US-12626811-B2 - System and method for AI-based prioritization of patients

US12626811B2US 12626811 B2US12626811 B2US 12626811B2US-12626811-B2

Abstract

A system for an automated dental patient prioritization and treatment processing based on dental patient-related data, including a processor of a dental patient processing server node configured to host a machine learning (ML) module and connected to an office manager-entity node and to at least one dentist entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire a dental patient report including a list of dental procedures prescribed to a dental patient from the office manager-entity node; parse the dental patient report a to derive a plurality of key ordered features; query a local dental-patient's database to retrieve local historical dental-patients'-related data based on the plurality of the key ordered features; generate at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and provide the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generate at least one procedure performance recommendation and dental patient prioritization based on the at least one dental-patient processing recommendation parameter.

Inventors

Lior Tamir

Assignees

Lior Tamir

Dates

Publication Date: 20260512
Application Date: 20240604

Claims (16)

1 . A system for an automated dental patient prioritization and treatment processing based on dental patient-related data, comprising: a processor of a dental patient processing server node configured to host a machine learning (ML) module and connected to an office manager-entity node and to at least one dentist entity node over a network; and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire a dental patient report comprising a list of dental procedures prescribed to a dental patient from the office manager-entity node; parse the dental patient report a to derive a plurality of key ordered features; query a local dental-patient's database to retrieve local historical dental patients'-related data based on the plurality of the key ordered features; generate at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and provide the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generate at least one procedure performance recommendation and dental patient prioritization based on the at least one dental-patient processing recommendation parameter; continuously monitor incoming dental patient reports to determine if at least one value of procedure-related parameters deviates from a previous value of a previous procedure related parameter by a margin exceeding a pre-set threshold value; record the at least one dental-patient processing recommendation parameter on a blockchain ledger along with the dental patient report; and execute a smart contract to record data reflecting the at least one dental-patient processing recommendation parameter and scheduling of a procedure based on the at least one procedure performance recommendation and the dental patient prioritization corresponding to the dental patient report.
2 . The system of claim 1 , wherein the instructions further cause the processor to generate at least one scheduling parameter based on the at least one procedure performance recommendation and the dental patient prioritization for scheduling the at least one procedure associated with the dental patient report.
3 . The system of claim 1 , wherein the instructions further cause the processor to retrieve remote historical dental patients'-related data from at least one remote patients' database based on the plurality of the key ordered features, wherein the remote historical patients'-related data is collected at locations associated with remote dental offices.
4 . The system of claim 3 , wherein the instructions further cause the processor to generate the at least one feature vector based on the plurality of the key ordered features, the local historical patients'-related data combined with the remote historical patients' related data.
5 . The system of claim 1 , wherein the instructions further cause the processor to parse the dental patient report to generate a plurality of values to be hashed.
6 . The system of claim 5 , wherein the instructions further cause the processor to generate the key ordered features based on the plurality of hashed values.
7 . The system of claim 6 , wherein the instructions further cause the processor to, responsive to the at least one value of the procedure-related parameters deviating from the previous value by the margin exceeding the pre-set threshold value, generate an updated feature vector based on the incoming dental patient report data and generate the notification to the patient based on the at least one dental-patient processing recommendation parameter produced by the predictive model in response to the updated feature vector.
8 . The system of claim 7 , wherein the instructions further cause the processor to retrieve the at least one dental-patient processing recommendation parameter from the blockchain responsive to a consensus among the dental entity nodes.
9 . A method for an automated dental patient prioritization and treatment processing based on dental patient-related data, comprising: acquiring, by a patient processing server (PPS) node, a dental patient report comprising a list of dental procedures prescribed to a dental patient from the office manager-entity node; parsing, by the PPS node, the dental patient report a to derive a plurality of key ordered features; querying, by the PPS node, a local dental-patient's database to retrieve local historical dental patients'-related data based on the plurality of the key ordered features; generating, by the PPS node, at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and providing, by the PPS node, the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generating, by the PPS node, at least one procedure performance recommendation and dental patient prioritization based on the at least one dental patient processing recommendation parameter; continuously monitor incoming dental patient reports to determine if at least one value of procedure-related parameters deviates from a previous value of a previous procedure related parameter by a margin exceeding a pre-set threshold value; record the at least one dental-patient processing recommendation parameter on a blockchain ledger along with the dental patient report; and execute a smart contract to record data reflecting the at least one dental-patient processing recommendation parameter and scheduling of a procedure based on the at least one procedure performance recommendation and the dental patient prioritization corresponding to the dental patient report.
10 . The method of claim 9 , further comprising retrieving remote historical dental patients'-related data from at least one remote patients' database based on the plurality of the key ordered features, wherein the remote historical patients'-related data is collected at locations associated with remote dental offices.
11 . The method of claim 10 , further comprising generating the at least one feature vector based on the plurality of the key ordered features, the local historical patients'-related data combined with the remote historical patients'-related data.
12 . The method of claim 9 , further comprising continuously monitoring incoming dental patient reports to determine if at least one value of procedure-related parameters deviates from a previous value of a previous procedure-related parameter by a margin exceeding a pre-set threshold value.
13 . The method of claim 12 , further comprising, responsive to the at least one value of the procedure-related parameters deviating from the previous value by the margin exceeding the pre-set threshold value, generating an updated feature vector based on the incoming dental patient report data and generating the notification to the patient based on the at least one dental-patient processing recommendation parameter produced by the predictive model in response to the updated feature vector.
14 . The method of claim 9 , further comprising, recording the at least one dental patient processing recommendation parameter on a blockchain ledger along with the dental patient report.
15 . A non-transitory computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform: acquiring a dental patient report comprising a list of dental procedures prescribed to a dental patient from the office manager-entity node; parsing the dental patient report a to derive a plurality of key ordered features; querying a local dental-patient's database to retrieve local historical dental patients'-related data based on the plurality of the key ordered features; generating at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and providing the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generating at least one procedure performance recommendation and dental patient prioritization based on the at least one dental-patient processing recommendation parameter; continuously monitor incoming dental patient reports to determine if at least one value of procedure-related parameters deviates from a previous value of a previous procedure related parameter by a margin exceeding a pre-set threshold value; record the at least one dental-patient processing recommendation parameter on a blockchain ledger along with the dental patient report; and execute a smart contract to record data reflecting the at least one dental-patient processing recommendation parameter and scheduling of a procedure based on the at least one procedure performance recommendation and the dental patient prioritization corresponding to the dental patient report.
16 . The non-transitory computer readable medium of claim 15 , further comprising instructions, that when read by the processor, cause the processor to, responsive to the at least one value of the procedure-related parameters deviating from the previous value by the margin exceeding the pre-set threshold value, generate an updated feature vector based on the incoming dental patient report data and generate the notification to the patient based on the at least one dental-patient processing recommendation parameter produced by the predictive model in response to the updated feature vector.

Description

FIELD OF DISCLOSURE The present disclosure generally relates to determining and scheduling dental procedures, and more particularly, to an AI-based automated system for real-time selection, prioritization and scheduling of dental procedures based on predictive analytics of dental patients'-related historical heuristic data. BACKGROUND The process of scheduling dental appointments after the initial consultation often becomes time and resource consuming as dental patients try to postpone or even avoid certain procedures. While dental offices may use scheduling applications, these patient management software does not assist in the patients scheduling and actually going through with the dental procedures after the initial screening is done at the dental appointment and a report with a list of the procedures is generated. While the report is there and the patient is placed on the list for scheduling, many patients require multiple contacts (calls, emails, etc.) to schedule an appointment for the procedure according to the report because of the fear, financial considerations and general procrastinations that are very typical in dental industry. Many dental patients never follow through with the prescribed procedures at all. This way many patients are lost or require multiple notifications that cost dental business losses in time and revenues. What is needed is an automated method to prioritize dental patients (and corresponding procedures) based on some collected data from the patients of the same type—i.e., gender, age. race, locations, assigned procedure, insurance type, etc., etc. For example, a 19-year-old male patient may be likely to come back for filling or cleaning, but is initially less likely to deal with root canal and subsequent crown. The 19-year-old male patient may be best reached over SMS and will not respond to phone calls or emails, etc. However, the existing scheduling and healthcare management applications do not take any of these scenarios into consideration and do not improve the dental procedure scheduling statistics. Accordingly, a system and method for automated real-time selection, prioritization and scheduling of dental procedures based on predictive analytics of dental patients'-related historical heuristic data are desired. BRIEF OVERVIEW This brief overview is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This brief overview is not intended to identify key features or essential features of the claimed subject matter. Nor is this brief overview intended to be used to limit the claimed subject matter's scope. One embodiment of the present disclosure provides a system for an automated dental patient prioritization and treatment processing based on dental patient-related data, including a processor of a dental patient processing server node configured to host a machine learning (ML) module and connected to an office manager-entity node and to at least one dentist entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire a dental patient report including a list of dental procedures prescribed to a dental patient from the office manager-entity node; parse the dental patient report a to derive a plurality of key ordered features; query a local dental-patient's database to retrieve local historical dental-patients'-related data based on the plurality of the key ordered features; generate at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and provide the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generate at least one procedure performance recommendation and dental patient prioritization based on the at least one dental-patient processing recommendation parameter. Another embodiment of the present disclosure provides a method that includes one or more of: acquiring a dental patient report including a list of dental procedures prescribed to a dental patient from the office manager-entity node; parsing the dental patient report a to derive a plurality of key ordered features; querying a local dental-patient's database to retrieve local historical dental-patients'-related data based on the plurality of the key ordered features; generating at least one feature vector based on the plurality of the key ordered features and the local historical dental patients'-related data; and providing the at least one feature vector to the ML module configured to generate a predictive model for producing at least one dental-patient processing recommendation parameter; and generating at least one procedure performance recommendation and dental patient prioritization based on the at least one dental-patient processing recommen