Diagnosis and treatment recommendation using quantum computing

Patent metadata

Field	Value
Publication number	US-2023207124-A1
Application number	US-202117646252-A
Country	US
Kind code	A1
Filing date	Dec 28, 2021
Priority date	Dec 28, 2021
Publication date	Jun 29, 2023
Grant date	—

Abstract

This disclosure describes techniques for providing diagnosis and treatment recommendations using quantum computing. For example, a quantum computing device encodes diagnosis-relevant information of a patient as one or more patient diagnosis qubits. The quantum computing device implements a first quantum search algorithm using the patient diagnosis qubits to determine a diagnosis likelihood for each condition of a plurality of conditions. The quantum computing device further encodes the diagnosis data and treatment-relevant information of the patient as one or more patient treatment qubits. The quantum computing device implements a second quantum search algorithm using the treatment-relevant information of the patient to determine one or more treatment recommendations for the patient.

First claim

What is claimed is:

1 . A quantum computing device comprising:
a first quantum encoder configured to encode diagnosis-relevant information of a patient as one or more patient diagnosis qubits, wherein the diagnosis-relevant information comprises information of potential relevance to determining a diagnosis of the patient; a first quantum circuit configured to implement a first quantum search algorithm that uses the one or more patient diagnosis qubits to search within a first database for one or more entries that correspond to the diagnosis-relevant information of the patient, wherein the one or more entries that correspond to the diagnosis-relevant information of the patient comprises diagnosis data for the patient, wherein the diagnosis data for the patient comprises a likelihood for each condition of a plurality of conditions; a second quantum encoder configured to encode the one or more entries that correspond to the diagnosis data for the patient and treatment-relevant information of the patient as one or more patient treatment qubits, wherein the treatment-relevant information comprises information of potential relevance to determining a treatment of the patient; and a second quantum circuit configured to implement a second quantum search algorithm that uses the one or more patient treatment qubits to search within a second database for one or more entries that correspond to the diagnosis data for the patient and the treatment-relevant information of the patient, wherein the one or more entries that correspond to the diagnosis data for the patient and the treatment-relevant information of the patient indicates one or more treatment recommendations for the patient.

2 . The quantum computing device of claim 1 , wherein the diagnosis-relevant information of the patient comprises one or more characteristics of the patient, one or more symptoms of the patient, or medical history of the patient.

3 . The quantum computing device of claim 1 , wherein the treatment-relevant information of the patient comprises one or more of medication adherence information of the patient or medication efficacy information of the patient.

4 . The quantum computing device of claim 1 , wherein the likelihood for each condition of the plurality of conditions is computed based on the diagnosis-relevant information of the patient.

5 . The quantum computing device of claim 1 , wherein the first quantum search algorithm and the second quantum search algorithm each comprises a Grover's algorithm.

6 . The quantum computing device of claim 1 , wherein the one or more treatment recommendations for the patient each comprises a recommendation score computed based on a risk of a particular drug in treating a particular condition of the plurality of conditions, an efficacy of the particular drug in treating the particular condition, a risk associated with using the particular drug incorrectly, a likelihood of the patient having the particular condition, and a likelihood of the patient using the particular drug incorrectly.

7 . The quantum computing device of claim 1 , wherein to implement the first quantum search algorithm that uses the one or more patient diagnosis qubits to search within the first database for one or more entries that correspond to the diagnosis-relevant information of the patient, the first quantum circuit configured to:
receive as input the one or more patient diagnosis qubits; receive as input a plurality of qubits encoded with the diagnosis data for the patient; and output one or more of the plurality of qubits encoded with the diagnosis data for the patient that match a state of the one or more patient diagnosis qubits.

8 . The quantum computing device of claim 1 , wherein to implement the second quantum search algorithm that uses the one or more patient treatment qubits to search within the second database for one or more entries that correspond to the diagnosis data for the patient and the treatment-relevant information of the patient, the second quantum circuit configured to:
receive as input the one or more patient treatment qubits; receive as input a plurality of qubits encoded with the one or more treatment recommendations for the patient; and output one or more of the plurality of qubits encoded with the treatment recommendations for the patient that match a state of the one or more patient treatment qubits.

9 . A method comprising:
encoding, by a quantum computing device, diagnosis-relevant information of a patient as one or more patient diagnosis qubits, wherein the diagnosis-relevant information comprises information of potential relevance to determining a diagnosis of the patient; implementing, by the quantum computing device, a first quantum search algorithm that uses the one or more patient diagnosis qubits to search within a first database for one or more entries that correspond to the diagnosis-relevant information of the patient, wherein the one or more entries that correspond to the diagnosis-relevant information of the patient comprises diagnosis data for the patient, wherein the diagnosis data for the patient comprises a likelihood for each condition of a plurality of conditions; encoding, by the quantum computing device, the one or more entries that correspond to the diagnosis data for the patient and treatment-relevant information of the patient as one or more patient treatment qubits, wherein the treatment-relevant information comprises information of potential relevance to determining a treatment of the patient; and implementing, by the quantum computing device, a second quantum search algorithm that uses the one or more patient treatment qubits to search within a second database for one or more entries that correspond to the diagnosis data for the patient and the treatment-relevant information for the patient, wherein the one or more entries that correspond to the diagnosis data for the patient and the treatment-relevant information of the patient indicates one or more treatment recommendations for the patient.

10 . The method of claim 9 , wherein the diagnosis-relevant information of the patient comprises one or more characteristics of the patient, one or more symptoms of the patient, or medical history of the patient.

11 . The method of claim 9 , wherein the treatment-relevant information of the patient comprises one or more of medication adherence information of the patient or medication efficacy information of the patient.

12 . The method of claim 9 , wherein the likelihood for each condition of the plurality of conditions is computed based on the diagnosis-relevant information of the patient.

13 . The method of claim 9 , wherein the quantum search algorithm comprises a Grover's algorithm.

14 . The method of claim 9 , further comprising:
computing, by the quantum computing device, a recommendation score for each of the one or more treatment recommendations, wherein the recommendation score is computed based on a risk of a particular drug in treating a particular condition of the plurality of conditions, an efficacy of the particular drug in treating the particular condition, a risk associated with using the particular drug incorrectly, a likelihood of the patient having the particular condition, and a likelihood of the patient using the particular drug incorrectly.

15 . The method of claim 9 , wherein implementing the first quantum search algorithm that uses the one or more patient diagnosis qubits to search within the first database for one or more entries that correspond to the diagnosis-relevant information of the patient comprises:
receiving as input the one or

Assignees

• Optum Services Ireland Ltd

Inventors

• Walsh Lisa E
• Del Pino Ruiz Vicente Rubén
• Godden Paul J
• Paidimukkala Vikas Raj

Classifications

• G06N10/40

  Physical realisations or architectures of quantum processors or components for manipulating qubits, e.g. qubit coupling or qubit control · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06N10/20

  Models of quantum computing, e.g. quantum circuits or universal quantum computers · CPC title

• G06N10/60

  Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms · CPC title

• G16H10/60 Primary

  for patient-specific data, e.g. for electronic patient records · CPC title