Apply on Employer Site

Houston Methodist · 3 hours ago

Lead, Research Data Scientist - Cancer, Dr. Cullen lab

Houston, TX

Full-time

Onsite

Senior Level, Lead/Staff

7+ years exp

Houston Methodist is a leading academic institute focused on advancing healthcare through innovative research. The Lead Research Data Scientist will oversee the integration and management of clinical and research data for the Cancer Prevention and Control Program, ensuring compliance and data quality while facilitating research collaborations and optimizing data pipelines.

Health CareMedical

Growth Opportunities

H1B Sponsor Likely

Responsibilities

Design, implement, and maintain a state-of-the-art data management infrastructure that includes robust DataMart from multiple novel sources reflecting medical, social, genomic, and environmental drivers of health, consistent with the departmental mission

Engage in strategic negotiations and collaborations with key data providers, including institutional EMR teams, the Texas Cancer Registry, and other state and local agencies, to secure access to data critical to understanding the medical and socioecological contexts of health in patients with cancer. Liaise with multidisciplinary teams to ensure seamless data flow, integration, and alignment with project objectives

Oversee strategic guidance on data elements, methods, and models required for clinical and research objectives, and facilitate the identification and extraction of these elements from the EHR and data warehouse systems

Oversee data collection and harmonization processes, ensuring compliance with applicable industry data standards (e.g., FHIR, HL7, NAACCR)

Collaboratively develop and deploy quality assurance (QA) and quality control (QC) measures to maintain data integrity and reliability

Apply statistical and epidemiological methods to analyze data on health outcomes and survival in patients with cancer. Develop and adhere to statistical analysis plans (SAP), prepare research presentations, and draft results for peer-reviewed publications

Monitor emerging trends and developments in real-world clinico-omic data informatics and provide strategic recommendations on technologies and processes to optimize and advance the CPC data ecosystem

Prepare and present data insights, integration strategies, and progress reports to internal and external stakeholders

Enhance scientific discovery by contributing to hypothesis generation, cohort identification, publications, presentations, and proposals that advance CPC program goals

Establish a streamlined process for research approval that includes developing an umbrella IRB protocol and standardized data-use agreements for the novel data warehouses to facilitate quicker start times for research projects

Manage an expanding team with varied expertise within the Clinical Informatics and Data Sciences Group. Train, mentor, and supervise staff on data workflow processes, good practices, and standards

Strong understanding of data interoperability standards (e.g., FHIR, HL7, OMOP, CDISC, NAACCR)

Knowledge of regulatory frameworks such as HIPAA, GDPR, and GCP

Familiarity with cancer genomics repositories and/or cancer registries is highly desirable

Proficiency with data integration tools and platforms (e.g., ETL processes, APIs, databases)

Knowledge of programming languages or tools commonly used in data analysis and integration (e.g., Python, R, SQL, Tableau)

Knowledge of EPIC, PACS, LIS, and other HealthIT/business systems

Deep understanding of AI lifecycle Management, AI/ML Platform architecture

Familiarity with cloud-based data environments (e.g., AWS, Google Cloud, or Azure)

Familiarity with terminology systems, including SNOMED, LOINC, RxNorm, and ICD, to encode and query healthcare data

Manages multiple client/researcher relationships by leading the delivery of innovative strategies and solutions for our clients. Assigns projects to other data scientists

Oversees project progress and presents results to the stakeholders

Mentors and guides less experienced members of the data-science and analytics teams in their development of skills and proficiencies to be more effective in their roles

Drives contributions towards improvement of department scores for employee engagement, i.e., peer-to-peer accountability

Leads the research data analytics insights across the hospital system

Leads/co-leads a data science/research/business team targeted at fulfilling the organization's needs to access and understand research, clinical, financial, operational, population health, social, behavior, and marketing data

Leads a portfolio of advanced and complex projects that require more experience and expertise. Assigns the execution of multiple, complex analytical plans and projects and leads lower-level data scientists

Leads, as subject matter expert, on clinical data quality issues and assurance as well as patient privacy and data security and compliance

Oversees documenting the project requirements and results on a timely basis and reviews documentation and code submitted by lower-level research data scientists

Facilitates quality improvement process evaluations to improve data research analytics. Reviews presentation ideas prior to being viewed by leadership

Provides guidance to HDSA leadership on strategic and infrastructural needs for the organization

Leads the continuous improvement of clinical and operational data and analytics

Actively seeks out innovative solutions to the many challenges facing researchers in the clinical outcomes space and explores solutions to collaboration across and external to the institution. solutions with the clinicians, hospital administration, and other stakeholders

Translates the findings into implementable informatics solutions with the clinicians, hospital administration, and other stakeholders, leading assisting the Technical and Research Data Scientists with these tasks

Seeks opportunities to identify self-development needs and takes appropriate action. Ensures own career discussions occur with appropriate management. Completes and updates the My Development Plan on an on-going basis

Qualification

Data management infrastructureStatistical analysisData integration toolsHealth data standardsProgramming languagesAI/ML Platform architectureCloud computingCancer genomics knowledgeResearch collaborationQuality assuranceTeam managementCommunication skills

Required

Master's degree in computer science, Clinical Informatics, Public Health Administration, Business Administration, or Data Science, or Engineering, or an MD with experience in Informatics and Statistics or related field

Seven years' experience in health care data analytics and/or database management in a healthcare organization

Advanced skill in fields of computer science or mathematics and applications, modeling, statistics, and analytics