Logical Analysis of Data (LAD) model for the early diagnosis of acute ischemic stroke
2008

Using Blood Samples to Diagnose Ischemic Stroke

Sample size: 48 publication 10 minutes Evidence: moderate

Author Information

Author(s): Reddy Anupama, Wang Honghui, Yu Hua, Bonates Tiberius O, Gulabani Vimla, Azok Joseph, Hoehn Gerard, Hammer Peter L, Baird Alison E, Li King C

Primary Institution: Rutgers Center for Operations Research, RUTCOR

Hypothesis

Can biomarkers from blood samples accurately diagnose acute ischemic stroke?

Conclusion

Three biomarkers were identified that can detect ischemic stroke with an accuracy of 75%.

Supporting Evidence

  • The classification model achieved 75% accuracy on an independent validation set.
  • The predictive model outperformed alternative algorithms in predicting stroke severity.
  • The study identified a small set of 3 peaks as significant biomarkers.

Takeaway

Doctors can use a simple blood test to help tell if someone is having a stroke.

Methodology

The study used mass spectrometry to analyze blood samples from 48 stroke patients and 32 controls to identify biomarkers.

Potential Biases

Potential bias due to exclusion of patients with certain conditions.

Limitations

The study focused only on ischemic stroke and did not compare with hemorrhagic stroke.

Participant Demographics

Stroke patients had a median age of 78 years, with 52% male; controls had a median age of 76 years, with 34% male.

Statistical Information

P-Value

0.05

Confidence Interval

95%

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1472-6947-8-30

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication