#DataHarmonization

Journal for the Measurement of Physical Behaviour

@jmpbjournal.bsky.social

2 months ago

🤝 Wearables don’t always agree, but what if one metric could harmonize data across research and consumer devices?

📰 Details here: doi.org/10.1123/jmpb...

@physactivityed.bsky.social
#WearableTech #PhysicalActivityResearch #DataHarmonization #SensorData #PediatricHealth #DataScience #DigitalHealth

TERN Australia

@tern-aus.bsky.social

3 months ago

🎤 Dr Eleanor Velasquez and Elisa Girola from TERN presented at #ESA2025. Eleanor discussed TERN's new education strategy and projects that integrate #ecosystemscience with creative practise and community engagement. Elisa introduced a new tutorial on #dataharmonization.

Matasoft

@matasoft.bsky.social

6 months ago

Conduct HR surveys or customer feedback? Automate text analysis and topic clustering in bulk spreadsheets using cutting-edge LLM-powered workflows.
🔗 matasoft.hr/qtrendcontro...
#HRAutomation #NLP #SurveyTools #DataHarmonization #Automation #SmartTools #LLM #CloudComputing #OnPremAI #ScalableAI

Matasoft

@matasoft.bsky.social

6 months ago

Hate wrangling spreadsheets with different data schemas? (Un)Perplexed Spready normalizes structures and names, harmonizing workbooks in bulk.
🔗 matasoft.hr/qtrendcontro...
#DataHarmonization #Automation #SmartTools #LLM #CloudComputing #OnPremAI #ScalableAI #BigData #DataProcessing #AI #Data

JMIR Publications

@jmirpub.bsky.social

6 months ago

Automated Data Harmonization in Clinical Research: Natural Language Processing Approach Background: Integrating data is essential for advancing clinical and epidemiological research. However, because datasets often describe variables (e.g., demographic, health conditions, etc.) in diverse ways, the process of integrating and harmonizing variables from research studies remains a major bottleneck. Objective: The objective was to assess a natural language processing (NLP)-based method to automate variable harmonization to achieve a scalable approach to integration of multiple datasets. Methods: We developed a fully connected neural network (FCN) method, enhanced with contrastive learning, using domain-specific embeddings from the BioBERT language representation model, using three cardiovascular datasets: the Atherosclerosis Risk in Communities (ARIC) study, the Framingham Heart Study (FHS) and the Multi-Ethnic Study of Atherosclerosis (MESA). We used metadata variable descriptions and curated harmonized concepts as ground truth. We framed the problem as a paired sentence classification task. The accuracy of this method was compared to a logistic regression baseline method. To assess the generalizability of the trained models, we also evaluated their performance by separating the three datasets when preparing the training and validation sets. Results: The newly developed fully connected neural network (FCN) achieved a top-5 accuracy of 98.95% (95% CI: 98.31%-99.47%) and an AUC of 0.990 (95% CI: 0.988-0.991), outperforming the standard logistic regression model, which exhibited a top-5 accuracy of 22.23% (95% CI: 19.91% - 24.87%) and an AUC of 0.824 (95% CI: 0.815 – 0.834). The contrastive learning enhancement also outperformed the logistic regression model, although slightly below the base FCN model, exhibiting a top-5 accuracy of 89.88% (95% CI: 87.88% - 91.68%) and an AUC of 0.977 (95% CI: 0.975 – 0.979). Conclusions: This novel approach provides a scalable solution for harmonizing metadata across large-scale cohort studies. The proposed method significantly enhances the performance over the baseline method by utilizing learned representations to categorize harmonized concepts more accurately for cohorts in cardiovascular disease and stroke.

JMIR Formative Res: Automated Data Harmonization in Clinical Research: Natural Language Processing Approach #DataHarmonization #ClinicalResearch #NaturalLanguageProcessing #NLP #MachineLearning

DataPrudence

@dataprudence.bsky.social

8 months ago

Merging biological datasets like public, proprietary, or platform-specific is no simple task.

It takes real expertise to resolve inconsistencies, integrate them seamlessly, and extract insights.

#bioinformatics #computationalbiology #dataintegration #dataharmonization

Abhishek Jha

@ajelucidata.bsky.social

8 months ago

All normalized to biomedical ontologies, such as MONDO and UBERON.

All traceable to the source.

Read the full preprint - biorxiv.org/content/10.1...

#FAIRdata #metadata #biomedicalAI #healthcaredata #dataharmonization #AI

CanPath - Canadian Partnership for Tomorrow's Health

@canpath.bsky.social

9 months ago

Lessons from CanPath on demystifying data harmonization - CanPath - Canadian Partnership for Tomorrow’s Health Data harmonization is essential to produce multi-cohort research. Learn more about best practices for harmonizing large-scale cohort data.

TOMORROW: Learn how Maelstrom Research tackles data harmonization using CanPath as a case study.

🗓️ June 10 | 🕐 1 PM EDT

🔗 Register: canpath.ca/2025/05/less...
#DataHarmonization #HealthData #CohortResearch

CanPath - Canadian Partnership for Tomorrow's Health

@canpath.bsky.social

10 months ago

CanPath Webinar: Lessons from CanPath on demystifying data harmonization. Dr. Isabel Fortier, Principal Investigator, Maelstrom Research. Anouar Nechba, Project Manager, Maelstrom Research. Tuesday, June 10, 2025. 1:00 pm - 2:00 pm EDT.

Working with multi-regional data? 🗺️

Learn how Maelstrom Research tackles data harmonization using CanPath as a case study.

📅 June 10 | 🕐 1 PM EDT

🔗 Register >> us02web.zoom.us/webinar/regi...

#HealthData #DataHarmonization #CohortResearch

Lex Maliga Davis (She/Her/Hers)

@lexmaligadavis.bsky.social

1 year ago

Check out the newest ODC-TBI blog post about the most recent CDE policy!

odc-tbi.org/about/odc_tb...

#commondataelements #ocd-tbi #datasharing #dataharmonization