Dynamic Mortality Risk Prediction in Myelodysplastic Syndromes Using Longitudinal Clinical Data
Jonathan Bobak, Philipp Spohr, Sarah Richter, Alexander Streuer, Felicitas Isabel Schulz, Corinna Strupp, Catharina Gerhards, Nanni Schmitt, Thomas Luft, Sascha Dietrich, Ulrich Germing, Gunnar W. Klau · 2025
Read Dynamic Mortality Risk Prediction in Myelodysplastic Syndromes Using Longitudinal Clinical Data by Jonathan Bobak, Philipp Spohr, Sarah Richter, Alexander Streuer, Felicitas Isabel Schulz, Corinna Strupp, Catharina Gerhards, Nanni Schmitt, Thomas Luft, Sascha Dietrich, Ulrich Germing, Gunnar W. Klau (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-12727070.txt.
Description
Jonathan Bobak and co-authors build, in a 2025 study, a tool that updates death-risk estimates for patients with myelodysplastic syndromes as their disease unfolds. These bone marrow disorders follow very different courses, from slow watch-and-wait cases to ones needing stem cell transplants. Standard scores give one fixed rating at diagnosis and never change. The authors wanted a forecast that keeps learning from new blood tests and clinical data.
Their machine learning model estimates the risk of dying within one year, and it can be rerun across the whole disease course. Trained on a German registry of about a thousand patients, it held up in two outside hospital groups. It beat a diagnosis-only baseline and gave sound estimates within the first ninety days. The features it leaned on made clinical sense, which the authors take as a good sign for trust.
Catalog record
| CREATOR | Jonathan Bobak, Philipp Spohr, Sarah Richter, Alexander Streuer, Felicitas Isabel Schulz, Corinna Strupp, Catharina Gerhards, Nanni Schmitt, Thomas Luft, Sascha Dietrich, Ulrich Germing, Gunnar W. Klau |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |