Skip to main content
100%

Visualization

✓ Published0🌍 Public
Aandressarg
Last edited Aug 29, 2018
Created on Aug 29, 2018

This interactive scatter plot visualizes the probability of mortality for ICU patients at Beth Israel Deaconess Medical Center (2001–2012), based on anonymized medical records. Each dot represents a patient, positioned by age and length of ICU stay, with hover interactions revealing patient details. A legend grouped by ICU type allows users to toggle between deceased and surviving patients, with filled markers indicating mortality. The visualization uses a subset of the public MIMIC ICU dataset, with mortality probabilities predicted via XGBoost. The SVG-based animation updates the scatter plot dynamically when legend categories are selected, enabling comparison between actual outcomes and model predictions across different ICU units.

AI-generated description

Interactive Scatter Plot/Legend

Description

This scatter plot was built to help visualize probability of mortality associated with patients at the Beth Israel Deaconess Medical Center between 2001 and 2012, based on their anonymized medical records.

Interpretation

Hovering over each dot shows information associated with each patient. By clicking on the legend (divided by ICU), one can see if the patient is deceased or not (filled represents mortality) and compare that against what our model's predicted probability.

Data

The data used is a subset of the MIMIC ICU Data, which is publicly available. XGBoost was used to predict the mortality rate.

Inspired by

Built with blockbuilder.org

forked from <a href='http://bl.ocks.org/floofydugong/'>floofydugong</a>'s block: <a href='http://bl.ocks.org/floofydugong/9c94ab01d8c3ed8ea3821d4a7e119b07'>Interactive Scatter Plot/Legend</a>

gpl-3.0 Licensed

Similar vizzes

Loading thumbnail…

Visualization

This interactive scatter plot visualizes ICU patient mortality risk at Beth Israel Deaconess Medical Center (2001–2012). Each dot is a patient, positioned by age and length of stay, with color indicating ICU type. Hovering reveals patient details, while clicking the legend toggles mortality status—filled dots represent deceased patients—and compares actual outcomes with XGBoost-predicted probabilities. The visualization is rendered in SVG with animation, using publicly available MIMIC ICU data.

GGerardoFurtado
96% match
Loading thumbnail…

Visualization

This interactive scatter plot visualizes patient mortality probability at Beth Israel Deaconess Medical Center, using age, ICU length of stay, and predicted mortality from anonymized MIMIC ICU data. Dots are colored by ICU unit, with size reflecting length of stay, and hovering reveals tooltips with patient details. The view supports zooming and panning via `d3.behavior.zoom`, with a legend that filters dots by care unit on click, including toggling between deceased (filled) and surviving patients. Built with D3.js, the chart displays SVG circles and axes, with buttons to reset zoom or switch the x-axis to length of stay.

AAndresAnayaIsaza
94% match
Loading thumbnail…

Visualization

This interactive scatter plot visualizes patient mortality probability data from the Beth Israel Deaconess Medical Center’s MIMIC ICU dataset, showing age against predicted mortality probability with circle size representing ICU length of stay. The code uses D3.js with `d3.svg.axis`, `d3.behavior.zoom`, and `d3-tip` for tooltips, rendering circles as SVG elements. A clickable legend filters the display by ICU unit, while filled versus unfilled markers indicate actual patient mortality via the `hospital_expire_flag` field. The CSV data includes anonymized patient records with age, stay duration, and care unit classifications.

AAjayyy
93% match
Loading thumbnail…

Visualization

This interactive scatter plot visualizes patient mortality probability against age, with the size of each dot representing the patient’s length of stay in the ICU. The visualization, built with D3.js, uses the `d3.tip` library to display tooltips on hover and `d3.behavior.zoom` for panning and zooming. A clickable legend allows filtering by ICU type, while filled dots indicate deceased patients. The data comes from the MIMIC ICU dataset and was used with XGBoost to predict mortality rates. The rendering uses SVG with animation for interactive transitions.

TThanaporn-sk
90% match
Loading thumbnail…

ICU Mortality/Event Visualization

This visualization tracks ICU patients’ predicted mortality risk over the course of their stay, with each dot representing a measurement taken at a given relative time. The y-axis shows the model’s predicted probability of death, and the x-axis shows relative time from admission. Each dot is colored by procedure category, and hovering over a dot reveals a tooltip with the patient ID, procedure type, relative time, and absolute time in hours. The chart includes a legend for procedure categories and uses an SVG line-and-dot layout with D3 v4. Animation is not present in the rendering despite the metadata listing it.

Aallenwko
84% match
Loading thumbnail…

ICE-6 Impact of Cancer Deaths 2019

This interactive visualization displays cancer mortality trends in the United States from 1990 to 2019, plotting individual yearly death counts for fifteen distinct cancer types as colored dots. The scatterplot uses SVG circles rendered through React and D3, with each cancer type assigned a unique color and an interactive tooltip revealing exact death numbers on hover. Built with D3 scales (`scaleTime`, `scaleLinear`), axes (`axisLeft`, `axisBottom`), and event handlers, the chart reads from a CSV dataset filtered for USA records, making temporal patterns across cancer categories immediately comparable.

AAsrar Al Qassem
68% match
Loading thumbnail…

Reusable D3 Scatter Plot

This animated scatter plot cycles through cancer types—liver, breast, prostate, and thyroid—displaying death rates over time using the Iris Dataset-inspired structure. Built with reusable D3.js components and SVG rendering, the visualization updates every 2 seconds, transitioning between datasets while updating the title and axis labels. Symbols vary by cancer type (circle, square, star) and axes represent years and number of deaths, with smooth transitions on each refresh.

AAsrar Al Qassem
68% match
Loading thumbnail…

Fork of Bonus ICE Scatter plot using D3.js

This example visualizes heart patient statistics across countries using an interactive 3D scatter plot. It displays two traces: death cases in red and active cases in blue, plotted against country name and patient category. The visualization uses Plotly.js within an HTML page, loading data from a CSV file via D3.js’s `d3.csv` function. D3’s `unpack` helper extracts columns for the x, y, and z axes, while Plotly’s `newPlot` renders the scatter3d chart with custom marker styling and opacity.

SSurikanti Swathi
68% match