# US 12,603,180 B2 · Method, apparatus, and computer program for providing precocious puberty prediction and solution for each growth stage using artificial intelligence

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

- Number: US 12,603,180 B2
- Document ID: US12603180B2
- Status: Granted
- Kind: B2
- Application number: 18/572,301
- Filed: 2023-07-06
- Published: 2025-03-13
- Granted: 2026-04-14
- Earliest claimed: 2022-09-29
- Assignees: GP Ltd.
- Applicants: Gp Co., Ltd.
- Inventors: Je Hyeok Seong
- Web page: https://patentgrep.com/patent/US12603180B2

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B 5/00: Measuring for diagnostic purposes (radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00); Identification of persons
- A61B 5/103: Measuring devices for testing the shape, pattern, {colour,} size or movement of the body or parts thereof, for diagnostic purposes (measuring instruments specially adapted for dentistry A61C19/04)
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/08: Learning methods
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H 50/30: for calculating health indices; for individual health risk assessment
- 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
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present invention relates to a method, apparatus, and computer program for predicting precocious puberty for each stage of growing children and adolescents using an artificial intelligence model. The method for providing precocious puberty prediction and solution for each growth stage using artificial intelligence includes: receiving time series physical information on an evaluation subject; classifying a plurality of growth stages based on the input physical information on the evaluation subject, and then extracting physical information corresponding to a normal growth stage among the plurality of growth stages; predicting precocious puberty by inputting the extracted physical information to a trained neural network; and providing a precocious puberty management solution based on the physical information on the evaluation subject when the evaluation subject corresponds to the precocious puberty.

## Claims

### Claim 1

A method for providing precocious puberty prediction and solution for each growth stage using artificial intelligence, the method being performed by one or more processors of a computer system and comprising:
receiving time series physical information on an evaluation subject;
classifying, by a growth stage determination module executed on the computer system, a plurality of growth stages based on the input physical information on the evaluation subject, and then extracting physical information corresponding to a normal growth stage among the plurality of growth stages;
predicting precocious puberty by inputting the extracted physical information corresponding to the normal growth stage and an estimated bone maturity value generated by a bone maturity prediction model to a trained neural network stored in a memory and executed on the computer system, the trained neural network including a first neural network model trained with normal growth stage time-series physical information and a second neural network model trained with bone maturity data, such that an output of the second neural network model is provided as an input to the first neural network model; and
providing a precocious puberty management solution based on the physical information on the evaluation subject when the evaluation subject corresponds to the precocious puberty,
wherein the predicting comprises considering a difference between physical information of the evaluation subject and physical information corresponding to a normal growth stage so as to improve prediction accuracy for precocious puberty,
wherein the precocious puberty management solution is determined differently for each of the plurality of growth stages based on the physical information on the evaluation subject,
wherein the precocious puberty management solution is output through a user interface,
wherein the method accurately predicts the precocious puberty by considering the plurality of growth stages of the evaluation subject through the neural network generated through artificial intelligence learning and provides solutions necessary to prevent the precocious puberty based on the accurate growth stage of the evaluation subject,
wherein the predicting and providing are performed through a computer-implemented multi-model inference pipeline configured to improve computational accuracy and processing efficiency of the computer system, and
wherein the second neural network model derives bone maturity from a carpal image using a convolutional neural network trained with the bone maturity data of the evaluation subject as training data, and the convolutional neural network includes a plurality of convolution layers that creates a feature map for features in an image to be analyzed among carpal images.

### Claim 2 (depends on 1)

The method of claim 1, further comprising after the receiving of the physical information on the evaluation subject, classifying a gender of the evaluation subject.

### Claim 3 (depends on 2)

The method of claim 2, wherein a period of the normal growth stage is set differently based on the gender of the evaluation subject to extract physical information.

### Claim 4 (depends on 1)

The method of claim 1, wherein the neural network performs multi-modal learning using different types of training data.

### Claim 5 (depends on 4)

The met hod of claim 4, wherein the neural network includes a first model that trains physical information corresponding to a normal growth stage among a plurality of growth stages as training data based on the time series physical information on the plurality of sample subjects.

### Claim 6 (depends on 5)

The method of claim 5, wherein the neural network further includes a second model trained using bone maturity data of the evaluation subject as the training data.

### Claim 7 (depends on 1)

A program stored in a computer-readable recording medium including a program code for executing the method for providing precocious puberty prediction and solution for each growth stage using artificial intelligence of claim 1.

### Claim 8 (depends on 1)

A computer-readable recording medium in which a program for executing the method for providing precocious puberty prediction and solution for each growth stage using artificial intelligence of claim 1 is recorded.

### Claim 9

A computer-implemented apparatus for providing precocious puberty prediction and solution for each growth stage using artificial intelligence, the apparatus comprising:
an input unit operable by one or more processors and configured to receive time series physical information on an evaluation subject;
a growth stage determination unit implemented using hardware and software components, and configured to classify a plurality of growth stages based on the physical information on the evaluation subject input to the input unit, and then extract physical information corresponding to a normal growth stage among the plurality of growth stages;
a precocious puberty prediction unit configured to predict the precocious puberty by inputting the extracted physical information corresponding to the normal growth stage and an estimated bone maturity value generated by a bone maturity prediction model to a trained neural network model stored in memory and executed on the apparatus, the trained neural network model including a first neural network model trained with normal growth stage time-series physical information and a second neural network model trained with bone maturity data, such that an output of the second neural network model is provided as an input to the first neural network model;
a solution generation unit configured to generate a precocious puberty management solution based on the physical information on the evaluation subject when the evaluation subject corresponds to the precocious puberty; and
a display unit configured to display the generated precocious puberty management solution to a user interface,
wherein the prediction unit is configured to consider a difference between physical information of the evaluation subject and physical information corresponding to a normal growth stage so as to improve prediction accuracy for precocious puberty,
wherein the solution generation unit is configured to determine the precocious puberty management solution differently for each of the plurality of growth stages based on the physical information on the evaluation subject,
wherein the apparatus is configured to implement a computer-implemented multi-model inference pipeline configured to improve computational accuracy and processing efficiency of the apparatus, and
wherein the second neural network model derives bone maturity from a carpal image using a convolutional neural network trained with the bone maturity data of the evaluation subject as training data, and the convolutional neural network includes a plurality of convolution layers that creates a feature map for features in an image to be analyzed among carpal images.

### Claim 10 (depends on 9)

The apparatus of claim 9, further comprising:
a gender determination unit configured to classify a gender of the evaluation subject input to the input unit,
wherein the solution generation unit generates a precocious puberty management solution differently depending on the gender of the evaluation subject.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the growth stage determination unit extracts the physical information by setting a period of the normal growth stage differently based on the gender of the evaluation subject.

### Claim 12 (depends on 9)

The apparatus of claim 9, wherein the neural network performs multi-modal learning using different types of training data.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the neural network includes a first model that trains physical information corresponding to a normal growth stage among a plurality of growth stages as training data based on the time series physical information on the plurality of sample subjects.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the neural network further includes a second model trained using bone maturity data of the evaluation subject as the training data.