Pre-operative plan generation for an operation on a spine

Patent metadata

Field	Value
Publication number	US-12544138-B2
Application number	US-202117479303-A
Country	US
Kind code	B2
Filing date	Sep 20, 2021
Priority date	Sep 20, 2021
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

A method and system for automatically generating a pre-operative plan is disclosed that may include using a computing device to receive, from an electronic device associated with a physician, an identification message comprising identifying information associated with a target patient for a surgical procedure. The computing device may retrieve medical information associated with the target patient based on the identifying information, and apply machine learning models to identify a predicted condition of the target patient and to predict a surgical approach and one or more surgical components to use and may generate a surgical plan that comprises an indication of the surgical approach and an indication of the one or more surgical components.

First claim

What is claimed is:

1 . A system for generating a pre-operative plan, the system comprising:
one or more computer readable storage devices configured to store a plurality of computer executable instructions; and one or more hardware computer processors in communication with the one or more computer readable storage devices and configured to execute the plurality of computer executable instructions, the plurality of computer executable instructions configured to, when executed, cause the processor to:
receive, from an electronic device associated with a physician, an identification message comprising identifying information associated with a target patient for a surgical procedure;
retrieve medical information associated with the target patient based on the identifying information;
apply a first machine learning model to at least a portion of the medical information to identify a predicted condition of the target patient;
transmit an indication of the predicted condition to the electronic device;
in response to receiving a confirmation message of the predicted condition from the electronic device, apply a second machine learning model to the predicted condition to predict a surgical approach and one or more surgical components to use;
receive one or more radiographic measurements associated with the target patient, wherein the radiographic measurements comprise alignment parameters and/or segmental measurements;
receive one or more correction thresholds related to restoring spinal alignment; and
generate a surgical plan comprising steps to achieve a target spinal geometry, the surgical plan based on the one or more radiographic measurements, the one or more correction thresholds, the indication of the surgical approach, and the indication of the one or more surgical components.

2 . The system of claim 1 , wherein causing the system to apply the first machine learning model to at least a portion of the medical information comprises:
causing the system to train the first machine learning model on a data set for the surgical procedure, wherein the data set comprises one or more images depicting one or more conditions of anatomy corresponding to the surgical procedure; and causing the system to apply the trained first machine learning model to the at least a portion of the medical information to identify the predicted condition.

3 . The system of claim 1 , wherein causing the system to apply the first machine learning model to at least a portion of the medical information comprises:
causing the system to train the first machine learning model on a data set for the surgical procedure, wherein the data set comprises one or more images depicting one or more conditions of anatomy corresponding to the surgical procedure and feedback from the physician diagnosing a condition depicted in an image; and causing the system to apply the trained first machine learning model to the at least a portion of the medical information to identify the predicted condition.

4 . The system of claim 1 , wherein causing the system to apply the second machine learning model to the predicted condition comprises:
causing the system to train the second machine learning model on a data set for the surgical approach, wherein the data set comprises surgeon preferences for the predicted condition; and causing the system to apply the trained second machine learning model to the predicted condition to predict the surgical approach.

5 . The system of claim 1 , wherein causing the system to apply the second machine learning model to the predicted condition to predict one or more implants for the target patient comprises causing the system to determine a shape and a size associated with the one or more implants based on radiographic images of the target patient.

6 . The system of claim 1 , wherein the system is further caused to:
apply the first machine learning model to at least a portion of the medical information to determine a probability of the predicted condition of the target patient; apply the first machine learning model to at least a portion of the medical information to determine a probability of a second predicted condition of the target patient; and transmit the probability of the predicted condition and the probability of the second predicted condition to the electronic device.

7 . The system of claim 1 , wherein the system is further caused to select one or more surgical components from a surgical component data store based on the surgical plan.

8 . The system of claim 1 , further comprising applying the first machine learning model to at least a first portion of the medical information and at least a second portion of the medical information to identify the predicted condition of the target patient based on a difference between the first portion and the second portion.

9 . The system of claim 1 , wherein:
the instructions that are configured to cause the processor to receive the one or more correction thresholds comprise instructions that cause the processor to receive a lordosis threshold; the instructions are further configured to cause the processor to determine a height adjustment target based on the one or more radiographic measurements; and the instructions that are configured to cause the processor to generate the surgical plan comprise instructions that are configured to cause the processor to generate the plan comprising the step:
adding posterior and anterior height to a construct to achieve the height adjustment target and the lordosis threshold.

10 . The system of claim 9 , wherein the instructions that are configured to cause the processor to determine the height adjustment target based on the one or more radiographic measurements comprise instructions configured to cause the processor to determine an average disc height for a portion of a spine, the average disc height excluding discs having a height that satisfies a reduced-height threshold.

11 . A method of automatically generating a pre-operative plan, the method comprising:
by a computing device:
receiving, from an electronic device associated with a physician, an identification message comprising identifying information associated with a target patient for a surgical procedure;
retrieving medical information associated with the target patient based on the identifying information;
applying a first machine learning model to at least a portion of the medical information to identify a predicted condition of the target patient;
transmitting an indication of the predicted condition to the electronic device; in response to receiving a confirmation message of the predicted condition from the electronic device, applying a second machine learning model to the predicted condition to predict a surgical approach and one or more surgical components to use;
receiving one or more radiographic measurements associated with the target patient, wherein the radiographic measurements comprise alignment parameters and/or segmental measurements;
receiving one or more correction thresholds related to restoring spinal alignment; and
generating a surgical plan comprising steps to achieve a target spinal geometry, the surgical plan based on the one or more radiographic measurements, the one or more correction thresholds, the indication of the surgical approach, and the indication of the one or more surgical components.

12 . The method of claim 11 , wherein applying the first machine learning model to at least a portion of the medical information comprises:
training the first machine learning model on a data set for the surgical procedure, wherein the data set comprises one or more images depicting one

Assignees

• Medicrea Int

Inventors

• Benson Nicholas
• Deitz Adam K

Classifications

• G06N20/00

  Machine learning · CPC title

• G16H10/60

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

• G16H20/40

  relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture · CPC title

• A61B2034/256

  having a database of accessory information, e.g. including context sensitive help or scientific articles · CPC title

• A61B2034/108

  Computer aided selection or customisation of medical implants or cutting guides · CPC title