US-20260128171-A1 - DIAGNOSIS AND TREATMENT RECOMMENDATION USING QUANTUM COMPUTING

US20260128171A1US 20260128171 A1US20260128171 A1US 20260128171A1US-20260128171-A1

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.

Inventors

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

Assignees

OPTUM SERVICES (IRELAND) LIMITED

Dates

Publication Date: 20260507
Application Date: 20251219

Claims (20)

1 . A quantum computing device comprising: a quantum encoder configured to encode classical data including treatment-relevant information associated with a patient and diagnosis data as one or more patient treatment qubits; and a quantum circuit configured to determine that a state of at least one risk or efficacy qubit that encodes a particular treatment for the patient matches a state of a corresponding patient treatment qubit of the one or more patient treatment qubits, wherein the quantum computing device is configured to decode the at least one risk or efficacy qubit that matches the state of the corresponding patient treatment qubit into classical data specifying the particular treatment and output the classical data specifying the particular treatment to a classical computing device.
2 . The quantum computing device of claim 1 , wherein the quantum circuit comprises a second quantum circuit, wherein the second quantum circuit is further configured to receive the diagnosis data encoded in a diagnosis probability qubit that is output from a first quantum circuit, and wherein the first quantum circuit is configured to output the diagnosis probability qubit in response to determining that a state of the diagnosis probability qubit matches a state of a corresponding patient diagnosis qubit of one or more patient diagnosis qubits encoded with diagnosis-relevant information associated with the patient.
3 . The quantum computing device of claim 1 , wherein the diagnosis data specifies a diagnosis probability associated with a particular condition from among a plurality of conditions.
4 . The quantum computing device of claim 3 , wherein the diagnosis probability associated with the particular condition is computed based on diagnosis-relevant information associated with the patient.
5 . The quantum computing device of claim 4 , wherein the diagnosis-relevant information associated with the patient comprises at least one of a characteristic of the patient, a symptom of the patient, or medical history of the patient.
6 . The quantum computing device of claim 5 , wherein the medical history of the patient comprises at least one of: a number of days since a prior surgery was performed; a number of days since a prior medication was used; a number of days since a last doctor visit; a number of minutes the patient experienced a particular symptom; a dosage amount of medication prescribed; or family medical history.
7 . The quantum computing device of claim 3 , wherein the diagnosis probability associated with the particular condition is computed based on diagnosis-relevant information associated with a different patient.
8 . The quantum computing device of claim 1 , wherein the treatment-relevant information associated with the patient comprises at least one of medication adherence information of the patient or medication efficacy information of the patient.
9 . The quantum computing device of claim 1 , wherein the quantum circuit comprises one or more quantum gates configured to implement a quantum search algorithm.
10 . The quantum computing device of claim 9 , wherein the quantum search algorithm is based at least in part on Grover's algorithm.
11 . The quantum computing device of claim 1 , wherein the particular treatment for the patient is associated with a recommendation score computed based on at least one of a risk of a particular drug in treating a particular condition of a 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, or a likelihood of the patient using the particular drug incorrectly.
12 . A computer-implemented method comprising: encoding, by a quantum encoder of a quantum computing device, classical data including treatment-relevant information associated with a patient and diagnosis data as one or more patient treatment qubits; and determining, by a quantum circuit of the quantum computing device, that a state of at least one risk or efficacy qubit that encodes a particular treatment for the patient matches a state of a corresponding patient treatment qubit of the one or more patient treatment qubits, decoding, by the quantum computing device, the at least one risk or efficacy qubit that matches the state of the corresponding patient treatment qubit into classical data specifying the particular treatment and output the classical data specifying the particular treatment to a classical computing device.
13 . The computer-implemented method of claim 12 , wherein the quantum circuit comprises a second quantum circuit of the quantum computing device, the method further comprising: outputting, by a first quantum circuit of the quantum computing device, a diagnosis probability qubit that matches a state of a corresponding patient diagnosis qubit of one or more patient diagnosis qubits, wherein the diagnosis probability qubit encodes the diagnosis data; and receiving, by the second quantum circuit, the diagnosis data that is encoded in the diagnosis probability qubit.
14 . The computer-implemented method of claim 12 , wherein the diagnosis data specifies a diagnosis probability associated with a particular condition from among a plurality of conditions.
15 . The computer-implemented method of claim 14 , wherein the diagnosis probability associated with the particular condition is computed based on diagnosis-relevant information associated with the patient.
16 . The computer-implemented method of claim 15 , wherein the diagnosis-relevant information associated with the patient comprises at least one of a characteristic of the patient, a symptom of the patient, or medical history of the patient.
17 . The computer-implemented method of claim 16 , wherein the medical history of the patient comprises at least one of: a number of days since a prior surgery was performed; a number of days since a prior medication was used; a number of days since a last doctor visit; a number of minutes the patient experienced a particular symptom; a dosage amount of medication prescribed; or family medical history.
18 . The computer-implemented method of claim 14 , wherein the diagnosis probability associated with the particular condition is computed based on diagnosis-relevant information associated with a different patient.
19 . The computer-implemented method of claim 12 , wherein the treatment-relevant information associated with the patient comprises at least one of medication adherence information of the patient or medication efficacy information of the patient.
20 . The computer-implemented method of claim 12 , wherein the quantum circuit comprises one or more quantum gates configured to implement a quantum search algorithm.

Description

This application is a continuation of U.S. patent application Ser. No. 17/646,252, filed Dec. 28, 2021, the entire contents of which is incorporated herein by reference. TECHNICAL FIELD The disclosure relates to quantum computing. BACKGROUND In contrast to classical computing, which is based on classical physics, quantum computing leverages quantum mechanics to process information. Specifically, quantum computers may perform computational tasks by executing quantum algorithms (e.g., quantum logic operations applied to quantum bits (“qubits”)). A quantum algorithm may represent a quantum circuit that includes one or more quantum gates configured to act on qubits. By applying quantum gates in succession, a quantum computer may perform a transformation to a set of qubits in some initial state. Due to the laws of quantum mechanics, qubits are not binary in nature. For example, a qubit may exist as 0, 1, or simultaneously as both 0 and 1, with a numerical coefficient representing a probability for each state. This superposition of states may enable computational leaps over classical computing techniques. A variety of physical systems have been developed for quantum computing applications. Examples include superconducting circuits, trapped ions, spin systems and others. SUMMARY In general, this disclosure is directed to techniques for providing diagnosis of medical conditions and treatment recommendations using quantum computing. For example, a treatment recommendation system using quantum computing receives patient information of potential relevance to determine a diagnosis of the patient (referred to herein as “diagnosis-relevant information”), such as biological characteristics, current symptoms, medical history, etc., and encodes the information as one or more qubits (referred to herein as “patient diagnosis qubits”). The treatment recommendation system applies a quantum search algorithm that uses the patient diagnosis qubits to search within a diagnosis risk database—that includes a diagnosis risk (e.g., diagnosis probability) for each condition based on all combinations of the diagnosis-relevant information of the patient—to determine the diagnosis likelihood for each condition of a plurality of conditions. In response to determining the diagnosis likelihood for each condition for the patient, the treatment recommendation system then encodes the diagnosis likelihood for each condition and treatment information of the patient (“treatment-relevant information”), such as medication adherence information and/or medication efficacy information, as one or more qubits (referred to herein as “patient treatment qubits”). The treatment recommendation system applies a quantum search algorithm that uses the patient treatment qubits to search within a medication risk/efficacy database to determine one or more treatment recommendations for the patient, such as one or more recommended medications for the patient. The medication risk/efficacy database may include a recommendation score for each medication computed, e.g., based on the non-adherence drug risk, drug to condition efficacy, and drug to condition risk. The techniques may provide one or more technical advantages. For example, due to the large datasets within the diagnosis risk database and medication risk/efficacy database resulting from all combinations of patient information, existing treatment recommendation systems that use classical computing are unable to search within the large datasets to determine the likely condition and treatment recommendation within a short duration of time, e.g., during the duration of a typical doctor's visit. Instead, existing treatment recommendation systems may use reduced datasets of patient information that do not take into consideration, for example, the full historical and current medical information of a patient and/or the risk of misdiagnosis and mistreatment based on patient specific information, which may increase the risk of misdiagnosis and/or mistreatment. By using quantum computing to determine the likely diagnosis and one or more treatment recommendations, the treatment recommendation system is able to provide one or more treatment recommendations in real-time or near real-time while taking into account the patient's full historical and current medical information. Moreover, by determining one or more treatment recommendations based on a diagnosis likelihood of a condition and the risk of misdiagnosis and treatment based on a patient's medical history, the treatment recommendation system may consider all combinations of information of a patient's medical history, including much more granular information (e.g., specific day of last medical procedure or medication prescription), which may reduce the risk of misdiagnosis and/or mistreatment. In one example, a quantum computing device comprises: a first quantum encoder configured to encode diagnosis-relevant information of a patient as one or more patient diagnosis qubi