| Accession |
PRJCA007255 |
| Title |
Dynamic forecasting of severe acute graft-versus-host disease after transplantation |
| Relevance |
Medical |
| Data types |
clinical data
|
| Organisms |
Homo
|
| Description |
To anticipate critical events, clinicians intuitively rely on multidimensional time-series data. It is, however, difficult to model such decision process using machine learning (ML), since real-world medical records often have irregular missing and data sparsity in both feature and longitudinal dimensions. Here we propose a nonparametric approach that updates risk score in real time and can accommodate sampling heterogeneity, using forecasting of severe acute graft-versus-host disease (aGVHD) as the study case. The area under the receiver operator characteristic curve (AUC) rose steadily after transplantation and peaked at >0.7 in both adult and pediatric cohorts. Various numerical experiments provided guidelines for future applications. |
| Sample scope |
Not applicable |
| Release date |
2022-02-17 |
| Publication |
| PubMed ID |
Article title |
Journal name |
DOI |
Year |
| 38177449
|
Dynamic forecasting of severe acute graft-versus-host disease after transplantation
|
Nature Computational Science
|
10.1038/s43588-022-00213-4
|
2022
|
|
|
| Grants |
| Agency |
program |
Grant ID |
Grant title |
| State Key Laboratory of Experimental Hematology
|
|
Z20-01
|
|
| Chinese Academy of Medical Sciences (CAMS)
|
|
2020-I2M-CT-B-089
|
|
| Tianjin Science and Technology Plan
|
|
20ZYJDSY00010
|
|
|
|
| Submitter |
Xueou
Liu (liuxueou@ihcams.ac.cn)
|
| Organization |
Institute of Hematology and Blood Diseases Hospital, Chinese Academy of Medical Sciences |
| Submission date |
2021-11-18 |
