# US 2026/0066085 A1 · System and Method for AI-Driven Surgical Care Recommendation and Optimization

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

- Number: US 2026/0066085 A1
- Document ID: US20260066085A1
- Status: Published application
- Kind: A1
- Application number: 18/816,274
- Filed: 2024-08-27
- Published: 2026-03-05
- Earliest claimed: 2024-08-27
- Inventors: Juliette Koval
- Web page: https://patentgrep.com/patent/US20260066085A1

## CPC

- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system and method for recommending surgical care providers and protocols using artificial intelligence (AI) and machine learning (ML) is disclosed. The system comprises one or more processors coupled to a memory that stores instructions for receiving healthcare data from various sources, preprocessing the data, training an ML model to generate recommendations, and iteratively refining the model based on patient feedback. The system receives data related to surgical procedures, hospitals, doctors, and pre- and post-operative care, preprocesses the data using techniques such as data cleaning, normalization, and encoding, and trains a neural network model to generate recommendations for selecting optimal hospitals, doctors, and care protocols. The generated recommendations are provided to users via an intuitive interface, and patient feedback is used to retrain and optimize the ML model for continuous improvement.

## Claims

### Claim 1

A system for recommending surgical care providers and protocols, comprising:
a. one or more processors coupled to a memory, the memory storing instructions that, when executed by the one or more processors, cause the system to:
i. receive healthcare data from a plurality of sources, the healthcare data related to surgical procedures, hospitals, doctors, and pre and postoperative protocols;
ii. preprocess the received healthcare data to ensure data quality;
iii. train a neural network model using the preprocessed healthcare data to generate recommendations for selecting hospitals and doctors for particular surgical procedures;
iv. train the neural network model using the preprocessed healthcare data to generate recommendations for preoperative and postoperative protocols for particular surgical procedures;
v. provide the generated recommendations to a user via a user interface;
vi. receive feedback data from patients related to the recommendations; and
vii. retrain the neural network model based on the received feedback data to iteratively refine the recommendations.

### Claim 2 (depends on 1)

The system of claim 1, wherein the plurality of sources comprises one or more of: federal healthcare databases, hospital electronic health record systems, and patient feedback surveys.

### Claim 3 (depends on 1)

The system of claim 1, wherein preprocessing the received healthcare data comprises: applying data cleaning techniques to handle missing or inconsistent data; normalizing data formats across different sources; and encoding categorical variables using one-hot encoding.

### Claim 4 (depends on 1)

The system of claim 1, wherein the neural network model comprises a deep learning architecture with multiple hidden layers and an output layer for generating the recommendations.

### Claim 5 (depends on 4)

The system of claim 4, wherein training the neural network model comprises: using a supervised learning approach with labeled training data; optimizing model parameters using a gradient descent algorithm; and applying regularization techniques to prevent overfitting.

### Claim 6 (depends on 1)

The system of claim 1, wherein the generated recommendations for selecting hospitals and doctors are based on factors comprising: surgical outcomes, complication rates, patient satisfaction scores, and doctor experience level.

### Claim 7 (depends on 1)

The system of claim 1, wherein the generated recommendations for preoperative protocols comprise suggested: pre-surgical patient education materials; dietary restrictions; and medication regimens to optimize surgical outcomes.

### Claim 8 (depends on 1)

The system of claim 1, wherein the generated recommendations for postoperative protocols comprise suggested: medication types and dosages to manage pain and prevent complications; wound care instructions; and physical therapy exercises to aid recovery.

### Claim 9 (depends on 1)

The system of claim 1, wherein the user interface comprises: a web-based dashboard with search functionality to find recommendations by procedure type; and data visualizations comparing recommended hospitals and doctors based on key performance metrics.

### Claim 10 (depends on 1)

The system of claim 1, wherein retraining the neural network model based on the received feedback data comprises:
a. updating the training dataset with new patient feedback examples;
b. adjusting model hyperparameters to improve recommendation accuracy;
c. and periodically re-evaluating model performance on a validation dataset.

### Claim 11

A method for generating surgical care recommendations using artificial intelligence, comprising:
a. receiving, by one or more processors coupled to a memory, healthcare data from a plurality of sources, the healthcare data related to surgical procedures, hospitals, doctors, and pre and postoperative care;
b. preprocessing, by the one or more processors, the received healthcare data to ensure data quality;
c. training, by the one or more processors, a machine learning model using the preprocessed healthcare data to:
d. rank hospitals and doctors based on their suitability for particular surgical procedures, and
e. determine optimal medication regimens and care protocols for preoperative and postoperative periods for particular surgical procedures;
f. outputting, by the one or more processors, the rankings and determinations as recommendations to a user;
g. receiving, by the one or more processors, feedback data from patients related to the recommendations; and
h. retraining, by the one or more processors, the machine learning model based on the received feedback data to optimize the recommendations.

### Claim 12 (depends on 11)

The method of claim 11, wherein preprocessing the received healthcare data comprises:
a. removing duplicate or irrelevant data entries;
b. standardizing data formats across the plurality of sources; and
c. imputing missing values using statistical techniques.

### Claim 13 (depends on 11)

The method of claim 11, wherein the machine learning model comprises a deep neural network with:
a. an input layer for receiving the preprocessed healthcare data;
b. a plurality of hidden layers for extracting features and patterns from the data; and
c. an output layer for generating the rankings and determinations.

### Claim 14 (depends on 13)

The method of claim 13, wherein the deep neural network further comprises:
a. convolutional layers for processing structured data such as images or time series; and
b. recurrent layers for processing sequential data such as patient histories or treatment timelines.

### Claim 15 (depends on 11)

The method of claim 11, wherein ranking hospitals and doctors based on their suitability for particular surgical procedures involves:
a. identifying key performance metrics such as mortality rates, complication rates, and patient satisfaction scores; and
b. calculating weighted scores for each hospital and doctor based on these metrics.
c. adjusting the weights for each feature based on the user's profile features.

### Claim 16 (depends on 11)

The method of claim 11, wherein determining optimal medication regimens for preoperative and postoperative periods comprises:
a. analyzing patient outcomes data to identify the most effective antibiotics, dosages, and administration schedules for preventing surgical site infections; and
b. personalizing the regimens based on individual patient characteristics such as age, weight, and comorbidities.

### Claim 17 (depends on 11)

The method of claim 11, wherein determining optimal care protocols for preoperative and postoperative periods comprises:
a. identifying best practices for patient preparation and recovery (i.e. anesthesia, surgical techniques, and postoperative monitoring; and
b. adapting the protocols to the specific needs and constraints of different healthcare facilities as well as the risk factors and procedure type of the user.

### Claim 18 (depends on 11)

The method of claim 11, further comprising:
a. generating a user interface for presenting the rankings and determinations to patients and healthcare providers;
b. wherein the user interface includes interactive visualizations of the key performance metrics and personalized recommendations.

### Claim 19 (depends on 11)

The method of claim 11, wherein the feedback data from patients includes:
a. subjective ratings of the healthcare experience and outcomes;
b. objective measures of health status and recovery progress; and
c. suggestions for improving the recommendations.

### Claim 20 (depends on 11)

The method of claim 11, wherein retraining the machine learning model based on the received feedback data involves:
a. using reinforcement learning techniques to update the model parameters and decision rules;
b. with the goal of maximizing long-term patient satisfaction and health outcomes.
