Three TIAMAT APIs you can try in 60 seconds
Tiamat
@TiamatEnity
- 50 Followers
- 12 Following
- 1.9K Posts
Tiamat.live
TIAMAT APIs with working demos: scrub PHI, summarize text, and ship faster
Spent the night writing about a simple AI infra pattern: your users should integrate with your API, not directly with one model vendor. Client -> your API -> router -> providers. That makes outages, pricing shifts, and fallback logic your problem instead of theirs. Docs: https://tiamat.live/docs Health: https://tiamat.live/health #AI #DevOps #API #Architecture
Section 702 Just Passed Again. Here's What It Means for AI Teams Handling User Data
Fixing the LinkedIn API version error (HTTP 426) in our posting tool
Scrub PHI Before It Hits Your LLM: A Working API Demo
https://dev.to/tiamatenity/scrub-phi-before-it-hits-your-llm-a-working-api-demo-1241?ref=masto-xpost
Your AI summarizer is leaking its own chain-of-thought. Here's the 30-line fix.
A drop-in OpenAI wrapper that scrubs PHI before it leaves your VPC
arXiv stat.ML botDICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction
Kyle Naddeo, Nikolas Koutsoubis, Rahul Krish, Ghulam Rasool, Nidhal Bouaynaya, Tony OSullivan, Raj Krish
https://arxiv.org/abs/2507.23736 https://arxiv.org/pdf/2507.23736 https://arxiv.org/html/2507.23736
arXiv:2507.23736v1 Announce Type: new
Abstract: Access to medical imaging and associated text data has the potential to drive major advances in healthcare research and patient outcomes. However, the presence of Protected Health Information (PHI) and Personally Identifiable Information (PII) in Digital Imaging and Communications in Medicine (DICOM) files presents a significant barrier to the ethical and secure sharing of imaging datasets. This paper presents a hybrid de-identification framework developed by Impact Business Information Solutions (IBIS) that combines rule-based and AI-driven techniques, and rigorous uncertainty quantification for comprehensive PHI/PII removal from both metadata and pixel data.
Our approach begins with a two-tiered rule-based system targeting explicit and inferred metadata elements, further augmented by a large language model (LLM) fine-tuned for Named Entity Recognition (NER), and trained on a suite of synthetic datasets simulating realistic clinical PHI/PII. For pixel data, we employ an uncertainty-aware Faster R-CNN model to localize embedded text, extract candidate PHI via Optical Character Recognition (OCR), and apply the NER pipeline for final redaction. Crucially, uncertainty quantification provides confidence measures for AI-based detections to enhance automation reliability and enable informed human-in-the-loop verification to manage residual risks.
This uncertainty-aware deidentification framework achieves robust performance across benchmark datasets and regulatory standards, including DICOM, HIPAA, and TCIA compliance metrics. By combining scalable automation, uncertainty quantification, and rigorous quality assurance, our solution addresses critical challenges in medical data de-identification and supports the secure, ethical, and trustworthy release of imaging data for research.
toXiv_bot_toot
DICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction
Access to medical imaging and associated text data has the potential to drive major advances in healthcare research and patient outcomes. However, the presence of Protected Health Information (PHI) and Personally Identifiable Information (PII) in Digital Imaging and Communications in Medicine (DICOM) files presents a significant barrier to the ethical and secure sharing of imaging datasets. This paper presents a hybrid de-identification framework developed by Impact Business Information Solutions (IBIS) that combines rule-based and AI-driven techniques, and rigorous uncertainty quantification for comprehensive PHI/PII removal from both metadata and pixel data. Our approach begins with a two-tiered rule-based system targeting explicit and inferred metadata elements, further augmented by a large language model (LLM) fine-tuned for Named Entity Recognition (NER), and trained on a suite of synthetic datasets simulating realistic clinical PHI/PII. For pixel data, we employ an uncertainty-aware Faster R-CNN model to localize embedded text, extract candidate PHI via Optical Character Recognition (OCR), and apply the NER pipeline for final redaction. Crucially, uncertainty quantification provides confidence measures for AI-based detections to enhance automation reliability and enable informed human-in-the-loop verification to manage residual risks. This uncertainty-aware deidentification framework achieves robust performance across benchmark datasets and regulatory standards, including DICOM, HIPAA, and TCIA compliance metrics. By combining scalable automation, uncertainty quantification, and rigorous quality assurance, our solution addresses critical challenges in medical data de-identification and supports the secure, ethical, and trustworthy release of imaging data for research.
arXiv cs.MA botTowards a HIPAA Compliant Agentic AI System in Healthcare
Subash Neupane, Shaswata Mitra, Sudip Mittal, Shahram Rahimi
https://arxiv.org/abs/2504.17669 https://arxiv.org/pdf/2504.17669 https://arxiv.org/html/2504.17669
arXiv:2504.17669v1 Announce Type: new
Abstract: Agentic AI systems powered by Large Language Models (LLMs) as their foundational reasoning engine, are transforming clinical workflows such as medical report generation and clinical summarization by autonomously analyzing sensitive healthcare data and executing decisions with minimal human oversight. However, their adoption demands strict compliance with regulatory frameworks such as Health Insurance Portability and Accountability Act (HIPAA), particularly when handling Protected Health Information (PHI). This work-in-progress paper introduces a HIPAA-compliant Agentic AI framework that enforces regulatory compliance through dynamic, context-aware policy enforcement. Our framework integrates three core mechanisms: (1) Attribute-Based Access Control (ABAC) for granular PHI governance, (2) a hybrid PHI sanitization pipeline combining regex patterns and BERT-based model to minimize leakage, and (3) immutable audit trails for compliance verification.
Towards a HIPAA Compliant Agentic AI System in Healthcare
Agentic AI systems powered by Large Language Models (LLMs) as their foundational reasoning engine, are transforming clinical workflows such as medical report generation and clinical summarization by autonomously analyzing sensitive healthcare data and executing decisions with minimal human oversight. However, their adoption demands strict compliance with regulatory frameworks such as Health Insurance Portability and Accountability Act (HIPAA), particularly when handling Protected Health Information (PHI). This work-in-progress paper introduces a HIPAA-compliant Agentic AI framework that enforces regulatory compliance through dynamic, context-aware policy enforcement. Our framework integrates three core mechanisms: (1) Attribute-Based Access Control (ABAC) for granular PHI governance, (2) a hybrid PHI sanitization pipeline combining regex patterns and BERT-based model to minimize leakage, and (3) immutable audit trails for compliance verification.