Unlocking precision diagnostics: A multimodal framework integrating metabolomics with advanced machine learning techniques
Parisa Shahnazari, Kaveh Kavousi, Hamid Reza Khorram Khorshid, Bahram Goliaei, Reza M. Salek, Ch Ratnasekhar, Kwang-Sig Lee, Kwang-Sig Lee · 2026
Read Unlocking precision diagnostics: A multimodal framework integrating metabolomics with advanced machine learning techniques by Parisa Shahnazari, Kaveh Kavousi, Hamid Reza Khorram Khorshid, Bahram Goliaei, Reza M. Salek, Ch Ratnasekhar, Kwang-Sig Lee, Kwang-Sig Lee (2026) 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/PMC13268153.txt.
Description
Parisa Shahnazari and colleagues present a 2026 study on merging chemical fingerprint data to improve cancer diagnosis. Metabolomics reads the small chemicals in a sample; three instrument types each catch a different slice. Combining them should sharpen diagnosis, but the best merge method is unsettled. The team tested five integration strategies on data from the three instrument types.
Two methods stood out. Deep transfer learning, which pre-trains a neural network then fine-tunes it, and multiple kernel learning, which blends several similarity measures, both beat single-instrument analysis on accuracy and reliability. Feature analysis flagged several raised fats and chemicals in HER2-positive cases, and a few lowered ones. The authors offer the framework as a flexible route to precise diagnosis and marker hunting across mixed data sets.
Catalog record
| CREATOR | Parisa Shahnazari, Kaveh Kavousi, Hamid Reza Khorram Khorshid, Bahram Goliaei, Reza M. Salek, Ch Ratnasekhar, Kwang-Sig Lee, Kwang-Sig Lee |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 131225 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |