# US 2019/0244712 A1 · Drug Dosing Recommendation

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

- Number: US 2019/0244712 A1
- Document ID: US20190244712A1
- Status: Published application
- Kind: A1
- Application number: 16/318,753
- Filed: 2017-07-14
- Published: 2019-08-08
- Earliest claimed: 2016-07-18
- Assignees: Fresenius Medical Care Deutschland GmbH
- Applicants: Fresenius Medical Care Deutschland GmbH
- Inventors: Carlo Barbieri; Flavio Mari
- Web page: https://patentgrep.com/patent/US20190244712A1

## CPC

- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H 40/63: for local operation
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/50: for simulation or modelling of medical disorders
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

The present disclosure relates to a method for calculating or estimating at least one medical value based on several input values using artificial intelligence.

## Claims

### Claim at position 1

1-15. (canceled)

### Claim 16

A method for calculating or estimating at least one medical value based on several input values using artificial intelligence, the method comprising:
simulating effects of several doses of a drug; and
selecting a dose of the several doses of the drug that provided optimal performance according to a reward function.

### Claim 17 (depends on 16)

The method according to claim 16, wherein the at least one medical value is a recommended drug dosage.

### Claim 18 (depends on 17)

The method according to claim 17, wherein the recommended drug dosage is recommended to determine that a certain measurable diagnostic value remains in or moves towards a certain target range.

### Claim 19 (depends on 17)

The method according to claim 17, wherein the recommended drug dosage concerns an erythropoiesis stimulating agent.

### Claim 20 (depends on 19)

The method according to claim 19, wherein the erythropoiesis stimulating agent is erythropoietin or iron.

### Claim 21 (depends on 19)

The method according to claim 19, wherein the erythropoiesis stimulating agent is erythropoietin and iron.

### Claim 22 (depends on 18)

The method according to claim 18, wherein the diagnostic value is a haemoglobin level.

### Claim 23 (depends on 16)

The method according to claim 16 comprising using an artificial neural network.

### Claim 24 (depends on 23)

The method according to claim 23, wherein the artificial neural network is a multilayer perceptron feed-forward artificial neural network.

### Claim 25 (depends on 23)

The method according to claim 23, wherein the artificial neural network has been trained using historical patient data.

### Claim 26 (depends on 25)

The method according to claim 25, wherein the historical patient data is dialysis patient data.

### Claim 27 (depends on 25)

The method according to claim 25, wherein the training of the artificial neural network is adaptive.

### Claim 28 (depends on 16)

The method according to claim 16, wherein the method is a computer implemented method and the computer implemented method is certified as a medical device

### Claim 29

A device configured to execute a method, the method comprising:
simulating effects of several doses of a drug; and
selecting a dose of the several doses of the drug that provided optimal performance according to a reward function.

### Claim 30

A drug in a dosage recommended by a method, the method comprising:
simulating effects of several doses of a drug; and
selecting a dose of the several doses of the drug that provided optimal performance according to a reward function.

### Claim 32

A non-transitory computer-readable storage medium with an executable program stored thereon, wherein the program instructs a programmable computer system to execute a method comprising:
simulating effects of several doses of a drug; and
selecting a dose of the several doses of the drug that provided optimal performance according to a reward function.
