Optimal dose escalation methods using deep reinforcement learning in phase I oncology trials
In phase I trials of a novel anticancer drug, one of the most important objectives is to identify the maximum tolerated dose (MTD). To this end, a number of methods have been proposed and evaluated under various scenarios. However, the percentages of correct selection (PCS) of MTDs using previous methods are insufficient to determine the dose for late-phase trials. The purpose of this study is to construct an action rule for escalating or de-escalating the dose and continuing or stopping the trial to increase the PCS as much as possible. We show that deep reinforcement learning with an appropriately defined state, action, and reward can be used to construct such an action selection rule. The simulation study shows that the proposed method can improve the PCS compared with the 3 + 3 design, CRM, BLRM, BOIN, mTPI, and i3 + 3 methods.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
---|---|
Enthalten in: |
Journal of biopharmaceutical statistics - 33(2023), 5 vom: 03. Sept., Seite 639-652 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Matsuura, Kentaro [VerfasserIn] |
---|
Links: |
---|
Themen: |
Adaptive design |
---|
Anmerkungen: |
Date Completed 22.08.2023 Date Revised 29.08.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1080/10543406.2023.2170402 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM352283491 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM352283491 | ||
003 | DE-627 | ||
005 | 20231226053348.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1080/10543406.2023.2170402 |2 doi | |
028 | 5 | 2 | |a pubmed24n1174.xml |
035 | |a (DE-627)NLM352283491 | ||
035 | |a (NLM)36717962 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Matsuura, Kentaro |e verfasserin |4 aut | |
245 | 1 | 0 | |a Optimal dose escalation methods using deep reinforcement learning in phase I oncology trials |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 22.08.2023 | ||
500 | |a Date Revised 29.08.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a In phase I trials of a novel anticancer drug, one of the most important objectives is to identify the maximum tolerated dose (MTD). To this end, a number of methods have been proposed and evaluated under various scenarios. However, the percentages of correct selection (PCS) of MTDs using previous methods are insufficient to determine the dose for late-phase trials. The purpose of this study is to construct an action rule for escalating or de-escalating the dose and continuing or stopping the trial to increase the PCS as much as possible. We show that deep reinforcement learning with an appropriately defined state, action, and reward can be used to construct such an action selection rule. The simulation study shows that the proposed method can improve the PCS compared with the 3 + 3 design, CRM, BLRM, BOIN, mTPI, and i3 + 3 methods | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Adaptive design | |
650 | 4 | |a Clinical trial | |
650 | 4 | |a Dose-finding | |
650 | 4 | |a Maximum tolerated dose | |
650 | 4 | |a Optimal design | |
650 | 7 | |a Antineoplastic Agents |2 NLM | |
700 | 1 | |a Sakamaki, Kentaro |e verfasserin |4 aut | |
700 | 1 | |a Honda, Junya |e verfasserin |4 aut | |
700 | 1 | |a Sozu, Takashi |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of biopharmaceutical statistics |d 1991 |g 33(2023), 5 vom: 03. Sept., Seite 639-652 |w (DE-627)NLM012811432 |x 1520-5711 |7 nnns |
773 | 1 | 8 | |g volume:33 |g year:2023 |g number:5 |g day:03 |g month:09 |g pages:639-652 |
856 | 4 | 0 | |u http://dx.doi.org/10.1080/10543406.2023.2170402 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 33 |j 2023 |e 5 |b 03 |c 09 |h 639-652 |