# US 2026/0100265 A1 · Using machine-learning language processing model for radiotherapy treatment planning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0100265 A1
- Document ID: US20260100265A1
- Status: Published application
- Kind: A1
- Application number: 18/907,368
- Filed: 2024-10-04
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Applicants: Siemens Healthineers International AG
- Inventors: Jarkko Peltola; Martin Sabel; Esa Kuusela; Elena Czeizler; Ismo Hautala; Kellee Donnelly
- Web page: https://patentgrep.com/patent/US20260100265A1

## CPC

- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- A61N 5/1031: {using a specific method of dose optimization}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G16H 70/20: relating to practices or guidelines
- A61N 2005/1074: {Details of the control system, e.g. user interfaces}
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)

## Abstract

Disclosed herein are methods and systems for using machine-learning language processing models to provide contextual data while a medical professional is using a radiotherapy treatment planning user interface to generate a treatment plan for a patient. One method comprises monitoring, by at least one processor, a radiotherapy treatment planning user interface comprising an interaction interface to identify one or more radiotherapy planning attributes associated with a radiotherapy treatment of a patient via a radiotherapy treatment planning computer model; receiving, by at least one processor from the c, an indication associated with the radiotherapy planning attribute; responsive to the indication satisfying a threshold: executing, by at least one processor, a machine-learning language processing model to generate contextual data associated with the one or more radiotherapy planning attributes; and presenting, by at least one processor, the contextual data within the radiotherapy treatment planning user interface.

## Claims

### Claim 1

A method comprising:
monitoring, by at least one processor, a radiotherapy treatment planning user interface comprising an interaction interface to identify one or more radiotherapy planning attributes associated with a radiotherapy treatment of a patient via a radiotherapy treatment planning computer model;
receiving, by at least one processor from the radiotherapy treatment planning computer model, an indication corresponding to at least one missing data point required for generating a patient specific radiotherapy treatment plan, the at least one missing data point associated with the one or more radiotherapy planning attributes; and
responsive to the indication satisfying a threshold:
executing, by at least one processor, a machine-learning language processing model to generate contextual data associated with the one or more radiotherapy planning attributes;
presenting, by at least one processor, the contextual data within the radiotherapy treatment planning user interface;
updating, by at least one processor, at least one radiotherapy planning attribute in the radiotherapy treatment planning computer model based on the contextual data; and
generating, by at least one processor, an updated patient specific radiotherapy treatment plan based on the updated radiotherapy planning attribute.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The method of claim 1, wherein the indication corresponds to detecting that the one or more radiotherapy planning attributes would cause at least one attribute of the radiotherapy treatment to violate a plan objective.

### Claim 4 (depends on 1)

The method of claim 1, wherein presenting the contextual data corresponds to outputting an electronic document corresponding to at least one of an instruction manual, a setting or guideline specific to the radiotherapy treatment planning computer model, or a treatment planning guideline.

### Claim 5 (depends on 1)

The method of claim 1, wherein the contextual data is specific to a clinic implementing the radiotherapy treatment of the patient.

### Claim 6 (depends on 1)

The method of claim 1, wherein the contextual data comprises a visualization of the radiotherapy treatment of the patient.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
recalibrating, by at least one processor, the machine-learning language processing model using an input corresponding to a quality of the contextual data.

### Claim 8

A system comprising:
a non-transitory computer-readable medium having non-transitory instructions that when executed, cause a processor to:
monitor a radiotherapy treatment planning user interface comprising an interaction interface to identify one or more radiotherapy planning attributes associated with a radiotherapy treatment of a patient via a radiotherapy treatment planning computer model;
receiving, by at least one processor from the radiotherapy treatment planning computer model, an indication corresponding to at least one missing data point required for generating a patient specific radiotherapy treatment plan, the at least one missing data point associated with the one or more radiotherapy planning attributes; and
responsive to the indication satisfying a threshold:
execute a machine-learning language processing model to generate contextual data associated with the one or more radiotherapy planning attributes;
present the contextual data within the radiotherapy treatment planning user interface;
update at least one radiotherapy planning attribute in the radiotherapy treatment planning computer model based on the contextual data; and
generate an updated patient specific radiotherapy treatment plan based on the updated radiotherapy planning attribute.

### Claim 9

(canceled)

### Claim 10 (depends on 8)

The system of claim 8, wherein the indication corresponds to detecting that the one or more radiotherapy planning attributes would cause at least one attribute of the radiotherapy treatment to violate a plan objective.

### Claim 11 (depends on 8)

The system of claim 8, wherein presenting the contextual data corresponds to outputting an electronic document corresponding to at least one of an instruction manual, a setting or guideline specific to the radiotherapy treatment planning computer model, or a treatment planning guideline.

### Claim 12 (depends on 8)

The system of claim 8, wherein the contextual data is specific to a clinic implementing the radiotherapy treatment of the patient.

### Claim 13 (depends on 8)

The system of claim 8, wherein the contextual data comprises a visualization of the radiotherapy treatment of the patient.

### Claim 14 (depends on 8)

The system of claim 8, wherein the instructions further cause the processor to:
recalibrate the machine-learning language processing model using an input corresponding to a quality of the contextual data.

### Claim 15

A system comprising:
a machine-learning language processing model; and
a processor in communication with the machine-learning language processing model, the processor configured to:
monitor a radiotherapy treatment planning user interface comprising an interaction interface to identify one or more radiotherapy planning attributes associated with a radiotherapy treatment of a patient via a radiotherapy treatment planning computer model;
receiving, by at least one processor from the radiotherapy treatment planning computer model, an indication corresponding to at least one missing data point required for generating a patient specific radiotherapy treatment plan, the at least one missing data point associated with the one or more radiotherapy planning attributes; and
responsive to the indication satisfying a threshold:
execute the machine-learning language processing model to generate contextual data associated with the one or more radiotherapy planning attributes;
present the contextual data within the radiotherapy treatment planning user interface;
update at least one radiotherapy planning attribute in the radiotherapy treatment planning computer model based on the contextual data; and
generate an updated patient specific radiotherapy treatment plan based on the updated radiotherapy planning attribute.

### Claim 16

(canceled)

### Claim 17 (depends on 15)

The system of claim 15, wherein the indication corresponds to detecting that the one or more radiotherapy planning attributes would cause at least one attribute of the radiotherapy treatment to violate a plan objective.

### Claim 18 (depends on 15)

The system of claim 15, wherein presenting the contextual data corresponds to outputting an electronic document corresponding to at least one of an instruction manual, a setting or guideline specific to the radiotherapy treatment planning computer model, or a treatment planning guideline.

### Claim 19 (depends on 15)

The system of claim 15, wherein the contextual data is specific to a clinic implementing the radiotherapy treatment of the patient.

### Claim 20 (depends on 15)

The system of claim 15, wherein the contextual data comprises a visualization of the radiotherapy treatment of the patient.
