FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of invention:
SYSTEMS AND METHODS FOR MANAGEMENT AND OPTIMIZATION OF A SERVICE PROVIDER NETWORK
Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed.
2
TECHNICAL FIELD
[001]
The disclosure herein generally relates to the field of service provider network, and, more particularly, to systems and methods for management and optimization of a service provider network.
5
BACKGROUND
[002]
To increase the coverage of their members, payer organizations typically create a country wide network of providers that meet varying needs of its members (e.g., from primary care to specialty treatments to home care etc.). Building a network that satisfactorily serves its members and own business 10 objectives (e.g., competitive challenges, revenue management) even while meeting government and regulatory requirements is a complex task. There can be multiple business objectives for setting up a network like maximizing revenue, minimizing cost, maximizing member experience etc. With thousands of assets in a service provider network and multiple business objectives, it becomes complex to identify 15 the most optimum network for a specific purpose.
[003]
Traditional service provider networks pose technical challenges of converting business objectives and constraints into well-defined dataset that can be processed mathematically. Once data is available, traditional analytics and visualization approaches can help identify outliers only and not an optimum 20 combination of network components. Further, traditional optimization frameworks deal with single objective outcome and not on multiple objective outcomes such as a network list, and the like. Multiple objectives give the lever to select alternate sites of care based on user preference. By the time business is able to come to a conclusion regarding optimized network, the data already becomes outdated. The 25 optimization has to be done keeping in mind the trends in requirements of patients. Further, utilization of optimization results in innovative ways that can directly impact upstream or downstream business processes, is a challenge.
30
3
SUMMARY
[004]
Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a processor implemented method is provided. The processor 5 implemented method, comprising obtaining, via one or more hardware processors, a set of business objectives from a library and a set of constraints corresponding to a service provider network; identifying, via the one or more hardware processors, one or more user demands in the service provider network using a clustering technique and a predictive technique in accordance with the set of business 10 objectives and the set of constraints; predicting, via the one or more hardware processors, a mapping of the one or more user demands with one or more service end points and a future state of the service provider network using at least a machine leaning model from a set of machine learning based models from the library; inputting, via the one or more hardware processors, the one or more user demands 15 mapped with the one or more service end points, the future state of the service provider network, the set of business objectives and the set of constraints to a population based heuristic model implemented using a combination of genetic algorithm and binary integer programming technique; dynamically optimizing, via the one or more hardware processors, a current state and the future state of the 20 service provider network against one or more user specified criteria based on the predicted mapping of the one or more user demands with the one or more service end points to obtain an optimum service provider network, wherein the current state and the future state of the service provider network are optimized using the population based heuristic model; segmenting, via the one or more hardware 25 processors, the optimized service provider network into a set of tiers in accordance with the set of business objectives using the optimized current state and the optimized future state of the optimum service provider network; and determining, via the one or more hardware processors, the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the 30 population based heuristic model.
4
[005]
In another aspect, a system is provided. The system comprising a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: obtain a set of business objectives from a library 5 and a set of constraints corresponding to a service provider network; identify one or more user demands in the service provider network using a clustering technique and a predictive technique in accordance with the set of business objectives and the set of constraints; predict a mapping of the one or more user demands with one or more service end points and a future state of the service provider network using at 10 least a machine leaning model from a set of machine learning based models from the library; input the one or more user demands mapped with the one or more service end points, the future state of the service provider network, the set of business objectives and the set of constraints to a population based heuristic model implemented using a combination of genetic algorithm and binary integer 15 programming technique; dynamically optimize a current state and the future state of the service provider network against one or more user specified criteria based on the predicted mapping of the one or more user demands with the one or more service end points to obtain an optimum service provider network, wherein the current state and the future state of the optimum service provider network are optimized using 20 the population based heuristic model; segment the provider network into a set of tiers in accordance with the set of business objectives using the optimized current state and the optimized future state of the optimum service provider network; and determine the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the population based heuristic 25 model.
[006]
In yet another aspect, a non-transitory computer readable medium is provided. The non-transitory computer readable medium are configured by instructions for obtaining, a set of business objectives from a library and a set of constraints corresponding to a service provider network; identifying, one or more 30 user demands in the service provider network using a clustering technique and a
5
predictive technique in accordance with the set of business objectives and the set of
constraints; predicting, a mapping of the one or more user demands with one or more service end points and a future state of the service provider network using at least a machine leaning model from a set of machine learning based models from the library; inputting, the one or more user demands mapped with the one or more 5 service end points, the future state of the service provider network, the set of business objectives and the set of constraints to a population based heuristic model implemented using a combination of genetic algorithm and binary integer programming technique; dynamically optimizing, a current state and the future state of the service provider network against one or more user specified criteria based on 10 the predicted mapping of the one or more user demands with the one or more service end points to obtain an optimum service provider network, wherein the current state and the future state of the service provider network are optimized using the population based heuristic model; segmenting, the optimized service provider network into a set of tiers in accordance with the set of business objectives using 15 the optimized current state and the optimized future state of the optimum service provider network; and determining, the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the population based heuristic model.
[007]
In accordance with an embodiment of the present disclosure, the 20 optimum service provider network is continuously monitored using a plurality of temporal data to identify one or more shifts in the optimum service provider network.
[008]
In accordance with an embodiment of the present disclosure, a corrective action and engagements with one or more users are performed when the 25 one or more shifts are identified in the optimum service provider network.
[009]
In accordance with an embodiment of the present disclosure, a cross service provider network collaboration and a competitive assessment are enabled using the optimum service provider network.
[010]
In accordance with an embodiment of the present disclosure, the 30 cross service provider network collaboration is performed based on modelling of a
6
new set of service end points in the service provider network and analysis of impact
of the new set of service end points on the set of business objectives.
[011]
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. 5
BRIEF DESCRIPTION OF THE DRAWINGS
[012]
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles: 10
[013]
FIG. 1 illustrates an exemplary system for management and optimization of a service provider network, according to some embodiments of the present disclosure.
[014]
FIG. 2 illustrates an architectural overview of the system of FIG. 1 for management and optimization of a service provider network, in accordance with 15 some embodiments of the present disclosure.
[015]
FIG. 3 illustrates an exemplary flow diagram illustrating a method for management and optimization of a service provider network, in accordance with some embodiments of the present disclosure.
[016]
FIG. 4 depicts a block diagram illustrating a multi-objective 20 optimization approach for management and optimization of a service provider network, in accordance with some embodiments of the present disclosure.
[017]
FIG. 5 shows an application interface for optimization problem configuration for management and optimization of the service provider network, in accordance with some embodiments of the present disclosure. 25
[018]
FIG. 6 shows an application interface displaying optimization results as multiple lists, in accordance with some embodiments of the present disclosure.
[019]
FIGS. 7A and 7B depict convergence graphs for cost objective and a combined cost & utilization objectives respectively for management and 30
7
optimization of the service provider network,
in accordance with some embodiments of the present disclosure
[020]
FIG. 8 depicts a graphical representation illustrating parallel coordinate plot (PCP) charts to visualize a solution space with multiple business objectives for management and optimization of the service provider network, in 5 accordance with some embodiments of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS
[021]
Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number 10 identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. It is 15 intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following embodiments described herein.
[022]
Embodiments of the present disclosure provide a system and method for management and optimization of a service provider network. The expression ‘service provider network’ is applicable to all business domains that deal with " a 20 set of service delivery points which constitutes a network" (can this be better -> “set of service delivery points which constitutes a network”. These business domains may include but are not limited to a retail store chain, bank automated telling machines (ATMs), and Healthcare Service Provider Network. In the case of bank ATMs, the network of ATMs is optimized such that maximum customers are 25 able to use it with minimum travel time. Similarly, a retail store chain could be optimized based on maximizing revenues, minimizing time for customers to travel, and/or the like. In the case of the healthcare, the service provider network refers to a list of the doctors, other health care providers, and hospitals that a health plan contracts with to provide medical care to its members. These providers are called 30 “network providers” or “in-network providers.” A provider that isn’t contracted
8
with the plan is called an “out
-of-network provider.” In the method of present disclosure, the needs of members (i.e., a demand) of the service provider network are predicted and mapped with a current service provider network (i.e., supply). Further optimization of the service provider network is performed against one or more criteria of such as revenue/costs, member experience, quality of service, and 5 regulatory obligations. The optimized service provider network is further monitored continuously using temporal data to identify shifts in network and accordingly trigger actions and engagements with stakeholders.
[023]
Referring now to the drawings, and more particularly to FIGS. 1 through 8, where similar reference characters denote corresponding features 10 consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[024]
FIG. 1 illustrates an exemplary system 100 for management and optimization of a service provider network, according to some embodiments of the 15 present disclosure. In an embodiment, the system 100 includes or is otherwise in communication with one or more hardware processors 104, communication interface device(s) or input/output (I/O) interface(s) 106, and one or more data storage devices or memory 102 operatively coupled to the one or more hardware processors 104. The one or more hardware processors 104, the memory 102, and 20 the I/O interface(s) 106 may be coupled to a system bus 108 or a similar mechanism.
[025]
The I/O interface(s) 106 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface(s) 106 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a 25 mouse, an external memory, a plurality of sensor devices, a printer and the like. Further, the I/O interface(s) 106 may enable the system 100 to communicate with other devices, such as web servers and external databases.
[026]
The I/O interface(s) 106 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for 30 example, local area network (LAN), cable, etc., and wireless networks, such as
9
Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface(s)
106 may include one or more ports for connecting a number of computing systems with one another or to another server computer. Further, the I/O interface(s) 106 may include one or more ports for connecting a number of devices to one another or to another server. 5
[027]
The one or more hardware processors 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 are configured to fetch and 10 execute computer-readable instructions stored in the memory 102. In the context of the present disclosure, the expressions ‘processors’ and ‘hardware processors’ may be used interchangeably. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, portable computer, notebooks, hand-held devices, workstations, mainframe computers, servers, a 15 network cloud and the like.
[028]
The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable 20 ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 102 includes a plurality of modules 102a and a repository 102b for storing data processed, received, and generated by one or more of the plurality of modules 102a. The plurality of modules 102a may include routines, programs, objects, components, data structures, and so on, which perform particular 25 tasks or implement particular abstract data types.
[029]
The plurality of modules 102a may include programs or computer-readable instructions or coded instructions that supplement applications or functions performed by the system 100. The plurality of modules 102a may also be used as, signal processor(s), state machine(s), logic circuitries, and/or any other 30 device or component that manipulates signals based on operational instructions.
10
Further, the plurality of modules
102a can be used by hardware, by computer-readable instructions executed by the one or more hardware processors 104, or by a combination thereof. Further, the memory 102 may include information pertaining to input(s)/output(s) of each step performed by the processor(s) 104 of the system 100 and methods of the present disclosure. 5
[030]
The repository 102b may include a database or a data engine. Further, the repository 102b amongst other things, may serve as a database or includes a plurality of databases for storing the data that is processed, received, or generated as a result of the execution of the plurality of modules 102a. Although the repository 102b is shown internal to the system 100, it will be noted that, in 10 alternate embodiments, the repository 102b can also be implemented external to the system 100, where the repository 102b may be stored within an external database (not shown in FIG. 1) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. For example, new data may be added into the external database and/or existing data may be 15 modified and/or non-useful data may be deleted from the external database. In one example, the data may be stored in an external system, such as a Lightweight Directory Access Protocol (LDAP) directory and a Relational Database Management System (RDBMS). In another embodiment, the data stored in the repository 102b may be distributed between the system 100 and the external 20 database.
[031]
FIG. 2 illustrates an architectural overview of the system 100 of FIG. 1 for management and optimization of a service provider network, in accordance with some embodiments of the present disclosure. As shown in FIG. 2, one or more payer data source of a service provider network, an optimization platform for the 25 service provider network, and end users of the service provider network are described.
[032]
FIG. 3 illustrates an exemplary flow diagram illustrating a method for management and optimization of a service provider network, in accordance with some embodiments of the present disclosure. 30
11
[033]
Referring to FIG. 3, in an embodiment, the system(s) 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more hardware processors 104 and is configured to store instructions for execution of steps of the method by the one or more processors 104. The steps of the method 200 of the present disclosure will now be explained with reference to 5 components of the system 100 of FIG. 1, the functional block diagram of FIG. 2, the flow diagram as depicted in FIG. 3, and one or more examples. Although steps of the method 200 including process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of 10 steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any practical order. Further, some steps may be performed simultaneously, or some steps may be performed alone or independently.
[034] With reference to the architectural overview of the system 100 15 depicted in FIG. 2 and referring to the steps of the method 200, at step 202 of the present disclosure, the one or more hardware processors 104 are configured to obtain a set of business objectives from a library and a set of constraints corresponding to a service provider network. The set of business objectives may include but are not limited to minimizing cost, maximizing hospital utilization, 20 maximizing use of ambulatory surgical centers, improving quality by minimizing hospital acquired infections and readmissions, and/or the like. The set of business constraints may include but are not limited to an ability to meet minimum provider criteria per county as defined by regulatory bodies, ability to meet minimum revenues, and ability to serve minimum X% of existing patients, and/or the like. In 25 an embodiment, the library comprises a plurality of features obtained from one or more data payer data sources as shown in FIG. 2. The plurality of features may include but are not limited to cost of services, gap in services, experience of services, and quality of services (Combinedly referred as CGEQ features). In case of a healthcare service provider network, the cost of services feature may include 30 but are not limited to co-pay amounts, claim amounts, unit price, prescription drug
12
costs, surgeries cost,
and consultation costs. Further, the gaps in services features may include but are not limited to the minimum number of hospitals required per county per specialty, and facility types (e.g., ambulatory surgical centers, OPD, IPD). The experience of services feature may include but are not limited to travel time to reach a facility, waiting period at the facility, number of beds for in-patient 5 hospitals. The quality of service (QoS) feature may include but are not limited to facility certification information, hospital acquired infections, post procedure readmissions, and/or the like. In an embodiment, business expectations can also be converted into constraints. For example, a Business as Usual (BAU) in spite of optimization could mean elimination of certain hospital facilities from the service 10 provider network, however there may be need to not disturb existing member base. In such case, constraints could be 90% (or configured) of patient servicing capacity to remain.
[035]
Further, at step 204 of the present disclosure, the one or more hardware processors 100 are configured to identify one or more user demands in 15 the service provider network using a clustering technique and a predictive technique in accordance with the set of business objectives and the set of constraints. The clustering technique may include but are not limited to K-Means clustering, and hierarchical clustering, and/or the like. In an embodiment, the predictive technique is a time series technique which forecasts future values of the plurality of features 20 (i.e., CGEQ features) by first fetching historical data for those features from the plurality of features on which forecasting is needed. Further, a generalized additive modelling or classical modelling approach such as Auto Regression, Autoregressive moving-average model (ARMA), Autoregressive integrated moving average (ARIMA), and/or the like is used as shown in equation (1) below: 25
𝐴(𝑡) = 𝑤∗𝐴(𝑡−𝑛) + 𝑒 (1)
The forecasted values of the plurality of features are used as a baseline objective’s for finding possible service provider networks of the future.
[036]
Again, in case of the healthcare service provider network, the system 100 enables understanding needs of the population and predict that into future to 30 identify which specialties would be required more or which geographies would see
13
gaps in
the service provider network. Such an analysis helps in identifying the needs and issues of population (i.e., members of the service provider network) with respect to the plurality of features (i.e., CGEQ features). This is enabled through predictions from a plurality of machine learning (ML) models to predict future needs at population scale. For example, network adequacy to meet compliance and 5 member needs. In an embodiment, some non-limiting examples of external factors that can be modelled to predict demand using the clustering technique include prevalence and incidence of a particular disease in specific areas, network attrition due to provider fatigue, compliance requirements to demonstrate that networks have enough providers/facilities to meet minimum number requirements and allow 10 adequate access for beneficiaries/potential enrollees, and compliance requirements to demonstrate that networks do not unduly burden beneficiaries in terms of travel time and distance to network providers/facilities.
[037]
At step 206 of the present disclosure, the one or more hardware processors 104 are configured to predict a mapping of the one or more user demands 15 with one or more service end points and a future state of the service provider network using at least a machine leaning model from a set of machine learning based models from the library. The one or more service end points may include a current service provider in the service provider network. For identifying the one or more user demands and be able to predict better, the demand is first defined 20 granularly using clustering technique. For example, potential medical cases that can be diverted to ambulatory surgical centers (ASC) which are a low-cost option compared to in patient hospitalization (IPD). Here clustering (e.g., k-means clustering) can be performed using a set of features such as length of stay, patient disposition, elective procedure, hospital specialty, and/or the like. Similarly, for 25 prevalence of lifestyle diseases in comparison to chronic diseases, clustering can be performed based on features like demography and social determinant characteristics (SDoH).
[038]
At step 208 of the present disclosure, the one or more hardware processors 104 are configured to input the one or more user demands mapped with 30 the one or more service end points, the future state of the service provider network,
14
the set of business objectives and the set of constraints
to a population based heuristic model implemented using a combination of genetic algorithm and binary integer programming technique. Once the one or more user demands is identified at the specified granularity, it can be mapped to the one or more service end points which include hospitals. The one or more user demand can also be mapped to 5 demand generation end points that includes geographies. In case of mapping to the one or more service end points, the clusters are mapped to the specific ASC’s and IPD hospitals. In case of mapping to the demand generation end point, the granular demand is mapped to the geographies (e.g. counties or zip codes). This provides a better view of future demand on a granular scale using predictive techniques and 10 clustering techniques. With these inputs, the optimization is performed using the population based heuristic model implemented using the combination of genetic algorithm and binary integer programming technique. Genetic algorithm (GA) is a class of population based heuristic algorithms that are inspired by biological themes such as mutation and selection. A binary integer programming problem is a 15 mathematical optimization program in which all of the variables are restricted to be binary integers (i.e., 0 and 1 only). In the case of service provider network, there cannot be a 0.3 hospital. It has to be 0 or 1. For example, if the health care providers are selected to form a service provider network based on their cost. Then decision variable 𝑋𝑖 for selecting provider 𝑖 can take values either 0 which means not 20 selected or 1 which means selected. The overall string of binary numbers for k health care providers looks like 101110....0011 (i.e., k digits long) where index of each digit represents index of health care provider and value at each index represents whether corresponding health care provider is selected or not. This binary string acts like a chromosome of gene sequence and the cost for each health 25 care provider acts like weightage of each gene to be selected. A genetic algorithm generates permutations of such binary strings using evolutionary techniques such as mutation, crossover and selection and then calculates a weighted sum of all permutations and rank them. The binary strings at the top based on rank are observed to best fit the solution. 30
15
[039]
Further, at step 210 of the present disclosure, the one or more hardware processors 104 are configured to dynamically optimize a current state and the future state of the service provider network against one or more user specified criteria based on the predicted mapping of the one or more user demands with one or more service end points to obtain an optimum service provider network. The 5 current state and the future state of the service provider network are optimized using the population based heuristic model implemented using the combination of genetic algorithm and binary integer programming technique.
[040]
The steps 208 and 210 are better understood by way of the following description provided as exemplary explanation. 10
[041]
The system 100 enables payers to use CGEQ features dimensions and create a plurality of optimization projects with one or more combinations of CGE feature dimensions. For example, (i) least overall cost of service, where cost dimension includes unit cost of services for diagnosis related group (DRG)-severity combinations, (ii) least overall gaps in care with respect to compliance requirements 15 of minimum services to be provided, (iii) best overall experience of patient and doctors such as GIS based members information with zip codes falling within a radius around hospital to reflect best travel convenience. DRGs are manageable and clinically coherent set of patient classes that relate a hospital’s case mix to the resource demands and associated costs experienced by the hospital. DRGs are 20 defined based on the principal diagnosis, secondary diagnoses, surgical procedures, age, sex and discharge status of the patients treated. From a doctor’s perspective, it relates to utilization percentage of the doctors of a facility which directly impacts the time they are able to give for each patient, and (iv) best quality of care where quality dimension includes credential validity period, readmission, hospital 25 acquired infection, Consumer Assessment of Healthcare Providers & Systems (CAHPS) score, clinical documentation gaps, and/or the like. CAHPS represents a set of surveys done by Centers for Medicare & Medicaid Services (CMS.gov).
[042]
For a mathematical representation of an optimization project from a plurality of optimization projects, CGEQ dimensions are filtered based on counties 30 and specialty combination for each state and specialty combination. For example,
16
for a given geographical region
𝑅, there are a set of counties 𝐶 = 𝐶𝑖 such that each 𝐶𝑖 belongs to the region 𝑅, a set of health care providers 𝐻 = 𝐻𝑖 such that each 𝐻𝑖 belongs to region 𝑅, and a set of specialties 𝑆 = 𝑆𝑘 such that each 𝑆𝑘 is delivered by at least one hospital/health care provider in the region 𝑅. Further, 𝐵𝑖𝑘 represents minimum number of health care providers having specialty 𝑆𝑘 in each county 𝐶𝑖, 5 𝐹𝑖𝑘 represents a list of health care providers having specialty 𝑆𝑘 in each county 𝐶𝑖, 𝐶𝑆𝑇𝑖𝑗 represents total cost of specialties 𝑆𝑗 (=1..𝑛) belonging to a given health care provider 𝐻𝑖, 𝑈𝑇𝐿𝑖𝑗 represents utilizations of specialties 𝑆𝑗 (=1..𝑛) belonging to a given health care provider Hi, 𝑅𝐸𝐴𝐷𝑖𝑗 represent the readmissions of specialties 𝑆𝑗 (=1..𝑛) belonging to given health care provider 𝐻𝑖, 𝐻𝑇𝑌𝑃𝐸𝑖𝑗 represents 10 hospital type of specialties 𝑆𝑗 (=1..𝑛) belonging to given health care provider 𝐻𝑖, and 𝐻𝐴𝐼𝑖𝑗 represents infections of specialties 𝑆𝑗 (=1..𝑛) belonging to given health care provider 𝐻𝑖. All data obtained for the region 𝑅 is cleaned again to weed out any inconsistency such as missing values for county and specialty. A moving average (MA) approach is used for imputing missing values of CGEQ parameters. 15 Here, the length of window is defined for moving average calculation. Historical records for the data on which MA is needed is fetched and then rolling window calculation with mean aggregation is used to get MA.
[043]
In an embodiment, the optimization of the current state and the future state of the service provider network is a multi-objective optimization. FIG. 20 4 depicts a block diagram illustrating a multi-objective optimization approach for management and optimization of the service provider network, in accordance with some embodiments of the present disclosure. As shown in FIG. 4, the first problem is analyzed and then multiple business objectives and constraints are added. For example, 𝑋 represent a list of all health care providers containing 1 if an 𝑋𝑖 is 25 present in the service provider network and 0 if it is not part of the service provider network. For a given specialty 𝑆𝑗, the set of business objectives derived are as (i) Minimize (Product (𝐶𝑆𝑇𝑖𝑗,𝑋𝑖) for all 𝑖) (ii) Maximize (Product (𝑈𝑇𝐿𝑖𝑗,𝑋𝑖) for all 𝑖); (iii) Minimize (Product (𝑅𝐸𝐴𝐷𝑖𝑗,𝑋𝑖) for all 𝑖); (iv) Minimize (Product
17
(
𝐻𝑇𝑌𝑃𝐸𝑖𝑗,𝑋𝑖) for all 𝑖), and (v) Minimize (Product (𝐻𝐴𝐼𝑖𝑗,𝑋𝑖) for all), subject to constraints which is provided below in equation (2) as:
𝑓𝑜𝑟 𝑎𝑙𝑙 𝐶𝑖,𝐶𝑜𝑢𝑛𝑡 (𝐻𝑖 𝑝𝑟𝑒𝑠𝑒𝑛𝑡 𝑖𝑛 𝐶𝑖)>= 𝐵𝑖𝑗; 𝑀𝑎𝑥𝑖𝑚𝑖𝑧𝑒 ( 𝑃𝑟𝑜𝑑𝑢𝑐𝑡 (𝑈𝑇𝐿𝑖𝑗,𝑋𝑖)𝑓𝑜𝑟 𝑎𝑙𝑙 𝑖)> (2)= 𝑆𝑢𝑚 (𝑈𝑇𝐿𝑖𝑗 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑖)∗0.9 5
The above problem formulation is an integer programming problem. Solution for the above multi objective optimization problem, gives a set of 𝑋𝑖 and values of each business objective for those individual 𝑋𝑖. To solve the above multi objective optimization problem, Non-dominated Sorting Genetic Algorithm (NSGA2) genetic algorithm is used. The NSGA2 algorithm ensures the solution set is pareto 10 optimal, if found. Pareto optimal solutions are trade off solutions where none of the individual solution dominates any other solution.
[044]
FIG. 5 shows an application interface for optimization problem configuration for management and optimization of the service provider network, in accordance with some embodiments of the present disclosure. As shown in FIG. 5, 15 the application interface allows configuration of business objectives, constraints, algorithm into an optimization project where end users utilize the population based heuristic model implemented using the combination of genetic algorithm and binary integer programming technique to configure the optimization problem with the application interface. If a solution set is found, Technique for Order of Preference 20 by Similarity to Ideal Solution (TOPSIS) which is a multi-criteria decision-making theory is used to select top 𝑁 operating points for end users. As a result of optimization, a list of hospitals that form the service provider network is obtained and shared with user(s). There can be a single list with best optimization results or multiple lists (e.g., top optimized network for each objective). FIG. 6 shows an 25 application interface displaying optimization results as multiple lists, in accordance with some embodiments of the present disclosure. Such a set of lists enables users to objectively decide which service provider network suits their requirements in best possible way considering the multiple business objectives being set which could be contrary to each other (e.g., maximizing revenue and minimizing costs). 30
18
[045]
In an embodiment, outcomes of the population based heuristic model are verified by plotting various measures such as hypervolume indicator which is a measure of the region dominated by a particular solution set and hence needs to be higher indicating better quality of results obtained and convergence graphs that are plotted for the business objectives which shows how fast the genetic 5 algorithm converges towards the optimal solution. FIGS. 7A and 7B depict convergence graphs for cost objective and a combined cost & utilization objectives respectively for management and optimization of the service provider network, in accordance with some embodiments of the present disclosure. As shown in FIG. 7A, for the cost objective, the absolute value of cost is converging after 20000 10 iterations. As shown in FIG. 7B, multiple business objectives together are plotted with scaled objective values rather than absolute values to understand dynamics of contrary objectives.
[046]
FIG. 8 depicts a graphical representation illustrating parallel coordinate plot (PCP) charts to visualize a solution space with multiple business 15 objectives for management and optimization of the service provider network, in accordance with some embodiments of the present disclosure. In FIG. 8, scaled business objectives together including cost, utilization, readmission, hospital acquired infections and hospital type priority for various iterations of the optimization model are shown. 20
[047]
In an embodiment, at the step 212 of the present disclosure, the one or more hardware processors are configured to segment the service provider network into a set of tiers in accordance with the set of business objectives using the optimized current state and the optimized future state of the service provider network. For example, the service provider network is divided into tiers based on 25 costs and utilization. For segmenting the service provider network into the set of tiers, decision variables, objective function and constraints are defined. It is assumed that 𝑋𝑖 is the count of variable 𝑖, the objective function is to minimize sum of products of the variables 𝑋𝑖 and their average costs 𝑊𝑖 which can be written as 𝑆𝑢𝑚(𝑋𝑖∗ 𝑊𝑖), where 𝑊𝑖 is the average cost of tier 𝑖, and the set of constraints are: 30 (a) all variables must be non-negative: 𝑋𝑖>0 for all 𝑖, and (b) the sum of counts
19
must be equal to a given value:
𝑆𝑢𝑚(𝑋𝑖) = 𝑃, where 𝑃 is overall count of the service providers in a given area. This optimization problem is solved using integer programming principles. The output is the count of service providers in each tier. For example, considering business objective are maximize utilization and minimize cost as: Minimize 5 (𝑃𝑟𝑜𝑑𝑢𝑐𝑡 (𝐶𝑆𝑇𝑖𝑗,𝑋𝑖) f𝑜𝑟 𝑎𝑙𝑙 𝑖), Maximize (𝑃𝑟𝑜𝑑𝑢𝑐𝑡 (𝑈𝑇𝐿𝑖𝑗,𝑋𝑖) 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑖), subject to constraints that resultant service provider network is still serving 90% of members as: 𝑀𝑎𝑥𝑖𝑚𝑖𝑧𝑒 ( 𝑃𝑟𝑜𝑑𝑢𝑐𝑡 (𝑈𝑇𝐿𝑖𝑗,𝑋𝑖) 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑖) >= 𝑆𝑢𝑚 (𝑈𝑇𝐿𝑖𝑗 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑖)∗0.9. By iteratively running the optimization with above constraint as >90%, between 70-90%, between 50-70% and <50%, four tiers of the 10 service provider network are created.
[048]
Further, at the step 212 of the present disclosure, the one or more hardware processors 104 are configured to determine the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the population based heuristic model. The one or more service end 15 points are referred to as count of service providers in each tier. For finding count of service providers in each tier that can minimize the overall cost of the providers, binary integer programming is used. For, finding the service providers in each tier given the count of each tier, the decision variables are defined, where 𝑋𝑖 represents a binary variable for each service provider. Further, the business objective functions 20 are defined as:
(a) 𝑀𝑖𝑛𝑖𝑚𝑖𝑧𝑒: 𝑆𝑢𝑚_𝑖(𝑋𝑖∗𝑊𝑖), where 𝑊𝑖 is cost of each service provider, (b) Minimize: 𝑆𝑢𝑚_𝑗(𝐶𝑗−𝑆𝑢𝑚(𝑠𝑒𝑟𝑣𝑖𝑐𝑒 𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑟𝑠 𝑠𝑒𝑙𝑒𝑐𝑡𝑒𝑑 𝑏𝑒𝑙𝑜𝑛𝑔𝑖𝑛𝑔 𝑡𝑜 𝑡𝑖𝑒𝑟 𝑗)), where 𝐶𝑗 is the count of service providers in tier 𝑗, and the constraints is that the selected service providers 25 should satisfy each Centers for Medicare & Medicaid Services (CMS) minimum service provider constraint. This is solved using binary integer programming to arrive at a list of service providers for each Tier.
20
[049]
In an embodiment, a segmentation technique is used to identify segments based on Travel Distance & time between Member to service provider location based on Latitude and Longitude as following:
(i)
If Calculated Distance (Member to Provider) <= CMS Distance for given specialty and state, then the service provider sis classified as “Matched”. 5
(ii)
If Calculated Distance (Member to Provider) > CMS Distance for given specialty and State and Both Member and Facility State ZIP Codes are in same state, then the service provider is classified as “Not matched – Poor (Within state)”.
(iii)
If Calculated Distance (Member to Provider) > CMS Distance for given 10 specialty and State and Either Member (or) Facility State ZIP Codes are not in same state, then the service provider is classified as “Out of Network”.
(iv)
If Calculated Distance (Member to Provider) > CMS Distance for given specialty and State and Either Member (or) Facility State ZIP Codes are not in same state, then service provider is classified as “Out of Network “ 15
In an embodiment, a score is assigned to each of the above classified service providers and an aggregated score is calculated for a hospital using weightage-based aggregation of the scores of all of the above classified service providers for all patients coming to that hospital. Thus, a score is obtained for Matched, Not Matched, and Out of Network service providers for each hospital. For example, the 20 score for the service providers classified as ‘Matched’ for the hospital is determined as shown in equation (3) below:
“𝑀𝑎𝑡𝑐ℎ” 𝑆𝑐𝑜𝑟𝑒 (𝑖) = 𝑆𝑢𝑚 {𝑀𝑎𝑡𝑐ℎ 𝑆𝑐𝑜𝑟𝑒 (𝑛)} (3)
Here, 𝑖 represents hospital and 𝑛 represents patients.
[050]
In an embodiment, the optimum service provider network is 25 continuously monitored using a plurality of temporal data to identify one or more shifts in the service provider network. A corrective action and engagements with one or users are performed when one or more shifts are identified in the service provider network. The system 100 of the present disclosure enables to perform temporal data analysis such as changes in Tier/segment of a service provider over 30 time. These changes help in creating next best actions (NBAs) (either predictive or
21
rule based) for the service providers.
The optimum service provider network is monitored continuously using temporal data to identify shifts (e.g., member needs, physician stickiness) and accordingly trigger actions and engagements with stakeholders. For example, next best engagement (NBE) opportunities for physicians for increasing loyalty/stickiness of Tier one physicians or additional 5 diligence for service providers getting downgraded in Quality based Tiers.
[051]
In an embodiment, a cross service provider network collaboration and a competitive assessment are enabled using the optimum service provider network. The cross-service provider network collaboration is performed based on modelling of a new set of service end points in the service provider network and 10 analysis of impact of the new set of service end points on the set of business objectives. The cross-service provider network indicates that any new set of providers can be modeled and analyzed for their impact on overall user objectives. This helps in decision making whether to include new providers into the network (e.g., based on objective impact) and with what terms and conditions (e.g., based 15 on Tiers). Different organizations have different service provider networks where there may be overlapping set(s) or common service providers and distinct sets. Typically, the members can utilize another service provider network by paying additional amount either as premium or co-pay. Hence out of network payments are an important consideration for the payers managing the service provider network. 20 Payers can model the new providers in an optimization model to see the impact it can bring to the overall business objectives (i.e., CGEQ features like minimizing out-of-network payments). If the business objectives are positively met, then those new providers can be brought into the payers’ network. Similarly, depending on the tiers of the new providers, appropriate decisions can be enabled for users. For 25 competitive assessment, individual service provider networks of a payer and its competitor are modeled. Then comparative analysis of outcome (e.g. how many providers in Tier-1 for each) can be done to come to strengths, weaknesses, opportunities, and threats analysis (SWOT) conclusions. This is further monitored continuously. 30
22
[052]
The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined herein and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the present disclosure if they have similar elements that do not 5 differ from the literal language of the embodiments or if they include equivalent elements with insubstantial differences from the literal language of the embodiments described herein.
[053]
It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message 10 therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination 15 thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both 20 hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
[054]
The embodiments herein can comprise hardware and software 25 elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can 30
23
comprise, store, communicate, propagate, or transport the program for use by or in
connection with the instruction execution system, apparatus, or device.
[055]
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. 5 These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, 10 variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items 15 following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[056]
Furthermore, one or more computer-readable storage media may be 20 utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or 25 stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any 30 other known physical storage media.
24
[057]
It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated herein by the following claims.We Claim:
1. A processor implemented method (200), comprising:
obtaining (202), via one or more hardware processors, a set of business objectives from a library and a set of constraints corresponding to a service provider network;
identifying (204), via the one or more hardware processors, one or more user demands in the service provider network using a clustering technique and a predictive technique in accordance with the set of business objectives and the set of constraints;
predicting (206), via the one or more hardware processors, a mapping of the one or more user demands with one or more service end points and a future state of the service provider network using at least a machine leaning model from a set of machine learning based models from the library;
inputting (208), via the one or more hardware processors, the one or more user demands mapped with the one or more service end points, the future state of the service provider network, the set of business objectives and the set of constraints to a population based heuristic model implemented using a combination of genetic algorithm and binary integer programming technique;
dynamically optimizing (210), via the one or more hardware processors, a current state and the future state of the service provider network against one or more user specified criteria based on the predicted mapping of the one or more user demands with the one or more service end points to obtain an optimum service provider network, wherein the current state and the future state of the service provider network are optimized using the population based heuristic model;
segmenting (212), via the one or more hardware processors, the optimized service provider network into a set of tiers in accordance with the set of business objectives using the optimized current state and the optimized future state of the optimum service provider network; and

determining (214), via the one or more hardware processors, the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the population based heuristic model.
2. The processor implemented method as claimed in claim 1, wherein the optimum service provider network is continuously monitored using a plurality of temporal data to identify one or more shifts in the optimum service provider network.
3. The processor implemented method as claimed in claim 2, wherein a corrective action and engagements with one or more users are performed when the one or more shifts are identified in the optimum service provider network.
4. The processor implemented method as claimed in claim 1, wherein a cross service provider network collaboration and a competitive assessment are enabled using the optimum service provider network.
5. The processor implemented method as claimed in claim 4, wherein the cross service provider network collaboration is performed based on modelling of a new set of service end points in the service provider network and analysis of impact of the new set of service end points on the set of business objectives.
6. A system (100), comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the
one or more communication interfaces (106), wherein the one or more
hardware processors (104) are configured by the instructions to:
obtain a set of business objectives from a library and a set of constraints corresponding to a service provider network;

identify one or more user demands in the service provider network using a clustering technique and a predictive technique in accordance with the set of business objectives and the set of constraints;
predict a mapping of the one or more user demands with one or more service end points and a future state of the service provider network using at least a machine leaning model from a set of machine learning based models from the library;
input the one or more user demands mapped with the one or more service end points, the future state of the service provider network, the set of business objectives and the set of constraints to a population based heuristic model implemented using a combination of genetic algorithm and binary integer programming technique;
dynamically optimize a current state and the future state of the service provider network against one or more user specified criteria based on the predicted mapping of the one or more user demands with the one or more service end points to obtain an optimum service provider network, wherein the current state and the future state of the optimum service provider network are optimized using the population based heuristic model;
segment the provider network into a set of tiers in accordance with the set of business objectives using the optimized current state and the optimized future state of the optimum service provider network; and
determine the one or more service end points in each tier from the set of tiers using the binary integer programming technique and the population based heuristic model.
7. The system as claimed in claim 6, wherein the optimum service provider
network is continuously monitored using a plurality of temporal data to identify one or more shifts in the optimum service provider network.

8. The system as claimed in claim 7, wherein a corrective action and engagements with one or more users are performed when the one or more shifts are identified in the optimum service provider network.
9. The system as claimed in claim 6, wherein a cross service provider network collaboration and a competitive assessment are enabled using the optimum service provider network.
10. The system as claimed in claim 9, wherein the cross service provider network collaboration is performed based on modelling of a new set of service end points in the service provider network and analysis of impact of the new set of service end points on the set of business objectives.