What question did this study set out to answer?

This research evaluates methods for enhancing accuracy in medical text classification using case narratives.

December 12, 2025Scientific ReportsOpen Access

An empirical evaluation of dimensionality reduction and class balancing for medical text classification

View Full Paper

Ask AI

Bookmark

Authors

Empirical analysis shows dimensionality reduction improves decision quality in medical text classification.

This research evaluates methods for enhancing accuracy in medical text classification using case narratives.
Employed a continuum-reduction model to lessen dimensionality of clinical text data.
Utilized manifold-learning techniques including Principal Component Analysis and Synthetic Minority Over-sampling Technique.
Conducted experiments on the MTSamples corpus using 5-fold cross-validation.
Achieved 91.2% accuracy and a 6.4% macro-F gain over the baseline.
Reduced model training time by 42% compared to unreduced baselines, improving efficiency.

Jamil et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

December 12, 2025Scientific ReportsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Empirical analysis shows dimensionality reduction improves decision quality in medical text classification.

This research evaluates methods for enhancing accuracy in medical text classification using case narratives.
Employed a continuum-reduction model to lessen dimensionality of clinical text data.
Utilized manifold-learning techniques including Principal Component Analysis and Synthetic Minority Over-sampling Technique.
Conducted experiments on the MTSamples corpus using 5-fold cross-validation.
Achieved 91.2% accuracy and a 6.4% macro-F gain over the baseline.
Reduced model training time by 42% compared to unreduced baselines, improving efficiency.

Jamil et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark