Search

US-12626820-B2 - Moderated communication system for infertility treatment

US12626820B2US 12626820 B2US12626820 B2US 12626820B2US-12626820-B2

Abstract

The systems and methods of the invention provide several improvements directed at fertility treatment. These improvements include an expert/AI system configured to guide a caregiver, e.g., a physician, through the process of providing fertility treatment. They also include a communication system between the caregiver and a patient, which is moderated by the expert/AI system.

Inventors

  • John Patrick Holden

Assignees

  • John Patrick Holden

Dates

Publication Date
20260512
Application Date
20230717

Claims (20)

  1. 1 . A communication system for the treatment of infertility, the communication system comprising: an expert system embodied in one or more computing devices, wherein the expert system includes: a rule-based logic database storing selections for infertility treatments, the rule-based logic database including a plurality of rules stored in association with clinical data and the infertility treatments, wherein the rule-based logic database is configured to apply the plurality of rules to provide selections of one or more infertility treatments from among the one or more of the alternative treatments, a reinforcement logic database storing quality scores in association with respective rules of the plurality of rules, the scores being based on at least clinical success of the selections, a knowledge graph storing a patient's accrued data in association with a plurality of nodes, wherein each node is associated with one or more of the selections, a library database storing information regarding the infertility treatments and the clinical data regarding the first patient, a content distribution logic configured to automatically provide content from the library of information to the first patient, a microprocessor operatively coupled to the rule-based logic database, the reinforcement logic database and the knowledge graph, wherein the microprocessor is configured to execute the plurality of rules stored in the rule-based logic database and the content distribution logic, wherein members of the plurality of rules are associated with an initial score, the initial score being based on a perceived quality of data on which the respective rule is based, and the scores are based on both the initial score associated with a particular member and the clinical success of the selections and wherein a machine learning system is configured to supplement the selections provided by the rule-based logic database, wherein the machine learning system is trained based on clinical success of the selections from among the infertility treatments to thereby provide a preference among the selections provided by the rule-based logic database and wherein the training logic is configured to train the machine learning system based on clinical success provided by the caregiver and the clinical data; a caregiver application embodied in a caregiver computing device, wherein the caregiver application includes: a clinical input element configured to receive the clinical data, a caregiver user interface elements configured for a caregiver to receive the selections from among the infertility treatments, and status logic configured to track treatment status of the patient, the treatment including the selections of the infertility treatments; and one or more patient applications, each embodied in a patient computing device, wherein the patient applications include: a patient user interface element configured to display the content from the library to the first patient.
  2. 2 . The system of claim 1 , further comprising a couple logic configured to treat a pair of patients as a reproductive unit and to coordinate the selections provided to both members of the reproductive unit.
  3. 3 . The system of claim 1 , further comprising the clinical input configured to receive the clinical data, the clinical input being included on the caregiver computing device or the patient computing device.
  4. 4 . The system of claim 1 , further comprising a sensor connected to the patient computing device, the sensor being configured to collect at least part of the clinical data.
  5. 5 . The system of claim 1 , wherein the clinical data includes at least one of: patient age, patient race, patient weight, patient H 1 c, patient birth history.
  6. 6 . The system of claim 1 , wherein the library of information includes content selected to answer patient questions, and wherein the content distribution logic is optimized to minimize a number of questions asked a caregiver.
  7. 7 . The system of claim 1 , wherein the caregiver user interface is configured for a caregiver to approve the selections, to forward the selections to the patient, to approve the content from the library of information, to forward the content from the library of information to the patient, to answer questions received from the patient, to require that the caregiver provide the clinical data, and/or to enter the clinical data.
  8. 8 . The system of claim 1 , wherein the patient user interface is further configured for the patient to enter the clinical data, to send questions to the caregiver, to require that the patient provide clinical data, and/or to display data generated by the sensor.
  9. 9 . The system of claim 1 , wherein the machine learning system is further configured to provide a preference among the selections provided by the rule-based logic database.
  10. 10 . The system of claim 2 , wherein the reproductive unit includes a male patient and a female patient, and the selections are based on clinical data regarding both the male patient and the female patient.
  11. 11 . The system of claim 3 , wherein the clinical input is configured to receive the clinical data from a medical records system or a sensor.
  12. 12 . The system of claim 3 , wherein the sensor is configured to be worn by the first patient.
  13. 13 . The system of claim 3 , wherein the sensor is a temperature sensor, a sleep sensor, a blood glucose sensor, a motion sensor, or a hormone sensor.
  14. 14 . A method for the treatment of infertility, the method comprising: storing, in a rule-based logic database, selections for infertility treatments, the rule-based logic database including a plurality of rules stored in association with clinical data and the infertility treatments, wherein the rule-based logic database is configured to apply the plurality of rules to provide selections of one or more infertility treatments from among the one or more of the alternative treatments wherein members of the plurality of rules are associated with an initial score, the initial score being based on a perceived quality of data on which the respective rule is based, and the scores are based on both the initial score associated with a particular member and the clinical success of the selections; storing, in a reinforcement logic database, quality scores in association with respective rules of the plurality of rules, the scores being based on at least clinical success of the selections; storing, in a knowledge graph, a patient's accrued data in association with a plurality of nodes, wherein each node is associated with one or more of the selections, a library database storing information regarding the infertility treatments and the clinical data regarding the first patient, automatically providing content, based on a content distribution logic, from the library of information to the first patient; and supplementing the selections provided by the rule-based logic database with a machine learning system, wherein the machine learning system is trained based on clinical success of the selections from among the infertility treatments to thereby provide a preference among the selections provided by the rule-based logic database and wherein the training logic is configured to train the machine learning system based on clinical success provided by the caregiver and the clinical data.
  15. 15 . The method of claim 14 , further comprising treating a pair of patients as a reproductive unit and to coordinate the selections provided to both members of the reproductive unit.
  16. 16 . The method of claim 14 further comprising collecting at least a part of the clinical data with a sensor connected to a patient computing device.
  17. 17 . The method of claim 14 , wherein the clinical data includes at least one of: patient age, patient race, patient weight, patient H1c, patient birth history.
  18. 18 . The method of claim 14 , wherein the library of information includes content selected to answer patient questions, and wherein the content distribution logic is optimized to minimize a number of questions asked a caregiver.
  19. 19 . The method of claim 14 , wherein a caregiver user interface is configured for a caregiver to approve the selections, to forward the selections to the patient, to approve the content from the library of information, to forward the content from the library of information to the patient, to answer questions received from the patient, to require that the caregiver provide the clinical data, and/or to enter the clinical data.
  20. 20 . The method of claim 14 , wherein a patient user interface is further configured for the patient to enter the clinical data, to send questions to the caregiver, to require that the patient provide clinical data, and/or to display data generated by the sensor.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to and benefit of U.S. provisional patent application Ser. No. 63/389,918 filed Jul. 27, 2022, the disclosure of which is hereby incorporated herein by reference in its entirety. BACKGROUND Field of the Invention The invention is in the field of fertility treatment, and in some embodiments in the field of communication management for the optimization of fertility treatment. Related Art Fertility treatment is an area of medicine in which expertise is concentrated in a few locations and practitioners. It is, therefore, difficult for most patents to receive optimum care. SUMMARY The systems and methods of the invention provide several improvements directed at fertility treatment. These improvements include an expert/AI system configured to guide a caregiver, e.g., a physician, through the process of providing fertility treatment. They also include a communication system between the caregiver and a patient, which is moderated by the expert/AI system. The expert/AI system (hereafter referred to simply as the “expert system”) can include a traditional rules-based expert system and/or a machine learning system, the machine learning system including neural networks and/or knowledge graphs. The communication system is configured to provide patients with appropriate information customized to their particular medical circumstances. For example, the communication system may provide documents and/or other information to patients to preemptively answer questions that they would otherwise direct at their caregiver. The information provided may be selected, at least in part, by the expert system, and may be responsive to the medical circumstances of the patient, e.g., to lab tests or other medically relevant characteristics. Patients experiencing difficulties with conception and/or carrying a fetus to delivery, otherwise known as infertility, may often have a large number of potential anatomic or hormonal anomalies that can occur in either the man or the woman. The Fertility Basics Applications are a linked app system which facilitates a primary care provider of human healthcare to work up a couple with fertility issues. At its most fundamental level, human fertility management involve a male and female source of gametes and a medical provider managing the production and utilization of these gametes. The two apps in the Fertility Basics system include a Provider app (FB-Pro) and a Patient app (FB-Patient). The provider app guides a medical provider through the evaluation and management of fertility issues in both males and females. The Patient app is an interactive app to the Provider app which allows for enhanced communication between providers and patients. The Patient app will not work without a link to the provider app. FB-Pro contains an algorithm that walks a medical care provider through the workup and treatment of both male and female fertility issues. There is a standardized medical workup of fertility problems recognized in the medical literature [reference]. However, this workup is basic in nature and the success of this treatment in achieving a pregnancy is reportedly 28%. The FB-Pro algorithm is an expanded workup which is significantly more successful in achieving and maintaining pregnancies. It is based on more than 25 years of clinical experience and medical literature which has been overlooked or underutilized by the healthcare industry in the United States. The steps of the protocol are all within normal medical care standards. The barriers for primary care providers (PCP) to enter into treatment of fertility issues are many; however, the biggest two issues are knowledge base and time. This has created a sub-specialty that is focused on fertility management. This sub-specialty has focused on a procedure heavy approach to fertility management. Our system favors a medical management approach. FB-Pro addresses the knowledge gap that is present in the medical community on fertility management. The FB-Patient app provides information to the individual or couple seeking care to answer the questions they may have over why steps are being taken, what the steps will inform the team of, how to interpret the results and what the next step in the evaluation will be. The Patient App reduces the burden of communication that can prevent the normal functioning of a PCP's office while enhancing the communication between provider and patient of medical information that is desired by the patient or patients. The Fertility Basics system collects data while progressing through the algorithm and the provider/patient interactions to track incident data. The causes for fertility problems in the US are generally known but incident data is sparse. Data collection allows for refining of this information. Definitions of medical terms are imprecise which impedes machine learning. This has limited the ability of researchers and other interested parties from minin