Back

Towards Superhuman Imitation Learning for Sequential Head-and-Neck Cancer Treatment Decisions

2025-12-15 health informatics Title + abstract only
View on medRxiv
Show abstract

We propose a simulator-driven imitation learning framework for sequential decision making in head and neck cancer (HNC) treatment. Our method, Superhuman Policy Gradient Optimization (SPGO), integrates inverse reinforcement learning principles with policy gradient updates to derive three-stage treatment policies directly from recorded physician decisions. It leverages a pre-trained clinical simulator--combining a variational autoencoder and gradient boosting models--to generate complete, tempora...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 5% 17.7%
2
npj Digital Medicine
85 training papers
Top 1% 9.0%
3
Journal of the American Medical Informatics Association
53 training papers
Top 3% 6.4%
4
Nature Communications
483 training papers
Top 16% 6.4%
5
Journal of Biomedical Informatics
37 training papers
Top 2% 6.0%
6
JAMIA Open
35 training papers
Top 3% 6.0%
7
PLOS Digital Health
88 training papers
Top 4% 6.0%
8
BMC Medical Informatics and Decision Making
36 training papers
Top 3% 5.6%
9
PLOS ONE
1737 training papers
Top 82% 5.0%
10
Computers in Biology and Medicine
39 training papers
Top 2% 3.9%
11
Journal of Medical Internet Research
81 training papers
Top 6% 3.1%
12
PLOS Computational Biology
141 training papers
Top 7% 1.9%
13
Communications Medicine
63 training papers
Top 0.7% 1.9%
14
International Journal of Medical Informatics
25 training papers
Top 4% 1.6%
15
JMIR Medical Informatics
16 training papers
Top 4% 1.6%
16
Nature Medicine
88 training papers
Top 7% 1.3%
17
BMC Medical Research Methodology
41 training papers
Top 4% 1.3%
18
Patterns
15 training papers
Top 2% 1.0%
19
Scientific Data
30 training papers
Top 4% 0.7%
20
Brain Communications
79 training papers
Top 9% 0.7%
21
JAMA Network Open
125 training papers
Top 31% 0.7%
22
Bulletin of Mathematical Biology
17 training papers
Top 1% 0.7%
23
Frontiers in Digital Health
18 training papers
Top 4% 0.7%
24
eLife
262 training papers
Top 65% 0.5%