Quick Disability Determinations speed up likely disability claims

SSA's Inspector General found that 537 of 575 sampled claims picked by the QDD model, about 93%, were allowed and that decisions took 18 days on average.

  • 1 a person

    Claimants in the sample got medical determinations in 18 days on average, and those allowed got them in 15 days on average.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent audit report supports the benefit.

Compared with

SSA's recommended timeframe for QDD claims. Measured.

Without the system
20 days or fewer
With it
18 days on average for all sampled claims and 15 days for allowed claims
The system’s part
Not isolated. The audit measured outcomes only for claims that the model picked and compared none decided without it. In its 2009 report the Inspector General calls it a predictive model, and SSA later described it as a statistical modeling program that generates a score. Neither the Inspector General nor SSA says whether the model learned from data.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
Quick Disability Determination (QDD) predictive model
Made by
IBM, which originally designed the model according to SSA, with later changes by the Social Security Administration
Used by
Social Security Administration with state Disability Determination Services
Where
United States (national)
Stage
Expanding
Date
Kind
Aggregate result
Broad benefit
Analyzing Data or Information, Organizing, Planning, and Prioritizing Work
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Audit report, by authors with no tie to the system.

    Social Security Administration, Office of the Inspector General. National Rollout of Quick Disability Determinations. Audit report A-01-09-19030, 13 May 2009 (archived copy of the report at oig-files.ssa.gov).

    Since the national rollout, QDD is working as intended. We found that SSA allowed 93 percent of claims selected for QDD and generally made medical determinations for these claims within the recommended timeframe of 20 days or fewer.

  2. Other, by the organization that used it. Context or contrary evidence.

    Social Security Administration. Description of the predictive model, reproduced as Appendix E of the Office of the Inspector General's audit report Compassionate Allowance Initiative (A-01-10-21080), 6 August 2010 (archived copy).

    The PM software was originally designed by International Business Machines Corporation for the QDD process. It is a statistical modeling program that generates a score to identify initial cases that have a high degree of probability that the claimant is disabled

Details

AI system

Workflow

A predictive model scored the information that claimants gave on their disability applications. State Disability Determination Services handled flagged claims on a recommended timeframe of 20 days or less. SSA field offices completed the non-medical work on flagged claims as quickly as possible.

Follow-up

Conditions for replication

Medical evidence for flagged claimants must be easy and quick to obtain. The model must pick claims with a high potential that the claimant is disabled.

Entry details

Sector

Social security (disability benefits).

Purpose

IBM built the QDD predictive model for the Social Security Administration to pick out initial disability claims that are likely to be allowed and can be decided quickly.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Quick Disability Determinations speed up likely disability claims (AIBD-0673). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0673.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions