---
title: "How Imperial College London is accelerating dementia research with a modern data platform"
description: "Imperial College London’s Care Research and Technology Centre (CR&T) needed to scale Minder, a platform that combines in-home sensors, sleep monitors, and electronic health records to support dementia care and research. Growing data volumes caused competing workloads, tightly coupled storage and compute, and limited access for researchers and clinicians. The re-architected platform validates IoT data through Kubernetes, stores it in Delta Lake on Azure Data Lake Storage using bronze, silver, and anonymized gold layers, and adds Databricks analytics with Unity Catalog governance while retaining FHIR-based EHR interoperability and Kubeflow for model deployment. Research-to-production workflows, reusable pipelines, dashboards, and timestamped data improve collaboration, accessibility, and reproducibility. During migration, uptime remained 100%; new sources integrated in as little as one month, model development fell to about one month, and insights reached 581 people living with dementia in five months."
---

# How Imperial College London is accelerating dementia research with a modern data platform

[Databricks](https://yomu.fyi/company/databricks) · Kacey Hertan · Jul 7, 2026

**Type:** Problem & solution

## Summary

Imperial College London’s Care Research and Technology Centre (CR&T) needed to scale Minder, a platform that combines in-home sensors, sleep monitors, and electronic health records to support dementia care and research. Growing data volumes caused competing workloads, tightly coupled storage and compute, and limited access for researchers and clinicians. The re-architected platform validates IoT data through Kubernetes, stores it in Delta Lake on Azure Data Lake Storage using bronze, silver, and anonymized gold layers, and adds Databricks analytics with Unity Catalog governance while retaining FHIR-based EHR interoperability and Kubeflow for model deployment. Research-to-production workflows, reusable pipelines, dashboards, and timestamped data improve collaboration, accessibility, and reproducibility. During migration, uptime remained 100%; new sources integrated in as little as one month, model development fell to about one month, and insights reached 581 people living with dementia in five months.

## Context

Minder’s growth in homes, devices, data volumes, and use cases created overlapping ingestion, analytics, and real-time workloads. Storage and compute were tightly coupled in operational databases, increasing infrastructure costs, while the absence of a dedicated research environment limited access for clinicians and other non-technical stakeholders. These constraints delayed the translation of research into clinical practice.

## Approach / What changed

CR&T separated operational and research workloads by validating IoT data through Kubernetes and storing it in Delta Lake on Azure Data Lake Storage with bronze, silver, and anonymized gold layers. Databricks became the analytics environment, Unity Catalog provided fine-grained governance, and dashboards and reusable pipelines supported research-to-production workflows. Existing FHIR-based EHR interoperability and Kubeflow model deployment remained in place.

## Takeaways

- Unity Catalog applies fine-grained permissions across research partners, user roles, approval levels, and data sensitivity.
- Every IoT data point keeps its original timestamp, allowing researchers to reconstruct what a clinician saw at a past point despite continuous updates.
- The platform grew 50% month over month, while the team estimates it saved hundreds of engineering hours compared with building equivalent infrastructure from scratch.

**Tags:** [Azure](https://yomu.fyi/topic/azure), [Databricks](https://yomu.fyi/topic/databricks), [Delta Lake](https://yomu.fyi/topic/delta-lake), [Kubernetes](https://yomu.fyi/topic/kubernetes), [Unity Catalog](https://yomu.fyi/topic/unity-catalog)

- Source: [Databricks](https://www.databricks.com/blog/how-imperial-college-london-accelerating-dementia-research-modern-data-platform)
- Source URL: https://www.databricks.com/blog/how-imperial-college-london-accelerating-dementia-research-modern-data-platform
- Ingested by Yomu: 2026-08-30T16:59:03.601Z

[Read original post](https://www.databricks.com/blog/how-imperial-college-london-accelerating-dementia-research-modern-data-platform)