Adam Sroka

Data & AI Director

Hypercube Consulting

Chief Executive Officer

Director

The Data Lab - Innovation Centre

The Innovation Advisory Board is responsible for advising on innovation and collaborative project activity for The Data Lab – Scotland’s Innovation Centre for Data and AI.

Innovation Advisory Board Member

Origami

Head of Machine Learning Engineering

Incremental Group

Senior Data Scientist

Sure Thing! Insurance

Data Scientist

Clear Returns

Thales

Research Engineer

I build data and AI platforms for the energy sector | Director at Hypercube Consulting

Dr Adam Sroka is a Co-founder and CEO at Hypercube Consulting, a firm that helps organisations unlock value from data by delivering enterprise-scale solutions and building high-performing data and analytics teams from the ground up. With over 10 years of experience in data science, machine learning, and artificial intelligence, Adam is a recognised expert and speaker in his field.

Adam's mission is to bridge the gap between technology and business, and to enable data-driven innovation and transformation across various industries. He shares his insights and best practices through his blog, podcast, and tech community events, where he showcases his approaches and systems for effective communication, engineering discipline, and experimentation. Adam is passionate about helping organisations and data professionals maximise their potential and impact with data and AI.

Atropos Health

Lead data integration, normalization, and quality initiatives across the company, owning client projects and internal data products for aggregated national and institutional EHR and claims datasets that range from 3 million to 220 million patients each and cover hundreds of billions of records

Design and maintain Common Data Model to facilitate cross-dataset compatibility

Own and execute major product releases, including data quality monitoring and documentation for general purposes and disease-specific datasets and lead functional and integration testing among data pipeline components

Senior Director, Data Engineering

Northeastern University

Developed and teaching "EAI6060 - Healthcare Information Processing." The course covers topics such as the history of healthcare information processing, HIPAA regulations, electronic health records (EHR), healthcare data standards, and the use of healthcare information for research. Additionally, it explores areas like unstructured text, natural language processing (NLP), and machine learning models in healthcare.

Part Time Lecturer

Tufts University School of Medicine

- Developed and taught HIA 225: Introduction to Python for Health Informatics and Analytics to HIA MSc students and MPH students

Instructor

Health Catalyst

Founding engineer on the Life Sciences Real World Data team, working in a small (<20), dynamic team aggregating, de-identifying, normalizing, cleaning, and enriching EHR data from 90+ data sources and 25+ health systems covering >60 million patient identities for RWE/RWD use that is updated weekly

Own and execute major product releases, including data quality monitoring and documentation for general purposes and disease-specific datasets in a cloud environment using SQL, Python, Spark, Azure Data Factory, Databricks, Snowflake, and HCAT’s proprietary ETL tools

Primary technical consulting resource for clients/partners to understand and derive clinical insights for general purpose and COVID-19 disease-specific datasets

Define new entities and data models using industry standards such as OMOP,  Sentinel CDM,  FHIR, HL-7 2.x and routinely work with complex clinical informatics problems and tools

Lead Data Engineer

Own the design and execution of purpose-built RWD datasets with quarterly releases, including unit testing, bug fix, documentation generation for  production data releases 

Designed and built a flexible pipeline infrastructure to automatically and scalably pipe semi-structured text values from Azure Synapse into Databricks, process the note texts using a John Snow Labs licensed NLP model to flag PII, and then return the results, achieving a >99% recall rate on over 40 billion records, with >50 million new records ingested weekly

Designed and implemented informatics pipeline to curate, clean, and transform more than 40 billion records of raw semi-structured flowsheets and note data into a de-identified, mapped, normalized data set of vitals, ventilator settings, oxygen flow rate, and other measures of interest with initial data delivered in 4 weeks

Senior Data Engineer

Owned and executed the creation of the enterprise's first expert-determination de-identified dataset for research with over 20 million patient identities with rich, longitudinal, deep clinical data

Initiated the design of and continue to act as lead data engineer for HCAT’s Touchstone COVID-19 dataset, starting in March 2020, an effort that was accepted into the FDA’s COVID-19 Real World Evidence Accelerator alongside industry-leading RWE/RWD companies including Cerner, Aetion, and Optum in close-knit small team (<10 technical team members)

Data Engineer

Assisted with course development 1.5 credit graduate level course at Tufts University School of Medicine: HIA 225: Introduction to Python for Health Informatics and Analytics 

Compiled course materials, created Jupyter notebook tutorials for students

Created and recorded 5-6 30-45 minute lectures on Python's background and basic structure, and its applications in healthcare data analytics

Assisted with course sessions in Spring 2021, Fall 2021, and Spring 2022 semesters, answering student questions, creating and leading classroom Python exercises, assisting with technology setup for students

Curriculum Development Assistant

OM1, Inc.

Ingested claims and EHR data into OM1's longitudinal health data cloud with longitudinal data covering 240 million patients for use in analytics, data science, and clinical research

Analyzed data quality and integrity and prepared, mapped, and transformed source data into OM1’s Snowflake and AWS architecture using SQL and Trifacta ETL tools

Clinical informatics lead analyst on small team that implemented a real time risk/utilization predictive model data pipeline with AMC partner using knowledge of EHR data models and FHIR

Led ingestion, validation, and documentation work on EHR integrations across six sites with different EHR systems and practice areas (cardiology, oncology, rheum, and others), ensuring data quality and de-duplication 

Authored CRF forms to fit study requirements and created/managed process for abstracting data from >40,000 note texts in three weeks, addressing negation, context, and date issues in note data 

Created clean datasets and derived variables for biostatisticians and epidemiologists to conduct observational studies utilizing client-provided and OM1 data

Delivered and QA's complex business development analyses using very specific requirements for major pharmaceutical and bio-pharmaceutical companies to determine if OM1’s data met prospective clients’ needs

Clinical Data Analyst

athenahealth

Implemented athenahealth Population Health product and ETL process for financial analytics, quality reporting, and care management at ACOs and other health systems and aligned data feeds to the requirements for MSSP and commercial value-based contracts

Acted as technical project manager for client, internal, and product teams to deliver implementations and communicate progress, solve issues, and ensured timelines for client go-lives

Validated data integrity and clinical concept mapping, worked with developers on data QA, and fixed data issues for clients with 260,000 at-risk lives and 68 live data feeds 

Used SQL and Microsoft Power BI to analyze medical claims and clinical data in diverse formats: HL-7, CCDA, X12, and EHR extracts from Epic, Cerner, eClinicalWorks,  Allscripts, and others

Data Acquisition and Interoperability Associate 

Mass General Brigham

Documented pharmacy operations and legacy system workflows, replicated functions in Epic, focusing on external pharmacy systems for preparation, dispensing, delivery,  and charging for medications  

Provided 24-hour support for issues in live system; triaged, determined root causes, tested solutions, and communicated fixes for >800 production issues

Primary support liaison for Newton Wellesley Hospital pharmacy, implemented Emergency Room take-home naloxone workflow and workflow for re-loading Omnicell dispensing stations, streamlining operations and reducing missing dispenses

Designed, tested, and implemented Epic downtime strategy for medication management across all Partners hospitals

Determined scope, tested, and supported deployment a custom QR-code based orders interface between Epic and CADD infusion pump, reducing user-entry errors

Associate Application Coordinator - Pharmacy

Designed, wrote, and executed application and integrated test scripts for Epic Willow build in Microsoft Test Manager (MTM) and Microsoft Team Foundation Server (TFS), logged and managed defects, communicated with application team and project leadership to reach bug resolution, confirmed bug fixes via re-test

Worked with clinical subject matter experts and application teams to design end-to-end patient scenarios, translated scenarios into Epic workflows,  and wrote MTM scripts for these workflows

Executed 119 test scenarios each month for seven month-long cycles of integrated testing, documented 114 bugs in TFS, and tracked application team progress toward resolution

Associate Testing Coordinator 

Tufts University

Office Assistant

United States Senate

Researched and composed responses to policy questions from Colorado Senator Michael Bennet’s constituents and staff on foreign affairs, technology, and transportation policy

Answered phones, gave tours to constituents, and performed administrative tasks

Legislative Intern

Sr Director, Data Engineering @ Atropos Health

I'm a clinical data engineer and have been working with EHR and medical/pharmacy claims data since 2014.

After working for 3 years testing and performing build and implementation of Epic at major hospitals, I've worked in Agile data teams ingesting, validating, enriching, and integrating claims and clinical data from many EHRs and different clinical systems and engineering and utilizing huge datasets to drive research and operational improvements, with a focus on NLP extraction of clinical entities from semi- and unstructured clinical text and notes.

I am especially interested in using FHIR alongside HL-7 2.x to speed up EHR integration pipelines for predictive modeling, quality improvement, and generating Real World Evidence for scientific research. I graduated with a MSc in Health Informatics and Analytics from the Tufts University School of Medicine in August 2022. 

My MSc capstone project, Implementing a Flexible, Modern, and Repeatable FHIR-based EHR Integration Framework, included design and build of a Spark pipeline in Databricks to interface with a cloud FHIR server that I created, used clinical data from 1 million de-identified hospitalizations to train an inpatient mortality prediction ML model, and returned results as a FHIR Observation resource. The model achieved a >.87 AUROC in predicting inpatient mortality from an extremely minimal set of data that would be easily available from a USCDI-compliant bulk FHIR interface.

Philip Ballentine

https://lnkd.in/emUSvU6g 

Come work with us! 

(Please no recruiters per policy)

Phil Ballentine

Open article: Data Engineer by jobs.ashbyhq.com

taplio

The Battle

Adam Sroka

Philip Ballentine

Followers

Posts

Engagements

Likes

Performance ScorePhilip Ballentine's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Adam Sroka

Philip Ballentine

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Philip Ballentine's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScorePhilip Ballentine's LinkedIn Performance