HMLA: A hybrid machine learning approach for enhancing stroke prediction models with missing data imputation techniques
M Sheetal Singh, Khelchandra Thongam, Krishna Kumar, Prakash Choudhary · 2025
Read HMLA: A hybrid machine learning approach for enhancing stroke prediction models with missing data imputation techniques by M Sheetal Singh, Khelchandra Thongam, Krishna Kumar, Prakash Choudhary (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12780014.txt.
Description
Sheetal Singh, Khelchandra Thongam, Krishna Kumar, and Prakash Choudhary published a machine learning study in twenty twenty-five on predicting stroke while coping with patchy medical records. Missing values and irrelevant features quietly sabotage clinical prediction models. Their hybrid approach attacks both problems before training the predictor.
An information measure first selected the features that matter, and a nearest-neighbor method filled the gaps in the Cardiovascular Health Study data. A deep neural network then classified stroke risk. Nested cross-validation guarded against leakage and optimistic scores. The framework reached about ninety-four percent accuracy with strong precision and sensitivity. The authors are candid that testing stayed internal, so outside validation is still owed.
Catalog record
| CREATOR | M Sheetal Singh, Khelchandra Thongam, Krishna Kumar, Prakash Choudhary |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |