Lead Clinical Science Informaticist

Oracle Oracle · Enterprise · United States

Lead Clinical Science Informaticist at Oracle Health Data Intelligence (HDI) focused on leveraging clinical data, ML, and AI for healthcare innovation. The role involves applying informatics techniques, statistical modeling, and annotation guidelines to improve healthcare delivery and patient outcomes. Key responsibilities include creating value sets, developing annotation guidelines, defining data requirements, implementing quality control for annotated data, leading annotation review cycles, conducting error analysis of AI model outputs, defining AI red teaming and guardrails, and overseeing data collection/pre-processing for AI/ML models. The role also involves defining requirements for AI/ML model effectiveness, designing ground truth algorithms, and collaborating with cross-functional teams on data quality and AI-driven projects.

What you'd actually do

  1. Create and curate clinical value sets composed of industry-standard terminologies such as SNOMED CT, ICD, and CPT, ensuring alignment with data science models and algorithms.
  2. Develop and document clear annotation guidelines to ensure they are understood by annotation teams and data scientists.
  3. Define data requirements and ensure integration within AI/ML-driven applications, with a focus on data quality and model readiness.
  4. Implement quality control processes to validate the integrity and reliability of annotated data, ensuring suitability for AI/ML solutions.
  5. Lead annotation review cycles and provide feedback to ensure labeling quality, while performing regular evaluations of model predictions to identify edge cases and improve performance.

Skills

Required

  • Clinical experience (e.g., registered nurse, pharmacist, clinical laboratory technician, respiratory therapist)
  • Clinical informatics
  • Familiarity with clinical EHR systems and data
  • Collaboration with healthcare professionals, IT specialists, and business users
  • Working with clinical data for evidence-based decision making, quality measurement, care coordination, and outcomes-based improvement programs
  • Supporting data annotation, machine learning (ML), natural language processing (NLP), and AI-driven projects in healthcare
  • Creation of evaluation frameworks for AI model performance
  • Understanding of the AI model life cycle
  • Statistical methods, machine learning techniques, and generative AI
  • Medical standards and ontologies
  • Data preprocessing, feature engineering, and model development for AI/ML applications
  • Defining data requirements, ensuring data readiness, and validating annotated data for AI/ML solutions
  • Proficiency in working with clinical terminologies (SNOMED CT, ICD, CPT)
  • Familiarity with healthcare data standards (FHIR Resources, QDM Categories)
  • Modeling clinical and administrative healthcare data for AI-driven solutions
  • Implementing quality control processes for data integrity, reliability, and clinical relevance
  • Working with disparate healthcare data types (EHR, billing, lab, eligibility, claims data)
  • Critical thinking and problem-solving skills for designing algorithms and models
  • Expertise in clinical and administrative healthcare data modeling
  • Advanced knowledge of data science techniques (statistical analysis, machine learning, NLP)
  • Proficiency in programming languages (Python, R, or SQL)
  • Experience with AI/ML frameworks (TensorFlow, PyTorch, or scikit-learn)
  • Knowledge of care management best practices and services
  • Ability to interpret complex clinical and business requirements
  • Excellent communication and collaboration skills

Nice to have

  • Life sciences, clinical trials, and regulatory experience

What the JD emphasized

  • clinical experience
  • clinical informatics
  • clinical EHR systems
  • clinical data
  • data annotation
  • machine learning (ML)
  • natural language processing (NLP)
  • AI-driven projects
  • evaluation frameworks
  • AI model life cycle
  • generative AI
  • medical standards and ontologies
  • data preprocessing
  • feature engineering
  • model development
  • clinical data integration
  • defining data requirements
  • ensuring data readiness
  • validating annotated data
  • AI/ML solutions
  • clinical terminologies
  • SNOMED CT
  • ICD
  • CPT
  • data science models
  • algorithms
  • healthcare data standards
  • FHIR Resources
  • QDM Categories
  • modeling clinical and administrative healthcare data
  • quality control processes
  • integrity
  • reliability
  • clinical relevance
  • disparate healthcare data types
  • EHR
  • billing
  • lab
  • eligibility
  • claims data
  • AI red teaming
  • guardrails
  • data models
  • terminology ontologies
  • platform rules engine
  • data compatibility
  • model training
  • ground truth algorithms
  • performance metrics
  • outcome validation
  • cross-functional teams
  • data scientists
  • annotators
  • engineers
  • project managers
  • data quality
  • model evaluation
  • performance monitoring
  • clinical objectives

Other signals

  • AI-driven projects
  • machine learning (ML)
  • natural language processing (NLP)
  • generative AI
  • model evaluation
  • data annotation
  • quality control