Estimation of a Preference-Based Summary Score for the Patient-Reported Outcomes Measurement Information System: The PROMIS®-Preference (PROPr) Scoring System

Abstract

Background: Health-related quality of life (HRQL) preference-based scores are used to assess the health of populations and patients and for cost-effectiveness analyses. The National Institutes of Health Patient-Reported Outcomes Measurement Information System (PROMIS^®) consists of patient-reported outcome measures developed using item response theory. PROMIS is in need of a direct preference-based scoring system for assigning values to health states.

Objective: To produce societal preference-based scores for 7 PROMIS domains: Cognitive Function-Abilities, Depression, Fatigue, Pain Interference, Physical Function, Sleep Disturbance, and Ability to Participate in Social Roles and Activities.

Setting: Online survey of a US nationally representative sample ( n = 983).

Methods: Preferences for PROMIS health states were elicited with the standard gamble to obtain both single-attribute scoring functions for each of the 7 PROMIS domains and a multiplicative multiattribute utility (scoring) function.

Results: The 7 single-attribute scoring functions were fit using isotonic regression with linear interpolation. The multiplicative multiattribute summary function estimates utilities for PROMIS multiattribute health states on a scale where 0 is the utility of being dead and 1 the utility of "full health." The lowest possible score is -0.022 (for a state viewed as worse than dead), and the highest possible score is 1.

Limitations: The online survey systematically excludes some subgroups, such as the visually impaired and illiterate.

Conclusions: A generic societal preference-based scoring system is now available for all studies using these 7 PROMIS health domains.

Keywords: PROMIS; US general population; health utility; health-related quality of life.

Figure 1:

The PROPr scoring system conceptual model. In A), a measurement on one of the 7 PROMIS domains used in PROPr, denoted θ, is the input to its single-attribute scoring function u_domain. In B), the output of u_domain (θ) is a score on the scale where 0 is the utility of that domain’s disutility corner state and 1 is the utility of full health. If we have all 7 PROMIS measurements, then we can take the outputs from the 7 single-attribute scoring functions (C) and use them as inputs to the multiplicative multi-attribute scoring function (D). The multi-attribute function produces a summary score, u(Θ), for the entire vector Θ of 7 PROMIS measurements, on the scale where 0 is the utility of dead and 1 is the utility of full health (E).

Figure 2

Health-state descriptions in the PROPr survey. Health-state descriptions were given as a table like the one above, with one answer selected for each item (row). For example, the health state describing the highest functional capacity on each domain (called full health) would have the rightmost column selected for all items. The health state describing the lowest functional capacity on each domain (called the all-worst state) would have the leftmost column selected for all items.

Figure 3:

The Visual Analogue Scale. An example valuation, using the Visual Analogue Scale (VAS).

Figure 4:

The Standard Gamble. An example step in an SG valuation. Choice A shows some gamble between the best and worst health states in the given domain - in this case, pain. Choice B shows the sure-thing of some intermediate health state.

Figure 5:

Example valuations. An example, using the cognition domain, of the data produced by the preference elicitations, in utility terms. (The associated disutility scale is produced by taking 1-utility.) In A), the participant evaluates intermediate states of cognition on a scale from the unhealthiest level of cognition (the cognition disutility corner state) to full health. In B), a participant who prefers the state of dead to the all-worst state values dead and the cognition disutility corner state on a scale from the all-worst to full health; panel C) shows the output of someone who prefers the all-worst state to dead. Panel A) corresponds to set (i) in the main text, and panels B) and C) to set (ii).

Figure 6:

Single-attribute disutility functions. Isotonic regression with linear interpolation modeling the conditional mean disutility for each level of theta corresponding to Table 1.