Training & Certification

This two-day, hands-on workshop is for practicing data scientists who build on John Snow Labs’ medical language models. You’ll get temporary license keys and run live Python notebooks that put the models to work on real clinical tasks.

Day 1 covers the core pipeline: de-identification and PHI removal across text, FHIR, PDF, and DICOM; clinical information extraction, including named entities, assertion status, and relation extraction; entity resolution to SNOMED CT, RxNorm, LOINC, ICD-10, and other medical terminologies; and medical LLM use for clinical reasoning, summarization, and question answering. You’ll work through the published, peer-reviewed benchmarks behind these models, and learn how to choose between them and evaluate them for different tasks and versus general-purpose frontier models.

Day 2 goes deep on visual language models: OCR and document understanding, DICOM and image de-identification, and multimodal extraction, with their benchmarks. It will then introduce the Generative AI Lab, an annotation and model training tool that powers regulatory-grade human-in-the-loop workflows. We’ll then cover key aspects in taking these solutions to production: deployment options across SageMaker, Azure, Databricks, and Snowflake, inference cost optimization, privacy and security, and scaling inside your own environment, where data never leaves your control.

The workshop is led by current contributors to the John Snow Labs codebase and ends with a certification exam.

This one-day workshop shows architects, data engineers, and technical leaders how to turn messy, multimodal clinical data into a trusted, AI-ready foundation using the Patient Journey Intelligence Platform. The morning covers the platform architecture: how raw clinical notes, scanned PDFs, FHIR resources, DICOM images, lab feeds, and claims become a unified, enriched, and de-identified OMOP CDM dataset. We’ll then cover data governance capabilities including confidence scoring and full provenance on every extracted fact, versioning, audit trails, role-based access, and human-in-the-loop overrides.

The afternoon is hands-on, with access to a Patient Journey Intelligence environment you’ll ingest (synthetic) multimodal data, build cohorts with natural-language queries, explore complete patient timelines, and query the OMOP data directly over SQL, REST, and MCP. You’ll also build your own clinical AI agents on the same governed foundation, inheriting compliance and governance by default. Led by John Snow Labs product and engineering leaders, the day ends with a certification exam.

Comprehensive hands-on training and certification for those mastering the art of text annotation, crucial for the success of any LLMs

This is a comprehensive hands-on training designed for those keen on mastering the art of text annotation, crucial for the success of any Language Model training. Whether you are a beginner aiming to dip your toes or an expert looking to refine your skillset, this course offers insights and skills tailored for you.

• Preparing High-Quality Training Data for Language Models: Gain an in-depth understanding of how to prepare high-quality training data, the critical foundation for building robust Language Models.
• Mastering the Generative AI Lab: Obtain hands-on experience with John Snow Labs’ Generative AI Lab, a no-code high productivity tool designed for managing annotation and model training projects efficiently.
• Creating Effective Annotation Guidelines: Learn how to develop precise and comprehensive annotation guidelines. These guidelines are essential for maintaining consistency and accuracy in annotation tasks across teams.
• Data De-Identification: Explore techniques to safely de-identify sensitive data for use in annotation projects and for further analysis, ensuring data privacy and compliance.
• Tracking and Monitoring Progress: Discover best practices for tracking your annotation project’s progress and evaluating the quality of the annotations to ensure timely completion and high team productivity.
• Leveraging No-Code Pre-Annotations: Accelerate your project by utilizing John Snow Labs’ pre-trained models, rules, or Generative AI prompting to create pre-annotations. This not only speeds up the process but also enhances initial data quality.
• Seamless Custom Model Training: Learn how to train custom models with ease once you’ve gathered sufficient training data. Through an intuitive UI, models can be trained with just one click, yielding smaller, specialized models that are optimized for deployment on standard hardware.
• Model Testing and Evaluation: Test your custom models for accuracy, bias, fairness, performance, representation and robustness using over 70 out-of-the-box tests. You’ll also learn how to automatically augment your data to boost overall model’s quality.

This two-day workshop will walk you through building state-of-the-art Generative AI and Natural Language Processing (NLP) using John Snow Labs’ open-source libraries. This is a hands-on workshop for data scientists that will enable you to write and run live Python notebooks that put the technology to work.

The first day covers the open-source Spark NLP library for information extraction at scale – including reusing, training, and combining AI models for tasks like named entity recognition, text classification, spelling & grammar correction, question answering, knowledge extraction, sentiment analysis and more. The second day focuses on libraries and integrations specifically for preparing data for RAG LLM solutions, including document splitting, cleaning, metadata enrichment, summarization, and embeddings calculation.

The workshop is organized in two four-hour-long sessions, each followed by self-guided coding, on Python notebooks relevant to each section. This is a live online workshop whose instructors are current lead contributors to the John Snow Labs open-source codebase. A certification of expertise is provided to attendees who pass a final online exam.

This two-day workshop for practicing data scientists will enable you to use and extend John Snow Labs’ Healthcare NLP & LLM library. You will run live Python notebooks that walk through clinical entity recognition, entity resolution (mapping entities to medical codes), assertion status detection (i.e. negation detection), relation extraction, and de-identification. You will also learn how to train and tune your own models and how to choose which pre-trained models to start from.

The second day is focused on medical language models and will teach you how to make use of the medical text summarization, question answering, and text generation LLMs. It will also cover improving the accuracy of RAG LLM solutions that process medical documents by using healthcare-specific document splitting, enrichment, and embedding algorithms.

The workshop is organized in two four-hour-long sessions, each followed by self-guided coding. This is a live online workshop whose instructors are current lead contributors to the Healthcare NLP & LLM codebase.

This is a comprehensive hands-on training designed for those keen on mastering the art of text annotation, crucial for the success of any NLP model training. Whether you are a beginner aiming to dip your toes or an expert looking to refine your skillset, this course offers insights and skills tailored for you.

What You Will Learn:
1. Prepare High-Quality Training Data for NLP Models: Understand the intricacies of preparing high-quality training data, the backbone for creating robust NLP models.
2. Mastering The NLP Lab: Acquire hands-on experience in executing a complete annotation project with John Snow Labs’ high-productivity annotation tool: the NLP Lab.
3. Creating Effective Annotation Guidelines: Dive deep into the development of precise annotation guidelines. These guidelines are pivotal in ensuring consistency and accuracy across data annotation tasks and team members.
4. Tracking and Monitoring: Equip yourself with strategies to monitor your project’s progress and gauge the quality of annotations. This ensures that the project remains on course and maintains the highest standard.
5. Laverage No-Code Pre-Annotations: Jumpstart your projects leveraging pre-annotations from John Snow Labs pre-trained models, rules, prompts, or even with ChatGPT prompting. This integration not only accelerates the process but also enhances the quality right from the outset.
6. Effortless Custom Model Training: When you accumulate sufficient annotated data, leverage the ability to train custom models effortlessly via an intuitive UI, with the click of a button.

Why Choose This Training?
– Experienced Instructors: Our trainers are not just academicians; they have spearheaded multiple large-scale data annotation projects. Their rich experience ensures a practical approach to teaching, grounded in real-world challenges and solutions.
– Interactive Learning: Unlike conventional lectures, our training is hands-on. Instructors will be available during assignments to clarify doubts, offering a continuous learning experience.
– Certification: The journey culminates in a certification exam. Those who engage in the hands-on exercises and clear the exam will be awarded a certificate, recognizing them as Certified Data Annotation Experts.

Step into the world of data annotation with confidence and competence. Enroll now and set yourself on the path to becoming an expert in delivering successful data annotation projects.

Like any other technology, Natural Language Processing (NLP) requires business, product, and design leaders to understand what it can and cannot do – so that they can understand what opportunities it holds for improving their customers’ experience and bottom line with a solid ROI.

This five-hour live online workshop presents key concepts in NLP such as named entity recognition, document classification, transformers, pipelines, training, and annotation – but through the lens of real-world projects that got from concepts to production systems. The content is organized as a series of case studies, each starting with a business use case, diving into the solution architecture, explaining how NLP played part in the solution, and ends with best practices and lessons learned.

The instructor is a seasoned technology executive and NLP expert who oversaw the construction & operations of dozens of AI & NLP systems, and will be available for questions during and after the workshop.