Icon

assessment2

Data Processing Pipeline Data Cleaning
The top 20 ICD-10 diagnosis codes ranked by total Finished Consultant Episodes, disaggregated by sex, enabling identification of gender-specific admission patterns
The admission type chart (Figure 3) reveals the proportion of emergency versus elective activity per diagnosis, highlighting conditions driving unplanned care demand.
k-Means clustering (k=4) was applied following Z-score normalisation to ensure equal feature contribution.
A Decision Tree classifier was trained using a 70/30 stratified train-test split to predict whether a diagnosis code exhibits above-average spell duration.
CSV Reader
Column Filter
String to Number
Missing Value
Row Filter
Pivot
Missing Value
Column Filter
Normalizer
Scorer
k-Means
Decision Tree Learner
Decision Tree Predictor
Row Filter
Row Filter
Row Filter
Bar Chart
Column Filter
Color Manager
Scatter Plot
Row Filter
Bar Chart
Row Filter
String to Number
Column Filter
String to Number
Row Filter
Top k Row Filter
Column Filter
Rule Engine
Row Filter
Row Filter
Bar Chart
Table Partitioner
Column Filter
Top k Row Filter
Column Filter
String to Number

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: 3rigx
Created at: 2026-04-18
On NodePit since: 2026-04-30
Last update: 2026-04-30
Created with KNIME version: v5.10.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!