and access to paid work

Abstract

Background: Employment and improved quality of life (QOL) are, separately, valued outcomes of substance use disorder (SUD) treatment. It is also important to understand QOL changes caused by employment itself; therefore, we assessed QOL during a randomized trial of a contingency-management-based Therapeutic Workplace for people with opioid use disorder.

Methods: For 12 weeks, participants (n = 61) responded to QOL questionnaires in a mobile web app accessed with study-issued smartphones. At enrollment, participants were randomized to work in the Therapeutic Workplace immediately (immediate work group, IWG) or after a 3-week waitlist delay (delayed work group, DWG). Once both groups could work, wage-resetting contingencies were introduced for their opiate- and cocaine-urinalysis. Data were analyzed by (1) access to work with and without contingencies and (2) overall urinalysis-verified opiate- and cocaine-abstinence.

Results: DWG and/or IWG reported improvements in several QOL areas (sleep, transportation, recreation); however, they also reported increased money-related difficulties and less time spent with friends/family. These changes did not coincide with DWG's work access, but some (more sleep, money-related difficulties) coincided with the urinalysis contingencies. Greater opiate- and/or cocaine-abstinence was also associated with several improvements: sleep, paying bills, time spent with friends/family, and exercising. Surprisingly, intermediate cocaine abstinence was associated with reductions in work-capacity satisfaction and recreation.

Conclusions: Participants reported complex QOL differences during their experimental employment and associated with drug abstinence. Future work should help participants address issues that may be relevant to employment generally (e.g., time with friends/family) or contingency management specifically (e.g., money-related issues for non-abstinent participants).

Keywords: Cocaine; Contingency management; Opioid use disorder; Quality of life; Smartphone; Urinalysis.

Fig. 1

Participants’ responses to “Physical and emotional health” quality of life topics between the Immediate vs. Delayed Work Groups and across Therapeutic Workplace phases defined by participants’ access to paid work and the presence of abstinence-reinforcement contingencies. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, difference between groups within phase; b, different from Waitlist for Immediate Work Group. Opi, opiate urinalysis contingency; Opi+Coc, opiate and cocaine urinalysis contingencies.

Fig. 2

Participants’ responses to “Money” and “Transportation” quality of life topics between the Immediate vs. Delayed Work Groups and across Therapeutic Workplace phases defined by participants’ access to paid work and the presence of abstinence-reinforcement contingencies. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Individual modes of transportation other than walking and Maryland Transit Administration (MTA) public transit are not presented because they were used infrequently, and the statistical models did not converge. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, difference between groups within phase; b, different from Waitlist for Immediate Work Group; c, different from Induction for Immediate Work Group; d, different from Opi for Immediate Work Group; e, different from Waitlist for Delayed Work Group; f, different from Induction for Delayed Work Group; g, different from Opi for Delayed Work Group. Opi, opiate urinalysis contingency; Opi+Coc, opiate and cocaine urinalysis contingencies.

Fig. 3

Participants’ responses to “Friends and family” and “Recreation” quality of life topics between the Immediate vs. Delayed Work Groups and across Therapeutic Workplace phases defined by participants’ access to paid work and the presence of abstinence-reinforcement contingencies. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, difference between groups within phase; b, different from Waitlist for Immediate Work Group; c, different from Waitlist for Delayed Work Group; d, different from Induction for Delayed Work Group. Opi, opiate urinalysis contingency; Opi+Coc, opiate and cocaine urinalysis contingencies.

Fig. 4

Responses to “Physical and emotional health” quality of life topics among participants with different overall amounts of urinalysis-verified drug abstinence: Low, Intermediate (Mid), or High. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, different from Low for opiate abstinence; b, different from Low for cocaine abstinence; c, different from Mid for cocaine abstinence.

Fig. 5

Responses to “Money” and “Transportation” quality of life topics among participants with different overall amounts of urinalysis-verified drug abstinence: Low, Intermediate (Mid), or High. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Individual modes of transportation other than walking and Maryland Transit Administration (MTA) public transit are not presented because they were used infrequently, and the statistical models did not converge. For transportation by walking (panel g), only opiate abstinence is presented because the statistical model for cocaine abstinence did not converge. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, different from Low for cocaine abstinence.

Fig. 6

Responses to “Friends and family” and “Recreation” quality of life topics among participants with different overall amounts of urinalysis-verified drug abstinence: Low, Intermediate (Mid), or High. All data are presented as the least-squares means (± 1 standard error) from the multivariate model constructed for each endpoint. Within each panel, letters indicate statistically significant (p < .05) post-hoc pairwise differences: a, difference from Low for cocaine abstinence; b, different from Mid for cocaine abstinence.

Fig. 7

Arrangement of all quality of life items in two dimensions by nonmetric multidimensional scaling. a) responses of Immediate Work Group, b) responses of Delayed Work Group. Distances were determined as 1 minus the Spearman rank correlation coefficient for each pair of items: items with stronger correlations are closer to one another in space. The triangular points represent the Therapeutic Workplace phases. The color of each item indicates whether its correlational distance is closer to the Induction phase (dark red) or closer to the Opi+Coc phase (dark gray), and the shading is darker as a function of how closely the item is associated with the phase. The axis labels (x-axis as “Needs” and y-axis as “Activities”) represent our interpretation of the two dimensions made from inspection of the arrangement of the items.