“System And Method For Optimizing Home Visit Appointments And Related Travel” in Patent Application Approval Process (USPTO 20230005607): Patent Application

2023 JAN 20 (NewsRx) -- By a News Reporter-Staff News Editor at NewsRx COVID-19 Daily -- A patent application by the inventors Kogan, Daniel (Brooklyn, NY, US); Sumareva, Rada (New York, NY, US); Ukrainksy, Gennady (New York, NY, US), filed on June 24, 2022, was made available online on January 5, 2023, according to news reporting originating from Washington, D.C., by NewsRx correspondents.

This patent application has not been assigned to a company or institution.

The following quote was obtained by the news editors from the background information supplied by the inventors: “Clinically complex patients who are home-bound and/or live in remote areas require continuous care, but face tremendous barriers to accessing quality medical services, complying with treatment plans, staying on track with prescribed medications, and sustaining behaviors that support well-being. When patients do not receive the right kind of care, their health suffers, they wind up in an emergency room (ER) or are hospitalized, and insurance providers’ costs skyrocket. In the United States of America (USA), 15% of its annual gross domestic product (GDP) is spent on healthcare. This equates to more than about $3 trillion per annum or over about $10,000 per person. Eighty percent of the country’s expenditure is spent on behalf of 20% of its sickest population, that is, chronically ill and aging patients with complex medical conditions including, for example, diabetes, congestive heart failure, and respiratory diseases.

“To stem rising healthcare costs as a percentage of its GDP, the United States (U.S.) Government shifted the burden of healthcare costs from individuals, prior to 1950, to third party payers, hereinafter referred to as payers, including the government through programs such as Medicare, Medicaid, and the military health care system, and the private sector, for example, through managed care systems. Typically, a private sector entity seeks a profit margin of 2% in Medicaid and 15% in Medicare and, in order to control its medical expenditures, must effectively manage the 20% of its members with complex, chronic conditions. Over the past several decades, payers have experimented with, and failed at, programs such as disease management, case management, avoidance of emergency rooms, and avoidance of preventable hospital admissions. Payers have struggled to provide quality care, universal access to care, and cost-effective care due to continually rising costs in the hospital and pharmacy sectors of the marketplace. Payers have attempted to extend the reach of cost-effective care to nurse hot-lines, walk-in clinics, urgent care centers, doctor house calls, and most recently, telehealth. However, none have proven to be the Holy Grail of cost-effective healthcare because they have been unable to make a significant impact on the 20% of patients with 80% of the costs, whose barriers to care include lack of finances, lack of access, lack of compliance, poor healthcare choices such as smoking and obesity, and inability to overcome psychosocial issues that impact health and longevity.

“$800 billion is spent each year in the U.S. on Medicare recipients. $250 billion of that cost is spent by Medicare Advantage plans with a total membership of 3.5 million patients. There are more than 3,500 Medicare Advantage plans operating in the U.S., although 80% of that market is controlled by eight of the largest national and regional health plans. There is an unmet need for care of the neediest population who live in subsidized housing throughout major cities in the U.S. Underserved communities house the fastest growing and costliest populations, that is, seniors, in the country. Seniors have twice the level of chronic illness than the general population with 60% greater behavioral comorbidities and corresponding gaps in care. There is a need for cost-effective, quality care among the neediest patient populations.

“Moreover, ongoing and rapid growth has occurred in state government assist programs in the managed care market in the form of “Managed Long Term Care” (MLTC). Patients who require managed long term care are home-bound and require low-level personal care assistance with their daily activities. There has also been growth in the need for primary care in the “Skilled Nursing Facility” (SNF) market since skilled nursing facilities (SNFs) are a well-known nidus for repeated and frequent hospitalizations due to a paucity of care at those facilities. This has promulgated a growth in new companies providing primary care to nursing home patients but without resources to manage the entirety of this growing sector of the market. The growth in both MLTC and SNF healthcare needs have further demonstrated the need for a model of care which is entirely scalable to MLTC and SNF care.

“The largest growth sector in the U.S. has been in the population over the age of 65. Driven by the aging of the “baby boomers” generation, this demographic sector grew by over a third during the past decade, and by about 3.2%, that is, about 1,688,924, from the year 2018 to the year 2019. In addition to the aging of the population, there has been an increasing trend of chronic illnesses such as obesity and diabetes in the U.S. For example, the prevalence of diagnosed diabetes increased from 0.93% of the population in the year 1958 to 7.40% in the year 2015. The U.S. economy grew exponentially from 2017 through the beginning of 2020. Despite the negative impact on the economy as a result of the Coronavirus disease (COVID-19) pandemic, the U.S. economy is rebounding. Certain sectors of the economy continue to surge as a direct result of COVID-19. Additional forces driving upward growth in the health technology market has been the continuous downward pressure on Medicare and Medicaid premiums from both federal and state governments. Managed care plans in these sectors have seen continued erosion into their profit margins. Medicare Advantage plans have seen additional ceilings in their profitability as a result of a capping of their medical loss ratios, with no counter-balancing floor on their losses. As a result, entities in the healthcare space are searching for new and cost-effective ways to reduce the high costs of emergency room (ER) usage, hospital admissions, and pharmacy. The single largest driver of remote and at-home healthcare services has been the COVID-19 pandemic. As a result of voluntary and mandatory confinements during the height of the pandemic, healthcare delivery had become even less accessible and patients were dying from other diseases due to a lack of treatment and psychosocial factors dramatically increasing the risk of death due to heart disease, cancer, and suicides. Federal and local governments mandated payments for telehealth. Managed care payers have tried to expand home health visits. As a result, the public has a growing introduction and greater experience with remote care and has turned to remote care as an alternative to a doctor or emergency room visit.

“Due to high cost and lack of coordination of house calls, inadequate technology of telehealth, and general failures of disease management companies, telehealth solutions have been wanting. Spurred by the high cost of utilization and COVID-19, many entities have entered the remote, care-at-home, market. The growth of this market, due to COVID-19 becoming covered expenses, increases the need for care-at-home services as patients get exposed to the availability of such services. The general public has always embraced home healthcare. However, remote healthcare had greatly lagged and was either not well-accepted by patients and/or was not a covered expense by payers. Since the advent of the COVID-19 pandemic, acceptance of remote healthcare by the general public has increased dramatically. Use of telehealth, for example, is now commonplace and a covered benefit for Medicare and health plans and payment has been mandated by federal and local legislatures and executive orders.

“As an example of the need for a medical solution, it is estimated that 25% of Medicare patients are chronically affected by diabetes and 10% of those patients have complex, comorbid conditions that are poorly controlled. In the Medicare Advantage sector alone, this represents an estimated target of 80,000 members in need of an appropriate medical solution in the New York (N.Y.) tri-state area for diabetes alone. This patient population generates the highest cost to insurance providers due to non-compliance with prescribed medical, social, and behavioral protocols which results in recurring emergency room (ER) visits and re-hospitalization.

“Hence, there is a long-felt need in the healthcare industry for an at-home evaluation, management, and emergency room diversion system and method that optimizes home-visit appointments and related travel for delivering superior patient care as well as significant savings to health insurance providers.

“Furthermore, there is a long-felt need in the healthcare industry for a healthcare solution that bridges the divide between clinical primary care and managed care case management. Furthermore, there is a long-felt need for a healthcare model that provides real-time data on utilization, quality, and cost. Furthermore, there is a long-felt need for collection of medical and psychosocial data and to enhance machine learning (ML) algorithms that analyze and predict future population risks and cost-saving opportunities in any given geography.

“Furthermore, there is a long-felt need in the healthcare industry for a healthcare solution that improves patient compliance, satisfaction, and health outcomes, that removes barriers to healthcare and closes gaps in quality, that reduces emergency room visits and in-patient admissions and re-admissions, that increases patient, physician, and health insurance company satisfaction, and that achieves the elusive goal of cost-effective, quality care among patient populations that generate some of the highest costs incurred by healthcare companies.”

In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors’ summary information for this patent application: “This summary is provided to introduce a selection of concepts in a simplified form that are further disclosed in the detailed description of the invention. This summary is not intended to determine the scope of the claimed subject matter.

“The system and the computer-implemented method disclosed herein address the above-recited needs for an at-home evaluation, management, and emergency room diversion system and method that optimizes home-visit appointments and related travel for delivering superior patient care as well as significant savings to health insurance providers while capturing real-time data on utilization, quality, and cost. The system and the computer-implemented method provide a healthcare solution that improves patient compliance, satisfaction, and health outcomes, that removes barriers to healthcare and closes gaps in quality, that reduces emergency room visits and in-patient admissions and re-admissions, that increases patient, physician, and health insurance company satisfaction, and that achieves the elusive goal of cost-effective, quality care among patient populations that generate some of the highest costs incurred by healthcare companies. Moreover, the system and the computer-implemented method employ machine learning (ML) and artificial intelligence (AI) algorithms that analyze and predict future population risks and cost-saving opportunities in any given geography. The system and the computer-implemented method manage delivery of medical care through a comprehensive, continuous, coordinated, and technologically advanced system delivered to the most complex, costly, and chronically ill patients, extending the reach of an overburdened healthcare delivery system. The system and the computer-implemented method employ technology to bridge the gaps between patients, primary and specialty care, and third-party payers in the government and private sectors and focuses on healthcare value comprising access, care management/coordination, member compliance/adherence, and closing quality care gaps. The system and the computer-implemented method also employ technology to bridge the divide between clinical primary care and managed care case management. The system and the computer-implemented method manage patient care that focuses on continuity, coordination, and integration of care by blending medical, psychosocial, and behavioral care, bridging primary care with case management, and improving telemedicine. The system and the computer-implemented method employ leading edge technology to bring patient care into the home and areas remote from typical brick and mortar facilities.

“The system and the computer-implemented method disclosed herein provide a remote examination experience that approximates a doctor-present exam by providing a telemedicine scenario in which physicians not only see and hear patients remotely, but also conduct in-depth screenings and exams using hospital-grade, United States Food and Drug Administration (FDA)-registered diagnostic equipment deployed by trained onsite care coordinators (OCCs) acting as the “physician’s hands” at a patient location. The remote examination experience integrates the behavioral, social, and medical components of healthcare. The system and the computer-implemented method collect data in real time, measure trends using a predictive model, initiate solutions to reverse negative trends using machine learning and artificial intelligence algorithms, and optimize capitation models for healthcare providers and insurance providers. In separate embodiments, the system and the computer-implemented method provide a remote, high-touch patient examination mode where doctors, who are part of the healthcare providers, view data from a patient’s location in real time through a telehealth bridge from their offices to a telehealth kit at the patient’s location; and a telehealth mode where real-time data is not necessary, for example, for follow-ups, prescription refills, and routine check-ins. For example, chronic care management (CCM) programs include a mix of the remote, high-touch patient examination mode and the telehealth mode that work together to utilize and optimize available resources based on a patient’s needs. A patient-care solution that merely uses telehealth is not the same as the real physical data collected in real time during at-home or onsite visits, which is an integral part of the system and the computer-implemented method disclosed herein.

“The system and the computer-implemented method disclosed herein provide a proprietary appointment scheduling system that maximizes provider capacity across locations using proprietary algorithms. In effect, this allows one doctor to make multiple home visits concurrently. The system and the computer-implemented method collect medical and psychosocial data configured to be used in machine learning algorithms for analyzing and predicting future population risks and cost-saving opportunities. Given the fixed costs of hospitalization and re-hospitalization of patients with chronic conditions, emergency room (ER) visits, and an overall 80% budget spent on the population that uses ERs as the primary care, in an embodiment, the system and the computer-implemented method compute return on investment (ROI) by comparing a cohort of patients using the system to a few slices of similar cohorts from the same or even different plans, and clustering by similar age, conditions, and other social determinants of health. Given the cohort of patients, the system and the computer-implemented method create a home-visit appointment schedule according to the risk, among other factors, and attempts to cover visits to the most critical patients first, reducing unnecessary burden on the health system.

“The system and the computer-implemented method disclosed herein employ an appointment optimization and route planning system (AORPS) that defines computer program instructions executable by at least one processor for optimizing home-visit appointments and related travel for delivering patient care. The processor(s) is communicatively coupled to a non-transitory, computer-readable storage medium configured to store the computer program instructions and data defined and collected by the AORPS. Moreover, the system disclosed herein comprises one or more appointment scheduling modules, a global navigation satellite system (GNSS) module and a mapping module. The mapping module is configured to receive location input from the GNSS module. In an embodiment, the mapping module is a mapping module. The AORPS optimizes home-visit appointments and related travel for delivering patient care using algorithms comprising, for example, one or more of decision trees, machine learning models, and regression models.

“The appointment optimization and route planning system (AORPS) receives registration data and patient data from patients. The AORPS also receives client input comprising, for example, information about healthcare providers and onsite care coordinators such as their hours of availability; health plan commitments; appointment types; and a success rate of operation, from a client. The client is, for example, an administrator of a healthcare company that coordinates with the healthcare providers and the onsite care coordinators for the home-visit appointments. The AORPS receives the registration data and the patient data from the patients and the client input from the client through the appointment scheduling modules via a network, for example, the internet. The AORPS provides a user interface, for example, a web interface or a mobile application (app) interface, on the appointment scheduling modules for the patients and the client to input data depending on an electronic device used by the patients and the client to communicate with the appointment scheduling modules via the network. The AORPS collates the received patient data to capture information, for example, about the patients’ addresses, comorbidities, social and/or psychosocial determinants of health, religious beliefs, family status, gender, communities to which the patients belong, outstanding traits, insurance plans, insurance plan needs, and other relevant data in accordance with standard ontologies of health-related information for delivering relevant patient care, for clustering similar patients, and for matching appropriate healthcare providers and onsite care coordinators to each patient.”

There is additional summary information. Please visit full patent to read further.”

The claims supplied by the inventors are:

“1. A system for optimizing home-visit appointments and related travel for delivering patient care, the system comprising: one or more appointment scheduling modules; a global navigation satellite system module; a mapping module configured to receive location input from the global navigation satellite system module; a non-transitory, computer-readable storage medium configured to store computer program instructions and data defined by an appointment optimization and route planning system; at least one processor communicatively coupled to the non-transitory, computer-readable storage medium, the at least one processor configured to execute the defined computer program instructions; and the appointment optimization and route planning system comprising: a data reception module configured to receive registration data and patient data from patients; the data reception module further configured to receive client input comprising hours of availability of healthcare providers and onsite care coordinators, appointment types, health plan commitments, and a success rate of operation, from a client; an input processing module configured to collate the received patient data; the input processing module further configured to generate an input matrix based on the received client input and the collated patient data, covering a preconfigured period of time, the input matrix comprising schedules of the healthcare providers and the onsite care coordinators, patient cohorts, expected minimum daily and maximum monthly volumes of appointments, and success rates of the appointments; an output generation module configured to generate a predictive model based on training data comprising appointment history, patient history, feedback, and healthcare data; and the output generation module further configured to generate an appointment schedule with travel routes dynamically via the mapping module using the global navigation satellite system module based on optimization factors derived from the received client input, the collated patient data, the generated input matrix, the healthcare data, and the generated predictive model, incorporating real-time changes in the patient data, the client input, the optimization factors, and appointments.

“2. The system of claim 1, further comprising a client device configured for use by the client to communicate with the one or more appointment scheduling modules via a network.

“3. The system of claim 1, wherein the output generation module of the appointment optimization and route planning system is configured to utilize one or more of decision trees, machine learning models, and regression models for generating and executing the predictive model and for generating the appointment schedule.

“4. The system of claim 1, wherein the received patient data comprises age, gender, profession, location, lists of chronic health conditions, medical history, healthcare programs enrolled by the patients, free-form self-reports about current health, reasons for requiring medical attention, preferred time bounds to interact with one or more of the healthcare providers and the onsite care coordinators, and payment information.

“5. The system of claim 1, wherein the data reception module is further configured to match input from the patients, while receiving the patient data, with standard ontologies of health-related information in real time to provide input suggestions to the patients while receiving the patient data.

“6. The system of claim 1, wherein the data reception module is further configured to receive the feedback in the training data from the patients, the client, the healthcare providers, and the onsite care coordinators.

“7. The system of claim 1, wherein the healthcare data comprises healthcare information of cohorts similar to the patients in terms of demographics and comorbidities, costs of healthcare implementations in a country, and insurance information.

“8. The system of claim 1, wherein the predictive model comprises predicted patient behaviors, suggested cadence of appointments for each of the patients, predicted equipment requirements, appointment cancellation probabilities for each of the patients, potential outcomes, expected costs, capitation projections for insurance plans, return on investment for the insurance plans, and clusters of patients based on each of the collated patient data, the client input, the feedback in the training data, social and psychosocial determinants of health of the patients, insurance plans of the patients, and insurance plan needs of the patients.

“9. The system of claim 1, wherein the output generation module of the appointment optimization and route planning system is further configured to assign a mode of appointment comprising one of a remote, high-touch patient examination mode and a telehealth mode to each of the appointments in the generated appointment schedule based on the optimization factors.

“10. The system of claim 1, wherein the output generation module of the appointment optimization and route planning system is further configured to dynamically adjust the generated appointment schedule with the travel routes in real time based on changes in the optimization factors, changes in the patients, changes in the healthcare providers and the onsite care coordinators, and rejection of the appointments by the patients with minimal disruption.

“11. A computer-implemented method employing an appointment optimization and route planning system configured to define computer program instructions executable by at least one processor for optimizing home-visit appointments and related travel for delivering patient care, the method comprising: receiving registration data and patient data from patients; receiving client input comprising hours of availability of healthcare providers and onsite care coordinators, appointment types, health plan commitments, and a success rate of operation, from a client; collating the received patient data; generating an input matrix based on the received client input and the collated patient data, covering a preconfigured period of time, the input matrix comprising schedules of the healthcare providers and the onsite care coordinators, patient cohorts, expected minimum daily and maximum monthly volumes of appointments, and success rates of the appointments; generating a predictive model based on training data comprising appointment history, patient history, feedback, and healthcare data; and generating an appointment schedule with travel routes dynamically based on optimization factors derived from the received client input, the collated patient data, the generated input matrix, the healthcare data, and the generated predictive model, incorporating real-time changes in the patient data, the client input, the optimization factors, and appointments, via a mapping using a global navigation satellite system module.

“12. The computer-implemented method of claim 11, wherein the generation and execution of the predictive model and the generation of the appointment schedule is performed by utilizing one or more of decision trees, machine learning models, and regression models.

“13. The computer-implemented method of claim 11, wherein the received patient data comprises age, gender, profession, location, lists of chronic health conditions, medical history, healthcare programs enrolled by the patients, free-form self-reports about current health, reasons for requiring medical attention, preferred time bounds to interact with one or more of the healthcare providers and the onsite care coordinators, and payment information.

“14. The computer-implemented method of claim 11, further comprising matching input from the patients, while receiving the patient data, with standard ontologies of health-related information in real time to provide input suggestions to the patients while receiving the patient data.

“15. The computer-implemented method of claim 11, further comprising receiving the feedback in the training data from the patients, the client, the healthcare providers, and the onsite care coordinators.

“16. The computer-implemented method of claim 11, wherein the healthcare data comprises healthcare information of cohorts similar to the patients in terms of demographics and comorbidities, costs of healthcare implementations in a country, and insurance information.

“17. The computer-implemented method of claim 11, wherein the predictive model comprises predicted patient behaviors, suggested cadence of appointments for each of the patients, predicted equipment requirements, appointment cancellation probabilities for each of the patients, potential outcomes, expected costs, capitation projections for insurance plans, return on investment for the insurance plans, and clusters of patients based on each of the collated patient data, the client input, the feedback in the training data, social and psychosocial determinants of health of the patients, insurance plans of the patients, and insurance plan needs of the patients.

“18. The computer-implemented method of claim 11, further comprising assigning a mode of appointment comprising one of a remote, high-touch patient examination mode and a telehealth mode to each of the appointments in the generated appointment schedule based on the optimization factors.

“19. The computer-implemented method of claim 11, further comprising dynamically adjusting the generated appointment schedule with the travel routes in real time based on changes in the optimization factors, changes in the patients, changes in the healthcare providers and the onsite care coordinators, and rejection of the appointments by the patients with minimal disruption.”

There are additional claims. Please visit full patent to read further.

URL and more information on this patent application, see: Kogan, Daniel; Sumareva, Rada; Ukrainksy, Gennady. System And Method For Optimizing Home Visit Appointments And Related Travel. U.S. Patent Application Number 20230005607, filed June 24, 2022 and posted January 5, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20230005607)&db=US-PGPUB&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)