The use of cloud based machine learning to predict outcome in intracerebral haemorrhage without explicit programming expertise
2024

Using Cloud-Based Machine Learning to Predict Outcomes in Intracerebral Hemorrhage

Sample size: 1000 publication Evidence: moderate

Author Information

Author(s): Ajay Hegde, Deepu Vijaysenan, Pitchaiah Mandava, Girish Menon

Primary Institution: Manipal Academy of Higher Education, Manipal

Hypothesis

Can a cloud-based machine learning tool predict outcomes in intracerebral hemorrhage without requiring programming expertise?

Conclusion

The study found that machine learning models can predict outcomes in intracerebral hemorrhage more accurately than traditional logistic regression models.

Supporting Evidence

  • Machine learning models achieved an AUC ROC of 0.86 and an accuracy of 75.7%.
  • Logistic regression models had an AUC ROC of 0.74 and an accuracy of 73.8%.
  • The study demonstrated that machine learning can be applied by clinicians without programming skills.

Takeaway

This study shows that doctors can use a simple online tool to predict how well patients will do after a brain bleed, even if they don't know how to code.

Methodology

The study used a dataset of 1000 patients with spontaneous intracerebral hemorrhage, applying machine learning and logistic regression models to predict outcomes based on 17 variables.

Potential Biases

The automated nature of the machine learning process may introduce variability in results across different training sessions.

Limitations

The study was conducted at a single institution and may not be generalizable to other populations.

Participant Demographics

The cohort included 1000 patients, predominantly elderly, with a mean age of 58.34 years, and a male to female ratio of 701:299.

Statistical Information

P-Value

<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1007/s10143-024-03115-3

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication