KESER mental health
Electronic Health Records, or EHRs, hold a wealth of data and can be invaluable for mental health-related medical research. The challenge, however, is that the large number of codes representing health conditions, laboratory tests, medication and procedures makes it tricky to pinpoint relevant information. To address this, we introduce the Knowledge Graph for Mental Health.
Instead of using specific patient data, our method transforms these codes into embedding vectors, which are essentially compact representations of the data.
This method doesn’t just simplify the data; it makes it easier to share across different medical institutions while maintaining patient privacy. Using these embedding vectors, we construct a clinical knowledge map, a network that shows the relationships between different health conditions and treatments. Eventually, this makes it easier for researchers to identify patterns and insights from EHRs without getting bogged down by the sheer volume of codes and without compromising on patient privacy.
Using the app
Input on the Left
Input: enter some terms in the searchbar and select some rows in the table.
Click “Deselect” to unselect all nodes or “Submit” to visualize your chosen nodes.
“Hide the labels” checkbox: controls whether node labels are displayed in the network.
“Top nodes to show” slider: to set the maximum number of nodes displayed in the network.
“Cutoff of relatedness” slider: to filter out nodes with a cosine similarity below the specified value.
“Filter nodes by category” dropdown: to select specific node categories for visualization.
- Hover the network
- hover the node
- hover the edge
- Click on the node. There will be a popup window to show the details about the clicked node:
- Table of connected nodes.
- Hierarchy of the connected nodes.
- Cosine similarity of the connected nodes.
- More details.
Download: to download the data of the network as csv.
Tutorial: a step-by-step guide.
Settings on the Right
“Network” tab: customize the colors and shapes of different node categories in the network.
“Expand groups” tab: to select various groups and expand them in the network to reveal the nodes within, allowing for a deeper exploration of the relationships between your chosen groups.