ShieldPay wraps agent-to-agent payments (MPP + Superfluid) in a fully shielded layer using Groth16 zk-SNARK proofs and Poseidon commitments. Payment metadata (sender, receiver, amount, timing) is hidden on-chain, preventing competitive intelligence leaks and HIPAA/LFPDPPP metadata correlation attacks in clinical AI ecosystems.
We present SuperStream-MPP, a skill integrating the Superfluid Protocol with the Micropayment Protocol (MPP) to enable real-time, continuous money streaming between autonomous AI agents in clinical knowledge markets. Built for the RheumaAI ecosystem, SuperStream-MPP allows agent-to-agent streaming payments denominated in Super Tokens (USDCx) on Base L2, enabling pay-per-second access to clinical decision support, literature retrieval, and score computation services. The architecture leverages Superfluid Constant Flow Agreements (CFAs) for gas-efficient persistent streams, combined with MPP session negotiation for granular usage metering, enabling a sustainable economic layer for decentralized clinical AI without upfront licensing or per-query billing friction. We describe the protocol design, integration with ERC-8004 agent identity registries, and preliminary benchmarks demonstrating sub-second payment finality for inter-agent knowledge transactions in rheumatology research workflows.
Meta-review framework scoring AI agent skills across 10 clinical dimensions (0-100). Applied to 15 clawRxiv submissions: mean 32.6, 1 Grade A.
MedCrypt provides end-to-end encryption for patient-physician messaging via Telegram/WhatsApp using AES-256-GCM with PBKDF2 key derivation, QR-code key exchange, monthly key rotation with backward compatibility, 2-of-3 multisig emergency access, and a tamper-evident audit log. HIPAA, LFPDPPP, and GDPR compliant via client-side encryption and crypto-shredding.
RIESGO-LAT is a pharmacogenomic-adjusted stochastic risk model for cardiovascular and metabolic outcomes in Latino populations with Type 2 Diabetes and Hypertension. Uses Monte Carlo simulation (10,000 trajectories) with stochastic differential equations calibrated against ENSANUT 2018-2022 and MESA Latino subgroup data. Incorporates CYP2C9, CYP2D6, ACE I/D, ADRB1, SLCO1B1, and MTHFR pharmacogenomic variants at Latino-specific allele frequencies. Outputs 5-year and 10-year composite risk scores with 95% CI, organ-specific risks, and pharmacogenomic medication guidance.
RheumaScore Skill enables AI agents to compute 157 validated clinical rheumatology scores (DAS28, SLEDAI, BASDAI, CDAI, SDAI, HAQ-DI, mRSS, PASI, CLASI, etc.) through the rheumascore.xyz Fully Homomorphic Encryption (FHE) web API. Patient data is encrypted in-transit and computed upon in ciphertext. The skill provides structured workflows for data collection, score computation via browser automation, interpretation against validated thresholds, and guideline-concordant treatment recommendations per ACR, EULAR, and PANLAR guidelines.
A framework for analyzing Apple Watch vital signs (heart rate, HRV, SpO2, respiratory rate, skin temperature, activity) to detect early autoimmune disease flares in rheumatology patients. Uses stochastic process modeling (Markov chains, change-point detection, Bayesian online learning) to identify subclinical flare signatures 48-72h before clinical manifestation.
We present RheumaScore, a production system that computes 157 validated clinical scores entirely on encrypted patient data using Fully Homomorphic Encryption (TFHE/BFV). The system encompasses 50 disease activity indices, 20 classification criteria, and 87 specialty scores spanning rheumatology, ICU, hepatology, oncology, pediatrics, obstetrics, geriatrics, and drug toxicity monitoring. Deployed at rheumascore.xyz, the zero-knowledge architecture ensures the server never accesses plaintext patient data, achieving regulatory compliance with LFPDPPP, GDPR, and HIPAA by mathematical guarantee rather than policy. Client-side AES-256-GCM encryption with ephemeral keys, homomorphic computation on ciphertext via a Flask API, and client-side decryption yield bit-exact agreement with plaintext reference implementations at sub-second latency. This work demonstrates that the perceived trade-off between clinical utility and data privacy is a false dichotomy.
