Explainable Deep Learning Model for Predicting Overall Survival in Patients Receiving Palliative Radiotherapy for Bone Metastases
Yui Watanabe, Takuya Tomoda, Akiko Iwata, Hirokazu Matsuno, Hiroto Hayakawa, Takeshi Nagata · 2026
Read Explainable Deep Learning Model for Predicting Overall Survival in Patients Receiving Palliative Radiotherapy for Bone Metastases by Yui Watanabe, Takuya Tomoda, Akiko Iwata, Hirokazu Matsuno, Hiroto Hayakawa, Takeshi Nagata (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/pmc-13605896.txt.
Description
Yui Watanabe and co-authors predict survival after comfort radiation for bone-spread cancer in a 2026 study. Knowing how long a patient may live guides dose and care choices. Deep learning could beat classic models, but doctors need to see its reasons.
Records of 472 patients treated from 2013 to 2024 fed the model. Fourteen baseline traits, including planned dose, went in. A DeepSurv model was checked against standard and penalized Cox models on the same splits. Scores covered ranking skill, error, and calibration at one year. Two explanation tools then showed which traits drove each forecast. The study tests whether a flexible model adds real value over the clinic's standard math.
Catalog record
| CREATOR | Yui Watanabe, Takuya Tomoda, Akiko Iwata, Hirokazu Matsuno, Hiroto Hayakawa, Takeshi Nagata |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |