# US 2021/0174970 A1 · Integrated virtual patient framework

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

- Number: US 2021/0174970 A1
- Document ID: US20210174970A1
- Status: Published application
- Kind: A1
- Application number: 17/126,198
- Filed: 2020-12-18
- Published: 2021-06-10
- Earliest claimed: 2013-11-01
- Assignees: H. Lee Moffitt Cancer Center and Research Institute, Inc.
- Applicants: H. Lee Moffitt Cancer Center and Research Institute, Inc.
- Inventors: Alexander Robertson Allan Anderson; Mark Robertson-Tessi; Kevin McCash; Chandler Dean Gatenbee
- Web page: https://patentgrep.com/patent/US20210174970A1

## CPC

- G16H 50/50: for simulation or modelling of medical disorders
- G06Q 50/00: Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism (healthcare informatics G16H)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

An Integrated Virtual Patient Framework (IVPF) for providing decision support that evolves with increasing data collected on a given patient. Support decisions for patients with limited data is made using statistical prediction tools derived from historical trajectories of similar patients. As patient histories grow, decision support is provided by mathematical models that constrain the possible dynamics of the patient to more detailed predictive models. Weights for each model are assigned depending on uncertainties arising from data fitting and model properties. As new data are entered into a patient record, the models are recalibrated and the weights are adjusted, leading to updated decision support information. The framework also suggests the benefit of additional follow-up data collection events, optimizing the data collection as well as how the IVPF generates predictions. The framework also may present scenarios to patients in a way that informs them of treatment outcomes, given various strategies.

## Claims

### Claim 1

A model-based method for therapeutic decision support in an Integrated Virtual Patient Framework (IVPF), comprising:
defining a first disease-specific model, and one or more additional disease specific models that provide therapeutic decision support in accordance with a temporal relationship with multiple timepoints for a patient diagnosed with a condition;
determining, in accordance with each set of patient data at given timepoints, a first therapeutic decision by applying a first weight to the first disease-specific model, a second weight to the second disease-specific model, and subsequent weights to the additional disease-specific models;
ranking therapy choices of the first therapeutic decision in a user interface;
thereafter, repeating, for subsequent patient data received by the IVPF:
adjusting the first weight, second weight and additional weights in accordance with the types of subsequent patient data received;
comparing the subsequent patient data to virtual patent data in a database of simulated outcomes determined using the first disease-specific model, the second disease-specific model, and additional disease-specific models;
determining, in accordance with the comparing, a subsequent therapeutic decision by applying an adjusted first weight to the first disease-specific model, an adjusted second weight to the second disease-specific model, and additional adjusted weights to the additional disease-specific models; and
ranking subsequent therapy choices of the subsequent therapeutic decision in the user interface.

### Claim 2 (depends on 1)

The method of claim 1, further comprising comparing simulated outcomes determined using the first disease-specific model, the second disease-specific model or the additional disease-specific models with historical outcomes for actual patients.

### Claim 3 (depends on 1)

The method of claim 1, further comprising adjusting the first weight, second weight and additional weights in accordance with the types of subsequent patient data received each time the subsequent patient data is received.

### Claim 4 (depends on 3)

The method of claim 3, wherein the adjusting provides for continuous refinement of the subsequent therapeutic decision.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first disease-specific model is a statistical model, the second disease-specific model is a simple dynamic model, and the third disease-specific model is a complex dynamic model.

### Claim 6 (depends on 5)

The method of claim 5, wherein the first therapeutic decision is substantially determined in accordance with the statistical model.

### Claim 7 (depends on 5)

The method of claim 5, wherein subsequent therapeutic decisions are substantially determined in accordance with a combination of the simple dynamic model and the complex dynamic model.

### Claim 8 (depends on 1)

The method of claim 1, further comprising determining an optimal outcome based on the subsequent therapy choices.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
receiving inputs in the user interface to alter aspects of the subsequent therapy choices;
parsing the simulated outcomes in the database; and
comparing the subsequent patient data and the altered aspects of the subsequent therapy choices to the virtual patent data in the database of simulated outcomes; and
updating the subsequent therapeutic decision in accordance with the altered aspects.

### Claim 10 (depends on 1)

The method of claim 1, further comprising discarding simulated outcomes that do not match the subsequent patient data.

### Claim 11 (depends on 1)

The method of claim 1, further comprising determining at least one of the first therapeutic decision and the subsequent therapeutic decision in accordance with patent data that was acquired before the patient was diagnosed with the condition.

### Claim 12

A model-based method for therapeutic decision support in an Integrated Virtual Patient Framework (IVPF), comprising:
receiving, at a first time, first data associated with a patient;
defining at least two disease-specific models that provide the therapeutic decision support in accordance with a temporal relationship with the first time and a second time;
determining an initial therapeutic decision by applying weights to a first disease-specific model of the at least two disease-specific models;
receiving, at a second time later than the first time, second data associated with the patient;
determining a subsequent therapeutic decision by:
comparing the first data and the second data to virtual patients stored in a database of simulations performed in using the at least two disease-specific models;
applying weights to the virtual patients to generate a cloud of similar virtual patients to the patient for each of the at least two disease-specific models; and
subjecting the similar virtual patients to a trial process using available treatments to determine a range of outcomes; and
ranking subsequent therapeutic decisions associated with the outcomes in a user interface.

### Claim 13 (depends on 12)

The method of claim 12, further comprising comparing the range of outcomes with historical outcomes for actual patients.

### Claim 14 (depends on 12)

The method of claim 12, further comprising:
receiving subsequent second data; and
adjusting the weights of the virtual patients in response to receiving the subsequent second data.

### Claim 15 (depends on 14)

The method of claim 14, wherein the adjusting provides for continuous refinement of the ranking of the subsequent therapeutic decisions.

### Claim 16 (depends on 12)

The method of claim 12, wherein the first disease-specific model is a statistical model, the second disease-specific model is a dynamic model.

### Claim 17 (depends on 16)

The method of claim 16, wherein the first therapeutic decision is substantially determined in accordance with the statistical model.

### Claim 18 (depends on 16)

The method of claim 16, further comprising varying dynamic model from a simple dynamic model to a complex dynamic model as time progresses forward.

### Claim 19 (depends on 18)

The method of claim 18, wherein subsequent therapeutic decisions are substantially determined in accordance with a combination of the simple dynamic model and the complex dynamic model.

### Claim 20 (depends on 19)

The method of claim 19, wherein the simple dynamic model comprises one or more simple dynamic models, and wherein the complex dynamic model comprises one or more complex dynamic models.

### Claim 21 (depends on 12)

The method of claim 12, further comprising:
receiving inputs in the user interface to alter aspects of the subsequent therapy choices;
comparing the subsequent patient data and the altered aspects of the subsequent therapy choices to the virtual patent data in the database; and
updating the subsequent therapeutic decision in accordance with the altered aspects.

### Claim 22 (depends on 12)

The method of claim 12, further comprising presenting, for each of the subsequent therapy choices, a likelihood of a successful outcome, a statistical uncertainty, and trajectory of possible outcomes.

### Claim 23 (depends on 12)

The method of claim 12, further comprising presenting scenarios the patient in the user interface to informs the patient of treatment outcomes, given various strategies.
