Figure 4. Optimal Performance Achieved with 10 Rounds and 5 Clients for Various Machine Learning Models The results of our study demonstrate a significant
improvement in classification accuracy compared to other
research approaches in the field of clinical event
classification. Our method, which incorporates federated
learning, achieved an impressive 98.9% accuracy,
outperforming all other methods investigated in this
comparison. This finding highlights the effectiveness and
potential of federated learning in enhancing the performance
of machine learning models for clinical event classification.
The superior performance of our federated learning-based
method can be attributed to its ability to leverage distributed
datasets, maintain data privacy, and facilitate collaborative
learning among multiple clients. This approach allows for
the development of robust models that can generalize better
and adapt to diverse data sources, ultimately leading to
improved classification accuracy.
Table 3. Superior Performance of Federated Learning- based Method in Clinical Event Classification Research
in [29]
Research
in [30]
Research
in [31]
Our
model
Number
of
fixtures
6
1
2
6
Vital
signs
HR, BP,
RR, SPO
BP
HR, BP
HR,
BP,
RR,
SPO
Clinical
event
Any
Any
Any
Any
Number
of normal
samples
1300
30
571
Number
of
abnormal
samples
130
30
116
Accuracy
95.5
average
94%
ROC
max 0.86
98.9
Federated
learning
No
No
No
Yes
Основной
Основной
Основной
Основной
Основной
Основной
Основной
Random
Forest
AdaBoots
Classifier
Logistic
Regression
Gaussian
SGV
Machine Learning results
Train
Test
Ruzaliev R:
Federated Learning for Clinical Event Classification Using Vital
Signs Data
2
VOLUME XX, 2023
