USA-007

Social Security Administration (SSA) – Quick Disability Determinations (QDD) Predictive Model

Download PDF
United States North America High income Scaled & Institutionalised Confirmed

U.S. Social Security Administration (SSA) – Office of Retirement and Disability Programs; State Disability Determination Services (DDS)

At a Glance

What it does Prediction (including forecasting) — Decision support for eligibility and benefits
Who runs it U.S. Social Security Administration (SSA) – Office of Retirement and Disability Programs; State Disability Determination Services (DDS)
Programme Social Security Administration (SSA) – Quick Disability Determinations (QDD) Predictive Model
Confidence Confirmed
Deployment Status Scaled & Institutionalised
Key Risks Not assessed
Key Outcomes Official SSA materials and secondary reporting indicate that QDD is used nationally to expedite a subset of likely-favourable disability claims and that these cases are processed materially faster than standard disability claims.
Source Quality 4 sources — News article / media, Working paper / technical note, Government website / press release

The United States Social Security Administration (SSA) operates a system known as Quick Disability Determinations (QDD), which uses a computer-based predictive model to expedite the processing of some disability claims within the Social Security Disability Insurance (SSDI) programme. The QDD process screens initial disability applications to identify cases where a favourable disability determination appears highly likely and where medical evidence is readily available. When a claimant completes a disability application, SSA creates an electronic file containing their information and medical history. The QDD predictive model then scans the file for keywords and phrases that indicate the claimant is likely to be found disabled, including medical conditions that might meet one of SSA's published medical listings. If the programme identifies these keywords, it checks to ensure the application has all the necessary documentation before flagging the case for expedited processing.

QDD is one of SSA's longstanding fast-track disability processes, alongside Compassionate Allowances, which together represent what SSA describes as two of its greatest successes in recent years, allowing the agency to approve some cases in a matter of days instead of months. Official SSA materials describe QDD as a predictive screening tool that has been used nationally since February 2008 and is continually refined to reflect the characteristics of the recent applicant population. SSA is described as having actively employed artificial intelligence for over 20 years, with 14 current AI use cases as of 2024, making QDD part of a broader institutional commitment to data-driven decision support.

The retained sources support the conclusion that QDD functions as a screening and workload-prioritisation model rather than an automated benefits decision-maker. Applications flagged by the model are sent to a special group of QDD claims examiners, who review the file and make the actual determination. A disability examiner should start looking at a flagged file a day or two after receiving it. If the medical records are complete and the QDD unit agrees with the claimant's alleged onset date, the case can be approved in less than a month. However, if the record does not contain enough medical evidence or the date of disability onset is harder to determine, the QDD examiner may remove the application from the fast track and return it to standard processing. This does not result in a denial but means the claim will be processed through SSA's usual channels.

SSA has maintained formal operating instructions for staff handling QDD cases, including specific procedures for field offices and Disability Determination Services, and has continued to treat the model as an active operational tool rather than a one-off pilot. At the same time, SSA does not publicly disclose much detail about the current model logic, feature set, fairness testing, or performance drift management. The case is therefore best understood as a real and long-running high-consequence screening deployment with limited public technical transparency.

Publicly available secondary sources report materially faster processing times for QDD cases than for standard disability claims. According to the most recent SSA statistics available as of December 2022, QDD cases were taking an average of 27 days, with a median of only 13 days. SSA's chief artificial intelligence officer reported a 157 percent year-over-year jump in process rates for the disability screening tool and noted plans for expanded use across SSA teams. Those figures are directionally consistent with SSA's official framing that QDD accelerates clear-cut claims, but the exact contemporary coverage and selection-rate metrics are not richly disclosed in official primary materials.

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Assessment of needs/conditions + enrolment primary
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social insurance
Programme Name Social Security Administration (SSA) – Quick Disability Determinations (QDD) Predictive Model
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Old age, survivors and disability pensions
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Programme Description The Social Security Disability Insurance (SSDI) programme administered by the U.S. Social Security Administration, which provides benefits to individuals who are unable to work due to a qualifying disability. QDD is a fast-track process within this programme that uses a predictive model to identify and expedite clear-cut disability claims.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Classical ML
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Monitoring, Maintenance and Decommissioning
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Developed in-house
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary Not documented
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary Not assessed
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Not documented
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary Not documented
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary High
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HITL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Fully in-house
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Not assessed
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Not assessed

Risk Dimensions

Data-related risks
Governance and institutional oversight risks
Operational and system integration risks

Impact Dimensions

Autonomy, human dignity and due process
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Beneficiary registries and MISPersonalSingle source (no linkage)Currently available and usedHistorical disability claims data held exclusively within SSA federal IT systems; not publicly available; subject to federal privacy regulations
Unstructured and text-based contentSensitiveSingle source (no linkage)Currently available and usedMedical evidence documentation within disability applications; contains health-related information; subject to strict federal privacy protections

DisabilitySecrets (n.d.) 'What Is the Quick Disability Determination (QDD) Process?'. Available at: https://www.disabilitysecrets.com/resources/disability/quick-disability-determination-process-social- (Accessed: 23 March 2026).

View source News article / media

Glaze, K., Ho, D.E., Ray, G.K. and Tsang, C. (n.d.) 'Artificial Intelligence for Adjudication: The Social Security Administration and AI Governance', Stanford University Digital Health Observatory. Available at: https://dho.stanford.edu/wp-content/uploads/SSA.pdf (Accessed: 23 March 2026).

View source Working paper / technical note

Bracken, M. (2024) 'Data tracking, AI and modernization: How SSA has ditched its paper-based past', FedScoop, 5 July. Available at: https://fedscoop.com/social-security-administration-securitystat-ai-modernization/ (Accessed: 23 March 2026).

View source News article / media

U.S. Social Security Administration (2019) Quick Disability Determinations (QDD). Available at: https://www.ssa.gov/disabilityresearch/qdd.htm (Accessed: 23 March 2026).

View source Government website / press release
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Scaled & Institutionalised
Year Initiated The year the AI system was first initiated or development began. 2006
Scale / Coverage The scale and geographic or population coverage of the deployment. National — used across all SSA disability claims nationally since February 2008
Funding Source The source(s) of funding for the AI system development and deployment. Unknown
Technical Partners External technology vendors, academic partners, or development partners involved. Custom-developed and operated internally by SSA; no external commercial vendor is identified in primary documentation.
Outcomes / Results Official SSA materials and secondary reporting indicate that QDD is used nationally to expedite a subset of likely-favourable disability claims and that these cases are processed materially faster than standard disability claims. Public reporting has cited median handling times measured in days rather than months, but SSA's public primary materials provide only limited detail on current exact performance and coverage rates.

How to Cite

DCI AI Hub (2026). 'Social Security Administration (SSA) – Quick Disability Determinations (QDD) Predictive Model', AI Hub AI Tracker, case USA-007. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/USA-007 [Accessed: 1 April 2026].

Change History

Created 30 Mar 2026, 08:42
by v2-import (import)