cs.AISep 26, 2026

CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion

Authors: Garapati Keerthana, Manik Gupta

Organizations: Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, Hyderabad, India

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic forms. We developed and evaluated CLAIRE (Clinical Language and Agentic Intelligence for Reasoning and Entry), a hybrid workflow that separates field-state discovery, source-to-field mapping, deterministic validation, bounded correction, escalation, and audit tracing. We tested five synthetic healthcare administrative schemas, 1,000 source records, four interface variants, two data-quality suites, and six comparators, yielding 24,000 benchmark episodes. A separate strict-output audit evaluated direct mappings from Qwen2.5-1.5B and Qwen2.5-7B, and a trace-derived operational simulation covered 6,000 episodes. Under the evaluated synthetic benchmark conditions, full CLAIRE achieved 1.000 episode success, field accuracy, required-field completion, and dependency completion in both suites; removing validation reduced stress-suite success to 0.500. In the simulation, 100.0% of clean and validation-stress episodes reached a staff-reviewable draft, compared with 68.6% of escalation challenge episodes, unsupported cases were blocked. Scenario-based savings were 149.7-165.5 seconds per case, not observed staff times. The findings support schema-grounded, validation-first healthcare administrative automation in which language-model components assist mapping but do not authorize unsupported or consequential actions.

Figures & tables

What was already knownHealthcare organizations rely on administrative forms for prior authorization, benefit verification, credentialing, intake, and claims work. Browser automation can be brittle, and unconstrained language-model agents can generate plausible but unchecked entries.
What this study addedA schema-grounded hybrid workflow separates field discovery, mapping, validation, controlled error correction, and audit logging. In 24,000 benchmark episodes and a 6,000-episode operational simulation, the workflow completed validated cases, intercepted review needs, captured escalation cases, and produced scenario-based estimates of staff-time savings.
Table 1: Summary table.
Figure 1: Schema-grounded architecture. The four numbered roles share the same source record, schema, and working context. The Error Corrector uses only supported corrections, after which the Validator checks the state again. Unresolved cases are blocked for staff review.
ComponentDescription
SchemasPatient intake, prior authorization, benefit verification, provider credentialing, and claims resubmission.
Records1,000 deterministic synthetic source records: 500 clean records and a 500-record validation-stress copy.
Interface variantsOriginal labels, synonym labels, obfuscated identifiers, and shuffled layout.
ComparatorsExact ID, Labels only, Monolithic, CLAIRE without schema, CLAIRE without the Validator, and full CLAIRE.
MetricsEpisode success, field accuracy, required-field completion, dependency completion, validation errors, corrections, and model calls.
Table 2: Internal benchmark design.
Figure 2: Episode success in the full internal benchmark. CLAIRE maintains complete success across clean and validation-stress suites, while validation removal specifically degrades performance under dirty source values.
Figure 3: Strict LLM decision audit on a focused subset. Direct labels-only mappings are weak; schema conditioning and explicit correction improve performance substantially, but the guarded CLAIRE executor remains the most reliable condition.
Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 4: Intended workflow placement. CLAIRE prepares a validated draft and trace from an incoming administrative work item. Staff retain authority to approve, correct, escalate, or stop submission to a payer or vendor interface.
Figure 5: Internal benchmark design. The same schemas, records, and interface variants were applied to all six comparators.
Figure 6: Synthetic-data example. The schema defines the target, while the stress record contains invalid values and explicit corrections. All displayed names and identifiers are synthetic.
More in this topic

Workflow Automation

Workflow automation coordinates multi-step tasks across applications, tools, and people using software, AI agents, and explicit process logic.

See all 62 papers

Explore similar work

CardsList
Apr 22, 2026

LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic Compilation

Automatically filling Case Report Forms (CRFs) from clinical notes is challenging due to noisy language, strict output contracts, and the high cost of false positives. We describe our CL4Health 2026 submission for Dyspnea CRF filling (134 items) using a contract-driven two-stage design grounded in Schema-Guided Reasoning (SGR). The key task property is extreme sparsity: the majority of fields are unknown, and official scoring penalizes both empty values and unsupported predictions. We shift from a single-step "LLM predicts 134 fields" approach to a decomposition where (i) Stage 1 produces a stable SGR-style JSON summary with exactly 9 domain keys, and (ii) Stage 2 is a fully deterministic, 0-LLM compiler that parses the Stage 1 summary, canonicalizes item names, normalizes predictions to the official controlled vocabulary, applies evidence-gated false-positive filters, and expands the output into the required 134-item format. On the dev80 split, the best teacher configuration achieves macro-F1 0.6543 (EN) and 0.6905 (IT); on the hidden test200, the submitted English variant scores 0.63 on Codabench. The pipeline is language-agnostic: Italian results match or exceed English with no language-specific engineering.

Serhii Zabolotnii

Cherkasy State Business College2026 Cherkasy, Ukraine

HealthcareClinical Information ExtractionMedical LLMsLLM Reasoning
AskPDF
Apr 10, 2026

HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks

Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LLMs have received significant attention, no benchmark exists for evaluating CUAs on end-to-end administrative workflows. To address this gap, we introduce HealthAdminBench, a benchmark comprising four realistic GUI environments: an EHR, two payer portals, and a fax system, and 135 expert-defined tasks spanning three administrative task types: Prior Authorization, Appeals and Denials Management, and Durable Medical Equipment (DME) Order Processing. Each task is decomposed into fine-grained, verifiable subtasks, yielding 1,698 evaluation points. We evaluate seven agent configurations under multiple prompting and observation settings and find that, despite strong subtask performance, end-to-end reliability remains low: the best-performing agent (Claude Opus 4.6 CUA) achieves only 36.3 percent task success, while GPT-5.4 CUA attains the highest subtask success rate (82.8 percent). These results reveal a substantial gap between current agent capabilities and the demands of real-world administrative workflows. HealthAdminBench provides a rigorous foundation for evaluating progress toward safe and reliable automation of healthcare administrative workflows.

Suhana Bedi, Ryan Welch, Ethan Steinberg +12

Stanford University · Kinetic Systems · Stanford Health Care

Computer-Use Agent BenchmarksLLM Agent EvaluationWorkflow Automation
AskPDF
Oct 12, 2026

ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts

Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety, and identify risk factors outside randomized trials. Automating RWS with large language model agents is appealing but brittle: valid analyses depend on dataset-specific clinical semantics, including index dates, follow-up windows, patient/event-level units, and outcome boundaries that are often implicit in observational data. This leads to schema mismatches, temporal errors, inconsistent analytical granularity, and unsupported clinical claims. We present ProCARE, a profile-grounded framework that reformulates RWS automation as constrained compilation. ProCARE converts heterogeneous data profiles into Evidence Contracts specifying available variables, temporal attributes, distributions, and evidentiary limits, and compiles study objectives into RWS-IR, a strongly typed intermediate representation for variables, time relations, analysis units, and statistical tasks. Deterministic validation and localized repair then check and revise generated workflows across schema mapping, cohort construction, variable derivation, analysis, and interpretation. On 36 EHR-based benchmark tasks, ProCARE outperforms strong LLM-agent baselines in code executability, semantic consistency, and conclusion traceability, with automated violation diagnoses showing moderate-to-substantial agreement with blinded expert review.

Zhaoyu Fan, Bowen Han, Jincheng Ou +8

Tongji University · Shanghai Hengfang Health Technology Co., Ltd. · University of Electronic Science and Technology of China +1

Scientific Workflow AutomationEvidence-Grounded GenerationCompiler-Guided Program Synthesis
AskPDF